IL305325B2

IL305325B2 - System and method for determining proliferative disorder levels

Info

Publication number: IL305325B2
Application number: IL305325A
Authority: IL
Original assignee: Ariel Scient Innovations Ltd
Priority date: 2023-08-18
Filing date: 2023-08-18
Publication date: 2025-04-01
Also published as: IL305325B1; IL305325A; WO2025041130A1

Description

1 SYSTEM AND METHOD FOR DETERMINING PROLIFERATIVE DISORDER LEVELS FIELD OF THE INVENTION[001] The present invention relates generally to the field of assistive diagnostics. More specifically, the present invention relates to determining proliferative disorder levels.

BACKGROUND OF THE INVENTION[002] The current state of intraoperative cell diagnosis involves manual examination of tissue samples by pathologists, which introduces delays in surgery and may lead to suboptimal decisions due to the time-sensitive nature of oncologic procedures. Furthermore, the subjectivity inherent in manual assessments can result in variability and inconsistent diagnostic accuracy. These challenges underscore the pressing need for an automated system that can rapidly and objectively analyze tissue samples in real-time, or near real-time.

SUMMARY OF THE INVENTION[003] Embodiments of the invention may include a method of evaluating a level of proliferative disorder by at least one processor. Embodiments of the method may include radiating a population of cells with Infrared (IR) radiation, and obtaining, via one or more Attenuated Total Reflection (ATR) detectors, one or more respective spectral distribution data elements, each representing a spectral distribution of IR radiation reflected from a respective location in the population of cells. For at least one specific location in the population of cells, the at least one processor may analyze the respective spectral distribution data element, to calculate one or more indicator values that are characteristic of cell proliferation at the specific location. Based on the one or more indicator values, the at least one processor may calculate a proliferation score, indicating a level of proliferative disorder of cells in the specific location. [004] According to some embodiments, the one or more indicator values may include, for example, a membrane organic material indicator value, a motility-based indicator value, and an image-based indicator value. [005] The population of cells may include, for example a biological cell line, a sample of biological tissue, a biological tissue, a biological organ, and the like. 2 id="p-6" id="p-6" id="p-6" id="p-6" id="p-6" id="p-6" id="p-6"

[006] According to some embodiments, the one or more ATR detectors may include a plurality of ATR detectors, that may, for example, be arranged in one or more ATR detector vectors. [007] According to some embodiments, the at least one processor may be configured to scan the population of cells by the one or more ATR detector vectors, to obtain a plurality of location-specific proliferation scores; aggregate the location-specific proliferation scores along the scan; and produce, substantially in real time, a heat map of levels of a proliferative disorder, based on the aggregation of location-specific proliferation scores. [008] The proliferation scores may, for example include numerical values representing levels of proliferation disorders, such as a probability of a precancerous condition, a probability of a malignant condition, a level or degree of the malignant condition, a probability of a benign condition (e.g., a benign tumor) and a probability of a metastatic condition (e.g., a metastasis, or metastatic tumor). [009] According to some embodiments, the at least one processor may be configured to calculate an image-based indicator value by, for at least one location: producing a matrix (e.g., a two-dimensional) representation of the respective spectral distribution data element; applying a hierarchical image analysis algorithm on the matrix representation; and calculating an image-based indicator value, corresponding to the at least one location, based on outcome of said hierarchical image analysis algorithm. [0010] According to some embodiments, the hierarchical image analysis algorithm may be, or may include a Multifractal Analysis (MFA) algorithm. In such embodiments. the outcome of the hierarchical image analysis algorithm may, for example, be a multifractal dimension value. As known in the art, a multifractal dimension value may represent a variation in scaling exponents of an image. In such embodiments, the multifractal dimension value may me a variation in scaling exponents of the matrix representation of the spectral distribution data element. [0011] According to some embodiments, the at least one processor may be configured to calculate a motility-based value by, for at least one location: based on the respective spectral distribution data element, determining a value of an absorption peak of structured water; based on the respective spectral distribution data element, determining a value of an absorption peak of non-structured water; and calculating the motility-based indicator value, 3 corresponding to the at least one location, based on (i) the structured water absorption peak value and (ii) the non-structured water absorption peak value. [0012] According to some embodiments, the at least one processor may be configured to calculate a membrane organic material indicator value by, for at least one location: based on the respective spectral distribution data element, determining a value of an absorption peak of at least one membrane organic material; and calculating a membrane organic material indicator value, based on the absorption peak value of the at least one membrane organic material. [0013] According to some embodiments, the at least one processor may be configured to calculate the proliferation score of a specific location in the population of cells based on, or as a function of the indicator values. [0014] For example, the at least one processor may provide a Machine Learning (ML)-based model, that may be pretrained to predict a proliferation score based on input data that includes location-specific indicator values. In such embodiments, the at least one processor may apply, or infer the ML model on at least one of (e.g., all of) (i) the membrane organic material indicator value, (ii) the motility-based indicator value, and (iii) the image-based indicator value, to predict the proliferation score of the specific location. [0015] Additionally, or alternatively, the at least one processor may be configured to receive, from an imaging device, an image of the population of cells; analyze the image, to obtain one or more morphological features of the population of cells; and further infer the ML model on the one or more morphological features, to predict the proliferation score of the specific location. [0016] Embodiments of the invention may include a system for evaluating a level of a proliferative disorder in a population of cells. Embodiments of the system may include an array of one or more Attenuated Total Reflection (ATR) detectors, configured to be applied to the population of cells. Upon application, each detector may be configured to obtain a reading of Infrared (IR) radiation, reflected from a respective location in the population of cells. [0017] Embodiments of the system may further include a non-transitory memory device, where modules of instruction code are stored, and at least one processor associated with the memory device. The at least one processor may be configured to employ the memory device to execute the modules of instruction code. Upon execution of the modules of instruction 4 code, the at least one processor may be configured to receive one or more readings of IR radiation from one or more respective ATR detectors, and based on the one or more received readings, calculate a proliferation score indicating a level of proliferative disorder of cells in one or more respective locations. [0018] Additionally, or alternatively, the at least one processor may be configured to calculate a proliferation score by analyzing the one or more IR radiation readings, to obtain one or more corresponding spectral distribution data elements, each representing spectral distribution of IR radiation reflected from a respective location in the population of cells; for at least one specific location in the population of cells, analyzing the respective spectral distribution data element, to calculate one or more indicator values, characteristic of cell proliferation at the specific location; and based on the one or more indicator values, calculating a proliferation score, indicating a level of proliferative disorder of cells in the specific location. [0019] Embodiments of the system may further include one or more optical fibers, respectively associated with the one or more ATR detectors, and adapted to transmit the reflected infrared radiation from the biological sample or tissue to a receiver module associated with the at least one processor. The receiver module may be adapted to digitize the reflected infrared radiation, to produce the readings of infrared radiation. [0020] Additionally, or alternatively, the one or more ATR detectors may be implemented by, or as part of the one or more associated optical fibers. [0021] Embodiments of the system may include a casing (e.g., a hand-held casing). The casing may be adapted to house the array of ATR detectors, and facilitate connection of one or more detectors of the array of ATR detectors to the one or more respective optical fibers. [0022] Embodiments of the system may include an imaging device. In such embodiments, the at least one processor may be further configured to receive, from the imaging device, an image of the population of cells; analyze said image, to obtain one or more morphological features of the population of cells; and infer the ML model further on the one or more morphological features, to predict the proliferation score of the specific location. [0023] The morphological features may include, for example features of: a size of cells in the cell population, an area of cells in the cell population, a diameter of cells in the cell population, a shape of cells in the cell population, roundness of cells in the cell population, spiculation of cells in the cell population, a roughness of membranes of cells in the cell population, a ratio between sizes of cells in the cell population and their respective nuclei, and a concentration of cells in the cell population.

