Method and device for anatomopathology with object identification and tracking

Abstract

A method for the histopathological examination of biological tissues, in particular an operative specimen or biopsy, in particular for anatomo-cytopathology (ACP), the method comprising identification and tracking of an object by analysing a video stream during a step of pre-analysis and / or a step of analysis of the biological tissues.

Description

[0001] Method and device for anatomopathology with identification and tracking of objects

[0002] Technical field

[0003] The invention relates to pathological anatomy and cytology.

[0004] State of the art

[0005] Pathological anatomy and cytology, or anatomo-cytopathology (ACP), refers to the medical specialty that studies tissues, cells, and their abnormalities to aid in the diagnosis of diseases, such as tumors, or diseases of inflammatory, degenerative, vascular, metabolic, or infectious origin. Anatomic cytopathology also refers to autopsy and fetopathology procedures.

[0006] Anatomical cytopathology (ACP) is a medical specialty that lies at the intersection of clinical, imaging, and biology. It can only be practiced in France by physicians qualified in ACP, or by medical laboratory technicians, under the supervision of a medical biologist or a physician qualified in ACP (Article L4352-1 of the Public Health Code).

[0007] Pathological anatomy and cytology involves macroscopic study, as well as various methods of microscopy and molecular biology for histological and cytological analysis.

[0008] PCR diagnosis is based on the presence or absence of tissue or cellular abnormalities, macroscopic or microscopic, compared to normal. PCR diagnosis is essential for tumor diagnosis and personalized therapeutic management and targeted treatment of cancers.

[0009] The pathologist analyzes samples for histopathological examination: these are biopsies, curettage products, endoscopic resections and aspirations, spontaneous expulsion materials, samples of surgical or amputation specimens, organ samples. The examination can take place in a pathology laboratory, or during a surgical intervention (extemporaneous examination).

[0010] The term "biopsy" here refers to a small fragment of tissue taken transcutaneously or endoscopically, for example a tumor sample.

[0011] By "operative specimen" we mean partial or complete excisions of one or more organs, removed in the operating room during a surgical intervention.

[0012] The examination of surgical specimens includes a macroscopic examination allowing their measurement, weighing and description. The surgical specimens must be fixed, dissected, described, measured and sampled according to specific protocols.

[0013] Fixation must be carried out within a short time: otherwise, desiccation or autolysis of the tissue may make the study difficult or even impossible. Before fixation, hollow organs must be opened and, if necessary, washed of their contents, in order to prevent autolysis of the mucous membranes. Solid organs such as the liver and spleen must be cut into slices, to facilitate the homogeneous and rapid penetration of the fixative.

[0014] Macroscopy allows us to observe the appearance, colour, size and consistency of an organ or mucosa, which are suggestive of a pathology, for example hepatic steatosis, cholestasis, ulcerative colitis.

[0015] Digital images can be acquired during macroscopy or subsequent microscopy steps, to be indexed and saved in a laboratory management system (LMS). Images of the surgical specimen, fresh or fixed, which will be dissected, are stored digitally and attached to the patient's file. Macroscopy laboratory workstations typically include a stainless steel table on which a dissection board is placed. In some cases, the workstation is equipped with an imaging device to allow images to be taken and annotated during macroscopy.

[0016] During the macroscopy phase, the technician usually has one or more vials labeled with a sample-specific file number, and linked to the patient in the laboratory management system. The technician extracts the contents of the vial and places it in one or more cassettes that are also labeled.

[0017] Examples of cassettes are presented in US1 1 774320 (Biopath, 2023), EP231 601 0B1 (The Univ of Miami, 2022), US8877146 (Biopath, 2014), US7771992 (Leica Biosystems, 201 0), DE4306233 (Guenter, 1994), GB2278441 (Cellpath, 1994).

[0018] For medical laboratory technicians, manual operations are repetitive and performed in large numbers every day. This results in risks of error, such as bottle reversals and forgetfulness.

[0019] The risk of error, inversion or omission is also possible during other phases of pre-analysis, which begins with the collection from the patient and ends with the reading of the slide by the pathologist, such as during cryotomy, decalcification, dehydration, embedding or inclusion, microtomy, spreading and staining.

[0020] Sagar et al. (Laboratory errors in pathology and troubleshooting methods, Journal of Pharmaceutical Negative Results, 2022 Special Issue 7, Vol. 13, p272-278. 7p. DOI: 10.47750 / pnr.2022. 13.S07.037) present a list of human errors that can occur during pre-analytical, analytical and post-analytical stages.

[0021] Dimenstein (Root cause analysis of specimen misidentification in surgical pathology accession and grossing, 2006, DOI: 10. 1309 / B7KJB4QDM7YE35CV) presents different sources of human errors, for example confusion between right and left, writing errors, wrong choice of bottle or cassette, these errors being seen as linked to human psychology, and therefore inevitable.

[0022] Santana et al. (Errors in surgical pathology laboratory, 2018, DOI: 10.5772 / intechopen.72919), based on a synthesis of around forty articles, conclude that there is an inevitable risk of human error during analyses in anatomopathology laboratories, and that these errors can have serious consequences, generating false positives or false negatives.

[0023] We can also refer to the documents Simo Huang et al. (Errors encountered in the diagnostic pathway: A prospective single-institution study, Journal of Cutaneous Pathology, 2023, DOI / 10. 1 1 1 1 / cup. 14474), Steelman, Surgical Specimen Management: A Descriptive Study of 648 Adverse Events and Near Misses, Arch Pathol Lab Med, 2016, DOI 10.5858 / arpa.2016-0021 -OA), Tang et al. (Patient safety issues in pathology: from mislabelled specimens to interpretation errors, 2018, doi.org / 10.5772 / intechopen. 796334), Van Moll et al. (The Nature, Causes, and Clinical Impact of Errors in the Clinical Laboratory Testing Process Leading to Diagnostic Error: A Voluntary Incident Report Analysis, Journal of Patient Safety, 2023, 19(8), 573-579).

[0024] Pathology laboratories are prone to sample identification errors due to the many steps involved in sample modification.

[0025] Several different stakeholders must ensure that the identification of the sample is preserved during different stages of sample processing, in particular during collection, macroscopic description, placement in a cassette, inclusion in a block (most often in paraffin), transfer onto a slide after cutting the paraffin block with a microtome.

[0026] An identification error can occur at any of these stages, and can have serious consequences for the patient, such as a delay in diagnosing a disease (in the case of a false negative), or the performance of unnecessary surgical operations (in the case of a false positive).

[0027] Various empirical measures are implemented to try to prevent the risk of sample identity errors. For example, it is recommended to avoid recording and consecutively describing similar samples. It is also recommended to minimize distractions during transcription or sample identity verification operations.

[0028] To reduce the risk of errors, containers such as bottles or jars containing tissue samples submitted to the pathology laboratory bear two different identifiers: the patient's first and last name, and a patient-specific identification number. Each container may also bear the date of collection.

[0029] ISO 1 51 89-12 requires that all samples received be entered into an admission register in a computer system, and the date and time of receipt of the samples must be recorded. During this registration, an identification number is assigned to each sample received, and this identification number is retained throughout the sample processing process in the pathology laboratory. The 2022 version of ISO 151 89 states that each PCR examination request must be considered a contract, and must ensure the traceability of the patient, the request and the prescriber. By traceability, ISO 9000:2005 means the ability to trace the history, implementation or location of what is examined.

[0030] Anatomical cytopathology is a specialty practiced by a limited number of professionals. In France, according to the union of pathologists, 1,471 practitioners were practicing in 2018. According to the AFAQAP (French Association for Quality Assurance in Pathological Anatomy and Cytology), there were approximately 270 ACP structures and laboratories in France in 2020, including 130 private structures and 135 hospital structures.

[0031] The activities of anatomic pathology professionals are distinct, in technical and regulatory terms, as well as in terms of the machines used, from the activities of medical analysis laboratory technicians. In particular, the workflow of a PCR laboratory includes, for tissue samples, specific steps of fixation of the samples, macroscopy, placement in cassettes, inclusion (usually in paraffin), and cutting with a cryostat or microtome. Each of these steps can lead to errors and a loss of traceability.

[0032] In an attempt to reduce the risk of identification errors and improve traceability, thermal printing systems for alphanumeric characters and two-dimensional barcodes on cassettes or slides are commercially available. Examples include documents IT20190001 2333 (Logibiotech, 2021), US201 9324048 (Sakura Finetek, 2019), WO20140181 14, (Aperio technologies, 2014), W02007 / 078842 (Ventana Medical Systems, 2007). Reference may also be made to documents Mei-Hua et al. (The Effect of Barcode Technology Use on Pathology Specimen Labeling Errors, 2019, doi 10.1002 / aorn.12585), Pantanowitz et al. (Tracking in Anatomic Pathology, 2013, Arch Pathol Lab Med, DOI 10.5858. arpa.2013-0125-SA). Such systems reduce the risks associated with manual entry, but do not eliminate data entry errors in a computer system and handling errors.

