An image processing system, method and computer program

Abstract

An image processing system is provided, the image processing system comprising processing circuitry configured to: receive image data captured by a medical image capture device, the medical image capt

Description

BACKGROUND: Field of the Disclosure The present invention relates to an image processing system, method and computer program. Description of the Related Art The "background" description provided herein is for the purpose of generally presenting the context of the disclosure. Work of the presently named inventors, to the extent it is described in the background section, as well as aspects of the description which may not otherwise qualify as prior art at the time of filing, are neither expressly or impliedly admitted as prior art against the present invention. Imaging devices include any type of device which can be used in order to capture image data representing an image of a subject. Cameras are a type of imaging device which can be used to capture image data. Imaging devices may be used in a wide range of situations and scenarios. For example, imaging devices are now widely used in medical procedures. A medical procedure using an imaging device may include a medical observation procedure. For a medical observation procedure, the quality of the observation procedure is often limited by factors related to performance of the observation procedure by a medical professional. It can be very difficult to verify that a medical observation procedure has been correctly performed. It can also be difficult to identify whether any further observations (such as a repeat medical observation procedure) are required. This can have a negative impact on the quality of the observation procedure which may impact patient outcomes when the observation procedure is used in order to identify medical conditions. It is an aim of the present disclosure to address these issues. SUMMARY: A brief summary about the present disclosure is provided hereinafter to provide basic understanding related to certain aspects of the present disclosure. The disclosure is defined by the independent claims. Further respective aspects and features of the disclosure are defined in the appended claims. In accordance with embodiments of the disclosure more accurate and reliable imaging with a medical imaging device can be performed. This can improve patient outcomes when the medical imaging device is used in order to identify medical conditions. It will be appreciated that the present disclosure is not particularly limited to these advantageous technical effects. Other advantageous technical effects will become apparent to the skilled person when reading the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS: A more complete appreciation of the disclosure and many of the attendant advantages thereof will be readily obtained as the same becomes better understood by reference to the following detailed description when considered in connection with the accompanying drawings, wherein: Figure 1 illustrates an example apparatus which can be used in accordance with embodiments of the disclosure; Figure 2 illustrates an example medical observation procedure to which embodiments of the disclosure can be applied; Figure 3 illustrates an example image processing system in accordance with embodiments of the disclosure; Figure 4 illustrates an example an example timeline of a medical observation procedure in accordance with embodiments of the disclosure; Figure 5A illustrates example image data captured by a medical image capture device in accordance with embodiments of the disclosure; Figure 5B illustrates an example colour spectrum in accordance with embodiments of the disclosure; Figure 6A illustrates an example display in accordance with embodiments of the disclosure; Figure 6B illustrates an example of storing notification information in accordance with embodiments of the disclosure; Figure 7 illustrates an example timeline of a medical observation procedure in accordance with embodiments of the disclosure; Figure 8 illustrates an example image processing method in accordance with embodiments of the disclosure; Figure 9 is a block diagram illustrating an example of a schematic configuration of an endoscopic surgery system to which embodiments of the disclosure can be applied. DESCRIPTION OF THE EMBODIMENTS: The foregoing paragraphs have been provided by way of general introduction, and are not intended to limit the scope of the following claims. The described embodiments, together with further advantages, will be best understood by reference to the following detailed description taken in conjunction with the accompanying drawings (wherein like reference numerals designate identical or corresponding parts throughout the several views). Referring to Figure 1, an apparatus 1000 (an example of an information processing apparatus) according to embodiments of the disclosure is shown. Typically, an apparatus 1000 according to embodiments of the disclosure is a computer device such as a personal computer, an entertainment system or a terminal connected to a server. Indeed, in embodiments, the apparatus may also be a server. The apparatus 1000 is controlled using a microprocessor or other processing circuitry 1002. In some examples, the apparatus 1000 may be a portable computing device such as a mobile phone, laptop computer or tablet computing device. The processing circuitry 1002 may be a microprocessor carrying out computer instructions or may be an Application Specific Integrated Circuit. The computer instructions are stored on storage medium 1004 which may be a magnetically readable medium, optically readable medium or solid state type circuitry. The storage medium 1004 may be integrated into the apparatus 1000 or may be separate to the apparatus 1000 and connected thereto using either a wired or wireless connection. The computer instructions may be embodied as computer software that contains computer readable code which, when loaded onto the 2 processor circuitry 1002, configures the processor circuitry 1002 to perform a method according to embodiments of the disclosure. Additionally, an optional user input device 1006 is shown connected to the processing circuitry 1002. The user input device 1006 may be a touch screen or may be a mouse or stylist type input device. The user input device 1006 may also be a keyboard, controller, or any combination of these devices. Furthermore, the input device 1006 may be an audio input device such as microphone or the like which can receive audio instructions (sounds, speech or the like) which are provided by the user. A network connection 1008 may optionally be coupled to the processor circuitry 1002. The network connection 1008 may be a connection to a Local Area Network or a Wide Area Network such as the Internet or a Virtual Private Network or the like. The network connection 1008 may be connected to a server allowing the processor circuitry 1002 to communicate with another apparatus in order to obtain or provide relevant data. The network connection 1008 may be behind a firewall or some other form of network security. Additionally, shown coupled to the processing circuitry 1002, is a display device 1010. The display device 1010, although shown integrated into the apparatus 1000, may additionally be separate to the apparatus 1000 and may be a monitor or some kind of device allowing the user to visualise the operation of the system (e.g. a display screen or a head mounted display). In addition, the display device 1010 may be a printer, projector or some other device allowing relevant information generated by the apparatus 1000 to be viewed by the user or by a third party. Imaging devices include any type of device which can be used in order to capture image data representing an image of a subject. Cameras are a type of imaging device which can be used to capture image data. Imaging devices may be used in a wide range of situations and scenarios. For example, imaging devices are now widely used in medical procedures. A medical procedure using an imaging device may include a medical observation procedure. Medical observation procedures may be required to be performed on a patient in a number of different situations. These medical observation procedures enable a medical professional to perform a visual inspection on a patient. The medical observation procedures may form a part of a wider medical procedure. For example, medical observation procedures may be performed on a patient in a surgical environment in order to enable the surgeon to visually inspect the patient (including, for example, a region of a patient currently being operated on by the surgeon). However, medical observation procedures may also be performed independently. As an example, medical observation procedures can be used to perform a visual inspection of a region of interest in a patient. This can be as part of a medical investigation performed by the medical professional in response to a condition of a patient. Alternatively, a medical observation procedure can be used to perform a visual inspection of a region of interest as part of a screening program. A screening program is a way of identifying a condition (or indicators of a risk of a condition) in otherwise apparently healthy people. Screening may be performed on people who are considered to have an increased risk of a particular condition. One such screening program includes screening for bowl cancer. A certain demographic of a population may be invited for a colonoscopy in order to identify whether or not a patient has any indications of bowl cancer. For example, people over a certain age may be invited for a colonoscopy. During a colonoscopy, a colonoscope will be inserted into the large intestine of the patient. A colonoscope is a type of endoscope (a type of medical imaging device which can be used in order to capture images within a patient when inserted through an orifice of the body of the patient). Figure 2 of the present disclosure illustrates an example medical observation procedure. Specifically, this medical observation procedure is a colonoscopy. In this example, a medical professional 2000 is performing the colonoscopy on a patient 2002. The medical professional performing the colonoscopy (a colonoscopist) will insert a flexible tube 2004A of a colonoscope 2004 into the body of the patient 2002 via the anus of the patient. Once inserted, this will then be advanced to the end of the large intestine 2006 and then slowly retracted. The colonoscopist 2000 will view images captured by the colonoscope 2004 on a display device 2008 and will look for any signs or symptoms of bowl cancer. In particular, the colonoscopist 2000 may look for polyps in the large intestine 2006 (as these can change into cancer over a number of years). Visual inspection by the colonoscopist 2000 will take place during retraction / withdrawal of the colonoscope from the large intestine 2006. The adenoma detection rate is the percentage of colonoscopies performed by a medical professional that detect at least 1 adenoma (a benign (noncancerous) tumour). More generally, the adenoma detection rate can be calculated for a group of medical professionals. Indeed, it may include the percentage of patients age 50 and older undergoing screening colonoscopy, who have one or more adenomas detected. The adenoma detection rate can be used as a measure of quality in screening colonoscopy; a minimum benchmark for screening may be required in order to demonstrate that quality screening has been performed. However, there are a number of factors which may influence the quality of the colonoscopy (and the ability of the colonoscopist to identify the presence of signs and symptoms of bowl cancer. These may include the skill and level of experience of the colonoscopist, the bowl preparation (e.g. whether the bowl is empty) and the withdrawal time (the amount of time taken to withdraw the colonoscope from the patient (with the visual investigation being performed during this withdrawal phase). For colonoscopy (such as that illustrated in Figure 2 of the present disclosure), there is a scientific consensus that minimally 6 to 9 minutes of withdrawal time are required (with the length of the large intestine being approximately 120cm to 160cm in length). Monitoring of the withdrawal time is a manual action. Accordingly, it is vulnerable to human error. For example, a person may forget to measure the withdrawal time for a given colonoscopy. Alternatively, a person may make a mistake in measuring the withdrawal time for a given colonoscopy. Alternatively, data relating to the withdrawal time may be fabricated post-factum for a given colonoscopy. Given the impact withdrawal time has on the quality of the screening, errors in withdrawal time may be very significant. This can have a negative impact on the quality of the observation procedure which may impact patient outcomes when the observation procedure is used in order to identify medical conditions. For at least these reasons (in addition to those reasons explained in the Background) an image processing system, method and computer program are provided in accordance with embodiments of the disclosure. cimage processing system> An image processing system is provided in accordance with embodiments of the disclosure. Figure 3 of the present disclosure illustrates an example image processing system. The example image processing system 3000 of Figure 3 comprises circuitry 3002. The circuitry 3002 comprises circuitry 3002A configured to receive image data captured by a medical image capture device, the medical image capture device for insertion into and / or for extraction from a patient. Furthermore, the circuity 3002 comprises circuitry 3002B. The circuitry 3002B of the image processing system 3000 is configured to analyse the image data to identify a first time corresponding to a change of direction of travel of the medical image capture device within the patient. Furthermore, the circuitry 3002B is configured to analyse the image data to identify a second time corresponding to extraction of the medical image capture device from the patient. In the present disclosure, extraction of the medical image capture device is the moment at which the medical image capture device is removed from the patient (i.e. the point of exit from the patient). That