Pap smear pre-screening technique

Abstract

Present disclosure provides PAP smear prescreening system and method for detecting abnormality in PAP smear. The method comprises receiving a PAP smear slide image from a source. Thereafter, the method comprises splitting the PAP smear slide image into a plurality of PAP smear tile images and extracting a ROI in the PAP smear slide image. Subsequently, the method comprises checking and selecting each PAP smear tile image in a second region with presence of at least one cell. The method comprises classifying cells present in the ROI and at least one selected PAP smear tile image for cell condition using a trained Al technique and historic PAP smear slide images. Lastly, the method comprises reconstructing the at least one PAP smear slide image using the ROI, and the second region including the classification of the cells present in the ROI and the at least one selected PAP smear tile image.

Description

TITLE: “PAP SMEAR PRE-SCREENING TECHNIQUE”TECHNICAL FIELDThe present disclosure generally relates to a field of computational pathology. Particularly, but not exclusively, the present disclosure relates to Papanicolaou (PAP) smear prescreening technique.BACKGROUNDIn a conventional PAP smear screening method, pathologists have to review all PAP smear slides, which are to be diagnosed, under a microscope. This method is a manual process and is slow, time-consuming i.e., for example, 8 - 12 hours of pathologist’s time for 100 slides, and prone to human errors. With advancement in the screening technology, there are methods by which the pathologists manually review only flagged slides rather than every slide under the microscope. Slides are flagged by algorithms in these methods for pathologist review if any abnormal cells are detected. Currently, the pathologists must view each flagged slide in its entirety for identifying abnormalities in PAP smear samples. Consequently, this process is still inefficient and prone to human error.The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the disclosure and should not be taken as an acknowledgement or any form of suggestion that this information forms existing information already known to a person skilled in the art.SUMMARYThere is a need to overcome problems associated with existing screening technique for PAP smear.In an embodiment, the present disclosure relates to a method for detecting abnormality in PAP smear. The method comprising receiving at least one PAP smear slide image from at least one source. Thereafter, the method comprises splitting the at least one PAP smear slide image into a plurality of PAP smear tile images and extracting a Region of Interest (ROI) in the at least one PAP smear slide image. The ROI is extracted by detecting a PAP in the at least one PAP smear slide image, constructing a boundary box around the PAP detected in the at least one PAP smear slide image to form a first region enclosing the PAP, determining a centre point ofthe first region enclosing the PAP, determining a distance between the centre point and one of an edge of the boundary box, and extracting the ROI for the PAP using the distance as a radius of the ROI. Subsequently, the method comprises checking each PAP smear tile image of the plurality of PAP smear tile images in a second region for presence of at least one cell. The second region refers to a region outside the ROI and within the boundary box. The method comprises selecting at least one checked PAP smear tile image with presence of the at least one cell and classifying cells present in the ROI and the at least one selected PAP smear tile image for cell condition using a trained Artificial Intelligent (Al) technique and historic PAP smear slide images. Lastly, the method comprises reconstructing the at least one PAP smear slide image using the ROI, and the second region including the classification of the cells present in the ROI and the at least one selected PAP smear tile image.In another embodiment, the present disclosure relates to a PAP smear prescreening system for detecting abnormality in PAP smear. The PAP smear prescreening system comprising a processor, and a memory communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which on execution, cause the processor to receive at least one PAP smear slide image from at least one source. The processor is configured to split the at least one PAP smear slide image into a plurality of PAP smear tile images, and extract a ROI in the at least one PAP smear slide image. For extracting the ROI, the processor is configured to detect a PAP in the at least one PAP smear slide image, construct a boundary box around the PAP detected in the at least one PAP smear slide image to form a first region enclosing the PAP, determine a centre point of the first region enclosing the PAP, determine a distance between the centre point and one of an edge of the boundary box, and extract the ROI for the PAP using the distance as a radius of the ROI. Thereafter, the processor is configured to check each PAP smear tile image of the plurality of PAP smear tile images in a second region for presence of at least one cell. The second region refers to a region outside the ROI and within the boundary box. The processor is configured to select at least one checked PAP smear tile image with presence of the at least one cell and classify cells present in the ROI and the at least one selected PAP smear tile image for cell condition using a trained Al technique and historic PAP smear slide images. Lastly, processor is configured to reconstruct the at least one PAP smear slide image using the ROI, and the second region including the classification of the cells present in the ROI and the at least one selected PAP smear tile image.The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.BRIEF DESCRIPTION OF THE DRAWINGSThe accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and together with the description, serve to explain the disclosed principles. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the figures to reference like features and components. Some embodiments of system and methods in accordance with embodiments of the present subject matter are now described below, by way of example only, and with reference to the accompanying figures.FIG. la illustrates an environment for detecting abnormality in PAP smear in accordance with some embodiments of the present disclosure.FIGS, lb to Id show a method for extracting ROI in at least one PAP smear slide image in accordance with some embodiments of the present disclosure.FIG. 2 shows a detailed block diagram of a PAP smear prescreening system in accordance with some embodiments of the present disclosure.FIGS. 3a to 3b illustrate a flowchart showing a method for detecting abnormality in PAP smear in accordance some embodiments of the present disclosure.FIG. 4 illustrates a block diagram of a computer system for implementing embodiments consistent with the present disclosure.It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flowcharts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially representedin computer readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown.DESCRIPTION OF THE DISCLOSUREIn the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternatives falling within the scope of the disclosure.The terms “comprises”, “comprising”, or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus proceeded by “comprises. . . a” does not, without more constraints, preclude the existence of other elements or additional elements in the system or