[0033] Norgan et al. (Radio-frequency identification specimen tracking to improve quality in anatomic pathology, Arch Pathol Lab Med- Vol 144, February 2020, DOI: 10.5858 / arpa.2019-001 1 -OA) describe the use of passive high-frequency RFI D tags (902-928 MHz) to reduce the risk of errors during pre-analytical steps. The RFI D tags are placed on a support bearing a unidirectional barcode (encoding the patient identification number), and a bidirectional barcode (encoding the RFI D tag identifier). After a 6-month observation period on a total of 56,000 samples, the authors concluded that identification errors were reduced, compared to the use of barcodes alone. The use of RFI D tags has several disadvantages. The cost of RFI D tags is high. The risk of interference during reading cannot be eliminated.

[0034] WO2022 / 266459 (Bioptek, 2022) describes a system and method for automated processing of biopsy samples, and discusses analysis of still images.

[0035] General presentation of the invention

[0036] One of the objectives of the invention is to reduce the risk of error during pathological anatomy and cytology work.

[0037] One of the objects of the invention is to propose a method and a device ensuring the traceability of a sample in anatomopathology, from the operating room to cutting and spreading on slides and to the archiving of slides and paraffin blocks.

[0038] The invention aims to ensure traceability over all stages of the ACP, whether it is the pre-analytical phase or the analytical phase, and advantageously the post-analytical phase.

[0039] The analytical phase refers to all the stages in chronological order of work on biological material (human or animal), the collection or sample, from the analysis itself to its technical and / or medical validation.

[0040] The pre-analytical phase refers to all the steps in chronological order starting with the formulation of the analysis request by the prescriber, the identification of the patient, the collection of the biological material, its transport to the PCR laboratory, its reception at the PCR laboratory, its recording or encoding and any other operation or handling of this material before the start of the analytical phase. The post-analytical phase refers to all the steps in chronological order from the end of the analytical phase, including the review of the results, the authorization of release, the preparation of the report, the transmission of the validated results to their recipients, the storage, archiving and / or the elimination of the biological material.

[0041] The storage (including archiving and organization thereof) of biological material, including partial samples and residual material, is the ultimate responsibility of the PCR laboratory operator.

[0042] Paraffin blocks must be preserved: they may be useful or necessary later, in order to refine or complete the diagnosis of the patient from whom they come, for example in the event of additional immunohistochemical or molecular examination.

[0043] Histological sections and stained cytology slides, whether analog or digital, may be subject to subsequent interpretation and must also be preserved.

[0044] The minimum legal retention periods for biological materials vary from one state to another, and may be, for example, ten years for paraffin blocks, and twenty years from the date of collection for histological sections and stained cytology slides.

[0045] The invention also aims to ensure traceability on the conservation of biological materials.

[0046] For these purposes, a first aspect of the invention provides a method for the histopathological examination of biological tissues, in particular surgical specimens or biopsies, in particular for ACP anatomo-cytopathology, the method comprising object identification and tracking by analysis of a video stream during a pre-analytical step and / or an analytical step of the biological tissues. By object identification and tracking by analysis of a video stream, we mean here in particular computer vision techniques implementing segmentation of video images or segmentation or detection of objects, for example active contour methods using statistical criteria. By object detection, we mean here the detection and classification in images of objects belonging to sets of predefined categories. Object detection is for example carried out in still images, by deep learning such as R-CNN.Object detection is advantageously carried out by analyzing a video stream, with object detection and tracking being carried out using YOLO, for example.

[0047] Advantageously, the video stream comes from at least one digital camera recording in the wavelengths perceptible by the human eye.

[0048] Alternatively, the camera records wavelengths in the infrared range. The camera can thus provide information on the surface temperature of identified objects.

[0049] Alternatively, the camera records wavelengths in the ultraviolet range. The camera can thus provide information on the presence of markers for biological tissue, for example on the margins of a surgical specimen.

[0050] In some implementations, at least one camera is said to be proximity camera, and is placed as close as possible to the area in which the work carried out on a pre-analytical workstation and / or an analytical workstation and / or a post-analytical workstation takes place.

[0051] Alternatively, at least one camera is positioned so as to film an entire analytical or pre-analytical workstation, this camera being for example fixed to the ceiling of a room. Advantageously, the video streams from this camera are analyzed in parallel and simultaneously with the analysis of the video streams from the proximity camera (or proximity cameras).

[0052] Object tracking is advantageously carried out in real time, that is to say at a speed adapted to the progress of each pre-analytical step and / or each analytical step.

[0053] An error message is thus advantageously generated in the event of a discrepancy or difference between the state of an object and a reference state for this object. By state of an object, we mean here for example the open or closed situation of a container, a quantity of liquid in a container, information present on a support.

[0054] In various implementations, the pre-analytical step is selected from the group comprising the collection of biological tissues in the surgical field, orientation of the biological tissues, labeling of the collected biological tissues, placement of the tissues in a container in a fresh state, immersion of the collected biological tissues in a preservation liquid such as a fixative, preparation of a histopathological examination request form, transport of the sample to a recording station, recording of the sample in a laboratory management system.

[0055] According to various embodiments, an identification and tracking of an object by analysis of a video stream is carried out during at least one of these pre-analytical steps, the identified and tracked object being for example a sampled biological tissue, a container (bucket, bottle) in which a biological tissue must be placed, an examination request form, a label bearing a bar code intended to be attached to a container.

[0056] Advantageously, the method comprises a step of labeling biological tissues with generation of a first patient identity, in alphanumeric form or in coded form, in particular by bar code, the identification and tracking of the object by analysis of a video stream comprising a step of reading this first patient identity, in particular a bar code reading, or character recognition (OCR).

[0057] The barcode can be one-dimensional or two-dimensional, for example QR Code or Data Matrix.

[0058] Advantageously, the method comprises a step of preparing a histopathological examination request form, advantageously digital, generating a second patient identity, the identification and tracking of the object by analysis of a video stream comprising a step of reading this examination request form and the second patient identity, an alert message being generated in the event of a discrepancy between the first and second patient identities.

[0059] Advantageously, the method comprises a step of interrogating the computerized patient record and a step of collecting information elements contained in the computerized patient record, for copying into a histopathological examination request form generated in digital form.

[0060] Advantageously, the method comprises object identification and tracking by analysis of a video stream during the immersion of biological tissues such as an operating part in a preservative liquid, such as a fixative, an alert message being generated when the volume of preservative liquid is not adapted to the volume of biological tissues.

[0061] Advantageously, the method comprises a control step carried out in a buffer zone in which a plurality of samples of biological tissue are collected, in particular from different operating rooms of an operating theatre, the method comprising an identification and tracking of an object by analysis of a video stream for counting the containers placed in the buffer zone.

[0062] Advantageously, the method comprises object identification and tracking by analyzing a video stream during the recording of a sample in a laboratory management system, for counting containers and / or checking the adequacy of the volume of fixative for the sample placed in a container.

[0063] Advantageously, the method comprises an identification and tracking of an object by analysis of a video stream during a step of preparation of biological tissues chosen from the group comprising dehydration, inclusion in a material, in particular paraffin, cutting in particular with a cryostat or microtome to form ribbons, spreading of the ribbons on supports such as glass slides, distribution.

[0064] Advantageously, the method comprises reading all of the cassette identifiers, these identifiers being alphanumeric or coded, in particular in a bar code. In certain implementations, 50 bar codes are for example read for each still image.

[0065] Advantageously, at least one interface screen of a dehydration machine is filmed, an analysis of a video stream making it possible to generate information including for example the duration of the dehydration cycle, the time remaining until the end of dehydration, the type of cycle, the presence of an alarm.

[0066] Advantageously, the method comprises a step of generating an alert message, when an operating alarm has been detected for the dehydration machine, during the analysis of the video stream coming from the camera filming the interface screen of the dehydration machine.

[0067] Advantageously, the method comprises an identification and tracking of an object by analysis of a video stream during a step of inclusion of biological tissues in an inclusion material such as paraffin, the analysis of the video stream being capable of ensuring a count of the biological tissues transferred to the inclusion mold.

[0068] Advantageously, the analytical step is chosen from the group comprising the different steps of macroscopic study, in particular the inking of the margins of lesions, the production of samples, by sections in a sample of human tissue, or by cross-sections in a sample of animal tissue.

[0069] Advantageously, the method comprises an analysis of the video streams allowing a count of the samples present on the stained slides, from a cassette, and a step of verifying the correlation of this number with the number of samples present in the cassette, or a step of verifying the size of the samples (for example biopsy cores) and / or the surface area of ​​the samples, in particular to verify that no loss of material has occurred.

[0070] According to a second aspect, there is proposed an anatomopathology method comprising a step of introducing a tissue into a first container provided with a closing means, a step of closing the first container after introduction of the tissue, a step of placing on the first container an identifier of the tissue introduced into the first container, a step of opening the first container and extracting the tissue from the first container, a step of moving at least a portion of the tissue extracted from the first container into a second container, the second container carrying an identifier of the portion of tissue, the method comprising an identification and tracking of objects by analysis of a video stream, the opening of the first container being detected during this identification and tracking of objects, the method comprising a step of detecting and reading the identifier placed on the first container and the identifier placed on the second container,an error message being generated in the event of a mismatch between the identifier of the first container and the identifier of the second container.,

[0071] The process makes it possible to alert the technician of a loss of concordance during a step of moving the biological tissue from a first container such as a bottle or a pot, to a second container such as a cassette.