BRIEF DESCRIPTION OF THE DRAWINGS[0024] The subject matter regarded as the invention is particularly pointed out and distinctly claimed in the concluding portion of the specification. The invention, however, both as to organization and method of operation, together with objects, features, and advantages thereof, may best be understood by reference to the following detailed description when read with the accompanying drawings in which: [0025] Fig. 1 is a block diagram, depicting a computing device which may be included in a system for determining proliferative disorder levels, according to some embodiments; [0026] Fig. 2 is a block diagram, depicting a system for determining proliferative disorder levels in a population of cells according to some embodiments; [0027] Fig. 3 is a block diagram, depicting an example for implementation of a system for determining proliferative disorder levels in a population of cells, according to some embodiments; [0028] Fig. 4 is a block diagram, depicting an example for implementation of a spectral analysis module, according to some embodiments of the invention; [0029] Figs. 5A-5C are diagrams depicting an example of an image analysis algorithm that may be applied by embodiment of the invention on spectral distribution data, to obtain an image-based, proliferative disorder indication; [0030] Fig. 6 is a column graph, showing a multifractal number of acquired ATR-FTIR Spectra from a variety of cell lines over sequentially increasing cell concentration levels, as calculated by embodiments of the invention; [0031] Figs. 7A-7D are column graphs, showing multifractal numbers of acquired ATR-FTIR spectra from a variety of cell line mixtures, as calculated by embodiments of the invention; and [0032] Fig. 8 is a flow diagram, depicting stages in a method of determining proliferative disorder levels in a population of cells according to some embodiments. [0033] It will be appreciated that for simplicity and clarity of illustration, elements shown in the figures have not necessarily been drawn to scale. For example, the dimensions of some of the elements may be exaggerated relative to other elements for clarity. Further, where 6 considered appropriate, reference numerals may be repeated among the figures to indicate corresponding or analogous elements.

DETAILED DESCRIPTION OF THE PRESENT INVENTION[0034] One skilled in the art will realize the invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The foregoing embodiments are therefore to be considered in all respects illustrative rather than limiting of the invention described herein. Scope of the invention is thus indicated by the appended claims, rather than by the foregoing description, and all changes that come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. [0035] In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the invention. However, it will be understood by those skilled in the art that the present invention may be practiced without these specific details. In other instances, well-known methods, procedures, and components have not been described in detail so as not to obscure the present invention. Some features or elements described with respect to one embodiment may be combined with features or elements described with respect to other embodiments. For the sake of clarity, discussion of same or similar features or elements may not be repeated. [0036] Although embodiments of the invention are not limited in this regard, discussions utilizing terms such as, for example, "processing," "computing," "calculating," "determining," "establishing", "analyzing", "checking", or the like, may refer to operation(s) and/or process(es) of a computer, a computing platform, a computing system, or other electronic computing device, that manipulates and/or transforms data represented as physical (e.g., electronic) quantities within the computer’s registers and/or memories into other data similarly represented as physical quantities within the computer’s registers and/or memories or other information non-transitory storage medium that may store instructions to perform operations and/or processes. [0037] Although embodiments of the invention are not limited in this regard, the terms "plurality" and "a plurality" as used herein may include, for example, "multiple" or "two or more". The terms "plurality" or "a plurality" may be used throughout the specification to describe two or more components, devices, elements, units, parameters, or the like. The term "set" when used herein may include one or more items. 7 id="p-38" id="p-38" id="p-38" id="p-38" id="p-38" id="p-38" id="p-38"