method.In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.FIG. la illustrates an environment for detecting abnormality in PAP smear in accordance with some embodiments of the present disclosure.With reference to FIG. la, the environment 100 comprises one or more sources (also, referred as at least one source) 101, a database 103, a communication network 105, and a PAP smear prescreening system (also, referred as a pre-screening system) 107. In an embodiment, an electronic device (not show in FIG. la) may be a part of the PAP smear prescreening system 107, or separate from the PAP smear prescreening system 107 and communicatively connected to the PAP smear prescreening system 107. The electronic device may be used for display purpose. The electronic device may be any electronic device with a display such as a tablet, a smartphone, a laptop, or a computer system. The one or more sources 101 comprises a laboratory repository or a laboratory server. The laboratory repository or the laboratory server may be present at different locations at medical clinics, laboratories, or hospitals. The laboratory repository or the laboratory server is a source (or storage) for a plurality of PAP smear slide images. The PAP smear slide image may, also, be referred as a cell slide image or a Whole Slide Image (WSI). The plurality of PAP smear slide images are scanned on a scanner by a technician or a medical assistant and uploaded to the laboratory repository or the laboratory server. In an embodiment, the PAP smear slide images are images of PAP smear collected of a person (also, referred as a patient). The plurality of PAP smear slide images are sent from the one or more sources 101 for prescreening to the PAP smear prescreening system 107 using the communication network 105.The communication network 105 can be any of the following, but is not limited to, communication protocols / methods: a direct interconnection, an e-commerce network, a Peer- to-Peer (P2P) network, Local Area Network (LAN), Wide Area Network (WAN), wireless network (for example, using Wireless Application Protocol), Internet, Wi-Fi, Bluetooth, General Pack Radio Service (GPRS), Global System for Mobile communication (GSM), Code- Division Multiple Access (CDMA), WiMAX, WLAN, ZigBee, and the like.In the embodiment, the PAP smear prescreening system 107 includes an Input-Output (1-0) interface 111, a memory 113, and a processor 115. The 1-0 interface 111 is configured to receive at least one PAP smear slide image from at least one source 101 and transmit a report based on a Bethesda System of reporting to the electronic device. The 1-0 interface 111 employs communication protocols / methods such as, without limitation, audio, analog, digital, monoaural, Radio Corporation of America (RCA) connector, stereo, IEEE®- 1394 high speed serial bus, serial bus, Universal Serial Bus (USB), infrared, Personal System / 2 (PS / 2) port, Bayonet Neill-Concelman (BNC) connector, coaxial, fibre optic, component, composite,Digital Visual Interface (DVI), High-Definition Multimedia Interface (HDMI®), Radio Frequency (RF) antennas, S-Video, Video Graphics Array (VGA), IEEE® 802.11b / g / n / x, Bluetooth, cellular e.g., Code-Division Multiple Access (CDMA), High-Speed Packet Access (HSPA+), Global System for Mobile communications (GSM®), Long-Term Evolution (LTE®), Worldwide interoperability for Microwave access (WiMax®), or the like.The at least one PAP smear slide image received by the 1-0 interface 111 is stored in the memory 113. The memory 113 is communicatively coupled to the processor 115 of the PAP smear prescreening system 107. The memory 113, also, stores processor-executable instructions which may cause the processor 115 to execute the instructions for detecting abnormality in PAP smear. The memory 113 includes, without limitation, memory drives, removable disc drives, etc. The memory drives may further include a drum, magnetic disc drive, magneto-optical drive, optical drive, Redundant Array of Independent Discs (RAID), solid-state memory devices, solid-state drives, etc.The processor 115 includes at least one data processor for detecting abnormality in PAP smear. The processor 115 may include specialized processing units such as integrated system (bus) controllers, memory management control units, floating point units, graphics processing units, digital signal processing units, etc.The database 103 is communicatively connected to the at least one source 101 and the PAP smear prescreening system 107 through the communication network 105. In an embodiment, the database 103 is communicatively connected to the PAP smear prescreening system 107 directly. The database 103 may be a cloud server or a cloud database or a server. The database 103 may be populated or stored with historic data such as historic PAP smear slide images including historic PAP smear tile images collected of persons or patients. The term historic or historical refers to from the past. In an embodiment, the at least one PAP smear slide image from the at least one source 101 is directly stored in the database 103 through the communication network 105. The database 103 may, also, be updated at pre-defined intervals of time. These updates relates to the at least one PAP smear slide image for adaptive learning purpose.Hereinafter, the operation of the PAP smear prescreening system 107 for detecting abnormality in PAP smear is explained in two parts: (1) real-time or testing phase, and (2) training phase.Real-time or testing phase:When a patient visits a pathologist or a doctor, the pathologist or the doctor collects a PAP smear sample from the patient. After staining the PAP smear sample as a standard protocol, the pathologist or the doctor uploads (stained) PAP smear sample images to the database 103 or a laboratory repository. The sample images includes a plurality of PAP smear slide images. For prescreening of the PAP smear sample for detecting abnormality in PAP smear, the PAP smear prescreening system 107 receives at least one PAP smear slide image from the at least one source 101. The received at least one PAP smear slide image may be of any image format. Thereafter, the PAP smear prescreening system 107 splits the at least one PAP smear slide image into a plurality of PAP smear tile images. For instance, if the PAP smear slide image is, but not limited to, 1 million x 1 million pixels in dimension, the PAP smear prescreening system 107 splits the PAP smear slide image to a convenient image format with each PAP smear tile image of, but not limited to, 1000 x 1000 pixels in dimension. The convenient image format may refer to any image format that is a convenient for subsequent processing or internal processing. In an embodiment, the convenient image format may be, but not limited to, a Joint Photographic Experts Group (JPEG) image format. Subsequently, the PAP smear prescreening system 107 extracts a ROI 129 in the at least one PAP smear slide image. In detail, the PAP smear prescreening system 107 extracts the ROI in the following way. The PAP smear prescreening system 107 detects a PAP 121 in the at least one PAP smear slide image. The PAP smear prescreening system 107 detects the PAP 121 using a Convolutional Neural Network (CNN) technique. The CNN technique can be any known CNN technique in the art. The PAP smear prescreening system 107 constructs a boundary box 123 around the PAP 121 detected in the at least one PAP smear slide image to form a first region enclosing the PAP 121, as shown in FIG. lb. The PAP smear prescreening system 107 determines a