[0072] Advantageously, the method comprises a step of recording the instant at which the opening of the first container is detected. This recording improves the traceability of the method, the instant of detection of the opening of the first container being able to be compared with the instant at which the sample was taken, for example by excision or biopsy. If fixation must be carried out for the biological tissue, it can thus be verified that the fixation occurs within a short period of time, avoiding desiccation or autolysis of the tissue.

[0073] Advantageously, since the second container is a cassette, the closing of the cassette and the closing of the first container are detected by the identification and tracking of objects during the analysis of the video stream. It is thus possible to generate an error message if a new container is opened before the first container is closed.

[0074] Advantageously, a display of the objects identified during the analysis of the video stream is carried out, the shape of the identified objects being represented for example by a bounding window. The operator can thus verify that the identification of the objects corresponds to the operations carried out. The operator can, if necessary, add comments by voice command, or using a keyboard or mouse or even a touch screen.

[0075] According to a third aspect, a device is proposed for implementing a method as presented above, the device comprising means for identifying and tracking objects by analyzing a video stream coming from at least one camera.

[0076] According to another aspect, there is proposed an anatomopathology device for implementing a method as presented above, the device comprising a workstation comprising a dissection board (cutting board) intended to support a first container provided with a closing means and a second container, the device comprising means for identifying and tracking objects by analyzing a video stream, these means being capable of detecting the opening of the first container, the device comprising means for detecting and reading an identifier placed on the first container and an identifier placed on the second container, the device comprising means for generating an error message in the event of a discrepancy between the identifier of the first container and the identifier of the second container.

[0077] Advantageously, in certain implementations, the cutting board comprises a reservation capable of accommodating a first or a second container, the first container being for example a bottle, the second container being for example a cassette.

[0078] Advantageously, the detection and reading means comprise a one-dimensional or two-dimensional barcode reader, for example of the QR or Data Matrix type, or even Aztec code. Alternatively or in combination, character recognition (OCR) is carried out. Advantageously, the decoding of the barcode is carried out directly via an image captured by a camera.

[0079] Data Matrix refers to the coding of data in a matrix of cells, the code being presented in the form of a square or rectangular symbol. The Data Matrix code is described in the ISO / I EC16022 standard. An encoding algorithm combines the useful data with error correction codes. The coding format is advantageously ECC200 (Error Checking and Correcting).

[0080] The QR code is defined by the ISO / I EC 1 8004 standard. It also has a multi-level error correction system, allowing the reconstruction of missing data, when part of the code cannot be read. In some implementations, the QR code is static and advantageously integrates a URL (Uniform Resource Locator). In other implementations, the QR code is dynamic, and integrates a short URL, redirecting the user to another URL.

[0081] The Aztec code is described in the ISO / I EC 24778 standard.

[0082] The identification can be placed on the containers by gluing a label, thermal transfer, or even by engraving, particularly laser engraving. Advantageously, the workstation includes weighing equipment. It is thus possible to compare the weight of the biological tissue, measured during the biopsy or surgical excision, with the weight of the tissue arriving at the pathology laboratory. It is also possible to check that the quantity of formalin (or other preservation product used) is suitable for the sample to be analyzed.

[0083] Advantageously, the workstation includes means of measuring along several axes.

[0084] Advantageously, the device comprises a station for including biological tissue to form a block, for example of paraffin, a station for cutting the block into thin slices by microtome, the slices having for example a thickness of the order of 3 to 5 microns, and a station for spreading the slices on slides, the device comprising means for printing on the block and on the slides an identifier of the biological tissue.

[0085] In some implementations, the inclusion station includes one or more cameras and object identification and tracking is performed by analyzing a video stream, for operations performed at the inclusion station.

[0086] In some implementations, the microtome thin-slicing station includes one or more cameras and object identification and tracking is performed by analyzing a video stream, for operations performed at the cutting station.

[0087] Description of embodiments

[0088] Other objects and advantages of the invention will appear in the light of the description of embodiments, given below with reference to the appended drawings in which:

[0089] - Figure 1 is a view of a macroscopy laboratory workstation, with a closed bottle, an open cassette, a closed cassette, and a clamp placed on the workstation tray;

[0090] - figure 2 is a view similar to figure 1, after opening the bottle, a technician taking a fragment of tissue from the bottle, for example a biopsy, using forceps;

[0091] - figure 3 is a view similar to figure 2, the technician placing the fragment of tissue from the bottle in the open cassette;

[0092] - figure 4 is a view similar to figure 3, after closing the cassette containing the tissue fragment.

[0093] Figures 1 to 4 show a macroscopy laboratory workstation.

[0094] In some embodiments, the workstation comprises a board made of a polymeric material, such as polyamide, polyoxymethylene (POM), or high-density polyethylene (HDPE).

[0095] For example, the dissecting board (cutting board) is made of polyethylene, colored throughout, the color used corresponding to a predetermined use.

[0096] In some implementations, the polymer material board includes a measuring rod, for example made of stainless steel.

[0097] Advantageously, the board comprises at least one reservation, the dimensions and shape of which are such that an object such as a cassette or a bottle, placed in the reservation, is held in position.

[0098] Advantageously, the board is made of hard, washable, and long-lasting material. In some applications, the board is single-use and disposable.

[0099] Advantageously, the board is made of polymer material and is placed on a stainless steel plate, which serves as its support. Cameras film the cutting board and the items placed on the board. In some implementations, the cameras are of the RGB (Red-Green-Blue) digital camera type.

[0100] The cameras are connected to a central unit or server equipped with means to analyze and process the video streams coming from the cameras.

[0101] Advantageously, a screen allows you to view all the stages of the treatment.

[0102] An image processing algorithm detects the presence of objects on the cutting board and identifies these objects, as they appear in the figures.

[0103] The shape of the identified object is advantageously represented by an enclosing window, as it appears in the figures.

[0104] In other implementations, the shape of the object is represented by a point, located in the center of the object, or in the form of an outline, a silhouette.

[0105] Object detection, such as bottles and cassettes, can be achieved by interest point detection, background subtraction, image segmentation, or supervised classification.

[0106] The detection of points of interest is for example ensured by a Moravec algorithm, or a Harris detector, a Kanade-Lucas-Tomasi detector, a SI FT (Scale Invariant Feature Transform) detector.

[0107] A presentation of the detector developed in 1977 by Hans P Moravec, and of the detector developed in 1988 by Harris and Stephen , as well as a description of the SI FT method is given by Garcia (Tracking objects of interest in an image sequence: from salient points to statistical measures, thesis 2008). Detection by background subtraction is obtained for example by modeling the color intensity of each pixel by a Gaussian distribution.

[0108] Detection by image segmentation is for example obtained by a Mean shift algorithm.

[0109] Supervised learning detection is obtained, for example, by adaptive boosting (AdaBoost), or by a support vector machine.

[0110] Tracking of identified objects is achieved for example by point tracking, by a probabilistic method or by kernel tracking. Object tracking methods by video stream analysis are presented by Maggio et al. Video tracking, theory and practice, 978-0470749647, 201 1).

[0111] The processing of the video stream is thus advantageously carried out by an artificial vision (or computer vision) system, that is to say an artificial intelligence system making it possible to analyze and process the video streams obtained by an image acquisition means such as a camera, and to ensure object tracking.

[0112] An example of video stream processing will now be described, with certain steps of this processing corresponding to the attached figures 1 to 4.

[0113] In the first step, the technician creates a new file for the sample.

[0114] This creation of a new file is advantageously linked to an identifier, for example a bar code, in particular a two-dimensional bar code, notably of the Data Matrix or QR code type, or even an Aztec code.

[0115] The identifier is advantageously a unique identifier associated with a single individual. Preferably, a unique identifier is associated with a sample. A patient who has undergone multiple operations is associated with a different identifier for each surgical procedure.

[0116] In some implementations, the workstation includes a barcode reader connected to the server. Such readers are sometimes referred to as a barcode scanner or barcode gun. In other implementations, the workstation includes a camera connected to the server, with an application, for example stored on the server, enabling the reading of barcodes scanned by the camera.

[0117] Communication between the barcode reader and the server can be wired or wireless, notably via protocols known under the brands Wifi, Bluetooth, Sigfox, Zigbee, Lorawan, Z-Wave, or even via near field communication (NFC).

[0118] At the end of this first step, the workstation is, for example, as shown in Figure 1. A bottle bearing the barcode used to open the file is placed, closed, on the cutting board. Also placed on the board are pliers, an open cassette and a closed cassette.

[0119] In a second step, the technician opens the bottle placed on the cutting board, the bottle containing the sample to be analyzed.

[0120] The application detects that the bottle is open, via the image processing algorithm.

[0121] The technician is notified by the application of the opening of the bottle, as shown in figure 2.

[0122] The date the bottle was opened is conveniently recorded in a database.

[0123] In a third step, the technician places the cap on the cutting board. The algorithm identifies the cap replacement on the video stream and reads the associated barcode (e.g. Data Matrix type).

[0124] If the cap is missing or if the associated barcode does not match the scanned one, an error is reported to the user, who can then replace the bottle with the correct one. The user can also ignore the error, in the case of an application bug.