[0038] Unless explicitly stated, the method embodiments described herein are not constrained to a particular order or sequence. Additionally, some of the described method embodiments or elements thereof can occur or be performed simultaneously, at the same point in time, or concurrently. [0039] Reference is now made to Fig. 1, which is a block diagram depicting a computing device, which may be included within an embodiment of a system for determining proliferative disorder levels in a population of cells, according to some embodiments. [0040] Computing device 1 may include a processor or controller 2 that may be, for example, a central processing unit (CPU) processor, a chip or any suitable computing or computational device, an operating system 3, a memory 4, executable code 5, a storage system 6, input devices 7 and output devices 8. Processor 2 (or one or more controllers or processors, possibly across multiple units or devices) may be configured to carry out methods described herein, and/or to execute or act as the various modules, units, etc. More than one computing device 1 may be included in, and one or more computing devices 1 may act as the components of, a system according to embodiments of the invention. [0041] Operating system 3 may be or may include any code segment (e.g., one similar to executable code 5 described herein) designed and/or configured to perform tasks involving coordination, scheduling, arbitration, supervising, controlling or otherwise managing operation of computing device 1, for example, scheduling execution of software programs or tasks or enabling software programs or other modules or units to communicate. Operating system 3 may be a commercial operating system. It will be noted that an operating system may be an optional component, e.g., in some embodiments, a system may include a computing device that does not require or include an operating system 3. [0042] Memory 4 may be or may include, for example, a Random-Access Memory (RAM), a read only memory (ROM), a Dynamic RAM (DRAM), a Synchronous DRAM (SD-RAM), a double data rate (DDR) memory chip, a Flash memory, a volatile memory, a non-volatile memory, a cache memory, a buffer, a short term memory unit, a long term memory unit, or other suitable memory units or storage units. Memory 4 may be or may include a plurality of possibly different memory units. Memory 4 may be a computer or processor non-transitory readable medium, or a computer non-transitory storage medium, e.g., a RAM. In one embodiment, a non-transitory storage medium such as memory 4, a hard disk drive, 8 another storage device, etc. may store instructions or code which when executed by a processor may cause the processor to carry out methods as described herein. [0043] Executable code 5 may be any executable code, e.g., an application, a program, a process, task, or script. Executable code 5 may be executed by processor or controller possibly under control of operating system 3. For example, executable code 5 may be an application that may determine proliferative disorder levels in a population of cells as further described herein. Although, for the sake of clarity, a single item of executable code 5 is shown in Fig. 1, a system according to some embodiments of the invention may include a plurality of executable code segments similar to executable code 5 that may be loaded into memory 4 and cause processor 2 to carry out methods described herein. [0044] Storage system 6 may be or may include, for example, a flash memory as known in the art, a memory that is internal to, or embedded in, a micro controller or chip as known in the art, a hard disk drive, a CD-Recordable (CD-R) drive, a Blu-ray disk (BD), a universal serial bus (USB) device or other suitable removable and/or fixed storage unit. Data pertaining to scanned cells and/or cell assays may be stored in storage system 6 and may be loaded from storage system 6 into memory 4 where it may be processed by processor or controller 2. In some embodiments, some of the components shown in Fig. 1 may be omitted. For example, memory 4 may be a non-volatile memory having the storage capacity of storage system 6. Accordingly, although shown as a separate component, storage system may be embedded or included in memory 4. [0045] Input devices 7 may be or may include any suitable input devices, components, or systems, e.g., a detachable keyboard or keypad, a mouse and the like. Output devices 8 may include one or more (possibly detachable) displays or monitors, speakers and/or any other suitable output devices. Any applicable input/output (I/O) devices may be connected to Computing device 1 as shown by blocks 7 and 8. For example, a wired or wireless network interface card (NIC), a universal serial bus (USB) device or external hard drive may be included in input devices 7 and/or output devices 8. It will be recognized that any suitable number of input devices 7 and output device 8 may be operatively connected to Computing device 1 as shown by blocks 7 and 8. [0046] A system according to some embodiments of the invention may include components such as, but not limited to, a plurality of central processing units (CPU) or any other suitable multi-purpose or specific processors or controllers (e.g., similar to element 2), a plurality of 9 input units, a plurality of output units, a plurality of memory units, and a plurality of storage units. [0047] The term neural network (NN) or artificial neural network (ANN), e.g., a neural network implementing a machine learning (ML) or artificial intelligence (AI) function, may be used herein to refer to an information processing paradigm that may include nodes, referred to as neurons, organized into layers, with links between the neurons. The links may transfer signals between neurons and may be associated with weights. A NN may be configured or trained for a specific task, e.g., pattern recognition or classification. Training a NN for the specific task may involve adjusting these weights based on examples. Each neuron of an intermediate or last layer may receive an input signal, e.g., a weighted sum of output signals from other neurons, and may process the input signal using a linear or nonlinear function (e.g., an activation function). The results of the input and intermediate layers may be transferred to other neurons and the results of the output layer may be provided as the output of the NN. Typically, the neurons and links within a NN are represented by mathematical constructs, such as activation functions and matrices of data elements and weights. At least one processor (e.g., processor 2 of Fig. 1) such as one or more CPUs or graphics processing units (GPUs), or a dedicated hardware device may perform the relevant calculations. [0048] Reference is now made to Fig. 2, which depicts a system 10 for determining proliferative disorder levels in a population of cells, according to some embodiments. [0049] According to some embodiments of the invention, system 10 may be implemented as a software module, a hardware module, or any combination thereof. For example, system may be or may include a computing device such as element 1 of Fig. 1, and may be adapted to execute one or more modules of executable code (e.g., element 5 of Fig. 1) to determine proliferative disorder levels in a population of cells, as further described herein. [0050] As shown in Fig. 2, arrows may represent flow of one or more data elements to and from system 10 and/or among modules or elements of system 10. Some arrows have been omitted in Fig. 2 for the purpose of clarity. [0051] As shown in Fig. 2, system 10 may be configured to analyze a population of biological cells 20, also referred to herein as population 20. The term "population" or "cell population" may be used herein to refer to any aggregation of cells. Some embodiments of the invention may be adapted to analyze populations 20 that are in vitro, or ex-vivo, such as an assay of cells, a biological cell line (e.g., in a petri dish), a sample (e.g., a biopsy) extracted from a biological tissue (e.g., on a slide), and the like. [0052] Additional or alternative embodiments of the invention may be adapted to analyze cell populations 20 that are, or included in biological tissues and/or a biological organs, that may be analyzed in real-time or near real time, e.g., during a surgical procedure. [0053] According to some embodiments, system 10 may be configured to produce a proliferation score 100PS, indicating a level of proliferative disorder of cells in specific locations in population 20. [0054] The term "proliferative disorder" may be used herein to indicate any kind of normal, or abnormal condition that pertains to proliferation of cells in population 20. For example, proliferative disorder as used herein may refer to a condition of normal cells in population 20, a condition of pre-cancer cells in population 20, a malignancy of cells in population 20, a propensity of metastasis of cells in population 20, a condition in which cells of population pertain to a benign lesion or tumor, and the like. [0055] Accordingly, a "proliferative disorder level" may relate to a severity or a degree in which a respective proliferative disorder is manifested in population 20. Proliferation score 100PS may be, or include one or more numeric, or alpha-numeric values indicating the proliferative disorder level. The proliferation score 100PG may include, for example a probability of a precancerous condition in population 20, a probability of a malignant condition in population 20, a level or degree of the malignant condition in population 20, a probability of a benign tumor condition in population 20, a probability and/or degree of a metastatic condition in population 20, a degree of motility of cells in population 20, and the like. [0056] As known in the art, Attenuated Total Reflection (ATR) is a spectroscopic technique commonly used in infrared (IR) spectroscopy to analyze samples solid and liquid samples without the need for extensive sample preparation. [0057] An ATR detector typically consists of an ATR crystal, which is often made of a high refractive index material, an IR source and an IR sensor. In ATR spectroscopy, the sample is brought into direct contact with the ATR crystal's surface. An IR beam is directed into the ATR crystal at an angle greater than the crystal's critical angle. The beam undergoes total internal reflection at the ATR crystal's surface, creating an evanescent wave that penetrates the sample. After interacting with the sample, the attenuated IR beam is partially transmitted 11 back into the ATR crystal and then into the IR sensor. The IR sensor measures the intensity of the received IR beam, which contains information about the sample's molecular vibrations and composition. [0058] According to some embodiments, system 10 may include an array 120DA of ATR detectors 120D, configured to be applied to the population of cells 20. The structure of array 120DA may be adapted to implement a variety of applications: [0059] For example, array 120DA may be integrated into a scanning microscope device, adapted to automatically scan a population 20 of cells, e.g., on a slide or in a petri dish. In such embodiments, array 120DA may include a small number of detectors 120D (e.g., a single detector), to conveniently fit within the scanning microscope device. [0060] In another example, array 120DA may be integrated in a hand-held scanning device as elaborated herein (e.g., element 200SC of Fig. 3), adapted to allow a professional (e.g., a surgeon) to manually scan a cell population 20 such as a tissue or a sample thereof, and obtain real-time information regarding the scanned population 20. In such embodiments, array 120DA may include a plurality of detectors 120D, arranged in a two-dimensional (2D) array. Additionally, or alternatively, the plurality of detectors 120D may be arranged in one or more vectors of ATR detectors. It may be appreciated that such an arrangement may facilitate construction of a 2D data structure, such as a map (e.g., heatmap) showing a proliferation score 100PS in regions of the scanned population 20. [0061] It may be appreciated that an ATR detector array 120DA that includes multiple detectors 120D may be implemented in a variety of ways: [0062] For example, detector array 120DA may include a single IR emitter 120E, and a plurality of IR sensors 120S. [0063] Additionally, or alternatively, detector array 120DA may include a plurality of IR emitters 120E (that may be time-differentiated or frequency-differentiated), and a corresponding plurality of IR sensors 120S. [0064] Additionally, or alternatively, the plurality of detectors may be achieved by including, within array 120DA, a plurality of ATR crystals 120C, e.g., one crystal for each detector 120D. Any combination of these options may also be possible. [0065] Reference is also made to Fig. 3, which depicts an example for implementation of system 10 (which may be the same as system 10 of Fig. 2) for determining proliferative disorder levels in a population of cells, according to some embodiments. 12 id="p-66" id="p-66" id="p-66" id="p-66" id="p-66" id="p-66" id="p-66"