is, at a certain point once the medical image capture device is within the patient, the medical professional may start to retract or withdraw the medical image capture device from the patient (i.e. move the medical image capture device in a direction which will lead to extraction of the medical image capture device from the patient). This may continue until extraction of the medical image capture device occurs (i.e. the medical image capture device is fully removed from the patient). Finally, the circuitry 3002B is configured to generate notification information when the first time and the second time satisfies a predetermined condition. In examples, the predetermined condition may include a condition that the first time and the second time have been identified. That is, the notification information may be provided when the image processing system identifies that the observation phase of the medical observation procedure (which is performed during withdrawal of the medical image capture device) has been completed. In this way, more accurate and reliable monitoring of the withdrawal time) can be performed. That is, since a notification is automatically generated, a medical professional can be notified that an error in the performance of the observation has occurred. Therefore, it is possible to correct this error at the time of imaging the patient. This can improve the quality of a medical observation performed with the medical imaging device and thus improve patient outcomes. The different circuitry of the image processing system 3000 may be provided as a single circuitry. The circuitry maybe a microprocessor carrying out computer instructions or may be an Application Specific Integrated Circuit. Alternatively, the different circuitry of the image processing system 3000 may be provided as different units (such as a receiving unit, an analysing unit and a generating unit) within the image processing system 3000. The circuitry (or units) of the image processing system 3000 may be provided in a single apparatus or device. Alternatively, different units or processing circuitry of the image processing system 3000 may be distributed over a number of different apparatuses or devices. The present disclosure is not particularly limited in this regard. Furthermore, in some examples, the image processing system 3000 may further include a medical image capture device and / or at least one auxiliary device external to the medical image capture device (such as a surgical light, a display device or the like). However, the present disclosure is not particularly limited in this respect. These optional additional components of the image processing system are not shown in Figure 3 of the present disclosure. In examples, the image processing system 3000 may further comprise the medical image capture device (not shown in Figure 3). The medical image capture device may be an endoscopic device (such as a colonoscope). In this case, the medical image capture device may be configured to be moved in a first direction of travel corresponding to advancement of the medical image capture device within the patient (e.g. as the medical professional 2000 of Figure 2 inserts the flexible tube of the colonoscope into the patient) and a second direction of travel corresponding to retraction of the medical image capture device within the patient (e.g. as the medical professional 2000 of Figure 2 retracts the flexible tube of the colonoscope from the patient). Further details of the respective units of the image processing system 3000 will now be described with reference to an example situation. However, while certain features are described in this context, it will be appreciated that such an example is not to be interpreted to be exclusive or limiting, but rather exemplary or illustrative. <Receiving Image Data> As described with reference to Figure 3 of the present disclosure, the image processing system 3000 comprises circuitry 3002A configured to receive image data captured by a medical image capture device, the medical image capture device for insertion into and / or for extraction from a patient. Consider, again, the example situation as described with reference to Figure 2 of the present disclosure. In this example, a person 2000 (such as a surgeon or other medical person) will perform an observation procedure on a patient 2002. In this example, the surgical procedure is an endoscopic surgical procedure. That is, the medical professional 2000 is going to use an endoscope 2004 to obtain images from inside a patient. The endoscope 2004 is specifically, in this example, a colonoscope 2004. The endoscope (or colonoscope in this specific example) therefore forms a medical image capture device for insertion into and / or for extraction from a patient in accordance with the present disclosure. However, the present disclosure is not particularly limited to this example type of medical image capture device. For example, the medical image capture device for insertion into the patient may more generally comprise at least one of an arthroscope, cystoscope, hysteroscope, lasparoscope, laryngoscope, resctoscope, sinuscope, uteroscope and / or colonoscope. The type of medical image capture device will vary depending on the type of procedure or operation which is being performed by the medical professional. The circuitry 3002A of the image processing system 3000 is configured to receive image data captured by the medical image capture device. In examples, the images may be received directly from the medical image capture device. In some examples, the circuitry 3002A may be configured as a network connection 1008 as described with reference to apparatus 1000 and Figure 1 of the present disclosure. Furthermore, in some examples, the circuitry 3002A may receive image data from the medical image capture device over a network such as an IP network or the like. However, more generally, any suitable wired or wireless communication can be used in order for the circuitry to receive image data from the image processing system. Nevertheless, it will be appreciated that the circuity 3002A of the image processing system 3000 may be configured to receive the image data from the medical image capture device in a substantially real time environment. This enables the image processing system to perform processing in real time in accordance with the images which have been received from the medical image capture device. This ensures that the relevant notification and / or information can be provided to the medical professional in substantially real time during the medical observation procedure. The image data which is received by circuitry 3002A of the image processing system 3000 may be still image data. Alternatively, the image data may be a series of image frames such as a video sequence. The present disclosure is not particularly limited in this regard. The type of image data acquired may vary depending on the type of medical imaging device used and its mode of operation. Furthermore, the resolution of the image data which is received by circuitry 3002A may vary depending on the type of medical image capture device which is used and its mode of operation. However, in examples, the image data can have high resolution including 4K or 8K resolution, for example. The image data may also comprise a number of different colour channels (such as Red, Green and Blue colour channels, for example). Once received by the circuitry 3002A, the image data can be passed to other circuitry (such as circuitry 3002B) for further processing and / or analysis. In some examples, the circuitry 3002A may be configured to store the image data in a storage device prior to that image data being accessed by the circuitry 3002B. In other examples, the circuitry 3002A of the image processing system 3000 may be configured to pass the image data received from the medical image capture device directly to the circuitry 3002B for further processing and / or analysis. Furthermore, in some examples, the image data which has been received can be passed also to a server (in addition to the circuitry 3002B of the image processing device 3000) for storage and subsequent analysis. In some examples of the disclosure, the receiving circuitry 3002A may, optionally, further be configured to receive additional data from an additional data source. The additional data is any data received from a data source in addition to the image data from the medical image capture device. In some examples, the additional data may include at least one of: data relating to a vital sign of the patient or data relating to a stage of an operation, for example. Furthermore, the additional data may include information such as patient demographics. This additional data may, optionally, be stored with the image data which has been captured by the medical image capture device. Generally, any suitable wired or wireless communication can be used by the circuitry 3002A of the image processing system 3000 to receive the additional data. Once the image data has been received by the circuitry 3002A of the image processing system 3000, the image data can be analysed and / or further processed by the image processing system 3000. <Timeline of Medical Observation> Turning now to Figure 4 of the present disclosure, a medical observation timeline is shown. That is, Figure 4 illustrates an example an example timeline of a medical observation procedure in accordance with embodiments of the disclosure. The medical observation timeline illustrated in Figure 4 describes different phases of a medical observation. In this example, the medical observation procedure is a colonoscopy as performed by a medical professional and described with reference to Figure 2 of the present disclosure. However, a similar medical observation timeline may occur for other types of medical observation procedures. The medical observation procedure starts at timeT|N. This is a time when the medical professional inserts the medical image capture device into the patient. In the example of a colonoscopy, this is the time at which the colonoscopist inserts the flexible tube of the colonoscope into the body of the patient via the anus of the patient. Once inserted, the medical image capture device will then be advanced through the body of the patient. This phase, where the medical image capture device is advanced through the body of the patient, corresponds to phase 'A' of Figure 4 of the present disclosure. The medical professional does not perform visual inspection during this phase. Rather, visual inspection (such as visual inspection by the colonoscopist) will take place during retraction / withdrawal of the medical imaging device from the body of the patient (e.g. retraction / withdrawal of the colonoscope from the large intestine of the patient). The phase 'A' during which the medical image capture device is advanced through the body of the patient will continue until the medical image capture device reaches the desired extent within the body of the patient. This may correspond to a maximum extent reachable given the length of the image capture device. Alternatively, this may correspond to a maximum extent given the size of the body of the patient (e.g. the end of the large intestine of the patient). Alternatively, this may correspond to a predetermined maximum extent of the observation. At time Ti, the medical observation procedure will change to a second phase - phase 'B' as illustrated in Figure 4 of the present disclosure - whereby the medical image capture device is retracted or withdrawn from the patient. This phase 'B' (corresponding to retraction / withdrawal from the patient) is a phase during which the visual inspection is performed by the medical professional. Considering the example of a colonoscopy, the medical professional will perform visual inspection of the patient during this phase (i.e. as the medical image capture device is being withdrawn from the body of the patient). This second phase 'B' will continue for a given time duration until the end of the medical image capture device again reaches the orifice by which it was inserted into the patient. At this time (Tout of Figure 4) the medical image capture device will be extracted from the patient. The medical observation procedure ends at this time Tout. That is, once the medical image capture device has been extracted from the patient, no further observation within the body of the patient can be made (unless the medical image capture device is re-inserted into the body of the patient). As explained, the visual inspection is performed by the medical professional during the phase 'B' (i.e. the time between Ti and Tout in Figure 4 of the present disclosure). Furthermore, it is known that the length of this phase (phase 'B' of the example of Figure 4) may have a significant impact on the quality of the observation performed on the patient. For colonoscopy (as illustrated with reference to Figure 2 of the present disclosure) there is a scientific consensus that minimally 6 to 9minutes of withdrawal time are required (with the length of the large intestine being approximately 120cm to 160cm). However, monitoring of the withdrawal time is a manual action and vulnerable to human error (e.g. a person forgettingto measure the withdrawal time for a given colonoscopy). Accordingly, it may be difficult to ensure that an observation of appropriate length (and therefore appropriate quality) has been performed on the patient. However, in accordance with embodiments of the disclosure, the image processing system 3000 is configured to analyse the image data to identify the time corresponding to a change of direction of travel of the medical image capture device within the body of the patient. This enables the time Ti (i.e. the start of the observation) to be identified, as the change of direction of the medical image capture device occurs at the time the medical professional begins to retract / withdraw the medical image capture device from the patient. Furthermore, the image processing apparatus 3000 is configured to analyse the image data to identify the time at which the medical image capture device is extracted from the patient (corresponding to time Tout - i.e. the end of the observation) to be identified. Thus, by analysing the image data, the image processing system 3000 is able to accurately and reliably identify the start and the end