The present invention relates to a method and a system for processing a medical image.

High resolution microscopy is an indispensable tool for clinicians to analyze pa tient samples such as blood, urine sediment, tissue pathology samples, etc. Fou rier ptychography microscopy is a novel, lowcost and oil-free high-resolution mi croscope. Fourier ptychography microscopy enables computationally obtaining high resolution images with multiple low-resolution images with wide field of view, at varying angles of illumination. However, Fourier ptychography micros- copybased reconstruction of high-resolution image can be computationally inten sive and therefore time consuming. Therefore, implementing such method on a general-purpose processing unit may be inefficient.

There are other methods available for reconstruction of medical image which may include post processing of medical images on a standard microscope. Other meth ods include use of reconstruction algorithms which require a use of graphical pro cessing units for computation.

Currently, there is no way in which medical images can be processed which are less time consuming or not computationally intensive.

The object of the invention is therefore to provide a method and a system that en ables effective and fast processing of medical images.

The invention achieves the object by a method of processing a medical image. The method comprises receiving a medical image from a source. The medical image may include a plurality of objects. The objects may include clinically relevant objects and clinically non-relevant objects. The clinically relevant objects may in clude, for example, white blood cells (WBCs), urine sediments, pathogens, etc. In an embodiment, the medical image may be of a microscopic view of a blood smear. Alternatively, it may include microscopic view of urine analysis sample. The medical image may be a low resolution brightfield image. In a further em bodiment, the medical image may be obtained by combining one or more bright field images which are captured at monochromatic illuminations using red, green and blue LEDs. The medical image may be stored in a database and thereafter received by a processing unit from the database. Alternatively, the medical image may be received directly from a source with which the medical image may be cap tured, such as an image capturing device.

The method further comprises segmenting at least one object from the plurality of objects from the medical image. The segmented object may be a clinically rele vant object which may require further clinical analysis. In an embodiment, the segmentation of the at least one object may be performed based on morphological characteristics associated with the at least one object. The method comprises identifying at least one region of interest in the medical image, wherein the re gion of interest comprises the at least one object. The region of interest may be determined based on the segmented clinically relevant object in the medical im age. Further, the method comprises generating a high-resolution image of the re gion of interest. In an embodiment, the high-resolution image of the region of in terest may be generated using Fourier ptychography microscopy-based image re construction. Further, the method comprises displaying the high-resolution im age of the region of interest on a display unit. Advantageously, the method ena bles faster processing of the medical image as the computation time required to process the medical image is reduced.

According to an embodiment, segmenting the object from the medical image may comprise generating a hue, saturation, value (HSV) image from a red, green, blue (RGB) image, wherein the medical image is an RGB image. Hue is a dominant color observed by a human eye. Saturation is an amount of white hght assorted with hue. Value refers to brightness or intensity of the image. HSV color space separates image intensity from color information present in an image. HSV im age may be generated using any of the image processing tools known in the art. Further, the method comprises generating a binary mask from the HSV image, wherein the binary mask is generated by applying a threshold associated with HSV channels combined or either of the HSV channels. The threshold may be de termined based on the HSV image, a lower range of color observed in the HSV image and a higher range of color observed in the HSV image. Advantageously, the binary mask enables removal of background information from the medical image and only the objects of clinical relevance remain. The method further com prises segmenting the object using the generated binary mask from the HSV / original RGB color image. Advantageously, the binary mask enables effective identification of the object to be segmented in the medical image. Therefore, only relevant portions of the medical image are processed thereby reducing computa tion time.

According to another embodiment, identifying at least one region of interest com prises performing a morphological erosion of the binary mask of the HSV image. Morphological erosion enables erosion of boundaries of the segmented objects. Therefore, any noise in the segmented image is removed. Further, the method comprises performing a morphological dilation of the binary mask of the HSV im age. Morphological dilation of the binary mask enables gradual enlargement of the segmented object. Therefore, morphological dilation balances any shrinking of the segmented object that may be caused due to morphological erosion.