centre point 125 of the first region enclosing the PAP 121, as shown in FIG. 1c. The PAP smear prescreening system 107 determines a distance 127 between the centre point 125 and one of an edge of the boundary box 123, as shown in FIG. 1c. The PAP smear prescreening system 107 extracts the ROI 129 for the PAP 121 using the distance 127 as a radius of the ROI 129, as shown in FIG. Id. The PAP smear prescreening system 107 checks each PAP smear tile image of the plurality of PAP smear tile images in a second region for presence of at least one cell. The second region refers to a region outside the ROI 129 (i.e., ROI circle 129 shown in FIG. Id) and within the boundary box 123 (i.e., square box 123 shown in FIGS, lb and 1c). The PAP smear prescreening system 107 checks each PAP smear tile image of the plurality of PAPsmear tile images in the second region for different colours of cells resulted from staining process using an image processing technique. The image processing technique can be any image processing technique known in the art. Thereafter, the PAP smear prescreening system 107 selects at least one checked PAP smear tile image with presence of the at least one cell. The region outside the boundary box 123 is ignored (or not considered) by the PAP smear prescreening system 107 for checking the presence of at least one cell. Due to extraction process (or steps) of a ROI and (checking and) selection steps of at least one PAP smear tile image in the second region as mentioned-above, the PAP smear prescreening system 107 reduces processing time for PAP smear slide images of a person’s or patient’s sample and consequently, reduces processing cost.Subsequently, the PAP smear prescreening system 107 classifies cells present in the ROI 129 and the at least one selected PAP smear tile image for cell condition using a trained Al technique and historic PAP smear slide images. In detail, the PAP smear prescreening system 107 classifies cells for cell condition into an abnormal PAP cell condition, a micro-organism, an artifact and a normal PAP cell condition using the trained Al technique and historic PAP smear tile images. The micro-organism is one of a bacteria or a fungi. The artifact refers to objects not related to the PAP smear such as, but not limited to, a bubble, a crystalline structure or the like. In an embodiment, the classifying module 217 further classifies the normal PAP cell condition into one of a superficial, intermediate, and parabasal.In an embodiment, after classification step, the PAP smear prescreening system 107 may flag for review by the pathologist in situation when classification of cells for cell condition is an abnormal PAP cell condition. This approach overcomes false positives by flagging cases for review by the pathologist for a confirmatory diagnosis.The trained Al technique is at least one of a Convolutional Neural Network (CNN) technique, a CSPDarkNet technique, a Non-maximum Suppression (NMS) technique, and a Region Proposal Network (RPN) technique. The historic PAP smear tile images are stored in the database 103. The use of the trained Al technique and historic PAP smear tile images in the present disclosure minimizes the requirement of manual intervention of a pathologist or a doctor for an accurate detection of cell condition.The PAP smear prescreening system 107 annotates at least one co-ordinate of the classified cells present in the ROI 129 and the at least one selected PAP smear tile image with the cell condition. The annotation refers to a comment or a note mentioning cell condition i.e., either an abnormal PAP cell condition, a micro-organism, an artifact or a normal PAP cell condition. The normal PAP cell condition may be further annotated as one of a superficial, an intermediate, and parabasal.The PAP smear prescreening system 107 reconstructs the at least one PAP smear slide image using the ROI 129, and the second region including the classification of the cells present in the ROI 129 and the at least one selected PAP smear tile image. For instance, each PAP smear tile image of, but not limited to, 1000 x 1000 pixels in dimension is reconstructed by the PAP smear prescreening system 107 to the original PAP smear slide image size of, but not limited to, 1 million x 1 million pixels in dimension. Also, if an annotation is at coordinates (10, 10) in a PAP smear tile image but the PAP smear tile image is a fifth tile image in a first row of the original PAP smear slide image, then the coordinates with the annotation become (5010, 10) in the reconstructed PAP smear slide image. The reconstruction of the at least one PAP smear slide image to its original size allows the pathologists or the doctors to review the abnormality in PAP smear in an easy and efficient manner. Thereafter, the PAP smear prescreening system 107 generates a report based on a Bethesda System of reporting using the reconstructed at least one PAP smear slide image. PAP smears are typically reported under the Bethesda System of reporting. The PAP smear prescreening system 107 transmits the report based on a Bethesda System of reporting to the electronic device for display purpose. The transmission of the report based on a Bethesda System of reporting allows performing mass PAP smear screening camps even in locations where a pathologist or a doctor is not available. In an embodiment, the PAP smear prescreening system 107 transmits the reconstructed at least one PAP smear slide image to the electronic device for display purpose. The reconstructed at least one PAP smear slide image helps pathologists or doctors to spend more time on patient cases that have abnormal cell condition issues rather than spending time detecting abnormal cell condition from normal cell condition in patent’s PAP smear sample. The PAP smear prescreening system 107 is Liquid Based Cytology (LBC) agnostic and scanner agnostic. In detail, LBC is a method of preparing the PAP smear sample (or specimen). There are multiple companies that sell these preparation kits. The PAP smear prescreening system 107 works on all the LBC preparation kits available in the market. Scanner is a device used to take high resolution images of PAP smear sample on glass slides. These images are used for detecting abnormality in PAP smear. There are manyscanners available in the market with different image formats. The PAP smear prescreening system 107 works with all the scanners (including different image formats) and all the LBC available in the market while other prescreening techniques available in market may work only with specific LBC and specific scanners. In an embodiment, the PAP smear prescreening system 107 stores the reconstructed at least one PAP smear slide image and the report based on a Bethesda System of reporting in the database 103 for future use.The PAP smear prescreening system 107 performs the above-mentioned operations such as splitting, extracting, checking, selecting, classifying, annotating, reconstructing, and generating for each PAP smear slide image one at a time. Further, the technique of extracting a ROI in each of the plurality of PAP smear tile images can be implemented for any prescreening or detection method.Training phase:During training phase of the Al technique (also, referred as Al model), the PAP smear prescreening system 107 receives historic PAP smear slide images including historic PAP smear tile images collected of persons or patients from the database 103 and at least one PAP smear slide image from the at least one source 101. Thereafter, the Al technique is trained by performing