[0066] As shown in the example of Fig. 3, system 10 may be arranged, or distributed into two or more modules. A first module may be a scanning apparatus 200SC, that may be included in a hand-held casing 200HH. [0067] In some embodiments, hand-held casing 200HH may have an elongated form, e.g., shaped as a pen, and may be adapted to house the array of ATR detectors 120DA e.g., at a first extremity. Hand-held casing 200HH may also be adapted to enclose or attach one or more respective optical fibers 130, e.g., at the second extremity of the elongated form. Casing 200HH may facilitate connection of one or more detectors of the array of ATR detectors to one or more respective optical fibers 130, thereby allowing transmission of radiation from detectors 120D via optical fibers 130, to be analyzed by an analysis module 300. [0068] Additionally, or alternatively, one or more ATR detectors 120D may be implemented by, or as part of the one or more associated optical fibers 130. For example, in some embodiments the tips of optical fibers 130 may be polished. During operation of system 10, a polished tip of at least one optical fiber 130 may be attached to a cell population of interest. In this configuration, the optical fiber 130 may be used to irradiate the cell population 20, and act as an ATR crystal 120C, allowing simultaneous collection of reflected radiation 120R from cell population 20, and transmission of that radiation to analysis module 300. [0069] Additionally, or alternatively, at least one optical fiber 130 may be sufficiently bent, to allow emission of IR radiation onto the attached to a cell population 20, thereby irradiating the cell population 20, and acting as an ATR crystal 120C. [0070] Additionally, or alternatively, a portion of at least one optical fiber 130 may flattened e.g., by a mechanical or thermal process, creating a substantially semicircular cross section of the fiber. This cross section may allow emission of IR radiation onto the attached to a cell population 20, thereby irradiating the cell population 20, and acting as an ATR crystal 120C. [0071] According to some embodiments, one or more optical fibers 130, respectively associated with one or more ATR detectors 120D may be adapted to transmit the reflected infrared radiation 120R from biological sample or tissue 20 to a receiver module 140 that may be included in analysis module 300. [0072] Receiver module 140 may be associated with at least one processor 2 and may be configured to digitize the reflected infrared radiation 120R, to produce digital readings 140R 13 of infrared radiation. As elaborated herein, system 10 may subsequently receive one or more readings 140R of IR radiation via the one or more respective ATR detectors 120D, calculate, based on the one or more received readings 140R, a proliferation score 100PS indicating a level of proliferative disorder of cells in one or more respective locations of population 20. [0073] According to some embodiments, during activation, system 10 may be configured to employ the one or more IR emitters 120E of detector array 120DA, to irradiate a population of cells with IR radiation. Detector array 120DA may obtain, via one or more IR sensors 120S of the one or more ATR detectors 120D, one or more respective spectral distribution (SD) data elements 150SD. Each SD data element 150SD may represent a spectral distribution of IR radiation 120R reflected from a respective location in the population of cells 20. [0074] For example, as shown in Fig.2, system 10 may include a receiver, adapted to measure and/or sample reflected IR radiation 120R, and digitize IR radiation 120R, to obtain a digital reading 140R of IR radiation 120R, reflected from a respective location in the population of cells 20. [0075] As shown in Fig. 2, system 10 may also include a spectral analysis module 150, configured to produce spectral distribution data elements 150SD representing spectral distribution of the sampled, and digitized readings 140R of reflected IR radiation 120R. [0076] For example, spectral analysis module 150 may be a Fourier Transform Infrared Spectroscopy (FTIR) module, adapted to apply a Fast Fourier Transform (FFT) over digital reading 140R, to obtain ATR-FTIR spectral distribution data elements 150SD as known in the art. These spectral distribution data elements 150SD may pertain to location of specific, respective ATR detectors 120D in scanned cell population 20. [0077] Reference is also made to Fig. 4, which depicts an example for implementation of spectral analysis module 150, according to some embodiments of the invention. [0078] As shown in Fig. 4, for at least one specific location in the population of cells, spectral analysis module 150 may be configured to analyze the respective spectral distribution data element 150SD, to calculate one or more indicator values 150PI, characteristic of cell proliferation at the specific location. [0079] For example, spectral analysis module 150 may include a motility calculation module 154, configured to calculate, based on spectral distribution data element 150SD, an indicator value 150PI that is motility-based 150PIM. In other words, motility-based indicator 14 value 150PIM may indicate a level of motility of one or more cells of cell population 120P, and may be characteristic of a cell proliferation disorder, as explained herein. [0080] Additionally, or alternatively, spectral analysis module 150 may include a Membrane Organic Content (MOC) content calculation module 156, configured to calculate, based on spectral distribution data element 150SD, an indicator value 150PI that is based on content of organic materials in the membrane (denoted 105PIO). In other words, MOC-based indicator value 105PIO may indicate content of membrane organic material in one or more cells of cell population 120P, and may be characteristic of a cell proliferation disorder, as explained herein. [0081] Additionally, or alternatively, spectral analysis module 150 may include an image analysis module 158, configured to apply an image analysis algorithm on spectral distribution data element 150SD, to calculate one or more indicator values 150PI that are image-based 150PII. In other words, image-based indicator value 150PII may indicate image properties of spectral distribution data element 150SD, that may be characteristic of a cell proliferation disorder, as explained herein. [0082] According to some embodiments, system 10 may include a proliferation level computation module 160 (or "proliferation module 160", for short). Proliferation module 160 may be configured to calculate a proliferation score 100PS, indicating a level of proliferative disorder of cells in the specific location, based, at least in part, on the one or more indicator values 150PI (150PII, 150PIM, 105PIO). [0083] For example, proliferation module 160 may apply a function (e.g., a weighted sum) on the one or more indicator values 150PI of each location, to determine a proliferation score 100PS of that location. [0084] Additionally, or alternatively, proliferation module 160 may be, or may include a machine-learning (ML) model 165. ML based model 165 may be pretrained to predict a proliferation score 100PS based on input data of location-specific indicator values 150PI. [0085] For example, during a training stage, system 10 may receive (e.g., from an expert user, via input device 7 of Fig. 1) annotated examples of cell populations 20. The term "annotated" may indicate ground-truth knowledge of a type, or a level of a proliferation disorder, exhibited in an associated cell population 20. System 10 may thus apply a supervised training algorithm, to train ML model 165 to predict proliferation score 100PS. In other words, during training, System 10 may train ML model 165 to predict proliferation score 100PS based on examples of cell populations 20, while using the annotations as supervisory information. [0086] According to some embodiments, system 10 may subsequently (e.g., during an inference stage), apply or infer pretrained ML model 165 on at least one of (i) the MOC-based indicator value 105PIO, (ii) the motility-based indicator value 150PIM, and (iii) the image-based indicator value 150PII, to predict the proliferation score 100PS of the specific location. [0087] Reference is also made to Figs. 5A-5C which depict an example of an image analysis algorithm that may be applied by image analysis module 158 on spectral distribution data element 150SD, to obtain image-based indicator value 150PII. [0088] As shown in Fig. 5A, image analysis module 158 may receive spectral distribution data element 150SD, and produce a 2-dimensional (2D) matrix representation of the respective spectral distribution data element 150SD, as depicted in Fig. 5B. [0089] Image analysis module 158 may subsequently apply a hierarchical image analysis algorithm on the matrix representation and calculating an image-based indicator value, corresponding to the at least one location, based on outcome of said hierarchical image analysis algorithm. [0090] The term "hierarchical" may be used in this context to indicate an image processing algorithms that are used for analyzing and processing images in a structured and organized manner. These algorithms involve a hierarchy of steps or processes that gradually extract features, information, or representations from an image at different levels of complexity. The hierarchical image processing algorithm may involve analyzing images at multiple levels of detail or abstraction, starting with low-level features (e.g., edges, corners) and progresses to higher-level features (e.g., shapes, objects) as the analysis proceeds. Additionally, or alternatively, the hierarchical image processing algorithm may be implemented by a pyramid-like structure, where the base represents the original image, and each higher level represents a more abstract or reduced version of the image. This can be achieved through techniques like image subsampling or image decomposition. [0091] For example, as depicted in Fig. 5C, image analysis module 158 may apply a hierarchical image analysis algorithm such as a Multifractal Analysis (MFA) algorithm on the matrix (e.g., the image) of spectral distribution data element 150SD. As known in the art, an outcome of an MFA hierarchical image analysis algorithm may be a multifractal 16 dimension value, which may represent variation in scaling exponents of the underlying data (e.g., the matrix representation of the spectral distribution data element 150SD). Therefore, in such embodiments, image-based indicator value 150PII may be, or may include a multifractal dimension value of an image (as depicted in Fig. 5B) representing spectral distribution data element 150SD (as depicted in Fig. 5A). [0092] As elaborated herein (e.g., in relation to Figs. 6 and 7), applicants have experimentally observed that hierarchical image analysis features such as MFA multifractal dimension values, which indicate morphological resemblance among different hierarchies of the matrix representation of distribution data element 150SD may be highly indicative of a type, and/or proliferation score 100PS (e.g., level of proliferation disorder) in scanned population samples 20. According to some embodiments, features of other hierarchical image analysis algorithms (e.g., other than MFA) may also be used. [0093] As known in the art, a prevalent indicator of a cell’s malignancy is its motility, i.e., its capability of movement. As cell populations progress along a malignancy vector, e.g., from normal tissue cells via precancerous, malignant and metastatic phenotypes, the composition of water in their membranes gradually shifts, changing a ratio between structured water (where water molecules join together in hexagonally structured single layer sheets), and non-structured water. This shift of water composition (e.g., an increase of the non-structured water portion) is manifested by increased cell motility, characteristic of metastatic cells. Embodiments of the invention may utilize this observation, to produce additional indications of proliferation disorders. [0094] For example, based on the spectral distribution data element 150SD, motility calculation module 154 may (a) determine a value of an absorption peak of structured water, pertaining to a specific location in population 20, and (b) determine a value of an absorption peak of non-structured water, pertaining to that location in population 20. Motility calculation module 154 may then calculate a motility-based 150PIM indicator value 150PI, corresponding to the at least one location, based on (e.g., as a ratio between) the structured water absorption peak value and the non-structured water absorption peak value. [0095] As known in the art, another indicator of a cell’s proliferation disorder is the composition or content of organic materials in its membrane, such as membrane proteins, phospholipids, cholesterol, and the like. According to some embodiments, Membrane Organic Content (MOC) calculation module 156 (or "MOC module 156", for short) may 17 utilize this observation to produce additional indications of proliferation disorders, denoted herein interchangeably as "membrane organic material" indications or "membrane organic content" indications. [0096] For example, the inventors have experimentally observed statistically significant differences in Peak intensity of IR reflections 120R between different levels of proliferation disorders (e.g., between cancerous cells of different metastatic levels). Embodiments of the invention may utilize this observation to determine proliferation scores 100PS: Based on the spectral distribution data element 150SD, MOC content calculation module 156 may determine a value of an absorption peak of at least one specific type of organic material, such as a type of membrane protein, a phospholipid, and the like, that pertains to a specific location in population 20. MOC content calculation module 156 may calculate an MOC-based indicator value 150PI (denoted 105PIO), based on the at least one organic material (e.g., membrane protein) absorption peak value. As elaborated herein, system 10 (e.g., proliferation calculation module 160) may subsequently analyze the calculated MOC indicator value 105PIO to determine proliferation scores 100PS and/or diagnosis 100DG. [0097] As shown in Figs. 2 and 3, system 10 may include an imaging device 170, such as a camera (e.g., a visible light camera, an IR camera, and the like). [0098] For example, scanning element 200SC may be incorporated into an endoscope, adapted to be inserted into a patient’s body to scan internal tissues, and imaging device 1may be located at a tip of scanning element 200SC, to provide images of internal organs and cavities. [0099] According to some embodiments, imaging device 170 may be communicatively associated with receiver 140 via one or more wired, or wireless communication channels 135. For example, communication channels 135 may include one or more optical fibers, that may be coupled to imaging device, so as to transfer an image of population 20 from imaging device 170 to receiver 140. [00100] According to some embodiments, receiver 140 may receive, from imaging device 170, an image 170M of the population of cells 20, and direct image 170M (or a processed version thereof) to an image processing module 180. [00101] Image processing module 180 may be configured to analyze image 170M to obtain one or more morphological features 170MF of the population of cells 20. According to some embodiments, morphological features 170MF may include, for example features of 18 a size (e.g., an area, a diameter, etc.) of cells in population 20, features of a shape (e.g., roundness, spiculation, etc.) of cells in population 20, a ratio between sizes of cells in population 20 and their respective nuclei, a roughness of membranes of cells in population 20, and the like. [00102] For example, during a training stage, system 10 may receive (e.g., from an expert user, via input device 7 of Fig. 1) annotated examples of images 170M of cell populations 20, representing ground-truth knowledge of a type, or a level of a proliferation disorder in an associated cell population 20. Image analysis module 180 may extract features 170MF from annotated images 170M, as elaborated herein. System 10 may subsequently apply a supervised training algorithm, to train ML model 165 to predict proliferation score 100PS, further based on the extract features 170MF (e.g., in addition to proliferation indicators 150PI). In other words, during training, System 10 may train ML model 165 to predict proliferation score 100PS based on examples of cell populations 20, while using the annotations of images 170M as supervisory information. [00103] According to some embodiments, system 10 may further infer ML model 165 on the one or more morphological features 170MF, to predict a proliferation score 100PS of a location associated with image 170M of population 20. [00104] According to some embodiments, a user may scan the population of cells 20 by the one or more ATR detector vectors, e.g., by applying, and traversing scanning apparatus 200SC across cell population 20. As elaborated herein, system 10 may obtain a plurality of location-specific proliferation scores 100PS, along the scan path. A memory device (e.g., element 4 and/or element 6 of Fig. 1) may be configured to aggregate the location-specific proliferation scores 100PS along the scan path. System 10 may subsequently produce, in real time or near real-time a heat map 100HM representing proliferation scores 100PS (e.g., levels of a proliferative disorder), based on the aggregated proliferation scores 100PS. System 10 may subsequently present heatmap 100HM in a user interface (UI) 40 (e.g., output device 8) such as a computer screen. [00105] As known in the art, the term fractal dimension may refer to a measurement of a degree of self-similarity or complexity of an object or set. Fractal dimensions are typically used in the context of single-scale fractals, where a single dimension describes the scaling behavior at all scales. 19 id="p-106" id="p-106" id="p-106" id="p-106" id="p-106" id="p-106" id="p-106"