[0125] Advantageously, a photo is automatically taken by the device to trace the opening of the bottle and the file number. This photograph is also advantageously recorded in a database.

[0126] In a fourth step, the technician places a cassette in the intended location on the cutting board.

[0127] In some implementations, the cassette is made of a polymer material, such as acetate polymer. The cassette includes perforations, facilitating the circulation of liquids and drainage during impregnation steps. The cassette includes a cover, attached or hinged. In other implementations, particularly when the sample is from a biopsy, the cassette is closed by a metal mesh. Advantageously, the cassette is colored, the color being associated with a type of sample.

[0128] Advantageously, the application automatically detects the presence of the cassette and its number readable via barcode (for example Data Matrix type).

[0129] If the cassette number is different from the bottle number, an error is reported to the user. In this case, the user can change the cassette and use the one with the correct number.

[0130] Advantageously, a photo is automatically taken by the device, to trace the cassette number. Advantageously, the photograph is also saved in a database. The workstation is in a state such as for example shown in Figure 3.

[0131] In a fifth step, when the technician finishes pouring the contents of the bottle into the cassette, a photo of the contents of the cassette is advantageously taken.

[0132] The photography command can be performed by the technician by clicking with a computer mouse, or by voice command or foot command.

[0133] Advantageously, the photograph is saved in a database.

[0134] Advantageously, an automatic count of the biopsies contained in the cassette is carried out.

[0135] Alternatively or in combination, an automatic measurement of the biopsy fragments or cores contained in the cassette is carried out.

[0136] In a sixth step, the technician closes the cassette. The workstation is then in a state as shown in Figure 4.

[0137] Advantageously, if the technician does not close the cassette, he cannot create a new file.

[0138] In a possible seventh step, a new cassette is placed on the cutting board, one bottle corresponding to several cassettes. Advantageously, this new cassette is automatically detected with its number, via its barcode (for example Data Matrix type). Advantageously, the same steps as those described above are implemented.

[0139] In an eighth step, the technician must close the bottle. Advantageously, the application automatically detects the closing of the bottle. Advantageously, the time of closing the bottle is recorded in the database.

[0140] Advantageously, if another bottle is opened at the same time as the first, an error is reported to the user who is thus assured that only one bottle is open on the board, at any given time.

[0141] In a possible ninth step, if a new bottle associated with the same file is opened by the technician, the same steps as those described above are implemented.

[0142] Advantageously, if the technician tries to automatically process a cassette, while the bottle opening has not been detected, an error is reported to the user, notifying him to open the bottle in the area covered by the cameras.

[0143] Advantageously, if the bottle has not been closed within the cameras' field of view, any further bottle opening will not be effective until the bottle closure has been performed in the correct area.

[0144] In some implementations, the user can ignore errors reported by the application, particularly in the case of an application bug. Any ignored error is advantageously logged in the application.

[0145] All recorded information is conveniently available on a workstation screen.

[0146] Changes / deletions can be made manually by the user, particularly in the event of incorrect information provided by the application. This may concern, for example, the presence of an extra line for opening a bottle, an incorrect file number or even an incorrect count carried out by the automatic cassette analysis processing.

[0147] Video stream processing can be performed by an application on a workstation computer or server. Alternatively, video stream processing and image processing algorithms are executed on a remote server.

[0148] Error handling can be performed by the technician present at the macroscopy station.

[0149] Alternatively, error handling can be performed remotely, by another technician or supervisor.

[0150] Advantageously, the macroscopy station includes means of weighing and measuring along several axes (in particular the three main axes of an operating part).

[0151] Advantageously, the macroscopy station includes means for surface reconstruction of an operating part placed on the board.

[0152] Advantageously, a central unit controls all the electronic cards of the macroscopy station.

[0153] The central unit can be a computer or a server. The data produced by the macroscopy station can thus be communicated to a mobile or fixed communication terminal, belonging in particular to a laboratory management system (LMS). The data produced by the macroscopy station can also be accessible via an internet platform.

[0154] The data produced by the station, including photographs, videos, surface reconstructions can be shared in real time or not, for remote assistance, tele-pathology, or for training purposes. For training purposes, tutorial videos, showing the macroscopic examination step by step, can be advantageously distributed.

[0155] In some implementations, measurements, photographs, and scans can be viewed on a touchscreen connected to a central processing unit. Advantageously, a software application can annotate the photographic views taken or the scans performed. The annotated images, scans, and videos, as well as the reports, can be stored in a database.

[0156] The station allows for telepathology and extemporaneous telediagnostic examinations, with a technician present on site and sending digital photographs and videos to the pathologist. The pathologist can conveniently take remote control of the station, in particular to view the macroscopic image and indicate to the technician the area to be sampled.

[0157] The data produced by the station can serve as a basis for laboratory reports.

[0158] Archiving the data produced by the station makes medical data and material available for medical, scientific or forensic purposes.

[0159] Advantageously, the precise morphometry of the surgical piece is preserved, as well as the trace of the pre-analytical steps.

[0160] The data provided by the macroscopy station are advantageously coupled with digital slides or virtual slides.

[0161] In some implementations, a software application allows macroscopic images or those from digital slides to be placed in the volume delimited by the surface reconstruction.

[0162] In some implementations, digital slides are produced by a slide scanner. Slide scanners are marketed, for example, under the name Panoramic 1000 by the company 3D Histech. This avoids the need to handle physical slides and the time wasted searching for them.

[0163] The method and the macroscopy station according to the invention advantageously allow the tracking of all the stages through which the surgical samples pass, from surgical excision to the microscopy slides, and their archiving. The tracking thus allows the identification of the operations carried out at the slide (or paraffin block) archiving station, making it possible to identify and date the deposits and withdrawals carried out.

[0164] A quick presentation of these different stages is given for example by Altaleb (Surgical Pathology, ISBN 978-3-030-53689-3, 2021, see in particular page 41).

[0165] The method according to the invention makes it possible to ensure the traceability of samples (for example an operating specimen or a biopsy), from the operating table until the end of processing in the anatomopathology laboratory.

[0166] In some situations, the operating table is placed in an operating room of an operating theatre, the removal being in principle carried out by a surgeon.

[0167] In other situations, the operating table is placed in an interventional radiology room, with the sample (e.g., a breast biopsy) being taken by a radiologist or surgeon.

[0168] In other situations, the operating table is placed in an interventional room equipped with imaging equipment (hybrid interventional room in the SI BO operating theatre), the sample being in principle carried out by a surgeon, for example a vascular surgeon.

[0169] The medical team working in the operating room or in a hybrid SI BO room most often includes a surgeon, an anesthesiologist, an operating room nurse (I BODE). The surgeon may be accompanied by assistant surgeons. Most often, the anesthesiologist is assigned to the operating room and is in charge of several patients located in the different rooms of the block. The same applies to the operating room nurse, who may be an instrument operator, operating assistant, surgical or circulating assistant, or an anesthesia-resuscitation nurse. In France, the operating room nurse ensures the traceability of activities in the operating room and in associated sectors (article R431 1 - 1 1 of the Health Code).

[0170] Pre-analytical work from sampling to fixation

[0171] We now describe a first, pre-analytical step, from the sample taken from the operating field to its placement in a container, fresh or in a preservation liquid (fixative).

[0172] When the practitioner performs a sample by excision, the sample is often placed in a bowl, such as a kidney bean, given by the surgeon to a circulating I BODE. During this step, an anatomopathological examination form is completed by the nurse, the elements being dictated by the surgeon.

[0173] Each sample forms a biological material that can be sent as is to the pathology laboratory, or divided into samples before being sent to the pathology laboratory. For this shipment, each sample (or each sample) is placed in a transport container (for example, bag, bottle, bucket). The transport container is sterile before use.

[0174] In some organizations, samples from different operating rooms are collected in a common area, most often non-sterile, in the operating room or near the operating room.

[0175] Surgical specimens containing a tumor are preferably sent to the pathology laboratory fresh.

[0176] Direct transfer of surgical specimens from the operating room at room temperature is sometimes implemented. Such direct transfer is implemented when the pathology laboratory is located close to the operating room, the correct storage time for a surgical specimen at room temperature being limited to 40 minutes. In some organizations, samples taken in the operating room are vacuum-packed in a polymer bag and cooled to approximately 4°C for transfer to the laboratory. This technique allows the integrity of the specimen to be maintained for a limited period of approximately 72 hours.

[0177] Surgical specimens are most often sent to the PCR laboratory after immersion in a preservation liquid (fixative). The specimen or anatomical specimen must be immersed in the fixative as quickly as possible. A ratio of 20 to 50 times the volume of the specimen must be respected. The fixation time depends on the size of the specimen, and is most often between two hours for a biopsy and 12 to 24 hours for a surgical specimen. Depending on the nature of the specimen, fixation is obtained by immediate immersion in the fixative (for small specimens from biopsy or curettage), or after opening the anatomical specimen (digestive tract, gallbladder, liver). In some cases, the fixative is previously injected into the anatomical specimen, before its immersion in the fixative solution, for example for bronchi or lungs.