The method further comprises determining a set of characteristics associated with the object from the morphologically dilated binary mask of the HSV image. For example, the set of characteristics may include perimeter associated with the object, convex area of the object and/or eccentricity of the object. In an embodi ment, the characteristics associated with the object may have pre-defined thresh old based on which the region of interest associated with the object may be identi fied. The set of characteristics associated with the object enable the identification of right objects/clinically relevant objects in the medical image from the plurality of objects present in the medical image. Therefore, the method further comprises determining if the set of characteristics associated with the object meet the pre defined criteria. If the set of characteristics meet the pre-defined criteria, the at least one region of interest associated with the object is identified. The region of interest may be a region surrounding the perimeter of the object. Advanta geously, the region of interest associated with the object is accurately deter mined. Therefore, the clinically relevant objects are analyzed effectively.

In an alternate embodiment, other segmentation methods known in the art may also be used. For example, such segmentation methods may be based on color, shape, contrast etc. For example, the segmentation methods may include super pixel-based segmentation, histogram-based segmentation, clustering based seg mentation, machine learning based segmentation methods etc.

According to an embodiment, the method further comprises fusing the high-reso lution image of the region of interest with the low-resolution medical image. Fur ther, the resolution of the low-resolution medical image may be enhanced using methods such as interpolation and/or wavelet-fusion. Wavelet-fusion enables fus ing the high-resolution image from FPM reconstruction process with the low-res olution medical image. Wavelet-fusion method enables extraction of features from the images using image transformation and decomposition processes. Ad vantageously, a single image may be generated which includes the region of in terest in high resolution and the remaining portions of the medical image. This also allows for comparison between the object in the region of interest and the plurality of objects present in the remaining portions of the medical image. The object of the invention is also achieved by a system for processing a medical image. The system comprises one or more processing units, a medical database coupled to the one or more processing units, the medical database comprising a plurality of medical images. The system further comprises a memory coupled to the one or more processing units. The memory comprises an image processing module configured to perform the method steps as described above.

The invention relates in one aspect to a computer program product comprising a computer program, the computer program being loadable into a storage unit of a system, including program code sections to make the system execute the method according to an aspect of the invention when the computer program is executed in the system.

The invention relates in one aspect to a computer-readable medium, on which program code sections of a computer program are saved, the program code sec tions being loadable into and/or executable in a system to make the system exe cute the method according to an aspect of the invention when the program code sections are executed in the system.

The realization of the invention by a computer program product and/or a com puter-readable medium has the advantage that already existing management systems can be easily adopted by software updates in order to work as proposed by the invention.

The computer program product can be, for example, a computer program or com prise another element apart from the computer program. This other element can be hardware, for example a memory device, on which the computer program is stored, a hardware key for using the computer program and the like, and/or software, for example a documentation or a software key for using the computer program.

The present invention is further described hereinafter with reference to illus trated embodiments shown in the accompanying drawings, in which:

FIG 1 illustrates a block diagram of a device in which an embodiment for pro cessing a medical image can be implemented.

FIG 2 illustrates a flowchart of a method of processing a medical image, ac cording to an embodiment of the invention.

FIG 3 illustrates a flowchart of a method of segmenting an object in the medi cal image, according to an embodiment of the invention.

FIG 4 illustrates a flowchart of a method of identifying at least one region of interest in the medical image, according to another embodiment of the invention.

Hereinafter, embodiments for carrying out the present invention are described in detail. The various embodiments are described with reference to the drawings, wherein hke reference numerals are used to refer to like elements throughout. In the following description, for purpose of explanation, numerous specific details are set forth in order to provide a thorough understanding of one or more embodi ments. It may be evident that such embodiments may be practiced without these specific details.

In the following, the solution according to the invention is described with respect to the claimed providing systems as well as with respect to the claimed methods. Features, advantages or alternative embodiments herein can be assigned to the other claimed objects and vice versa. In other words, claims for the providing sys tems can be improved with features described or claimed in the context of the methods. In this case, the functional features of the method are embodied by ob ^¬ jective units of the providing system.

FIG 1 is a block diagram of a system 100 in which an embodiment can be imple ^¬ mented, for example, as a system 100 for processing a medical image, configured to perform the processes as described therein. In FIG 1, said system 100 com ^¬ prises a processing unit 101, a memory 102, a storage unit 103, an input unit 104, a bus 106, an output unit 105, and a network interface 107.