[00106] In multifractal analysis, the scaling behavior can vary across scales, requiring a more nuanced description: The terms "multifractal dimension" and "multifractal number" may thereby refer to mathematical measures that capture the multifractal properties of a system or phenomenon, and provide a quantitative characterization of the distribution of scaling exponents (typically denoted as ‘α’) or the scaling behavior across different scales. [00107] A multifractal dimension can take different forms, depending on the specific analysis technique employed. For example, in some cases, the concept of generalized dimensions is used, where a set of dimensions is associated with different subsets of a system. These dimensions collectively capture the multifractal nature of the system. [00108] The function f(α) is a fundamental mathematical construct that relates the scaling exponents (α) to the fractal dimensions of different subsets of a multifractal system. It is a central component of the singularity spectrum, which characterizes the multifractal behavior of a complex system. [00109] The scaling exponents (α) quantify the rate at which the size or magnitude of an object or phenomenon changes as the scale changes. Different regions or points within a multifractal system might have different scaling exponents. [00110] The function f(α) expresses the relationship between these scaling exponents (α) and the fractal dimensions of the subsets of the system that exhibit those scaling properties. In other words, f(α) provides a way to understand how the scaling properties are distributed across the different parts of the system. [00111] Reference is also made to Fig. 6, which are graphs depicting values of multifractal analysis, according to some embodiments of the invention. [00112] As explained herein, applicants have experimentally observed that hierarchical image analysis features such as MFA multifractal dimension values, which indicate morphological resemblance among different hierarchies of the matrix representation of distribution data element 150SD may be highly indicative of a type, and/or proliferation score 100PS (e.g., level of proliferation disorder) in scanned population samples 20. [00113] Fig. 6 shows image-based indicator values 150PII that are multifractal numbers (f(α) vs α) of ATR-FTIR spectra. In this example, the image-based indicators 150PII (e.g., the multifractal numbers) were acquired by spectral analysis module 150 from 4 different cell lines: Non-metastatic, and metastatic phenotypes of Melanoma and Adenocarcinoma cells. In each group of cell lines in Fig. 6, the values and error bars represent mean and standard deviation of the calculated indicators 150PII (multifractal numbers) as obtained for each respective cell line and each respective cell concentration as indicated. [00114] It may be observed that indicators 150PII (the multifractal numbers or dimensions) are indicative of specific cell types. In other words, Fig. 6 demonstrates the applicability of system 10 to produce diagnosis 100DG of cells in a cell population 20. [00115] Additionally, it may be observed that indicators 150PII (the multifractal numbers or dimensions) are indicative of specific proliferative levels of the underlying cell types. In other words, Fig. 6 demonstrates the applicability of system 10 to produce a proliferation score 100PS, indicating a proliferation disorder level (e.g., cancer grade) of diagnosed (100DG) cells in a cell population 20. [00116] Additionally it may be observed that indicators 150PII (the multifractal numbers or dimensions) are substantially unaffected by cell concentration in the sampled population 20. In other words, Fig. 6 emphasizes the applicability of system 10 to provide diagnosis 100DG, and proliferation score 100PS (indicate a proliferative disorder, such as a degree of cancer) regardless of cell concentration. [00117] It may be appreciated that such application of system 10 may be particularly beneficial, for example, in oncologic surgical procedures, where a surgeon may want to determine boundaries of a suspected tumor in real time. By applying scanning apparatus 200SC across cell population 20 such as a tissue, an organ or a biopsy sample, the surgeon may be presented a heatmap 100HM of the scanned population 20, identify the boundary of an examined tumor, and determine a correct location of incision, to safely remove the tumor. [00118] Reference is also made to Figs. 7A-7D, which are graphs depicting multifractal numbers or dimensions 150PII (f(α) vs α) of acquired ATR-FTIR spectra from mixtures of cell cultures, as obtained by embodiments of the invention. Fig. 7A depicts different mixtures of non-metastatic Melanoma cells with non-cancerous 3T3 cells; Fig. 7B depicts different mixtures of metastatic Melanoma cells with non-cancerous 3T3 cells; Fig. 7C depicts different mixtures of non-metastatic Adenocarcinoma cells with non-cancerous 3Tcells; and Fig. 7D depicts different mixtures of metastatic Adenocarcinoma cells with non-cancerous 3T3 cells. Each data point represents a sample containing 106 cells/ml in total. The values and error bars represent mean and standard deviation of the calculated multifractal number by MFA of 3 distinct ATR-FTIR spectra for each respective sample. Calculated p values are less than 0.0001. 21 id="p-119" id="p-119" id="p-119" id="p-119" id="p-119" id="p-119" id="p-119"