[0178] Fixation must occur within a short time: otherwise, desiccation or autolysis of the tissue can make the study difficult or even impossible. Before fixation, hollow organs must be opened and, if necessary, washed of their contents, in order to prevent autolysis of the mucous membranes. Solid organs such as the liver and spleen must be cut into slices, to facilitate the homogeneous and rapid penetration of the fixative. Many pathology laboratories recommend not sending fresh tissue samples, in order to ensure that the time between surgical resection and fixation by immersion in the fixative (most often formalin) does not exceed one hour for surgical specimens, and ten minutes for biopsies.

[0179] Chemical fixation should block endogenous enzymes responsible for the destruction of cellular organelles. Chemical fixation should also maintain cellular, tissue and molecular structures in a state as close as possible to the physiological state. Chemical fixation should also allow immunohistochemical studies and prepare the inclusion of the sample in an embedding medium, in particular paraffin.

[0180] Fixation develops from the surfaces in contact with the fixative, so the fixative must be placed in the container first, to prevent the specimen, for example the anatomical part, from sticking to the wall of the container. The size of the container must be adapted to the part to be fixed. The container can be a bottle, a box, or a bucket.

[0181] Formalin is widely used for the preservation of specimens, particularly for morphological analysis and immunohistochemistry. Formalin here refers to an aqueous solution of formic aldehyde, or formaldehyde, (CAS 50-00-0). Formaldehyde is also called methanal, oxomethane, and formalin is sometimes called formalin.

[0182] Other fixatives than formalin have been proposed, for example glyoxal or ethanedial. Reference can be made, for example, to document EP341 6482 (Addax Biosciences, 2018).

[0183] Formaldehyde (especially buffered formalin diluted to 4%) remains the gold standard in anatomopathology, despite its drawbacks. Standardized immunohistochemistry and in situ hybridization tests are validated for samples fixed in buffered formalin and embedded in paraffin, with patient participation in most international trials being conditional on formalin fixation of the tumor sample.

[0184] Formaldehyde is marketed in aqueous solution at concentrations most often between 30% and 55% by weight, aqueous solutions may contain a formaldehyde polymerization inhibitor, such as methanol, at a mass concentration of 0.5 to 15%. Chemical fixatives based on formaldehyde, in aqueous solution, are marketed in three main forms: neutral formalin to be diluted in demineralized water, the pH being adjusted with, for example, sodium hydroxide; buffered formalin to be diluted in a buffer solution; neutral buffered formalin to be diluted in a buffer solution and neutralized with, for example, calcium carbonate.

[0185] Bottles, jars, and buckets are sold pre-filled with formalin. Bottles are made of polypropylene, for example, with a polyethylene cap, and can hold up to 1.50 ml, for example. Jars are made of high-density polyethylene, with a capacity of half a liter to one liter. Buckets are made of polypropylene, with a capacity of several liters. When chemically fixing with formalin, it is important to ensure complete and constant immersion of the surgical specimens.

[0186] During this first, pre-analytical stage, of first handling of the samples and placing them in containers for sending to the PCR laboratory, many errors can be made.

[0187] When multiple samples are taken from the same patient, identification errors can occur, particularly when samples are taken from two paired organs such as lungs, kidneys, ovaries, breasts, or testicles. A misidentification between the left and right organs can be highly damaging when only one of the two organs has a tumor, or when only one of the two organs has a malignant tumor.

[0188] When the practitioner dictates to the I BODE the elements to fill out the anatomopathological examination form, wearing a surgical mask and the sound environment of the operating room can complicate understanding. We can refer for example to the document Magee et al. (Effects of face masks on acoustic analysis and speech perception: Implications for peri-pandemic protocols, J Acoust Soc Am, 2020). This results in risks of errors in the request that will be sent to the ACP laboratory. The current ACP examination request form is a form that must be completed by hand. A very large amount of information must be entered manually.An examination request form includes the patient's identity data, the name of the prescribing physician, the name of the sampler (if different from that of the prescribing physician), the date and time of the sample, the state of the sample (fresh or fixed), the time of fixation, the fixative used, the type of sample (biopsy, surgical specimen), the organ to be sampled, the location and topography, information for diagnosis (including patient history, ongoing medical treatments), the number of slides required, the existence of an infectious risk.

[0189] Filling out forms is an experience that is often experienced as tedious and repetitive, leading to fatigue and reduced attention, with the risk of forgetting and of confusing, fragmentary or erroneous information. In particular, the lack of clinical information can be detrimental during pathological interpretation. Furthermore, handwriting is more or less legible, with the risk of reading errors in the PCR laboratory.

[0190] In some organizations, samples from several patients may be on the same trolley or workbench, to be identified one after the other, leading to risks of identity monitoring errors.

[0191] Complex surgical specimens sometimes need to be oriented. For example, a mastectomy specimen is oriented by the surgeon using threads or clips during sampling. For example, during breast cancer surgery, for a partial excision specimen or a lumpectomy for which a lesion extension assessment is required, the specimen is oriented in the three planes of space, allowing differential anchoring of the edges. Information relating to the orientation of the specimen is not systematically transmitted to the PCR laboratory, or is incomplete.

[0192] In order to overcome these drawbacks, according to the invention, an analysis of the video stream is carried out with identification and tracking of objects, for the work carried out from sampling to containerization before sending to the ACP laboratory.

[0193] A workstation is placed near the operating table, this workstation comprising a board forming a tray and means for identifying and tracking objects by analyzing a video stream, the samples and the containers for these samples being manipulated on the tray of the workstation. At least one camera films the manipulations carried out. Computer vision algorithms analyze the video stream and ensure identification and tracking of objects.

[0194] By "placed nearby" we mean here that the workstation is placed in the operating room or the interventional radiology room or the hybrid SI BO room, the person taking the sample preferably placing the sample directly on the workstation tray.

[0195] By "placed nearby" we also mean the case where the workstation is located in a separate but adjacent room (advantageously contiguous) to the operating room, or the interventional radiology room or the hybrid SI BO room.

[0196] By "placed nearby" here we mean a fixed location for the workstation or a mobile location. Advantageously, the workstation is mounted on a mobile trolley, for example a four-wheeled trolley.

[0197] The analysis of the video stream with identification and tracking of objects advantageously concerns at least one of the following steps: labeling of the samples, immersion of the samples in the fixer.

[0198] Advantageously, for the labeling of each sample, after verification of the complete identity of the patient, a patient label is issued, this label including the identity of the patient (surname, first name, date of birth, sex), as well as the date and time of the sample. In certain implementations, this label includes the patient number, in alphanumeric form and / or in coded form (for example QR code or Data Matrix). The label is preferably issued by the person who took the sample. The label is placed on the tube, pot or bottle to contain the sample.

[0199] Analysis of the video stream with object identification and tracking, during labeling, allows the operator to be warned of a discrepancy between the patient's identity and the data on the ACP order form. Alphanumeric character recognition or reading of a unidirectional or bidirectional barcode (QR code, Data Matrix, Aztec, PDF417) provides access to the patient's identity, during analysis of the video stream. The ACP analysis order form is placed on the workstation tray, and character recognition is performed.

[0200] When the data in the ACP request form does not match the patient's identity, an alarm is generated. In various embodiments, the alarm is an audible and / or visual alarm and / or a vibration alarm.

[0201] In some implementations, the alarm includes opening a pop-up window.

[0202] Advantageously, computer vision and video stream analysis algorithms are interfaced with the computerized patient record.

[0203] By "computerized patient record" or DP I, we mean all the health data of a patient treated within a healthcare establishment, as well as the software used to organize and put this data online.

[0204] The DP I computerized patient record contains, for example, hospital discharge liaison letters, surgical reports, discharge prescriptions, biological reports and imaging reports. The computerized patient record contains the various documents that must be fed into the shared medical record (DMP), or the personal digital space “My health space”, launched in February 2022, to replace and improve the DM P.

[0205] When computer vision and video stream analysis algorithms are interfaced with the electronic patient record (DP I), the collection of clinical information is automated, and the prescription of the pathology examination voucher is simplified. Handwriting is no longer necessary, reducing the risk of errors.

[0206] Advantageously, human-machine interface means allow rapid navigation through the software functionalities, for example touch screen, optical pens, automatic speech recognition, voice synthesis, three-dimensional information visualization, virtual reality headset or glasses, in particular augmented reality.

[0207] In some embodiments, the workstation is provided with stereoscopic, infrared or laser depth cameras, allowing three-dimensional modeling of the surface of operating parts, the resulting model being able to be saved, oriented, and advantageously annotated digitally.

[0208] Advantageously, the workstation is equipped with means for digitally annotating the 2D images of the samples and saving them.

[0209] The workstation is provided with means for printing barcodes (one-dimensional or two-dimensional, for example QR code or Data Matrix), the barcode being placed on a container in which the sample is placed, an analysis of the video stream being carried out during the printing of the barcode, as well as during the placement of the label on the container.

[0210] Advantageously, the ACP examination request form is digital and the identification label placed on the container encrypts the patient's identity and guarantees their anonymity by pseudonymization. Pseudonymization here refers to measures guaranteeing the protection of personal data, access to this personal data requiring the use of additional information.