of the observation. In examples, this enables the image processing system 3000 to identify whether the observation has been performed by the medical professional for an appropriate length of time. By ensuring that the observation is performed for an appropriate length of time, the quality of the observation can be improved. This may improve patient outcomes (depending on the nature of the medical observation). Furthermore, image processing system 3000 can be used during training of a medical professional to ensure that the medical professional being trained learns to perform an appropriate length of medical observation. Moreover, as the notification information may be automatically generated once the first and second time satisfy a predetermined condition (e.g. the first and second time have both been identified) it becomes easier to monitor and record timing information concerning the medical observation procedure. <Detection of Insertion and Extraction> As explained, the circuitry 3002B of the image processing system 3000 is configured to analyse the image data in order to identify the start and end of the medical observation procedure (corresponding to time Ti and Tout as described with reference to Figure 4 of the present disclosure). In particular, in examples, the image processing system 3000 is configured in order to analyse the image data to identify a time corresponding to extraction of the medical image capture device from the patient. Optionally, in examples, the image processing system 3000 may also be configured to identify insertion of the medical image capture device into the patient. In examples, the processing to identify the change of direction of the medical image capture device (i.e. the time at which the medical observation procedure begins) may be performed only once insertion of the medical image capture device into the patient has been detected. In examples, detection of insertion and / or extraction or the medical image capture device from the body of the patient can be performed in a similar same way. Extraction of the medical image capture device from the body of the patient (such as at time Tout in the example of Figure 4 of the present disclosure) corresponds to the end of the medical observation procedure. Therefore, the image processing system 3000 of the present disclosure is configured perform analysis on the image data received from the medical image capture device in order to identify insertion and / or extraction of the medical image capture device from the patient. Consider, now, Figure 5A of the present disclosure. Figure 5A illustrates example image data captured by a medical image capture device (medical imaging device) in accordance with embodiments of the disclosure. In the example of Figure 5A, the medical imaging device is a laparoscope. Therefore, the images are images received by the image processing system 3000 from a laparoscope during surgery. In this example, a direct trocar is used. A direct trocar does not include a camera. Instead, the camera (such as the laparoscope) can be inserted once the direct trocar has been inserted. The present disclosure is not particularly limited in this regard to the use of a direct trocar. In some examples, an optical trocar can also be used. The optical trocar includes the camera such that the trocar and the camera are inserted at the same time. Nevertheless since, in this example, a direct trocar is used, the direct trocar is first inserted into the patient. This is then followed by insertion of the camera into the patient. Accordingly, concentric circles are observed in the images received from the image capture device as the camera is inserted into the patient (through the trocar). These concentric circles 50 can be seen in the top panel of Figure 5A as the image capture device is inserted into the patient through the trocar. Furthermore, concentric circles 52 can also be observed once the medical image capture device has passed through the trocar and is inside the patient. These can be seen in the bottom panel of Figure 5A of the present disclosure. Thus, the images received from the medical image capture device as it is inserted into the patient through the direct trocar are distinctive and can be used in order to identify insertion of the medical image capture device into the patient. In a similar way, extraction of the medical image capture device (i.e. the moment at which the medical image capture device is removed from the patient) can also be detected from the image data captured by the image capture device. That is, the images (image data) received from the medical image capture device as it is extracted from the patient - through the direct trocar - are distinctive and can be used in order to identify extraction of the medical image capture device from the patient. The type of analysis performed by the circuitry 3002B of the image processing system 3000 on the images received by the circuitry 3002A from the medical image capture device is not particularly limited in accordance with embodiments of the disclosure. That is, a different type of analysis can be performed by the circuitry 3002A of the image processing system 3000 depending on the situation to which the embodiments of the disclosure are applied. However, in some examples, the circuitry 3002B of the image processing system 3000 may be configured to use at least one of: a trained model (such as a machine learning model or deep learning model) and / or colour analysis of the image data to identify insertion and / or extraction of the medical image capture device. A trained model can be trained on a series of images from previous surgeries or medical observation procedures showing insertion and / or extraction of the medical image capture device into the patient. The trained model can also be trained on simulated data showing insertion and / or extraction of the medical imaging device into the patient. Distinctive features within the image data (such as the presence of the concentric circles described with reference to Figure 5A of the present disclosure) may be used by the trained model to identify insertion and / or extraction of the medical image capture device. Use of distinctive features such as the concentric circles improves the accuracy of identification of insertion and / or extraction of the medical image capture device during surgery. Once trained, the trained model can then be used on images received from the medical image capture device during surgery or medical observation procedures in order to identify insertion and / or extraction of the medical image capture device. By using a wide range of training data, the accuracy and efficiency of the trained model in identification of insertion and / or extraction of the medical image capture device can be improved. The training of the trained model can be either supervised or unsupervised. That is, supervised or unsupervised learning can be used in order to train the trained model. In supervised learning, the training data can be labelled in order that the model is trained on a known input (the images from previous surgeries and medical observation procedures) and a known output (whether the images relate to an insertion and / or extraction of the medical image capture device). The model can be trained to identify insertion and / or extraction of the medical image capture device on previously unseen input on this basis. Alternatively, in unsupervised training, the data are not labelled. During unsupervised training, the model analyses the unlabelled data sets (images from previous surgeries or medical observation procedures) to cluster the images and discover hidden patterns within the data. Once trained on a set of training data (including data from previous surgeries, data from previous medical observation procedures and / or simulated data showing insertion and / or extraction of the medical image capture device) the trained model will be able to identify insertion and / or extraction of the medical image capture device in previously unseen images during surgery. Furthermore, the circuitry 3002B of the image processing system 3000 can be configured to perform colour analysis of the image data to identify insertion and / or extraction of the medical image capture device. The colour analysis can be used as an alternative to or in addition with the use of the trained model. In examples, the trained model may use the colour of the images as distinctive features in order to identify insertion and / or extraction of the medical image capture device. Consider the example images shown in Figure 5A of the present disclosure received from a medical image capture device during insertion into the patient through a direct trocar. In this example, the image received as the medical image capture device passes through the trocar has a particular colour (silver in this example - shown in the top panel of Figure 5A). Then, once the image capture device has passed through the trocar, the colour changes as the medical image capture device is inserted into the patient (red in this example - shown in the bottom panel of Figure 5A). Accordingly, analysis of the colour of the images received from the medical image capture device can be used in order to identify insertion and / or extraction of the medical image capture device during surgery. That is, when a global change in colour occurs across the image it is likely that an insertion or extraction of the medical image capture device has occurred. In particular, an analysis of the colour spectrum of the image data received from the medical image capture device over time can be used in order to identify insertion and / or extraction of the medical image capture device. In some examples, circuitry 3002B of the image processing system 3000 can separately analyse different colour channels of the image data received from the image capture device (e.g. Red, Green and Blue channels) over time in order to identify insertion and / or extraction of the medical image capture device. An example colour spectrum is illustrated in Figure 5B of the present disclosure. Each of the different columns in the graph represents a different colour channel of a video recorded as an endoscope is inserted into and extracted from the patient. The horizontal axis represents time (with each instance of time relating to a specific video frame from the video). The variation in the colour spectrum can be used in order to detect insertion and / or extraction of the imaging device. Moreover, when used in combination with another technique (such as in combination with use of a trained model) the colour analysis can be used in order to verify identification of insertion or extraction of the image capture device (and thus reduce false positive detections). In this way, the circuitry 3002B of apparatus 3000 is configured to analyse the image data which has been received to identify at least one of insertion of the medical image capture device into the patient or extraction of the medical image capture device from the patient. While the analysis performed by circuitry 3002B to identify insertion or extraction of the patient has been described with reference to laparoscopic surgery, it will be appreciated that the present disclosure is not particularly limited in this regard. For example, the circuitry 3002B can be configured to identify insertion and / or extraction of any type of medical image capture device into the patient, including at least one of an arthroscope, cystoscope, hysteroscope, laryngoscope, resctoscope, sinuscope, uteroscope and / or colonoscope. The type of medical image capture device will vary depending on the type of surgical procedure or operation which is being performed in the operating room. Each type of medical image capture device will have its own distinctive characteristics (such as the pattern of concentric circles and / or colour spectrum) which can be used by the circuitry 3002B to identify insertion and / or extraction of the medical image capture device. Furthermore, in some examples, the circuitry 3002B may, optionally, be further configured to analyse the image data and the additional data to identify at least one of insertion of the medical image capture device into the patient or extraction of the medical image capture device from the patient. That is, in some examples, the circuitry 3002B can be configured to analyse additional data which has been received by the circuitry 3002A and use this additional data during the identification of at least one of the insertion and / or extraction of the image capture device. Additional data can be data from one or more other devices within the medical environment. Furthermore, additional data can include data (such as an input) from a person within the medical environment. This data can be used with the analysis on the image data performed by the image processing system 3000 in order to identify the moment of insertion and / or extraction of the medical image capture device from the patient. As the image processing system 3000 analyses the image data in order to identify the time corresponding to extraction of the medical image capture device from the patient, the end of the visual inspection phase of the medical observation procedure (and indeed, the end of the medical observation procedure) can be more accurately and reliably identified. <Detection of change of direction> In addition, the circuitry 3002B can be configured to detect the moment of change of direction of the medical image capture device as it is moved through the body of the patient. That is, as explained with 12 reference to Figure 3 of the present disclosure, the image processing system 3000 may be configured to analyse the image data to identify a time corresponding to a change of direction of travel of the medical image capture device within the patient. In examples, processing to detect the moment of change of direction of the medical image capture device as it is moved through the body of the patient may be performed only after the insertion of the medical image capture device into the patient has been detected. Consider, again, the example of colonoscopy as described with reference to Figure 2 of the present disclosure. In this example, the medical professional will, at time Ti, insert the medical image capture device into the body of the patient. Then, during phase A, the