[00119] It may be observed that indicators 150PII (the multifractal numbers or dimensions) are consistently indicative of a proportion between cell types and/or cells of different levels of proliferative disorders in the scanned cell population. In other words, Figs. 7A-7D demonstrate the applicability of system 10 to produce a proliferative score 100PS that indicates concentration of suspicious cells within cell population 20. [00120] Reference is also made to Fig. 8, which is a flow diagram depicting a method of evaluating a level of proliferative disorder by at least one processor (e.g., processor 2 of Fig. 1), according to some embodiments of the invention. [00121] As shown in step S1005, the at least one processor 2 may be configured to control ATR emitters (e.g., 120E of Fig. 2), to irradiate a population of cells (e.g., 20 of Fig. 2) with IR radiation. [00122] As shown in step S1010, the at least one processor 2 may be configured to obtain, via one or more ATR detectors (e.g., 120), one or more respective spectral distribution data elements (e.g., 150SD of Fig. 2). Each distribution data element 150SD may represent a spectral distribution of IR radiation reflected from a respective location in the population of cells. [00123] As shown in step S1015, the at least one processor 2 may be configured, for at least one specific location in the population of cells 20, to analyze the respective spectral distribution data element 150SD, to calculate one or more indicator values (e.g., 150PI of Fig. 2). As explained herein, indicator values 150PI (e.g., 150PII, 150PIO, 150PIM) may be characteristic of cell proliferation at the specific location in cell population 20. [00124] As shown in step S1020, the at least one processor 2 may be configured, based on the one or more indicator values, to calculating a proliferation score (e.g., 100PS of Fig. 2). Proliferation score 110PS may, for example, indicate a level of proliferative disorder of cells in the specific location of cell population 20. [00125] As elaborated herein, embodiments of the invention may provide a practical application in the technological fields of medical image analysis and assistive diagnosis. System 10 may provide a novel method of determining various aspects of cell populations, in vivo, ex-vivo, or in vitro. These aspects include, for example: identification or diagnosis of cells; determination of proliferative disorder levels of the identified cells; and determination of a proportion, or ratio of cells of interest in a cell population. 22 id="p-126" id="p-126" id="p-126" id="p-126" id="p-126" id="p-126" id="p-126"