the above-mentioned operations such as splitting, extracting, checking, selecting, classifying, annotating, reconstructing, and generating for the PAP smear slide image. The Al technique is trained to use the historic PAP smear slide images including historic PAP smear tile images for checking the at least one PAP smear slide image for detecting abnormality in PAP smear. The Al technique may be a fully supervised CNN. The fully supervised CNN technique may be at least one of a CSPDarkNet technique, a NMS technique, and a RPN technique.FIG. 2 shows a detailed block diagram of a PAP smear prescreening system in accordance with some embodiments of the present disclosure.The PAP smear prescreening system 107, in addition to the 1-0 interface 111 and the processor 115, includes data 200 and one or more modules 211 (also, referred as modules), which are described herein in detail. In the embodiment, the data 200 is stored within the memory 113.In an embodiment, the data 200 includes, for example, image data 201, and miscellaneous data 203.The image data 201 stores at least one PAP smear slide image received from the at least one source 101. The image data 201 may, also, be referred as diagnosis data.The miscellaneous data 203 stores data, including temporary data and temporary files, generated by modules 211 for performing various functions of the PAP smear prescreening system 107.In an embodiment, the data 200 in the memory 113 are processed by the one or more modules 211 present within the memory 113 of the PAP smear prescreening system 107. In the embodiment, the one or more modules 211 may be implemented as dedicated hardware units. As used herein, the term module refers to an Application Specific Integrated Circuit (ASIC), an electronic circuit, a Field-Programmable Gate Arrays (FPGA), Programmable System-on- Chip (PSoC), a combinational logic circuit, and / or other suitable components that provide the described functionality. In some implementations, the one or more modules 211 may be communicatively coupled to the processor 115 for performing one or more functions of the PAP smear prescreening system 107. The modules 211 when configured with the functionality defined in the present disclosure will result in a novel hardware.In an embodiment, the one or more modules 211 of the PAP smear prescreening system 107 includes, but are not limited to, a transceiver 213, an extracting module 215, a classifying module 217, and a rendering module 219. The one or more modules 211 may, also, include miscellaneous modules 221 to perform various miscellaneous functionalities of the PAP smear prescreening system 107.Transceiver 213:The transceiver 213 receives at least one PAP smear slide image from the at least one source 101. The one or more sources 101 comprises a laboratory repository. The PAP smear slide image (also, referred as cell slide image) are of PAP smear collected of a person or a patient. The transceiver 213 transmits a report based on a Bethesda System of reporting to an electronic device.Extracting module 215:The extracting module 215 splits the at least one PAP smear slide image into a plurality of PAP smear tile images. Thereafter, the extracting module 215 extracts a ROI 129 in the at least one PAP smear slide image. In detail, the extracting module 215 extracts the ROI 129 as following:The extracting module 215 detects a PAP 121 in the at least one PAP smear slide image. The PAP smear prescreening system 107 detects the PAP 121 using a Convolutional Neural Network (CNN) technique. The CNN technique can be any known CNN technique in the art. The extracting module 215 constructs a boundary box 123 around the PAP 121 detected in the at least one PAP smear slide image to form a first region enclosing the PAP 121. The extracting module 215 determines a centre point 125 of the region enclosing the PAP 121. The extracting module 215 determines a distance 127 between the centre point 125 and one of an edge of the boundary box 123. The extracting module 215 extracts the ROI 129 for the PAP 121 using the distance 127 as a radius of the ROI 129.Classifying module 217:The classifying module 217 checks each PAP smear tile image of the plurality of PAP smear tile images in a second region for presence of at least one cell. The second region refers to a region outside the ROI 129 and within the boundary box 123. The classifying module 217 checks each PAP smear tile image of the plurality of PAP smear tile images in the second region for different colours of cells resulted from staining process using an image processing technique. The image processing technique can be any image processing technique known in the art. The classifying module 217 selects at least one checked PAP smear tile image with presence of the at least one cell. Thereafter, the classifying module 217 classifies cells present in the ROI 129 and the at least one selected PAP smear tile image for cell condition using a trained Al technique and historic PAP smear slide images. The classifying module 217 classifies cells for cell condition into an abnormal PAP cell condition, a micro-organism, an artifact and a normal PAP cell condition using the trained Al technique and historic PAP smear tile images. The micro-organism is one of a bacteria or a fungi. The artifact refers to objects not related to the PAP smear such as, but not limited to, a bubble, a crystalline structure or the like. In an embodiment, the classifying module 217 further classifies the normal PAP cell condition into one of a superficial, intermediate, and parabasal. The trained Al technique (also, referred as Al model) is at least one of CNN technique, a CSPDarkNet technique, a NMS technique, and a RPN technique.Further, the classifying module 217 annotates at least one co-ordinate of the classified cells present in the ROI 129 and the at least one selected PAP smear tile image with the cell condition. The annotation refers to a comment or a note mentioning cell condition i.e., either an abnormal PAP cell condition, a micro-organism, an artifact or a normal PAP cell condition. The normal PAP cell condition may be further annotated as one of a superficial, an intermediate, and parabasal.The classifying module 217 comprises the Al technique or the trained Al technique (i.e., the Al model).Rendering module 219:The rendering module 219 reconstructs the at least one PAP smear slide image using the ROI 129, and the second region including the classification of the cells present in the ROI 129 and the at least one selected PAP smear tile image. Thereafter, the rendering module 219 generates a report based on a Bethesda System of reporting using the reconstructed at least one PAP smear slide image.FIGS. 3a to 3b illustrate a flowchart showing a method for detecting abnormality in PAP smear in accordance some embodiments of the present disclosure.As illustrated in FIGS. 3a to 3b, the method 300a and the method 300b include one or more blocks for detecting abnormality in PAP smear in accordance with some embodiments of the present disclosure. The method 300a and the method 300b may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, and functions, which perform particular functions or implement particular abstract data types.The order in which the method 300a the method 300b are described are not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof.At block 301, the transceiver 213 of the PAP smear prescreening system 107 receives at least one PAP smear slide image from at least one source 101.At block 303, the extracting module 215 of the PAP smear