The processing unit 101, as used herein, means any type of computational circuit, such as, but not limited to, a microprocessor, microcontroller, complex instruction set computing microprocessor, reduced instruction set computing microprocessor, very long instruction word microprocessor, explicitly parallel instruction computing microprocessor, graphics processor, digital signal processor, or any other type of processing circuit. The processing unit 101 may also include embedded controllers, such as generic or programmable logic devices or arrays, application specific integrated circuits, single-chip computers, and the like.

The memory 102 may be volatile memory and non-volatile memory. The memory 102 may be coupled for communication with said processing unit 101. The processing unit 101 may execute instructions and/or code stored in the memory 102. A variety of computer-readable storage media may be stored in and accessed from said memory 102. The memory 102 may include any suitable elements for storing data and machine -readable instructions, such as read only memory, random access memory, erasable programmable read only memory, electrically erasable programmable read only memory, a hard drive, a removable media drive for handling compact disks, digital video disks, diskettes, magnetic tape cartridges, memory cards, and the like. In the present embodiment, the memory 102 includes an image processing module 110 stored in the form of machine- readable instructions on any of said above-mentioned storage media and may be in communication to and executed by processor 101. When executed by the processor 101, the image processing module 110 causes the processor 101 to process a medical image. Method steps executed by the processor 101 to achieve the abovementioned functionality are elaborated upon in detail in FIG 2, 3 and 4.

The storage unit 103 may be a non-transitory storage medium which stores a medical database 112. The medical database 112 is a repository of medical images that is maintained by a healthcare service provider. The input unit 104 may include input means such as keypad, touch -sensitive display, camera (such as a camera receiving gesture-based inputs), etc. capable of receiving input signal such as a medical image. The bus 106 acts as interconnect between the processor 101, the memory 102, the storage unit 103, the input unit 104, the output unit 105 and the network interface 107.

Those of ordinary skilled in the art will appreciate that said hardware depicted in FIG 1 may vary for particular implementations. For example, other peripheral devices such as an optical disk drive and the like, Local Area Network (LAN)/ Wide Area Network (WAN)/ Wireless (e.g., Wi-Fi) adapter, graphics adapter, disk controller, input/output (I/O) adapter also may be used in addition or in place of the hardware depicted. Said depicted example is provided for the purpose of explanation only and is not meant to imply architectural limitations with respect to the present disclosure.

A system 100 in accordance with an embodiment of the present disclosure includes an operating system employing a graphical user interface. Said operating system permits multiple display windows to be presented in the graphical user interface simultaneously with each display window providing an interface to a different application or to a different instance of the same application. A cursor in said graphical user interface may be manipulated by a user through a pointing device. The position of the cursor may be changed and/or an event such as clicking a mouse button, generated to actuate a desired response.

One of various commercial operating systems, such as a version of Microsoft Windows™, a product of Microsoft Corporation located in Redmond, Washington may be employed if suitably modified. Said operating system is modified or created in accordance with the present disclosure as described.

Disclosed embodiments provide systems and methods for processing medical images.