medical professional will continue to advance the medical image capture device through the body of the patient (pushing the medical image capture device further inside the body of the patient). This will continue until the maximum extent of insertion has been reached (e.g. the end of the large intestine of the patient). At this time, the medical professional will change the direction of the medical image capture device and will start to withdraw the medical image capture device from the body of the patient. As explained, visual inspection of the patient is performed during this withdrawal phase (phase B of Figure 4 of the present disclosure). Accordingly, the withdrawal phase (during which the visual inspection is performed) will begin within, and is thus preceded by, a change of direction of the medical image capture device within the body of the patient. The medical professional may be able to move the medical image capture device in two prominent directions within the body of the patient. The first of these is a forward direction further into the patient (i.e. advancement) while the second is a backward direction out of the patient (i.e. retraction or withdrawal). Therefore, the change of direction which is detected that starts the withdrawal phase is a change from the forward direction to the backward direction within the body of the patient. The processing circuitry 3002B of image processing system 3000 is configured to detect the change of direction of travel of the medical image capture device within the body of the patient. The manner by which the image processing system 3000 is configured to detect this change of direction of travel is not particularly limited. That is, any suitable image processing which can detect a change of direction of the image capture device from the image data captured by the medical image capture device can be used in accordance with embodiments of the disclosure. In some examples, the processing circuitry may further be configured to use a trained model (such as a machine learning model or deep learning model) to detect the change of direction of travel of the medical image capture device within the patient. The trained model can be trained in a similar way as described for insertion and / or extraction of the medical image capture device from the body of the patient. That is, a trained model can be trained on a series of images from previous surgeries or medical observation procedures showing a change of direction of travel of the medical image capture device within the body of the patient. The trained model can also be trained on simulated data showing the change of direction of the medical imaging device within the patient. A change of direction between frames of image data received by the image processing circuitry 3002A from the medical image capture device may be identified by a number of distinctive features in the images. For example, an object or feature within the image may appear to increase in size as the medical image capture device advances through the patient (in a forward direction, toward the object or feature). 13 However, the same object or feature will then appear to decrease in size as the medical image capture device starts to retract (i.e. once a change of direction of the medical image capture device has occurred); this is because the medical image capture device will then move away from that object or feature. Thus, in examples, a comparison of image data obtained at different times from the medical image capture device will enable identification of the time corresponding to the change of direction. Once trained, the trained model can then be used on images (image data) received from the medical image capture device during surgery or medical observation procedures in order to identify a change of direction of the medical image capture device. By using a wide range of training data, the accuracy and efficiency of the trained model in identification of changes of direction of the medical image capture device can be further improved. The training of the trained model can be either supervised or unsupervised. That is, supervised or unsupervised learning can be used in order to train the trained model. In supervised learning, the training data can be labelled in order that the model is trained on a known input (the images from previous surgeries and medical observation procedures) and a known output (whether the images relate to a change of direction of the image capture device). The model can be trained to identify changes of direction of the medical image capture device on previously unseen input on this basis. Alternatively, in unsupervised training, the data are not labelled. During unsupervised training, the model analyses the unlabelled data sets (images from previous surgeries or medical observation procedures) to cluster the images and discover hidden patterns within the data. Once trained on a set of training data (including data from previous surgeries, data from previous medical observation procedures and / or simulated data showing changes of direction of the medical image capture device) the trained model will be able to identify changes of direction of the medical image capture device in previously unseen images during surgery. Thus, a trained model can be used in order to analyse the image data to identify a first time corresponding to a change of direction of travel of the medical image capture device within the patient. Alternatively or in addition, in examples, analysis of the image data to identify a first time corresponding to a change of direction of travel of the medical image capture device within the patient comprises motion analysis of the image data. Motion analysis is used in image processing to produce information regarding motion in the images. Motion analysis compares two or more consecutive images as received from an image source (such as the medical image capture device) are produces information based on the apparent motion in the images. Any suitable motion analysis processing can be used in order to detect a change in direction of the medical image capture device. For example, motion detection may analyse the motion of pixels between the images and / or the motion of certain objects or features within the images between the images received from the image source. As the image processing system 3000 analyses the image data in order to identify the time corresponding to a change of direction of travel of the medical image capture device within the patient, the start of the visual inspection phase of the medical observation procedure can be more accurately and reliably identified. <Notification> As explained with reference to Figure 3 of the present disclosure, the image processing system 3000 is configured to generate notification information when the first time and the second time satisfies a predetermined condition. The image processing system 3000 of the present disclosure is configured to analyse the image data in order to identify the change of direction of the medical image capture device (corresponding to the start of the visual inspection phase of the medical observation procedure) and the extraction of the medical image capture device from the patient (corresponding to the end of the visual inspection phase of the medical observation procedure). Once the change of direction of the medical image capture device has been identified, the image processing system 3000 may identify the time corresponding to this change of direction. This may be based on a time stamp associated with the image date received from the medical image capture device. Alternatively, this may be based on a time keeping mechanism or device (such as a clock) associated with the medical image capture device and / or the image processing system. Likewise, once the extraction of the medical image capture device has been detected (by analysis of the image data) the time corresponding to this extraction can readily be identified based on a time stamp associated with the image data received from the medical image capture device, a time keeping mechanism (such as a clock) associated with the medical image capture device and / or the image processing system, for example. This time information which is identified by the image processing system 3000 can then be used in order to generate notification information in accordance with embodiments of the disclosure (e.g. if the visual inspection phase of the medical observation procedure is too short). Generating notification information enables the image processing system 3000 to provide a warning or an alert to a person (such as a medical professional) performing a medical observation using the medical image capture device if the time of the medical observation is too short. More generally, it enables the medical professional to quickly and easily understand whether the medical observation procedure has been performed to an appropriate level (with the duration in time of the medical observation being strongly related to the quality of the medical observation procedure as described with reference to Figure 2 of the present disclosure). Consider, again, an example of a colonoscopy being performed on a patient. Such an example has been described with reference to Figure 2 of the present disclosure. The medical professional 2000 is performing the colonoscopy on the patient 2002 as part of a screening test to identify whether the patient 2002 is displaying any signs of bowl cancer. That is, the medical professional observes images captured from inside the patient 2002 by the medical image capture device 2004 and assesses these images in order to identify any signs of bowl cancer. For example, the medical professional 2004 may look to see whether they can observe any polyps in the bowl of the patient 2002. The medical image capture device 2004 captures image data throughout the medical observation procedure. However, the medical professional 2000 performs visual inspection of the bowl of the patient only during the phase during which the medical image capture device is withdrawn from the patient (i.e. during retraction of the medical image capture device). Therefore, the duration of the retraction phase of the medical image capture device from the patient (i.e. the phase B as illustrated in Figure 4 of the present disclosure) is a particularly important metric for understanding the quality of the medical observation procedure which has been performed by the medical professional. For colonoscopy (such as that illustrated in Figure 2 of the present disclosure), there is a scientific consensus that minimally 6 to 9 minutes of withdrawal time are required (with the length of the large intestine being approximately 120cm to 160cm in length). Therefore, the circuitry of the image processing system 3000 is configured to determine the time duration been the first time Ti (the time at which retraction of the medical image capture device began, corresponding to the start of the visual inspection phase of the medical observation procedure) and the time Tout (the time at which the medical image capture device was extracted from the patient, corresponding to the end of the visual inspection phase of the medical observation procedure). The time Ti and Tout can be accurately and reliably determined from the images captured by the image capture device as has already been described. The time between Ti and Tout therefore corresponds to the duration of the visual inspection phase of the medical observation procedure. This time duration can - in examples - be used in order to generate notification information, when satisfying a predetermined condition. In examples, the predetermined condition may include a condition that the time between the first time and the second time is less than a predetermined amount of time. However, the present disclosure is not particularly limited in this regard. In other examples, the predetermined condition may include a condition that the time between the first time and the second time exceeds a predetermined amount of time. In this way, errors in the performance of the observation can be corrected. However, more generally, it will be appreciated that the notification information may be generated when the first time and the second time satisfy a predetermined condition. This may include a predetermined condition that the first time and the second time have been identified. In other words, in examples, the notification information may be generated when a first time (corresponding to a change of direction of travel within the patient) and a second time (corresponding to extraction of the medical image capture device from the patient) have been identified. In examples, the notification information which is generated may include information concerning the timing of the medical observation procedure (such as the first and second time). Therefore, in examples, timing information of the medical observation procedure may be automatically generated and notified. In examples, this information may be stored in a storage unit or the like. In this way, the timing of the medical observation can be more accurately and reliably monitored. As such, errors in the performance of the medical observation procedure can be more easily detected. This can be advantageous when training a medical professional to perform the medical observation procedure. Moreover, as the timing information of the medical observation procedure is more accurately and reliably monitored and / or recorded, it becomes easier for a medical professional to demonstrate that the medical observation procedure was performed appropriately (e.g. that sufficient time was taken when performing the medical observation). In examples, the notification information may be generated when a time between the first time and the second time satisfies a predetermined condition (i.e. dependent upon the duration of the medical observation procedure). This enables notification information to be provided to the medical professional (and / or another person) when there is a potential problem with the medical observation procedure which has been performed. For example, when the medical observation procedure is less than a predetermined threshold value (which may vary depending on the type of medical observation being performed) the 16 medical professional may be notified that a further medical