[0211] Advantageously, the analysis of the video stream allows the control of the volume of fixative such as formalin, and the verification that the volume of fixative is adapted to the volume of the surgical specimen to be fixed.

[0212] In some implementations, the workstation has weight sensors, and an amount of fixer to use is communicated to the operator, either by text message or voice message.

[0213] The placement of the sample in the fixer is filmed and analysis of the video stream makes it possible to verify that the appropriate quantity of fixer is used.

[0214] Analysis of the video stream also allows the start of fixation to be dated. An alarm, for example an audible alarm and / or the display of a message, is triggered when the fixative has been omitted or when the quantity of fixative is not appropriate.

[0215] Advantageously, the operator using the workstation is identified by authentication means, for example with a login and password and / or facial recognition means, and / or the reading of a badge, for example RFI D or NFC.

[0216] Optional pre-analytical work in a buffer zone

[0217] A second, optional, pre-analytical stage of work carried out in a buffer zone is now described.

[0218] By "buffer zone" we mean a room which can be sterile and is most often non-sterile, preferably located near the operating theatre, and in which samples from the operating rooms are collected, before their transfer to the PCR laboratory. In this buffer zone, checks of PCR test request forms are carried out, as well as checks on the number of containers (bottles, buckets, bags). Traceability is carried out by handwritten transcription onto a paper notebook.

[0219] Checks carried out in the buffer zone are repetitive and tedious. This results in risks of human error, due to a momentary drop in vigilance or concentration of an operator. These errors can notably concern the identity of the patient, the nature of the sample, the number of containers. When a discrepancy is detected by the operator during checks in the buffer zone, the loss of time caused, for example, by searching for a missing container is a source of irritation, increasing fatigue and the risk of subsequent errors.

[0220] Advantageously, in a method according to the invention, an analysis of the video stream and computer vision algorithms, for example by image segmentation, are implemented during the work carried out in the buffer zone.

[0221] According to different implementations, the analysis of the video stream ensures an automatic count of the containers and / or a check of the adequacy of the volume of fixer for each sample placed in a container (for example by the ratio of volume of the sample / volume of fixer, the sample being placed in a transparent container).

[0222] Advantageously, the absence of fixative in a container or the presence of an insufficient quantity of fixative results in the creation of an alarm, for example a text message on a screen and / or an audible alarm.

[0223] In some implementations, there are means to digitize ACP application forms, for example by automatic OCR character analysis.

[0224] Advantageously, the data on the label (for example barcode, QR code or Data Matrix) placed on each container is read, the identity of each patient being encrypted, allowing anonymity to be preserved by pseudonymization.

[0225] Advantageously, the identity of the operator working in the buffer zone is controlled by authentication means, for example with a login and password and / or facial recognition means, and / or the reading of a badge, for example RFI D or NFC.

[0226] Work carried out at the ACP laboratory registration station

[0227] We now describe the work carried out at the recording station, at the entrance to the ACP laboratory.

[0228] By "registration station" we mean the workstation receiving the samples, delivered for example by a person (such as a courier or the patient himself), or arriving by automatic means of transport (for example by pneumatic transport).

[0229] Samples come to the registration station from various sources (operating theatres, hospital departments, private clinics), in variable and unpredictable quantities. The registration station receives all samples from the various prescribers using the PCR laboratory.

[0230] The registration station is a critical station in the PCR laboratory. In cases of high activity, this station can become a bottleneck, i.e., a station receiving more job requests than its maximum processing capacity can support.

[0231] The registration includes the patient's identity and the inventory of samples received. The registration is carried out by administrative staff or a laboratory technician.

[0232] During registration, the sample is identified by the PCR test request form. A large amount of information must be verified during registration: patient identity, administrative information, number of containers, description and appearance of the samples, clinical information.

[0233] During registration, an examination number is assigned to each sample received in the SGL laboratory's computerized management system, and a label bearing this number is often placed on the container.

[0234] The verification work to be carried out at the check-in station is repetitive, tedious and prone to human error, particularly in busy situations, which can be stressful. Traceability relies primarily on the concentration, rigor and vigilance of the staff working at the check-in station.

[0235] When an error is detected at this recording station, for example a labeling or recording error in the SGL laboratory management system, corrective measures are long and tedious, and add fatigue, increasing the risks of subsequent errors.

[0236] When the test request forms are incomplete or difficult to read, the staff at the registration desk must attempt to contact the issuer of the form, particularly the prescriber, which takes time and leads to additional risks of errors.

[0237] Advantageously, according to the invention, an analysis of the video stream and computer vision algorithms, for example by image segmentation, are implemented during the work carried out at the recording station, allowing identification and tracking of objects.

[0238] In some implementations, a workstation is placed at the recording station, this workstation comprising a tray on which the containers and samples are handled, the tray being equipped with one or more cameras. In some implementations, one or more cameras placed on the ceiling of the recording station operate in concert with the cameras of the workstation.

[0239] According to different implementations, the analysis of the video stream ensures an automatic count of the containers and / or a check of the adequacy of the volume of fixer for each sample placed in a container (for example by the ratio of volume of the sample / volume of fixer, the sample being placed in a transparent container).

[0240] Advantageously, the absence of fixative in a container or the presence of an insufficient quantity of fixative results in the creation of an alarm, for example a text message on a screen and / or an audible or vibrating alarm.

[0241] In some implementations, there are means to digitize ACP application forms, for example by automatic OCR character analysis.

[0242] Advantageously, the data on the label (for example, barcode, QR code or Data Matrix) placed on each container are read, the identity of each patient being encrypted, allowing anonymity to be preserved, by pseudonymization. The data on the label advantageously contains administrative information, the description of the samples, the number of containers and clinical information. Advantageously, the reading of the barcode is filmed and is the subject of an analysis of the video stream.

[0243] Advantageously, the workstation of the registration station comprises means for printing a bar code (one-dimensional or two-dimensional, for example QR code, Data Matrix), to print a bar code on each container, encoding an identification number generated by the SGL laboratory management system. Advantageously, the operations of printing the bar code and fixing this bar code on the container are filmed and are the subject of a video stream analysis. Advantageously, the identity of the operator working at the registration station is controlled by authentication means, for example with a login and a password and / or facial recognition means, and / or the reading of a badge, for example RFI D or NFC.

[0244] Work at the macroscopy station

[0245] The work carried out at the macroscopy station is now described. In addition to the work described previously with reference to Figures 1 to 4, the following arrangements are implemented in various embodiments.

[0246] Advantageously, cameras placed above the macroscopy station, for example cameras placed on the ceiling of the room, film the work carried out, and an analysis of the video stream coming from these cameras is carried out.

[0247] According to different implementations, the analysis of the video stream ensures an automatic count of the containers and / or a check of the adequacy of the volume of fixer for each sample placed in a container (for example by the ratio of volume of the sample / volume of fixer, the sample being placed in a transparent container).

[0248] Advantageously, the absence of fixative in a container or the presence of an insufficient quantity of fixative results in the creation of an alarm, for example a text message on a screen and / or an audible alarm.

[0249] Advantageously, the identity of the operator working at the macroscopy station is controlled by authentication means, for example with a login and password and / or facial recognition means, and / or the reading of a badge, for example RFI D or NFC.

[0250] Works at ion We now describe the work carried out at the dehydration station.

[0251] At the dehydration station, the cassettes from the macroscopic examination are collected in racks, which can contain, for example, up to 150 cassettes.

[0252] For example, the cassettes are collected in racks of a machine marketed under the brand Tissue-Tek VI P, by the Sakura company.

[0253] The workstation is a gray area in the workflow of the ACP laboratory: it is in fact impossible to quickly find a sample in a set of cassettes placed at the dehydration station, since all the numbers of the cassettes constituting a batch placed at the dehydration station are unknown.

[0254] Advantageously, in an installation according to the invention, one or more cameras film all of the cassettes, and the analysis of the video stream allows the reading of all of the cassette numbers, whether this number is alphanumeric or coded for example in an OCR code or a Data Matrix.

[0255] Advantageously, each cassette bears a number, for example printed on an adhesive backing attached to the cassette, or else printed on the cassette. On each cassette, a cassette identifier is also printed, for example 24H00000, and right next to it, a barcode (for example Data Matrix) which encodes this identifier.

[0256] In some implementations, an algorithm first attempts to decode the barcode, and if decoding fails (e.g. due to poor camera focus), an open character recognition (OCR) algorithm attempts to decrypt the cassette identifier placed next to the barcode.

[0257] In some implementations, one or more cameras are placed on a mobile, motorized support, allowing a traveling shot to be performed. Advantageously, the cassettes are illuminated, in particular by LEDs.

[0258] In some implementations, at least one screen of the dehydration machine is filmed by one or more cameras, and an analysis of the video stream is carried out, for example for OCR character recognition. The information obtained is saved in a database, this information advantageously comprising, for example, the following elements: duration of the dehydration cycle, time remaining until the end of the dehydration cycle, type of cycle.

[0259] Advantageously, alarms appearing on the PLC screen are notified in real time to the operator, for example a notification sent by email, by SMS, by a pop-up window of a dashboard application.

[0260] It is thus possible for an operator far from the machine to be warned of an operating anomaly in the dehydration machine, or of an anomaly during the dehydration stage.