[00126] Unless explicitly stated, the method embodiments described herein are not constrained to a particular order or sequence. Furthermore, all formulas described herein are intended as examples only and other or different formulas may be used. Additionally, some of the described method embodiments or elements thereof may occur or be performed at the same point in time. [00127] While certain features of the invention have been illustrated and described herein, many modifications, substitutions, changes, and equivalents may occur to those skilled in the art. It is, therefore, to be understood that the appended claims are intended to cover all such modifications and changes as fall within the true spirit of the invention. [00128] Various embodiments have been presented. Each of these embodiments may of course include features from other embodiments presented, and embodiments not specifically described may include various features described herein.

Claims

1. CLAIMS – CLEAN 1. A method of evaluating a level of proliferative disorder by at least one processor, the method comprising: radiating a population of cells with Infrared (IR) radiation; obtaining, via one or more Attenuated Total Reflection (ATR) detectors, one or more respective spectral distribution data elements, each representing a spectral distribution of IR radiation reflected from a respective location in the population of cells; for at least one specific location in the population of cells, producing a matrix representation of the respective spectral distribution data element; applying a hierarchical image analysis algorithm on the matrix representation; calculating one or more an image-based indicator values, characteristic of cell proliferation at the specific location, based on outcome of said hierarchical image analysis algorithm; and based on the one or more image-based indicator values, calculating a proliferation score, indicating a level of proliferative disorder of cells in the specific location.

2. The method of claim 1, further comprising, for at least one specific location in the population of cells: based on the respective spectral distribution data element, determining a value of an absorption peak of structured water, and determining a value of an absorption peak of non-structured water; calculating a motility-based indicator value, corresponding to the at least one location, based on (i) the structured water absorption peak value and (ii) the non-structured water absorption peak value; and calculating the proliferation score further based on the motility-based indicator value.

3. The method according to any one of claims 1-2, wherein the population of cells is selected from a list consisting of a biological cell line, a sample of biological tissue, a biological tissue, and a biological organ.

4. The method according to any one of claims 1-3, wherein the one or more ATR detectors comprise a plurality of ATR detectors, arranged in one or more ATR detector vectors.

5. The method of claim 4, further comprising: scanning the population of cells by the one or more ATR detector vectors, to obtain a plurality of location-specific proliferation scores; aggregating the location-specific proliferation scores along the scan; and producing, substantially in real time, a heat map of levels of a proliferative disorder, based on said aggregation.

6. The method according to any one of claims 1-5, wherein the proliferation scores are numerical values selected from a list consisting of a probability of a precancerous condition, a probability of a malignant condition, a level of the malignant condition, a probability of a benign condition, and a probability of a metastatic condition.

7. The method of claim 1, wherein the hierarchical image analysis algorithm is a Multifractal Analysis (MFA) algorithm, and wherein the outcome of said hierarchical image analysis algorithm is a multifractal dimension value, representing variation in scaling exponents of the matrix representation of the spectral distribution data element.

8. The method according to any one of claims 1-7, further comprising for at least one location: based on the respective spectral distribution data element, determining a value of an absorption peak of at least one membrane organic material; calculating a membrane organic material indicator value, based on the absorption peak value of the at least one membrane organic material; and calculating the proliferation score further based on the membrane organic material indicator value.

9. The method according to any one of claims 1-8, wherein calculating the proliferation score of a specific location in the population of cells comprises: providing a Machine Learning (ML)-based model, pretrained to predict a proliferation score based on input data comprising location-specific indicator values; and inferring the ML model on at least one of (i) the membrane organic material indicator value, (ii) the motility-based indicator value, and (iii) the image-based indicator value, to predict the proliferation score of the specific location.