observation procedure should be performed (i.e. that a portion of the medical observation procedure should be repeated) in order to ensure the quality of the medical observation procedure which has been performed. Consider, now, an example where the predetermined condition includes a condition that the time between the first and second time is less than a predetermined amount of time. In this example, the duration of the visual inspection phase of the medical observation procedure is less than a predetermined amount of time (corresponding to a minimum acceptable time of visual observation) then the image processing system 3000 may generate notification information to inform the medical professional that the time spent during the visual inspection phase was too short. As such, the medical professional can immediately understand that the time spent on the visual inspection phase was too short. The medical professional can then take necessary steps to rectify this (e.g. performing a repeat observation on the patient) which can improve the quality of the medical observation and may improve patient outcomes. As noted, for colonoscopy, there is a scientific consensus that minimally 6 to 9 minutes of withdrawal time are required (i.e. 6 to 9 minutes of visual inspection). However, the present disclosure is not particularly limited to 6 to 9 minutes as the predetermined amount of time. That is, the predetermined amount of time may be much shorter or much longer than this depending on the type of medical observation being performed and / or the current scientific consensus on best practice for the medical observation. In examples, the image processing system 3000 may identify the predetermined amount of time based on a type of medical observation being performed. Optionally, this may be identified by a type of medical observation device being used to capture the images of the patient. For example, when the image processing system 3000 detects that a colonoscope is being used to capture the image data of the patient, the image processing system 3000 may determine that a colonoscopy is being performed and set the predetermined amount of time accordingly (e.g. by looking up the predetermined amount of time for that medical observation in a server or the like). In other examples, the medical professional may identify at least one of the type of medical observation being performed and / or the predetermined amount of time which should be spent during the visual inspection phase. For example, during training, a trainer may inform the image processing time that a colonoscopy is being performed and that the duration should be 8 minutes of visual inspection (as minimum). This enables the trainer to control the image processing system 3000 such that a notification will be generated if the trainee performing the medical observation spends less than this predetermined amount of time on the visual inspection phase. Accordingly, it becomes easy for a trainer to ensure that an appropriate amount of time is spent by the trainee during the visual inspection phase thus improving the training of the trainee and ensuring that the trainee performs a higher quality observation of the patient. The type of notification which is generated by image processing system 3000 is not particularly limited and may vary depending on the situation to which the embodiments of the disclosure are applied. However, in some examples, comprises at least one of visual, auditory and / or haptic feedback. An example of visual feedback may include a notification (such as a message) configured to be displayed on the display screen being used by the medical professional during the medical observation procedure. An example of auditory feedback may include an alert or other sound which can be heard by the medical 17 professional performing the medical observation procedure which enables the medical professional to understand that the visual inspection phase was too short. An example of haptic feedback may include a vibration of other tactile sensation which can be felt by the medical professional performing the medical observation which enables the medical professional to understand that the visual inspection phase was too short. Consider, now, the example of Figure 6A of the present disclosure. Figure 6A of the present disclosure illustrates an example display in accordance with embodiments of the disclosure. Thus, Figure 6A provides an example of visual feedback (visual notification) which can be provided to the medical professional. In this example, a display device 2008 is shown. This is the display device being watched by a medical professional during the medical observation procedure (e.g. the colonoscopy described with reference to Figure 4 of the present disclosure). On this display device an image 2008A from the medical image capture device is shown. This is a real time image as captured by the medical image capture device being used by the medical professional. The medical professional can therefore observe the images shown on the display device and perform the necessary visual inspection on the patient. Two types of visual feedback (a type of notification information) have been generated by the image processing system 3000 in this example. The image processing system 3000 is configured to generate these notifications when a time between the first time and the second time satisfies a predetermined condition (e.g.. when it has been determined that the visual inspection phase was too short). The first type of visual feedback is a text based visual feedback 6000. In this example, the text based visual feedback is provided in a display area of the display device adjacent to an area of the display device displaying the image data from the medical image capture device. Furthermore, in this example, the text based visual feedback 6000 provides a message "WARNING - TOO SHORT". Thus, at the time at which the medical image capture device is extracted from the patient (i.e. Tout) the medical professional can receive a notification that the visual inspection phase of the medical observation procedure was too short. It will be appreciated that the text based visual feedback 6000 is not particularly limited to the specific example shown in Figure 6A of the present disclosure. That is, the type of wording used in the text based visual feedback is not particularly limited in this regard and may change depending on the situation to which embodiments of the disclosure are applied. For example, different information may also be provided in this text based feedback; as an example, the text based feedback may indicate to the medical professional how much shorter the visual inspection was than the predetermined period of time (minimum visual inspection time) for the given medical observation. Furthermore, the size and location of the text based visual feedback is not particularly limited to that shown in this example and may vary. Indeed, in other examples, this visual feedback may be provided on a separate display device (such as an auxiliary display device) to the display device displaying the images captured by the medical image capture device. The second type of visual feedback shown in the example of Figure 6A is graphical feedback. In this example, the graphical feedback is a box 6002 displayed around the images captured by the medical image capture device. Image processing system 3000 may be configured to change the graphical feedback provided to the medical professional when it is determined that a time between the first time and the second time satisfies a predetermined condition (e.g. that the visual inspection phase was too short). As an example, the box 6002 may only appear at the end of the medical observation if the visual inspection phase was too short. Alternatively, the box 6002 may change colour or shape if the visual inspection phase was too short. Therefore, at the time at which the medical image capture device is extracted from the patient (i.e. Tout), the medical professional can receive a notification that the visual inspection phase of the medical observation procedure was too short. It will be appreciated that the graphical feedback illustrated in Figure 6A of the present disclosure is merely one type of graphical feedback which can be provided to the user. That is, the present disclosure is not particularly limited in this regard and may change depending on the situation to which embodiments of the disclosure are applied. In examples, the notifications 6000 and / or 6002 as provided on the display device 2008 are notifications which are displayed when the a time between the first time and the second time is less than a predetermined amount of time. This enables the medical professional to understand that the time spent on the visual inspection phase (the time between Tiand Tout as described in Figure 4 of the present disclosure) was too short. Accordingly, the medical professional may then determine to repeat the medical observation procedure on this basis. However, the present disclosure is not particularly limited in this regard. For example, in some examples, one or more additional pieces of information may be displayed on the display device 2008 during the medical observation procedure. More generally, these notifications may be provided when the time between the first and second time satisfies a predetermined condition. In examples, the image processing system 3000 may be configured to start a timer at the time corresponding to the change of direction of the medical image capture device (i.e. a timer which is started at the time Ti as described with reference to Figure 4 of the present disclosure). By starting the timer at the time Ti, the image processing system 3000 starts the timer at the start of the visual inspection phase of the medical observation procedure (i.e. phase "B" as described with reference to Figure 4 of the present disclosure). This timer therefore measures the time which has elapsed since the start of the visual inspection phase of the medical observation procedure. In examples, the current value of this timer may be displayed to the medical professional on the display device 2008. In the example of Figure 6A, the current value of this timer is displayed as text based feedback 6004 ("Current Observation Time"). In this way, the medical professional can easily understand how much time has elapsed since the start of the visual inspection phase on the medical observation procedure. Therefore, even before the extraction of the medical image capture device from the patient (i.e. even before the time Tout as described with reference to Figure 2) the medical professional can understand the amount of time which has been spent on visual inspection. Therefore, the medical professional is able to adapt their operation of the medical image capture device and more easily ensure that a correct amount of time is spent during the visual inspection phase of the medical observation procedure. This mayfurther improve patient outcomes and the quality of the medical imaging performed. Hence, more generally, the circuitry of the image processing system 3000 is further configured to display information comprising a time which has elapsed since the first instance of time on the display device. Furthermore, as previously explained, in addition to detecting the change of direction of the medical image capture device, the image processing system 3000 may also analyse the images captured by the medical image capture device in order to determine the speed of the medical image capture device (i.e. the speed at which the medical professional is retracting the medical image capture device from the patient). This enables the image processing system 3000 to calculate one or more additional parameters of the medical observation procedure. As an example, the circuitry of the image processing system 3000 may further be configured to analyse the image data to identify a speed of the medical image capture device in the direction of travel and generate notification information when a speed of the medical image capture device is above a predetermined threshold speed. Similarly to the predetermined threshold time, the predetermined threshold speed is not particularly limited and may be set in accordance with a type of medical observation being performed on the patient. Taking colonoscopy as an example, it is known that the average length of the large intestine of a patient is approximately 120cm to 160cm. Furthermore, it is known that the scientific consensus is that the visual inspection phase of a colonoscopy should have a minimum duration of 6 to 9 minutes (i.e. 6 to 9 minutes of withdrawal time). Therefore, taking the shortest of these values (120cm in length and 6 minutes of observation time) an average speed of 20cm per minute may be calculated. Thus, for a colonoscopy, the predetermined threshold speed may be set at 20cm per minute. If the speed of the withdrawal performed by the medical professional is above this speed, then there is a risk that the visual inspection of the medical observation procedure will be too short. Accordingly, image processing system 3000 may generate notification information when a speed of the medical image capture device is above this predetermined threshold speed (e.g. notification information such as "WARNING- SPEED TOO FAST" may be displayed on the display device). In examples, a colour coding may be applied to the notification information to indicate whether the speed of the medical image capture device is appropriate. For example, if the speed of the medical image capture device is too fast, then the notification information (or other information) may be displayed in a first colour (e.g. red). On the other hand, if the speed of the medical image capture device is appropriate (e.g. less that the predetermined threshold speed) then the notification information (or other information displayed to the medical professional) may be displayed in a second colour (e.g. green). Furthermore, in some examples, the colour of the notification information (or other information displayed to the medical professional) may change as the speed of the medical image capture device increases and approaches the predetermined threshold speed (e.g. the colour may change from green, to orange and then to red). Thus, the medical professional may immediately identify that the