prescreening system 107 splits the at least one PAP smear slide image into a plurality of PAP smear tile images.At block 305, the extracting module 215 of the PAP smear prescreening system 107 extracts a ROI in the at least one PAP smear slide image. In detail, the extracting module 215 of the PAP smear prescreening system 107 extracts the ROI as following:At block 3051, the extracting module 215 of the PAP smear prescreening system 107 detects a PAP 121 in the at least one PAP smear slide image.At block 3053, the extracting module 215 of the PAP smear prescreening system 107 constructs a boundary box 123 around the PAP 121 in the at least one PAP smear slide image to form a first region enclosing the PAP 121.At block 3055, the extracting module 215 of the PAP smear prescreening system 107 determines a centre point 125 of the first region enclosing the PAP 121.At block 3057, the extracting module 215 of the PAP smear prescreening system 107 determines a distance 127 between the centre point 125 and one of an edge of the boundary box 123.At block 3059, the extracting module 215 of the PAP smear prescreening system 107 extracts the ROI 129 for the PAP 121 using the distance 127 as a radius of the ROI 129.At block 307, the classifying module 217 of the PAP smear prescreening system 107 checks each PAP smear tile image of the plurality of PAP smear tile images in a second region for presence of at least one cell. The second region refers to a region outside the ROI 129 and within the boundary box 123.At block 309, the classifying module 217 of the PAP smear prescreening system 107 selects at least one checked PAP smear tile image with presence of the at least one cell.At block 311, the classifying module 217 of the PAP smear prescreening system 107 classifies cells present in the ROI 129 and the at least one selected PAP smear tile image for cell condition using a trained Al technique and historic PAP smear slide images. The trained Al technique is at least one of CNN technique, a CSPDarkNet technique, a NMS technique, and a RPN technique.At block 313, the rendering module 219 of the PAP smear prescreening system 107 reconstructs the at least one PAP smear slide image using the ROI 129, and the second region including the classification of the cells present in the ROI 129 and the at least one selected PAP smear tile image.FIG. 4 illustrates a block diagram of an exemplary computer system for implementing embodiments consistent with the present disclosure.In an embodiment, the computer system 400 may be used to implement the PAP smear prescreening system 107. The computer system 400 may include a CPU or processor 402. The processor 402 may include at least one data processor for detecting abnormality in PAP smear. The processor 402 may include specialized processing units such as, integrated system (bus) controllers, memory management control units, floating point units, graphics processing units, digital signal processing units, etc. The processor 402 may be used to realize the processor 115 described in FIG 2.The processor 402 may be disposed in communication with one or more 1-0 devices via 1-0 interface 401. The 1-0 interface 401 employ communication protocols / methods such as, without limitation, audio, analog, digital, monaural, RCA connector, stereo, IEEE- 1394 high speed serial bus, serial bus, USB, infrared, PS / 2 port, BNC connector, coaxial, component, composite, DVI, HDMI, RF antennas, S-Video, VGA, IEEE 802.11b / g / n / x, Bluetooth, cellular e.g., CDMA, HSPA+, GSM, LTE, WiMax, etc.Using the 1-0 interface 401, the computer system 400 may communicate with one or more 1-0 devices such as input devices 409 and output devices 410. For example, the input devices 409may be an antenna, keyboard, mouse, joystick, (infrared) remote control, camera, card reader, fax machine, dongle, biometric reader, microphone, touch screen, touchpad, trackball, stylus, scanner, storage device, transceiver, video device / source, etc. The output devices 410 may be a printer, fax machine, video display (e.g., CRT, LCD, LED, plasma, PDP, OLED or the like), audio speaker, etc.In some embodiments, the computer system 400 consists of the PAP smear prescreening system 107. The processor 402 may be disposed in communication with the communication network 105 via a network interface 403. The network interface 403 may communicate with the communication network 105. The network interface 403 may employ connection protocols including, without limitation, direct connect, Ethernet (e.g., twisted pair 10 / 100 / 1000 Base T), TCP / IP, token ring, IEEE 802.1 la / b / g / n / x, etc. Using the network interface 403 and the communication network 105, the computer system 400 may communicate with the database 103 for detecting abnormality in PAP smear.The communication network 105 includes, but is not limited to, a direct interconnection, a P2P network, LAN, WAN, wireless network (e.g., using Wireless Application Protocol), the Internet, and Wi-Fi.In some embodiments, the processor 402 may be disposed in communication with a memory 405 (e.g., RAM, ROM, etc. not shown in FIG. 4) via a storage interface 404. The storage interface 404 may connect to the memory 405 including, without limitation, memory drives, removable disc drives, etc., employing connection protocols such as, SATA, IDE, IEEE- 1394, USB, fiber channel, SCSI, etc. The memory drives may further include a drum, magnetic disc drive, magneto-optical drive, optical drive, RAID, solid-state memory devices, solid-state drives, etc.The memory 405 may store a collection of program or database components, including, without limitation, a user interface 406, an operating system 407, etc. In some embodiments, the computer system 400 may store user / application data, such as, the image data 201, etc., as described in this disclosure. The memory 405 may be used to realize the memory 113 described in FIG. 2. The memory 405 may be communicatively coupled to the processor 402. The memory 405 stores instructions, executable by the processor 402.The operating system 407 may facilitate resource management and operation of the computer system 400. Examples of operating systems include, without limitation, APPLE® MACINTOSH® OS X®, UNIX®, UNIX-like system distributions (E.G., BERKELEY SOFTWARE DISTRIBUTION® (BSD), FREEBSD®, NETBSD®, OPENBSD, etc.), LINUX® DISTRIBUTIONS (E.G., RED HAT®, UBUNTU®, KUBUNTU®, etc.), IBM®OS / 2®, MICROSOFT® WINDOWS® (XP®, VISTA® / 7 / 8, 10 etc.), APPLE® IOS®, GOOGLE™ ANDROID™, BLACKBERRY® OS, or the like.In some embodiments, the computer system 400 may implement web browser 408 stored program components. Web browser 408 may be a hypertext viewing application, such as MICROSOFT® INTERNET EXPLORER®, GOOGLE™ CHROME™, MOZILLA® FIREFOX®, APPLE® SAFARI®, etc. Secure web browsing may be provided using HTTPS, SSL, TLS, etc. Web browser 408 may utilize facilities such as AJAX, DHTML, ADOBE® FLASH®, JAVASCRIPT®, JAVA®, APIs, etc. The computer system 400 may implement a mail server (not shown in FIG. 4) stored program component. The mail server may be an Internet mail server such as Microsoft Exchange, or the like. The mail server may utilize facilities such as ASP, ACTIVEX®, ANSI® C++ / C#, MICROSOFT®, .NET, CGI SCRIPTS, JAVA®, JAVASCRIPT®, PERL®, PHP, PYTHON®, WEBOBJECTS®, etc. The mail server may utilize communication protocols such as IMAP, MAPI, MICROSOFT® exchange, POP, SMTP, or the like. The computer system 400 may implement a mail client (not shown in FIG. 4) stored program component. The mail client may be a mail viewing application, such