10. The method of claim 9, further comprising: receiving, from an imaging device, an image of the population of cells; analyzing said image, to obtain one or more morphological features of the population of cells; and further inferring the ML model on the one or more morphological features to predict the proliferation score of the specific location.

11. A system for evaluating a level of a proliferative disorder in a population of cells, the system comprising: an array of one or more Attenuated Total Reflection (ATR) detectors, configured to be applied to the population of cells, whereupon application, each detector is configured to obtain a reading of Infrared (IR) radiation, reflected from a respective location in the population of cells; a non-transitory memory device, wherein modules of instruction code are stored; and at least one processor associated with the memory device, and configured to execute the modules of instruction code, whereupon execution of said modules of instruction code, the at least one processor is configured to: receive one or more readings of IR radiation from one or more respective ATR detectors; analyze the one or more IR radiation readings, to obtain one or more corresponding spectral distribution data elements, each representing spectral distribution of IR radiation reflected from a respective location in the population of cells; for at least one location, determining (a) a value of an absorption peak of structured water and (b) a value of an absorption peak of non-structured water, based on the respective spectral distribution data element; calculate a motility-based indicator value characteristic of cell proliferation, corresponding to the at least one location, based on (i) the structured water absorption peak value and (ii) the non-structured water absorption peak value; and based on the motility-based indicator value , calculate a proliferation score indicating a level of proliferative disorder of cells in one or more respective locations.

12. The system of claim 11, further comprising: one or more optical fibers, respectively associated with the one or more ATR detectors, and adapted to transmit the reflected infrared radiation from the biological sample or tissue to a receiver module associated with the at least one processor; and the receiver module, adapted to digitize the reflected infrared radiation to produce the readings of infrared radiation.

13. The system of claim 12, wherein the one or more ATR detectors are implemented as part of the one or more associated optical fibers.

14. The system according to any one of claims 11-13, further comprising a hand-held casing, wherein the casing is adapted to house the array of ATR detectors, and facilitate connection of one or more detectors of the array of ATR detectors to the one or more respective optical fibers.

15. The system according to any one of claims 11-14, wherein the population of cells is selected from a list consisting of a biological cell line, a sample of biological tissue, a biological tissue, and a biological organ.

16. The system according to any one of claims 11-15, wherein the at least one processor is configured to: receive a scan of the population of cells by the ATR detector array, to obtain a plurality of location-specific proliferation scores; aggregate the location-specific proliferation scores along the scan; and produce, substantially in real time, a heat map of levels of a proliferative disorder, based on said aggregation.

17. The system according to any one of claims 11-16, wherein the proliferation scores are numerical values selected from a list consisting of a probability of a precancerous condition, a probability of a malignant condition, a level of the malignant condition, a probability of a benign condition, and a probability of a metastatic condition.

18. The system according to any one of claims 11-17, wherein the at least one processor is configured to, for at least one location, by: produce a matrix representation of the respective spectral distribution data element; apply a hierarchical image analysis algorithm on the matrix representation; calculate an image-based indicator value, corresponding to the at least one location, based on outcome of said hierarchical image analysis algorithm; and calculate the proliferation score further based on the image-based indicator value.

19. The system of claim 18, wherein the hierarchical image analysis algorithm is a Multifractal Analysis (MFA) algorithm, and wherein the outcome of said hierarchical image analysis algorithm is a multifractal dimension value, representing variation in scaling exponents of the matrix representation of the spectral distribution data element.

20. The system according to any one of claims 11-19, wherein the at least one processor is configured to, for at least one location: based on the respective spectral distribution data element, determine a value of an absorption peak of at least one membrane organic material; calculate a membrane organic material indicator value, based on the absorption peak value of the at least one membrane organic material; and calculate the proliferation score further based on the image-based indicator value.

21. The system according to any one of claims 11-20, wherein the at least one processor is configured to calculate the proliferation score of a specific location in the population of cells by: providing a Machine Learning (ML)-based model, pretrained to predict a proliferation score based on input data comprising location-specific indicator values; and inferring the ML model on at least one of (i) the membrane organic material indicator value, (ii) the motility-based indicator value, and (iii) the image-based indicator value, to predict the proliferation score of the specific location.

22. The system of claim 21, further comprising an imaging device, wherein the at least one processor is further configured to: receive, from the imaging device, an image of the population of cells; analyze said image, to obtain one or more morphological features of the population of cells; and further infer the ML model on the one or more morphological features, to predict the proliferation score of the specific location.

23. The system of claim 22, wherein the morphological features are selected from a list consisting of a size of cells in the cell population, an area of cells in the cell population, a diameter of cells in the cell population, a shape of cells in the cell population, roundness of cells in the cell population, spiculation of cells in the cell population, a roughness of membranes of cells in the cell population, a ratio between sizes of cells in the cell population and their respective nuclei, and a concentration of cells in the cell population.

24. A system for evaluating a level of a proliferative disorder in a population of cells, the system comprising: an array of one or more Attenuated Total Reflection (ATR) detectors, configured to be applied to the population of cells, whereupon application, each detector is configured to obtain a reading of Infrared (IR) radiation, reflected from a respective location in the population of cells; a non-transitory memory device, wherein modules of instruction code are stored; and at least one processor associated with the memory device, and configured to execute the modules of instruction code, whereupon execution of said modules of instruction code, the at least one processor is configured to: obtain, via one or more Attenuated Total Reflection (ATR) detectors, one or more respective spectral distribution data elements, each representing a spectral distribution of IR radiation reflected from a respective location in the population of cells; for at least one specific location in the population of cells, produce a matrix representation of the respective spectral distribution data element; apply a hierarchical image analysis algorithm on the matrix representation; calculate one or more an image-based indicator values, characteristic of cell proliferation at the specific location, based on outcome of said hierarchical image analysis algorithm; and based on the one or more image-based indicator values, calculate a proliferation score, indicating a level of proliferative disorder of cells in the specific location.

25. A method of evaluating a level of a proliferative disorder in a population of cells by at least one processor, the method comprising: obtaining, from an array of one or more Attenuated Total Reflection (ATR) detectors, a reading of Infrared (IR) radiation, reflected from a respective location in the population of cells; receiving one or more readings of IR radiation from one or more respective ATR detectors; analyzing the one or more IR radiation readings, to obtain one or more corresponding spectral distribution data elements, each representing spectral distribution of IR radiation reflected from a respective location in the population of cells; for at least one location, determining (a) a value of an absorption peak of structured water and (b) a value of an absorption peak of non-structured water, based on the respective spectral distribution data element; calculating a motility-based indicator value characteristic of cell proliferation, corresponding to the at least one location, based on (i) the structured water absorption peak value and (ii) the non-structured water absorption peak value; and based on the motility-based indicator value , calculating a proliferation score indicating a level of proliferative disorder of cells in one or more respective locations.