current speed of visual observation is too fast. This enables the medical professional to take appropriate action to reduce the speed of the observation even before extraction of the medical image capture device from the patient. This can improve the quality of the visual inspection performed and may thus improve patient outcomes. In addition, in examples, the current observation speed 6006 may be displayed to the medical professional on the display device. This can further improve the medical professional's understanding of the current performance of the visual inspection. In examples, the circuitry of the image processing system 3000 may further be configured to analyse the image data to identify a speed of the medical image capture device in the direction of travel; generate a predicted amount of time, being an amount of time between the first time and a time at which extraction of the medical image capture device from the patient will occur; and generate second notification information when the predicted amount of time is less than the predetermined amount of time. Taking Figure 6A as an example, the circuitry of image processing system 3000 may determine that with a current speed of 25 cm per minute (and an average length of 120cm of the large intestine of the patient) then the predicted time for the visual inspection is 4.8 minutes. This information may be calculated and displayed to the user (the medical professional) as the predicted observation time 6008. Thus, even before the medical observation procedure has been completed, the medical professional can understand that it is likely that - based on the current speed - the visual inspection will be too short. As such, the medical professional can take necessary steps to reduce the speed of the visual inspection in order to ensure that an appropriate amount of time is taken on the medical observation procedure. While this example has been described using the current speed of the medical image capture device, in examples the image processing system 3000 may calculate an average speed of the medical image capture device during the visual inspection phase (i.e. between time Ti and Tout as described with reference to Figure 4) and may display the predicted observation time using the average speed which has been calculated. This may provide an improved prediction of the time of the visual inspection as minor fluctuations or variations in the speed of the medical image capture device will be accounted for. In this manner, as has been described with reference to Figure 6A of the present disclosure, image processing system 3000 is able to generate and display visual feedback to the medical professional in accordance with the notification information which has been generated. While providing feedback information to the user (medical professional) based on the notification information which has been generated enables the user to understand whether the visual inspection has been (or is being) appropriately performed, in some examples it may be advantageous to store the notification information which has been generated in order that it can be accessed at a later stage. As an example, it may be advantageous for a medical professional to store information regarding the visual inspection which has been performed as metadata with the image data of the visual inspection. This enables the medical professional to demonstrate at a later stage (if required) that an appropriate visual inspection was performed on the patient. As such, in examples, the circuitry of information processing system 3000 may further be configured to store one or more of: the first time (i.e. the time corresponding to the change of direction and thus the start of the visual inspection phase) and the second time (i.e. the time corresponding to extraction and thus the end of the visual inspection phase), the time between the first time and the second time (i.e. the amount of time spent during the visual inspection phase), and / or the notification information as metadata associated with the image data captured by the medical image capture device. Alternatively this information may be stored as metadata associated with the patient (e.g. with patient records, for example). Consider, now, Figure 6B of the present disclosure. Figure 6B illustrates an example of storing notification information in accordance with embodiments of the disclosure. In this example, a medical professional 2000 is performing a medical observation procedure on a patient 2002. As explained with reference to Figure 2 of the present disclosure, in examples this medical observation procedure may be a colonoscopy. During this medical observation procedure, the medical professional 2000 inserts at least a part of the colonoscope 2004 into the patient in order to acquire images of the inside of the patient. These images (image data) are shown to the medical professional 2000 on a display device 2008. This image data from the medical image capture device is also received by the circuitry 3002A of the image processing system 3000. In addition, the circuitry 3002A of image processing system 3000 may also receive auxiliary data from one or more additional sources. In this example of Figure 6B, the auxiliary data received by the circuitry 3002A of the image processing system 3000 is auxiliary information concerning patient demographics. This may include information such as the age of the patient or the like. Furthermore, in examples, the auxiliary information (also referred to as additional information) may include information concerning the medical staff performing the medical observation with the medical image capture device. This may include identification information (such as a name or a number for example) of the one or more medical professionals performing the medical observation. Once the image data has been received from the medical image capture device, this image data is anonymised to remove any identifying features of the patient. Then, this anonymous data (anonymous video) is provided to circuitry 3002B of image processing system 3000 which is configured to identify the start of the withdrawal (time Ti as described with reference to Figure 4 of the present disclosure) and the end of withdrawal (i.e. extraction; time Tout as described with reference to Figure 4 of the present disclosure). In examples, the image processing system 3000 may generate notification information when a time between the first time and the second time (i.e. the time between the start and end of withdrawal) is less than a predetermined amount of time. This may warn the medical professional that an insufficient amount of time has been spent on the visual inspection phase of the medical observation procedure. In addition, image processing system 3000 may be configured to store recordings from the visual inspection, patient demographics and withdrawal time as metadata in a storage device. The auxiliary information may also be included in this metadata. The storage device may be a secure storage device located in the medical facility in which the medical observation is being performed. The storage may be a magnetically readable medium, optically readable medium or solid state type circuitry. The storage may be integrated into the image processing system 3000 or may be separate to the image processing system 3000 and connected thereto using either a wired or wireless connection. In examples, the storage may form an archive which can be used to store the records of the medical observation procedures which have been performed. Then, at a later date, said information stored in the storage unit may be retrieved for inspection. This may be used by the medical professional, for example, in order to demonstrate that an appropriate amount of time was spent during the visual inspection phase of the medical observation procedure. In some examples, the data stored in the archive from the medical observation procedure may also be used as training data to update the training of the trained model used for analysis of the image data. This can further improve the accuracy and reliability of the trained model by increasing the amount of data upon which the trained model has been trained. cTimeline of Medical Observation Procedure> The embodiments of the disclosure have been described with reference to an example timeline of a medical observation procedure (a colonoscopy) as illustrated with reference to Figures 2 and 4 of the present disclosure. However, it will be appreciated that the present disclosure is not particularly limited in this regard and may, more generally, be applied to any medical observation procedure performed by a medical professional with an imaging device (such as an endoscope or the like). In particular, in the timeline of Figure 4 of the present disclosure, only a single change of direction is detected. That is, in this timeline it is assumed that the medical professional with insert the medical image capture device into the patient and time T|N and will continue to advance the medical imaging device through the patient until they reach the maximal extent of insertion (i.e. when the end of the large intestine is reached). Only at this stage will the medical professional change the direction of the medical image capture device to a retraction / withdrawal phase (by pulling on the flexible tube of the medical image capture device). It is during this retraction / withdrawal phase that the visual inspection is performed. However, in some situations, multiple changes of direction may exist prior to the commencement of the retraction / withdrawal phase. That is, for example, during the advancement of the medical image capture device into the patient, it may become necessary for the medical professional to retract or withdraw the medical image capture device by a small amount within the patient before they are able to continue advancement to reach the maximum extent of insertion. This may occur if they encounter a blockage during the advancement phase, for example. The duration of the visual inspection phase should then be determined only from the time at which the change of direction is detected corresponding to the start of the visual inspection (i.e. the change of direction which occurs once the maximum extent of insertion has been reached). Accordingly, in examples, the image processing system 3000 is configured to identify the first time (i.e. the time of commencement of the visual inspection) as the time when the final change of direction of travel of the medical image capture device is detected prior to extraction of the medical image capture device from the patient. Consider, now, the example of Figure 7 of the present disclosure. Figure 7 illustrates an example timeline of a medical observation procedure in accordance with embodiments of the disclosure. The medical observation timeline illustrated in Figure 7 describes difference phases of a medical observation (or observation procedure). In this example, the medical observation procedure is a colonoscopy as performed by a medical professional and described with reference to Figure 2 of the present disclosure, for example. However, it will be appreciated that a similar medical observation timeline may occur for other types of medical observation procedures. The medical observation procedure of Figure 7 starts at time T|N. This is a time when the medical professional inserts the medical image capture device into the patient. In the example of a colonoscopy, this is the time corresponding to insertion of the flexible tube of the colonoscope into the body of the patient via the anus of the patient by the colonoscopist. Once inserted, the medical image capture device will be advanced through the body of the patient. This phase, where the medical image capture device is advanced through the body of the patient, corresponds to phase 'Al' of Figure 7 of the present disclosure. The medical professional does not perform visual inspection during this phase of the observation procedure. Rather, visual inspection (such as visual inspection by the colonoscopist) will take place during retraction / withdrawal of the medical imaging device from the body of the patient (e.g. retraction / withdrawal of the colonoscope from the large intestine of the patient). The phase 'Al' during which the medical image capture device is advanced through the body of the patient will - in general - continue until the medical image capture device reaches the desired extent within the body of the patient. The maximum extent reachable may depend on the size of the body of the patient (e.g. the end of the large intestine of the patient), for example. However, in this example, at time Tia, the medical professional encounters a small blockage within the large intestine of the patient. Therefore, at timeTia, the medical professional will have to temporarily and prematurely stop the advancement of the medical image capture device. Instead, to work around this blockage, the medical professional will have to perform a minor retraction of the medical image capture device within the body of the patient. This is performed in phase Bl of Figure 7. Then, at time T2a, the medical professional will again change direction of the medical image capture device and will proceed with the advancement of the medical image capture device within the body of the patient. This enables the medical professional to work around the blockage. The advancement will then continue (assuming that no further blockages are encountered) until the maximum extent reachable is achieved. That is, advancement of the medical image capture device will continue through phase Cl of Figure 7 of the present disclosure. Then, at time Tja, having reached the maximum extent within the body of the patient, the medical professional will perform one further change of direction of the medical image capture device within the body of the patient (from a forward, advancement, direction to a backward, withdrawal, direction). This withdrawal of the medical image capture device will continue through phase DI until the medical image capture device is extracted from the body of the patient at time Tout. The medical professional performs visual inspection of the patient through the phase DI of Figure 7; that is, the visual inspection of the patient is performed as the medical image capture device is being withdrawn from