[0261] The analysis of the video stream can be carried out on each dehydration machine in the ACP laboratory, these machines being marketed by different suppliers where appropriate.

[0262] The invention thus proposes an agnostic device, indifferent to the models of commercially available machines, the operator using a single human-machine interface for a set of dehydration machines of different types.

[0263] It is no longer necessary for the operator to know in detail the operation and characteristics of each dehydration machine, a single human-machine interface allows the operator to know in real time the operating status of each machine. The operator can be present in the ACP laboratory, or be remote from the ACP laboratory. The operator can receive notifications from machines placed in different dehydration stations, located in separate locations.

[0264] Works at inclusion or cutting c

[0265] The work carried out at the inclusion station is now described, it being understood that what will be described below for the inclusion station also applies to the cryostat cutting stations.

[0266] The inclusion station determines the appearance of the block of inclusion material, most often paraffin.

[0267] The inclusion position is a sensitive position for the ACP laboratory for several reasons.

[0268] Firstly, the work carried out at the inclusion station requires manual skill and meticulousness. Some samples are difficult to orient and their orientation can condition the diagnosis, for example skin excision, Mohs, pseudo-Mohs.

[0269] By "Mohs" we mean here a piece resulting from excision by Mohs micrographic surgery (MMS). We can refer for example to the document Harmon et al Mohs micrography surgery, 2022, ISBN 9783132420175. The Mohs technique of excision and anatomopathological examination allows a comprehensive analysis of the edges associated with a reduction in the sacrifice of healthy tissue. By "pseudo Mohs" or slow Mohs we mean here a sample similar to MMS, followed by inclusion in paraffin, for a deferred PCR analysis. We can refer for example to the document Khaddaj, (medical thesis, University of Lille, 2021).

[0270] Secondly, there is a risk of sample loss during transfer between the cassette and the inclusion mold. Advantageously, the inclusion machine is provided with a workstation comprising a barcode scanner, one or more cameras, and a display screen.

[0271] In some implementations, one or more endoscopic cameras are placed close to the work surface.

[0272] In some implementations, one or more cameras are placed above the inclusion station, for example on the ceiling or on a wall of the ACP laboratory.

[0273] When a technician manually enters a cassette, a reading of its number (e.g. alphanumeric or barcode) is performed. For example, this reading is obtained using a scanner (handheld scanner) or a camera.

[0274] Advantageously, when the cassette number is recognized, a software interface opens the patient file and displays the macroscopic images. This data facilitates the determination of the direction of inclusion.

[0275] Advantageously, an analysis of the video stream and computer vision algorithms, in particular image detection and segmentation, allow a count of the samples transferred into the inclusion mold, and check the absence of superposition of samples (for example biopsy cores) inside the molds, or a comparison of the size and surface area, in order to verify that no loss of material has occurred.

[0276] In case of discrepancies in the number of biopsies, an alarm is advantageously generated, this alarm being for example a text or an audible alarm.

[0277] Work at the cutting and spreading station

[0278] We now describe the work carried out at the cutting and spreading station. The cutting station and the spreading station are sometimes one and the same station, for work carried out by a single technician.

[0279] In other implementations, the cutting station is separate from the spreading station, and the work is carried out on these two stations by the same technician or by two different technicians.

[0280] At the cutting station, the block of embedding material, usually paraffin, is cut using a microtome into ribbons a few microns thick. This ribbon is then spread on a glass slide, with or without the aid of a water bath, and the slides are then placed on a hot plate.

[0281] The cutting and spreading station is a sensitive position in a PCR laboratory. This workstation requires dexterity and consistency in movement.

[0282] Since the work is repetitive, there is a risk of human error.

[0283] In particular, a ribbon from a block may be spread on the wrong blade.

[0284] Furthermore, the cutting begins with a step of roughing out the block, during which the block may be over-cut, part of the sample then being lost unnecessarily.

[0285] Conversely, the block may be insufficiently started, the spread ribbons not allowing a diagnosis when observed under the microscope.

[0286] Advantageously, the microtome is provided with a workstation comprising a barcode scanner (one-dimensional or two-dimensional, for example QR code or Data Matrix), one or more cameras and a display screen.

[0287] In some implementations, a camera or cameras are focused on the block inserted into the jaws of the microtome. In some implementations, a camera or cameras are focused on the ribbons.

[0288] The screen conveniently displays instructions for the operator to follow, for example in the form of a text message.

[0289] Advantageously, video stream analysis and computer vision algorithms, including image detection and segmentation, enable tracking of the ribbons to the spreading blades.

[0290] Advantageously, a detection of the correct position of the ribbon on the blade is carried out, in particular the absence of folds or streaks.

[0291] Work at the distribution station

[0292] The work carried out at the distribution station is now described.

[0293] At the distribution station, the trays of slides are prepared in a specific order, with the trays accompanied by examination slips filed in the same order.

[0294] Advantageously, in an installation according to the invention, an analysis of the video stream and computer vision algorithms, in particular image detection and segmentation, allow a count of the samples present on the stained slides, a verification of the correlation of this count with that of the samples present in the cassette at the macroscopy station.

[0295] In the event of a discrepancy in the counts and / or in the size of the samples, an alarm signal is generated, for example a text message and / or an audible signal.

[0296] For example, when the biopsy core is only 6 mm while it measured 1.5 mm macroscopically, a message advises sending the sample back to the sectioning-spreading stage, with the note "please start more blocks". Advantageously, an analysis of the video stream and computer vision algorithms, in particular image detection and segmentation, allow

[0297] - a check of the alignment of the slides and films from the microtome with the glass slides and / or

[0298] - a check of the quality of the coloring, compared to coloring standards and / or

[0299] - a check of the correct positioning of the identification labels on the blades.

[0300] Work at the archiving station

[0301] The work carried out at the archiving station is now described.

[0302] At the archiving station, the paraffin blocks and glass slides are stored and archived in archive cabinets, in the order of their number assigned to the laboratory, for example 24H00000, and right next to it, a barcode (for example Data Matrix) which encodes this identifier.

[0303] The blades and blocks are classified in chronological order in drawers, according to a storage system by row or column in the cabinets, for periods ranging from 10 to 30 years in France.

[0304] Unarchiving blocks and slides is manual and often untracked, leading to situations where unarchived blocks and slides end up missing or lost.

[0305] Advantageously, in an installation according to the invention, a station comprising a central unit (PC), a touch screen, for example suspended in the immediate vicinity of the archiving cabinets, and a bar code reader makes it possible to identify:

[0306] - the operator, for example via a username and password, or a near-field communication (NFC) reading device, or facial recognition means, or a fingerprint reader;

[0307] - the block or blade to be archived / unarchived; - the location (for example the coordinates) of the replacement of the object to be archived (such as a drawer, a cabinet).

[0308] An analysis of the video stream and computer vision algorithms, including image detection and segmentation, allow a count of the de-archived objects, a verification of the correlation of this count with that of the objects identified on the software.

[0309] If there is a discrepancy in the counts of unarchived objects compared to scanned objects, an alarm signal is generated, for example a text message and / or an audible signal.

[0310] Advantages of the invention

[0311] The installations and methods according to the invention have numerous advantages.

[0312] Samples taken in the operating theatre follow a complex circuit, involving a large number of stages, with a multiplicity of locations (operating theatre, buffer zone, recording station and successive work stations in the ACP laboratory) and actors (prescriber, sampler, transporter, laboratory technicians).

[0313] Any failure in this circuit can lead to sample loss, identity errors, or sample orientation errors, unsuitable transport conditions, and sample deterioration. These failures can delay or distort a diagnosis, or require a new sample to be taken.

[0314] The installations and methods according to the invention improve the traceability of samples and reduce the risk of error, at each of the stages and workstations, from the operating field (for example in the operating room) to the analysis of thin sections by microscopy in the PCR laboratory.

[0315] When the surgical specimen is removed by a surgeon and placed in a bottle or jar, a camera advantageously films the placing of the specimen in the jar or jar, and an algorithm detects the surgical specimen and follows its movement into the jar or jar.

[0316] Advantageously, the algorithm allows the control of whether the quantity of formalin contained in the jar is sufficient to ensure good preservation of the tissues.

[0317] Advantageously, the surgical specimen is weighed and this weighing is compared to that carried out during surgical removal.

[0318] The macroscopy station implements at least one identification and tracking algorithm and advantageously at least one character recognition algorithm, making it possible to ensure that the bottle or pot placed on the board (associated with a patient, by a unique identifier) ​​corresponds to an operating sample placed in one or more cassettes.

[0319] The method thus makes it possible to detect possible human errors in the analysis of an operating sample for a patient P. In particular, the method makes it possible to detect the erroneous placement of a sample in a cassette,

[0320] - either by opening a bottle not coming from patient P and attempting to deposit this sample in a cassette corresponding to patient P, this error being able to be called bottle inversion;

[0321] - either by depositing the sample contained in a bottle corresponding to patient P in a cassette not corresponding to patient P, this error being able to be called cassette inversion.

[0322] The method further makes it possible to detect the erroneous placement of a sample in a bottle or a pot, by depositing a sample from a patient P in a bottle or a pot labeled (for example by Data Matrix) for a patient other than patient P, this error being able to be called a patient error. The method further makes it possible to detect the erroneous allocation of a thin section to a patient.