as APPLE® MAIL, MICROSOFT® ENTOURAGE®, MICROSOFT® OUTLOOK®, MOZILLA® THUNDERBIRD®, etc.Some of the technical advantages of the present disclosure are listed below.The use of a trained Al technique and historic PAP smear tile images in the present disclosure minimize the requirement of manual intervention of a pathologist or a doctor for an accurate detection of abnormal cell condition.The claimed subject matter of the present disclosure allows performing mass PAP smear screening camps even in locations where a pathologist or a doctor is not available.The claimed subject matter of the present disclosure helps pathologists or doctors to spend more time on patient cases that have abnormal cell condition issues rather than spending time determining abnormal cell condition from normal cell condition in patent’s PAP smear sample.The claimed subject matter of the present disclosure is Liquid Based Cytology (LBC) agnostic and scanner agnostic. In detail, LBC is a method of preparing the PAP smear sample (or specimen). There are multiple companies that sell these preparation kits. The PAP smear prescreening system of the present disclosure works on all the LBC preparation kits available in the market. Scanner is a device used to take high resolution images of PAP smear sample on glass slides. These images are used for detecting abnormality in PAP smear. There are many scanners available in the market with different image formats. The PAP smear prescreening system of the present disclosure works with all the scanners (including different image formats) and all the LBC available in the market while other prescreening techniques available in market may work only with specific LBC and specific scanners.The claimed subject matter of the present disclosure overcomes false positives by flagging cases for review by the pathologist for a confirmatory diagnosis. In situations where abnormal cells are detected, this approach overcomes the issue of incorrectly classifying the PAP cell condition as abnormal by flagging the case for review by a pathologist or a doctor.The pathologist assisted by the PAP smear prescreening system of the present disclosure takes about 60 minutes to process 100 PAP smear slide images for detecting abnormality in PAP smear samples (or specimen) as compared to 8 - 12 hours of manual diagnosis. Consequently, this results in a reduction of significant time of the pathologist and processing cost.Some of the clauses are mentioned below.[1]: A method for detecting abnormality in Papanicolaou (PAP) smear, the method comprising: receiving at least one PAP smear slide image from at least one source; splitting the at least one PAP smear slide image into a plurality of PAP smear tile images; extracting a Region of Interest (RO I) in the at least one PAP smear slide image, wherein the ROI is extracted by:detecting a PAP in the at least one PAP smear slide image; constructing a boundary box around the PAP detected in the at least one PAP smear slide image to form a first region enclosing the PAP; determining a centre point of the first region enclosing the PAP; determining a distance between the centre point and one of an edge of the boundary box; and extracting the ROI for the PAP using the distance as a radius of the ROI; checking each PAP smear tile image of the plurality of PAP smear tile images in a second region for presence of at least one cell, wherein the second region refers to a region outside the ROI and within the boundary box; selecting at least one checked PAP smear tile image with presence of the at least one cell; classifying cells present in the ROI and the at least one selected PAP smear tile image for cell condition using a trained Artificial Intelligent (Al) technique and historic PAP smear slide images; and reconstructing the at least one PAP smear slide image using the ROI, and the second region including the classification of the cells present in the ROI and the at least one selected PAP smear tile image.[2]: The method described in [1], wherein classifying the cells present in the ROI and the at least one selected PAP smear tile image for cell condition using the trained Al technique and historic PAP smear slide images comprises: classifying cells for cell condition into an abnormal PAP cell condition, a microorganism, an artifact and a normal PAP cell condition using the trained Al technique and historic PAP smear tile images.[3]: The method described in any of [1] to [2], wherein classifying the cells present in the ROI and the at least one selected PAP smear tile image for cell condition using the trained Al technique and historic PAP smear slide images further comprises: annotating at least one co-ordinate of the classified cells present in the ROI and the at least one selected PAP smear tile image with the cell condition.[4]: The method described in any of [1] to [3], wherein the micro-organism is one of a bacteria or a fungi; andwherein the artifact refers to objects not related to the PAP smear.[5]: The method described in any of [1] to [4], further comprising: generating a report based on a Bethesda System of reporting using the reconstructed at least one PAP smear slide image.[6]: A PAP smear prescreening system for detecting abnormality in PAP smear, the PAP smear prescreening system comprising: a processor; and a memory communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which on execution, cause the processor to: receive at least one PAP smear slide image from at least one source; split the at least one PAP smear slide image into a plurality of PAP smear tile images; extract a Region of Interest (ROI) in the at least one PAP smear slide image, wherein the ROI is extracted by: detect a PAP in the at least one PAP smear slide image; construct a boundary box around the PAP detected in the at least onePAP smear slide image to form a first region enclosing the PAP; determine a centre point of the first region enclosing the PAP; determine a distance between the centre point and one of an edge of the boundary box; and extract the ROI for the PAP using the distance as a radius of the ROI; check each PAP smear tile image of the plurality of PAP smear tile images in a second region for presence of at least one cell, wherein the second region refers to a region outside the ROI and within the boundary box; select at least one checked PAP smear tile image with presence of the at least one cell; classify cells present in the ROI and the at least one selected PAP smear tile image for cell condition using a trained Artificial Intelligent (Al) technique and historic PAP smear slide images; and reconstruct the at least one PAP smear slide image using the ROI, and the second region including the classification of the cells present in the ROI and the at least one selected PAP smear tile image.[7]: The PAP smear prescreening system described in [6], wherein the processor is configured to: classifying cells for cell condition into an abnormal PAP cell condition, a microorganism, an artifact and a normal PAP cell condition using the trained Al technique and historic PAP smear tile images.[8]: The PAP smear prescreening system described in any of [6] to [7], wherein the processor is configured to: annotate at least one co-ordinate of the classified cells present in the ROI and the at least one selected PAP smear tile image with the cell condition.[9]: The PAP smear prescreening system described in any of [6] to [8], wherein the microorganism is one of a bacteria or a fungi; and wherein the artifact refers to objects not related to the PAP smear.