the patient once the maximum extent reachable has been reached. Accordingly, it is the length of this phase (i.e. phase DI) which should be measured by the image processing system 3000 when determining whether or not the appropriate time has been spent on visual inspection. Accordingly, the image processing system 3000 should not include the period of time Bl - during which the minor retraction of the medical image capture device is made to move around the blockage - when determining whether the correct amount of time has been spent on the visual inspection. Therefore, in examples, when multiple changes of direction are detected (such as changes at Tia, T2a and Tsa) the image processing system is configured to take the time corresponding to the final change of direction (i.e. T3a) as the start of the visual inspection phase of the medical observation procedure and will take the time of extraction (i.e. Tout). More generally, when multiple changes of direction of travel of the medical image capture device are detected, the circuitry is configured to identify the first time as the time at which the final change of direction of travel of the medical image capture device is detected prior to extraction of the medical image capture device from the patient. This ensures that the time of the visual inspection is accurately and reliably obtained even when multiple changes of direction of the medical image capture device are made by the medical professional. However, while, in this example, the image processing system 3000 is configured to calculate the visual inspection phase based on the last of the multiple changes of direction, the present disclosure is not particularly limited in this regard. In some examples, the size or duration of a phase of movement (following a change of direction) may be used in order to determine whether or not said phase should be included in the calculation of the visual inspection phase of the medical observation procedure. In examples, minor phases of retraction (less than a predetermined time duration in length) may be excluded from the calculation. This is because small retractions (such as described for phase Bl of Figure 7 of the present disclosure) are generally associated with manoeuvres of the medical image capture device as the medical professional attempts to navigate around a blockage and may not necessarily be associated with a visual inspection phase of the medical observation procedure. Accordingly, in examples, these short phases may be excluded from the calculation of the visual inspection duration. <Advantageous Technical Effects> In accordance with embodiments of the present disclosure, an image processing system, method and computer program are provided. In accordance with embodiments of the disclosure, more accurate and reliable imaging with a medical imaging device can be performed. This can improve patient outcomes when the medical imaging device is used in order to identify medical conditions. In particular, notification information (such as timing information) of a medical observation procedure can be automatically generated based on the analysis of the image data received from the medical image capture device, the accuracy and reliability of the measurement of the visual inspection phase can be improved. It will be appreciated that the present disclosure is not particularly limited to these advantageous technical effects. Other advantageous technical effects will become apparent to the skilled person when reading the disclosure. <Method> Hence, more generally, an image processing method is provided in accordance with embodiments of the disclosure. An example image processing method is illustrated with reference to Figure 8 of the present disclosure. The image processing method starts at step S8000 and proceeds to step S8002. In step S8002, the method comprises receiving image data captured by a medical image capture device, the medical image capture device for insertion into and / or for extraction from a patient. In step S8004, the method comprises analysing the image data to identify a first time corresponding to a change of direction of travel of the medical image capture device within the patient. Then, the method proceeds to step S8006. In step S8006, the method comprises analysing the image data to identify a second time corresponding to extraction of the medical image capture device from the patient. The method then proceeds to step S8008. In step S8008, the method comprises generating notification information when the first time and the second time satisfy a predetermined condition. The method then proceeds to, and ends with, step S8010. The image processing method can be performed by an apparatus 1000 as described with reference to Figure 1 of the present disclosure and / or an image processing system 3000 as described with reference to Figure 3 of the present disclosure. However, the present disclosure is not particularly limited in this regard. When the medical image capture device is an endoscope, the endoscope may be inserted into and extracted from a natural orifice of the patient. Thus, imaging can be performed in a non-surgical procedure. It will be appreciated that the method described with reference to Figure 8 is an example method in accordance with embodiments of the present disclosure. Therefore, the present disclosure is not particularly limited to the example method illustrated in Figure 8. For example, while the example method of Figure 8 is shown in a sequence of steps, it will be appreciated that the present disclosure is not particularly limited in this regard. A number of the steps of the method may, alternatively, be performed in parallel. In addition, a number of additional steps (such as detection of the insertion of the medical imaging device) can also, optionally, be performed. <Computer Program> In addition, a computer program may be provided comprising instructions which, when implemented by a computer, cause the computer to perform an image processing method in accordance with embodiments of the disclosure. This computer program may be stored on a non-transitory computer readable storage medium. <Endoscopic surgical system> Turning now to Figure 9 of the present disclosure, a block diagram illustrating an example of a schematic configuration of an endoscopic surgery system 5000 to which the technology according to the present disclosure can be applied is shown. Figure 2 illustrates a state where an operator (doctor) 5067 is conducting surgery to a patient 5071 on a patient bed 5069 using the endoscopic surgery system 5000. As illustrated, the endoscopic surgery system 5000 is constituted by an endoscope 5001, other surgical tools 5017, and a support arm device 5027 supporting the endoscope 5001, and a cart 5037 on which various devices for endoscopic surgery are mounted. In the endoscopic surgery, the abdominal wall is punctured with a plurality of tubular hole-opening instruments called trocars 5025a to 5025d instead of cutting the abdominal wall to open the abdomen. Then, a lens barrel 5003 of the endoscope 5001 and the other surgical tools 5017 are inserted into a body cavity of the patient 5071 through the trocars 5025a to 5025d. In the illustrated example, as the other surgical tools 5017, an insufflation tube 5019, an energy treatment tool 5021, and forceps 5023 are inserted into the body cavity of the patient 5071. Furthermore, the energy treatment tool 5021 is a treatment tool that performs incision and peeling of a tissue, sealing of a blood vessel, or the like using high-frequency current or ultrasonic vibration. However, the illustrated surgical tool 5017 is merely an example, and various surgical tools generally used in endoscopic surgery, for example, tweezers, a retractor, and the like may be used as the surgical tool 5017. An image of an operation site in the body cavity of the patient 5071 captured by the endoscope 5001 is displayed on a display device 5041. The operator 5067 performs treatment, for example, to excise an affected site using the energy treatment tool 5021 or the forceps 5023 while viewing the image of the operation site displayed by the display device 5041 in real time. Note that the insufflation tube 5019, the energy treatment tool 5021, and the forceps 5023 are supported by the operator 5067, an assistant, or the like during surgery although not illustrated. Embodiments of the present disclosure may be applied to, and used with, an endoscopic surgical system 5000 as described with reference to Figure 9 of the present disclosure. <Clauses> In addition, embodiments of the present disclosure can be arranged in accordance with the following numbered clauses: 1. An image processing system comprising processing circuitry configured to: receive image data captured by a medical image capture device, the medical image capture device for insertion into and / or for extraction from a patient; analyse the image data to identify a first time corresponding to a change of direction of travel of the medical image capture device within the patient; analyse the image data to identify a second time corresponding to extraction of the medical image capture device from the patient; and generate notification information when the first time and the second time satisfy a predetermined condition. 2. The image processing system according to clause 1, wherein the predetermined condition is that the first time and the second time have been identified. 3. The image processing system according to clause 1, wherein circuitry is further configured to generate the notification information when a time between the first time and the second time satisfies the predetermined condition. 4. The image processing system according to clause 3, wherein the predetermined condition is a condition that the time between the first time and the second time is less than a predetermined amount of time. 5. The image processing system according to clause 3, wherein the predetermined condition is a condition that the time between the first time and the second time exceeds a predetermined amount of time. 6. The image processing system according to any preceding clause, wherein the notification information comprises at least one of visual, auditory and / or haptic feedback. 7. The image processing system according any preceding clause, wherein the notification information comprises a notification that the time between the first time and the second time is less than the predetermined amount of time. 8. The image processing system according to any preceding clause, wherein the image processing system comprises a display device on which the image data captured by the medical image capture device is displayed. 9. The image processing system according to clause 8, wherein the circuitry is further configured to display the notification information which has been generated on the display device. 10. The image processing system according to clause 8 or 9, wherein the circuitry is further configured to display information comprising a time which has elapsed since the first instance of time on the display device. 11. The image processing system according to any preceding clause, wherein the circuitry is further configured to store one or more of: the first time and the second time, the time between the first time and the second time, and / or the notification information as metadata associated with the image data captured by the medical image capture device. 12. The image processing system according to any preceding clause, wherein the circuitry is further configured to store one or more of: the first time and the second time, the time between the first time and the second time, and / or the notification information as metadata associated with the patient. 13. The image processing system according to any preceding clause, wherein the circuitry is further configured to store additional information as metadata associated with the image data captured by the medical image capture device and / or as metadata associated with the patient. 14. The image processing system according to clause 13 wherein the additional information includes an identification of medical staff performing a medical observation with the medical image capture device. 15. The image processing system according to any preceding clause, wherein the processing circuitry is further configured to use a trained model to detect the change of direction of travel of the medical image capture device within the patient. 16. The image processing system according to any preceding clause, wherein the processing circuitry is further configured to use a trained model to detect extraction of the medical image capture device from the patient. 17. The image processing system according to clause 15 or 16, wherein the trained model comprises at least one of a machine learning model and / or a deep learning model. 18. The image processing system according to any preceding clause, wherein analysis of the image data to identify a first time at which a change of direction of travel of the medical image capture device within the patient occurs comprises motion analysis of the image data. 19. The image processing system according to any preceding clause, wherein the circuitry is further configured to perform the analysis of the image data when the medical image capture device has been inserted into the patient. 20. The image processing system according to any preceding clause, wherein the circuitry is further configured to analyse the image data to identify insertion of the medical image capture device into the patient. 21. The image processing system according to any preceding clause, wherein when multiple changes of direction of travel of the medical image capture device are detected, the circuitry is configured to identify the first time as the time at which the final change of direction of travel of the medical image capture device is detected prior to extraction of the medical image capture device from the patient. 22. The image processing system according to any preceding clause, wherein the circuitry is further configured to analyse the image data to identify a speed of the medical image capture device in the direction of travel and generate notification information when a speed of the medical image capture device is above a predetermined threshold speed. 