[0323] As described, the placement of the sample in a cassette is subject to video stream analysis, object identification and tracking, as well as recognition of an identifier (for example a Data Matrix type barcode).

[0324] The cassette is then included in an embedding medium, particularly paraffin.

[0325] The block obtained is cut with a microtome, the slices obtained, a few microns thick, then being spread on slides. The slides are fixed and then stained to be sent to pathologists for analysis. The slides are deparaffinized before staining, using a solvent, for example toluene or xylene. If necessary, immunostaining is carried out in addition to the staining, to highlight certain tissue antigens, using labeled antibodies.

[0326] These operations are advantageously filmed and an object recognition and object tracking algorithm, as well as an identifier recognition algorithm (for example a bar code), ensures that the slides produced bear the identifier present on the cassette.

[0327] It is thus possible to ensure that the same identifier, advantageously a unique identifier assigned to a single patient, is present on the bottle or pot in which the surgical sample is placed, during surgical excision or biopsy.

[0328] It is thus also possible to ensure traceability of the sample taken, from its placement in a bottle or pot bearing the identifier, to its placement in one or more cassettes, the cassette(s) bearing the same identifier, and from the cassette(s) to the thin sections, each thin section bearing the same identifier. The opening and closing of the bottles, the opening and closing of the cassettes are advantageously subject to detection and dating (time stamping), in connection with recognition of the identifier of the biological tissue. The process alerts the technician of a loss of concordance between the biological tissue at the end of a processing step (in particular placement in a cassette, placement on a thin section).

[0329] The process can be advantageously implemented for small surgical specimens, such as skin excisions or biopsies.

[0330] Advantageously, when implementing the method, the operator can remain focused on the operating part to be analyzed, and does not have to be careful to press a control with his hand or foot. Possible visual distraction and repeated interruption of work linked to the use of manual or foot controls is a source of errors, which the method makes it possible to avoid.

[0331] The devices and methods according to the invention can be implemented for existing installations and equipment, and this in an agnostic manner, indifferent to the models of marketed automatons (in particular dehydration automatons, microtomes, cryostats), the operator advantageously using a single man-machine interface for a set of automatons of different types.

[0332] Thus, the devices and methods according to the invention do not require the replacement of existing machines in ACP laboratories, with the resulting costs.

[0333] The devices and methods according to the invention can be implemented in fully robotic ACP installations.

[0334] Advantageously, however, the invention can be implemented while retaining manual operations, thus preserving the expertise and experience of medical laboratory technicians and physicians qualified in PCR, and reducing the risks of error at each stage and station of biological tissue processing.

Claims

Claims 1. Method for histopathological examination of biological tissues, in particular surgical specimens or biopsy specimens, in particular for ACP anatomo-cytopathology, characterized in that it comprises identification and tracking of an object by analysis of a video stream during a pre-analytical step and / or an analytical step of the biological tissues.

2. Histopathological examination method according to claim 1, characterized in that the pre-analytical step is chosen from the group comprising the removal of biological tissues in the operating field, the orientation of the biological tissues, the labeling of the removed biological tissues, the placement of the tissues in a container in a fresh state, the immersion of the removed biological tissues in a preservation liquid such as a fixative, the preparation of a histopathological examination request form, the transport of the sample to a recording station, the recording of the sample in a laboratory management system.

3. Histopathological examination method according to claim 2, characterized in that it comprises a step of labeling the biological tissues with generation of a first patient identity, in alphanumeric form or in coded form, in particular by bar code, the identification and tracking of the object by analysis of a video stream comprising a step of reading this first patient identity, in particular a bar code reading.

4. Histopathological examination method according to claim 3, characterized in that it comprises a step of preparing a histopathological examination request form generating a second patient identity, the identification and tracking of an object by analysis of a video stream comprising a step of reading this examination request form and the second patient identity, an alert message being generated in the event of a discrepancy between the first and second patient identities.

5. Histopathological examination method according to claim 3 or 4, characterized in that it comprises a step of interrogating the computerized patient file and a step of collecting information elements contained in the computerized patient file, for copying into a histopathological examination request form generated in digital form.

6. Histopathological examination method according to any one of claims 1 to 5, characterized in that it comprises an identification and tracking of an object by analysis of a video stream during the immersion of biological tissues such as an operating part in a preservative liquid such as a fixative, an alert message being generated when the volume of preservative liquid is not adapted to the volume of biological tissues.

7. Histopathological examination method according to any one of claims 1 to 6, characterized in that it comprises a control step carried out in a buffer zone in which a plurality of biological tissue samples are collected, in particular from different operating rooms of an operating theatre, the method comprising an identification and tracking of an object by analysis of a video stream for counting the containers placed in the buffer zone.

8. Histopathological examination method according to any one of claims 1 to 7, characterized in that it comprises an identification and tracking of an object by analysis of a video stream during the recording of a sample in a laboratory management system, for a count of the containers and / or a check of the adequacy of the volume of fixative for the sample placed in a container.

9. Histopathological examination method according to any one of claims 1 to 8, characterized in that it comprises an identification and tracking of an object by analysis of a video stream during a step of preparation of biological tissues chosen from the group comprising dehydration, inclusion in a material, in particular paraffin, cutting in particular with a cryostat or microtome to form ribbons, spreading ribbons on supports such as glass slides, distribution.

10. Histopathological examination method according to claim 9, characterized in that it comprises a reading of all the cassette identifiers, these identifiers being alphanumeric or coded, in particular in a bar code. 1 1. Histopathological examination method according to claim 9 or 10, characterized in that at least one interface screen of a dehydration machine is filmed, an analysis of a video stream making it possible to generate information including the duration of the dehydration cycle, the time remaining until the end of dehydration.

12. Histopathological examination method according to claim 11, characterized in that it comprises a step of generating an alert message, when an operating alarm has been detected for the dehydration machine, during the analysis of the video stream coming from the camera filming the interface screen of the dehydration machine.

13. Histopathological examination method according to any one of claims 1 to 12, characterized in that it comprises an identification and tracking of an object by analysis of a video stream during a step of inclusion of biological tissues in an inclusion material such as paraffin, the analysis of the video stream being capable of ensuring a count of the biological tissues transferred to the inclusion mold.

14. Histopathological examination method according to any one of claims 1 to 13, characterized in that the analytical step is chosen from the group comprising the macroscopic study steps.

15. Histopathological examination method according to any one of claims 1 to 14, characterized in that it comprises an analysis of the video streams allowing a count of the samples present on the stained slides, coming from a cassette, and a step of verifying the correlation of this number with the number of samples present in the cassette.

16. A method of histopathological examination, in particular anatomopathology, comprising a step of introducing a tissue into a first container provided with a closing means, a step of closing the first container after introduction of the tissue, a step of placing on the first container an identifier of the tissue introduced into the first container, a step of opening the first container and extracting the tissue from the first container, a step of moving at least a portion of the tissue extracted from the first container into a second container, the second container carrying an identifier of the portion of tissue, the method being characterized in that it comprises an identification and tracking of objects by analysis of a video stream, the opening of the first container being detected during this identification and tracking of objects,the method comprising a step of detecting and reading the identifier placed on the first container and the identifier placed on the second container, an error message being generated in the event of a discrepancy between the identifier of the first container and the identifier of the second container., 17. Method according to claim 16, characterized in that it comprises a step of recording the moment at which the opening of the first container is detected.

18. Method according to claim 16 or 17, characterized in that the second container is a cassette, the closing of the cassette and the closing of the first container being detected by the identification and tracking of objects during the analysis of the video stream.

19. Method according to any one of claims 1 to 6, characterized in that a display of the objects identified during the analysis of the video stream is carried out, the shape of the identified objects being represented by an enclosing window.

20. Device for implementing a method according to any one of claims 1 to 19, the device being characterized in that it comprises means for identifying and tracking objects by analyzing a video stream coming from at least one camera.

21. Anatomopathology device, for implementing a method according to any one of claims 1 6 to 1 9, the device comprising a workstation comprising a cutting board intended to support a first container provided with a closing means and a second container, the device comprising means for identifying and tracking objects by analyzing a video stream, these means being capable of detecting the opening of the first container, the device comprising means for detecting and reading an identifier placed on the first container and an identifier placed on the second container, the device comprising means for generating an error message in the event of a discrepancy between the identifier of the first container and the identifier of the second container.

22. Device according to claim 21, characterized in that the cutting board comprises a reservation capable of housing a first or a second container, the first container preferably being a bottle, the second container preferably being a cassette.

23. Device according to claim 21 or 22, characterized in that the detection and reading means comprise a one-dimensional or two-dimensional bar code reader.

24. Device according to any one of claims 21 to 23, characterized in that the work station comprises weighing means.

25. Device according to any one of claims 21 to 24, characterized in that the work station comprises measuring means along several axes.

26. Device according to any one of claims 21 to 25, characterized in that it comprises a station for including biological tissue to form a block, a station for cutting the block into thin slices by microtome, and a station for spreading the slices on slides, the device comprising means for printing on the block and on the slides an identifier of the biological tissue.

Images