[0010] : The PAP smear prescreening system described in any of [6] to [9], wherein the processor is configured to: generate a report based on a Bethesda System of reporting using the reconstructed at least one PAP smear slide image.With respect to the use of substantially any plural and singular terms herein, those having skill in the art can translate from the plural to the singular and from the singular to the plural as is appropriate to the context or application. The various singular or plural permutations may be expressly set forth herein for sake of clarity.One or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which a software (program) readable by an information processing apparatus may be stored. The information processing apparatus includes a processor and a memory, and the processor executes a process of the software. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understoodto include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include RAM, ROM, volatile memory, non-volatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.The described operations may be implemented as a method, a system, or an article of manufacture using at least one of standard programming and engineering techniques to produce software, firmware, hardware, or any combination thereof. The described operations may be implemented as code maintained in a “non-transitory computer readable medium”, where a processor may read and execute the code from the computer readable medium. The processor is at least one of a microprocessor and a processor capable of processing and executing the queries. A non-transitory computer readable medium may include media such as magnetic storage medium (e.g., hard disk drives, floppy disks, tape, etc.), optical storage (CD ROMs, DVDs, optical disks, etc.), volatile and non-volatile memory devices (e.g., EEPROMs, ROMs, PROMs, RAMs, DRAMs, SRAMs, Flash Memory, firmware, programmable logic, etc.), etc. Further, non-transitory computer-readable media include all computer-readable media except for a transitory. The code implementing the described operations may further be implemented in hardware logic (e.g., an integrated circuit chip, PGA, ASIC, etc.).The terms “an embodiment”, “embodiment”, “embodiments”, “the embodiment”, “the embodiments”, “one or more embodiments”, “some embodiments”, and “one embodiment” mean “one or more (but not all) embodiments of the invention(s)” unless expressly specified otherwise.The terms “including”, “comprising”, “having” and variations thereof mean “including but not limited to”, unless expressly specified otherwise.The enumerated listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise.The terms “a”, “an” and “the” mean “one or more”, unless expressly specified otherwise.A description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary, a variety of optionalcomponents are described to illustrate the wide variety of possible embodiments of the invention.When a single device or article is described herein, it will be readily apparent that more than one device or article (whether or not they cooperate) may be used in place of a single device or article. Similarly, where more than one device or article is described herein (whether or not they cooperate), it will be readily apparent that a single device or article may be used in place of the more than one device, or article, or a different number of devices or articles may be used instead of the shown number of devices or programs. At least one of the functionalities and the features of a device may be alternatively embodied by one or more other devices which are not explicitly described as having such functionality or features. Thus, other embodiments of the invention need not include the device itself.The illustrated operations of FIGS. 3a, and 3b show certain events occurring in a certain order. In alternative embodiments, certain operations may be performed in a different order, modified, or removed. Moreover, steps may be added to the above-described logic and still conform to the described embodiments. Further, operations described herein may occur sequentially or certain operations may be processed in parallel. Yet further, operations may be performed by a single processing unit or by distributed processing units.Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. It is therefore intended that the scope of the invention be limited not by this detailed description, but rather by any claims that issue on an application based here on. Accordingly, the disclosure of the embodiments of the invention is intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.While various aspects and embodiments have been disclosed herein, other aspects and embodiments will be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope being indicated by the following claims.REFERRAL NUMERALS:

Claims

We Claim1. A method for detecting abnormality in Papanicolaou (PAP) smear, the method comprising: receiving at least one PAP smear slide image from at least one source; splitting the at least one PAP smear slide image into a plurality of PAP smear tile images; extracting a Region of Interest (RO I) in the at least one PAP smear slide image, wherein the ROI is extracted by: detecting a PAP in the at least one PAP smear slide image; constructing a boundary box around the PAP detected in the at least one PAP smear slide image to form a first region enclosing the PAP; determining a centre point of the first region enclosing the PAP; determining a distance between the centre point and one of an edge of the boundary box; and extracting the ROI for the PAP using the distance as a radius of the ROI; checking each PAP smear tile image of the plurality of PAP smear tile images in a second region for presence of at least one cell, wherein the second region refers to a region outside the ROI and within the boundary box; selecting at least one checked PAP smear tile image with presence of the at least one cell; classifying cells present in the ROI and the at least one selected PAP smear tile image for cell condition using a trained Artificial Intelligent (Al) technique and historic PAP smear slide images; and reconstructing the at least one PAP smear slide image using the ROI, and the second region including the classification of the cells present in the ROI and the at least one selected PAP smear tile image.

2. The method of claim 1, wherein classifying the cells present in the ROI and the at least one selected PAP smear tile image for cell condition using the trained Al technique and historic PAP smear slide images comprises: classifying cells for cell condition into an abnormal PAP cell condition, a microorganism, an artifact and a normal PAP cell condition using the trained Al technique and historic PAP smear tile images.

3. The method of claim 1, wherein classifying the cells present in the ROI and the at least one selected PAP smear tile image for cell condition using the trained Al technique and historic PAP smear slide images further comprises: annotating at least one co-ordinate of the classified cells present in the ROI and the at least one selected PAP smear tile image with the cell condition.

4. The method of claim 2, wherein the micro-organism is one of a bacteria or a fungi; and wherein the artifact refers to objects not related to the PAP smear.

5. The method of claim 1, further comprising: generating a report based on a Bethesda System of reporting using the reconstructed at least one PAP smear slide image.

6. A Papanicolaou (PAP) smear prescreening system for detecting abnormality in PAP smear, the PAP smear prescreening system comprising: a processor; and a memory communicatively coupled to the processor, wherein the memory stores processor-executable instructions, which on execution, cause the processor to: receive at least one PAP smear slide image from at least one source; split the at least one PAP smear slide image into a plurality of PAP smear tile images; extract a Region of Interest (ROI) in the at least one PAP smear slide image, wherein the ROI is extracted by: detect a PAP in the at least one PAP smear slide image; construct a boundary box around the PAP detected in the at least one PAP smear slide image to form a first region enclosing the PAP; determine a centre point of the first region enclosing the PAP; determine a distance between the centre point and one of an edge of the boundary box; and extract the ROI for the PAP using the distance as a radius of the ROI; check each PAP smear tile image of the plurality of PAP smear tile images in a second region for presence of at least one cell, wherein the second region refers to a region outside the ROI and within the boundary box;select at least one checked PAP smear tile image with presence of the at least one cell; classify cells present in the ROI and the at least one selected PAP smear tile image for cell condition using a trained Artificial Intelligent (Al) technique and historic PAP smear slide images; and reconstruct the at least one PAP smear slide image using the ROI, and the second region including the classification of the cells present in the ROI and the at least one selected PAP smear tile image.

7. The PAP smear pre-screening system of claim 6, wherein the processor is configured to: classifying cells for cell condition into an abnormal PAP cell condition, a microorganism, an artifact and a normal PAP cell condition using the trained Al technique and historic PAP smear tile images.

8. The PAP smear pre-screening system of claim 6, wherein the processor is configured to: annotate at least one co-ordinate of the classified cells present in the ROI and the at least one selected PAP smear tile image with the cell condition.

9. The PAP smear pre-screening system of claim 7, wherein the micro-organism is one of a bacteria or a fungi; and wherein the artifact refers to objects not related to the PAP smear.

10. The PAP smear pre-screening system of claim 6, wherein the processor is configured to: generate a report based on a Bethesda System of reporting using the reconstructed at least one PAP smear slide image.

Images