23. The image processing system according to clause 22, wherein the predetermined threshold speed is set in accordance with a type of medical observation being performed on the patient. 24. The image processing system according to any preceding clause, wherein the circuitry is further configured to analyse the image data to identify a speed of the medical image capture device in the direction of travel; generate a predicted amount of time, being an amount of time between the first time and a time at which extraction of the medical image capture device from the patient will occur; and generate second notification information when the predicted amount of time is less than the predetermined amount of time. 25. The image processing system according to any of clauses 22 to 24, wherein the circuitry is configured to change a colour of the notification information in accordance with a speed of the medical image capture device. 26. The image processing system according to any preceding clause, wherein the predetermined amount of time is set in accordance with a type of medical observation being performed on the patient. 27. The image processing system according to any preceding clause, further comprising the medical image capture device, and wherein the medical image capture device is configured to be moved in a first direction of travel corresponding to advancement of the medical image capture device within the patient and a second direction of travel corresponding to retraction of the medical image capture device within the patient. 28. The image processing system according to any preceding clause, wherein the medical image capture device is an endoscopic imaging device. 29. A computer program comprising instructions which, when executed by a computer, cause the computer to perform an image processing method comprising the steps of: receiving image data captured by a medical image capture device, the medical image capture device for insertion into and / or for extraction from a patient; analysing the image data to identify a first time corresponding to a change of direction of travel of the medical image capture device within the patient; analysing the image data to identify a second time corresponding to extraction of the medical image capture device from the patient; and generating notification information when the first time and the second time satisfy a predetermined condition. 30. A non-transitory computer readable medium comprising the computer program according to clause 29. 31. An image processing method comprising the steps of: receiving image data captured by a medical image capture device, the medical image capture device for insertion into and / or for extraction from a patient; analysing the image data to identify a first time corresponding to a change of direction of travel of the medical image capture device within the patient; analysing the image data to identify a second time corresponding to extraction of the medical image capture device from the patient; and generating notification information when the first time and the second time satisfy a predetermined condition. While some embodiments of the disclosure have been described with reference to a specific example of colonoscopy, it will be appreciated that the present disclosure is not particularly limited in this regard. Embodiments of the disclosure may be applied more generally to other medical observation procedures using a medical imaging device such as an endoscope. Therefore, the example of colonoscopy has been provided as one example situation to which embodiments of the disclosure may be applied. Numerous modifications and variations of the present disclosure are possible in light of the above teachings. It is therefore to be understood that within the scope of the appended claims, the disclosure may be practiced otherwise than as specifically described herein. In so far as embodiments of the disclosure have been described as being implemented, at least in part, by software-controlled data processing apparatus, it will be appreciated that a non-transitory machine-readable medium carrying such software, such as an optical disk, a magnetic disk, semiconductor memory or the like, is also considered to represent an embodiment of the present disclosure. It will be appreciated that the above description for clarity has described embodiments with reference to different functional units, circuitry and / or processors. However, it will be apparent that any suitable distribution of functionality between different functional units, circuitry and / or processors may be used without detracting from the embodiments. Described embodiments may be implemented in any suitable form including hardware, software, firmware or any combination of these. Described embodiments may optionally be implemented at least partly as computer software running on one or more data processors and / or digital signal processors. The elements and components of any embodiment may be physically, functionally and logically implemented in any suitable way. Indeed, the functionality may be implemented in a single unit, in a plurality of units, or as part of other functional units. As such, the disclosed embodiments may be implemented in a single unit or may be physically and functionally distributed between different units, circuitry and / or processors. Although the present disclosure has been described in connection with some embodiments, it is not intended to be limited to the specific form set forth herein. Additionally, although a feature may appear to be described in connection with particular embodiments, one skilled in the art would recognise that various features of the described embodiments may be combined in any manner suitable to implement the technique.

Claims

1) An image processing system comprising processing circuitry configured to:receive image data captured by a medical image capture device, the medical image capture device for insertion into and / or for extraction from a patient;analyse the image data to identify a first time corresponding to a change of direction of travel of the medical image capture device within the patient;analyse the image data to identify a second time corresponding to extraction of the medical image capture device from the patient; andgenerate notification information when the first time and the second time satisfy a predetermined condition.2) The image processing system according to claim 1, wherein the predetermined condition is that the first time and the second time have been identified.3) The image processing system according to claim 1, wherein circuitry is further configured to generate the notification information when a time between the first time and the second time satisfies the predetermined condition.4) The image processing system according to claim 3, wherein the predetermined condition is a condition that the time between the first time and the second time is less than a predetermined amount of time.5) The image processing system according to claim 3, wherein the predetermined condition is a condition that the time between the first time and the second time exceeds a predetermined amount of time.6) The image processing system according to any preceding claim, wherein the notification information comprises at least one of visual, auditory and / or haptic feedback.7) The image processing system according any preceding claim, wherein the notification information comprises a notification that the time between the first time and the second time is less than the predetermined amount of time.8) The image processing system according to any preceding claim, wherein the image processing system comprises a display device on which the image data captured by the medical image capture device is displayed.9) The image processing system according to claim 8, wherein the circuitry is further configured to display the notification information which has been generated on the display device.10) The image processing system according to claim 8 or 9, wherein the circuitry is further configured to display information comprising a time which has elapsed since the first instance of time on the display device.11) The image processing system according to any preceding claim, wherein the circuitry is further configured to store one or more of: the first time and the second time, the time between the first time and the second time, and / or the notification information as metadata associated with the image data captured by the medical image capture device.12) The image processing system according to any preceding claim, wherein the circuitry is further configured to store one or more of: the first time and the second time, the time between the first time and the second time, and / or the notification information as metadata associated with the patient.13) The image processing system according to any preceding claim, wherein the circuitry is further configured to store additional information as metadata associated with the image data captured by the medical image capture device and / or as metadata associated with the patient.14) The image processing system according to claim 13 wherein the additional information includes an identification of medical staff performing a medical observation with the medical image capture device.15) The image processing system according to any preceding claim, wherein the processing circuitry is further configured to use a trained model to detect the change of direction of travel of the medical image capture device within the patient.16) The image processing system according to any preceding claim, wherein the processing circuitry is further configured to use a trained model to detect extraction of the medical image capture device from the patient.17) The image processing system according to claim 15 or 16, wherein the trained model comprises at least one of a machine learning model and / or a deep learning model.18) The image processing system according to any preceding claim, wherein analysis of the image data to identify a first time at which a change of direction of travel of the medical image capture device within the patient occurs comprises motion analysis of the image data.19) The image processing system according to any preceding claim, wherein the circuitry is further configured to perform the analysis of the image data when the medical image capture device has been inserted into the patient.20) The image processing system according to any preceding claim, wherein the circuitry is further configured to analyse the image data to identify insertion of the medical image capture device into the patient.21) The image processing system according to any preceding claim, wherein when multiple changes of direction of travel of the medical image capture device are detected, the circuitry is configured to identify the first time as the time at which the final change of direction of travel of the medical image capture device is detected prior to extraction of the medical image capture device from the patient.22) The image processing system according to any preceding claim, wherein the circuitry is further configured to analyse the image data to identify a speed of the medical image capture device in the direction of travel and generate notification information when a speed of the medical image capture device is above a predetermined threshold speed.23) The image processing system according to claim 22, wherein the predetermined threshold speed is set in accordance with a type of medical observation being performed on the patient.24) The image processing system according to any preceding claim, wherein the circuitry is further configured to analyse the image data to identify a speed of the medical image capture device in the direction of travel; generate a predicted amount of time, being an amount of time between the first time and a time at which extraction of the medical image capture device from the patient will occur; and generate second notification information when the predicted amount of time is less than the predetermined amount of time.25) The image processing system according to any of claims 22 to 24, wherein the circuitry is configured to change a colour of the notification information in accordance with a speed of the medical image capture device.26) The image processing system according to any preceding claim, wherein the predetermined amount of time is set in accordance with a type of medical observation being performed on the patient.27) The image processing system according to any preceding claim, further comprising the medical image capture device, and wherein the medical image capture device is configured to be moved in a first direction of travel corresponding to advancement of the medical image capture device within the patient and a second direction of travel corresponding to retraction of the medical image capture device within the patient.28) The image processing system according to any preceding claim, wherein the medical image capture device is an endoscopic imaging device.29) A computer program comprising instructions which, when executed by a computer, cause the computer to perform an image processing method comprising the steps of:receiving image data captured by a medical image capture device, the medical image capture device for insertion into and / or for extraction from a patient;analysing the image data to identify a first time corresponding to a change of direction of travel of the medical image capture device within the patient;analysing the image data to identify a second time corresponding to extraction of the medical image capture device from the patient; andgenerating notification information when the first time and the second time satisfy a predetermined condition.30) A non-transitory computer readable medium comprising the computer program according to claim 29.31) An image processing method comprising the steps of:receiving image data captured by a medical image capture device, the medical image capture device for insertion into and / or for extraction from a patient;analysing the image data to identify a first time corresponding to a change of direction of travel of the medical image capture device within the patient;analysing the image data to identify a second time corresponding to extraction of the medical image capture device from the patient; andgenerating notification information when the first time and the second time satisfy a predetermined condition.34

Images