FIG 2 illustrates a flowchart of a method 200 of processing a medical image, ac ^¬ cording to an embodiment of the present invention. At step 201, the medical im ^¬ age is received from a source such as the medical database 112 or a microscope. The medical image is a microscopic image of a sample obtained from an individ ^¬ ual. The sample may be, for example, blood, urine, tissue sample, cerebrospinal fluid etc. In the present embodiment, the medical image is a microscopic image of a blood smear. The image includes a plurality of objects including white blood cells (WBCs) and red blood cells (RBCs). The plurality of objects may include one or more objects of clinical relevance. Such objects of clinical relevance may be the ones which may be analyzed further, for example, to determine a medical condi ^¬ tion in a patient. In an embodiment, the medical image is a low-resolution bright- field image obtained at monochromatic illuminations using red, green, and blue LEDs. A colored medical image may be generated by combining monochromatic red, green, and blue low-resolution brightfield images which are captured while illuminating the blood smear with the respective LED colors. Alternatively, the low-resolution brightfield image may be obtained using white light, filtered, mul- tispectral illumination including UV or infrared light with a monochrome/color camera. The method 200 further includes segmenting 202 at least one object from the plu ^¬ rality of objects in the medical image. The method steps illustrating the segmen ^¬ tation of the at least one object in the medical image is disclosed in further detail in FIG 3. Segmentation enables selecting the most clinically relevant objects from the plurahty of objects present in the medical image. At step 203, at least one re ^¬ gion of interest is identified in the medical image, wherein the region of interest comprises the at least one clinically relevant object. At step 204, a high-resolution image of the region of interest- is generated. For example, Fourier ptychography microscope-based reconstruction may be used to generate the high-resolution im ^¬ age of the region of interest. A Fourier spectrum is iteratively updated with low- resolution images which converges to a high-resolution image. Further, at step 205, the high-resolution image of the region of interest is displayed on a display unit of the output unit 105. In an embodiment, resolution of the remaining por ^¬ tion of the medical image may be enhanced using techniques such as interpola ^¬ tion or wavelet fusion.

FIG 3 illustrates a flowchart of a method 300 of segmenting the object in the medical image, according to an embodiment of the invention. At step 301, a hue, saturation, value (HSV) color image is generated from a red, green, blue (RGB) image, wherein the medical image is an RGB image. In an embodiment, the RGB image is converted to the HSV color space using image processing techniques known in the art. At step 302, a binary mask is generated using the HSV image. A threshold is applied to the HSV image to generate the binary mask. The threshold may be determined based on the medical image, a lower range pixel value in the medical image and a higher range of pixel value in the medical im ^¬ age. The ranges may be determined based on the pixel values present in the med ^¬ ical image. The binary mask is an array of Is and 0s where 1 indicates pixel val ^¬ ues within the lower and higher range of color in the medical image and 0 indi ^¬ cates pixel values outside the lower and higher range of color in the medical image. At step 303, the object falling in the array of 1 in the binary mask is seg mented.

FIG 4 illustrates a flowchart of a method 400 of identifying at least one region of interest, according to an embodiment of the present invention. At step 401, a morphological erosion of is performed on the binary mask obtained from the HSV image. Morphological erosion is applied to the binary image obtained as an out come of the segmentation. The boundaries of the object in the binary image are eroded by an erosion operator. The erosion operator uses the binary image as a first input and a set of coordinate points in the binary image as a second input. The set of coordinate points is also known as structuring element or kernel. The effect of erosion on the binary image is determined by the kernel. At step 402, a morphological dilation of the binary mask is performed. Morphological dilation enables gradual enlargement of the boundaries of the binary image. The dilation is performed by a dilation operator which also considers the binary image and the structuring element as the first and second inputs respectively. Dilation also ena bles edge detection of the object in the binary image.

At step 403, a set of characteristics associated with the object is determined with the help of the morphologically dilated binary mask. The set of characteristics in clude, but are not limited to, perimeter associated with the object, convex area of the object and eccentricity of the object. In particular, the convex area and the ec centricity of the object enable effective determination of the object of clinical rele vance in the medical image. The perimeter of the object enables identification of the region of interest. At step 404, it is determined if the set of characteristics as sociated with the object meet a pre-defined criteria. The pre-defined criteria may be defined based on the object of clinical relevance. For example, if the object of clinical relevance is a WBC, the pre-defined criteria may be the size of the WBC. If the pre-defined criteria are met, the at least one region of interest is identified associated with the object, at step 405. If the pre-defined criteria are not met, at step 406, the object is identified as not a clinically relevant object.

The advantage of the invention is the method and system enable effective compu- tation of medical images. As only selective regions of interest are used for compu tational FPM, the overall time take for processing and analyzing the medical im age is significantly reduced. Additionally, as wide field of view is provided by FPM, the most relevant regions of interest are identified using the low-resolution medical image. Therefore, complex and expensive raster scan mechanisms are avoided.

The foregoing examples have been provided merely for the purpose of explanation and are in no way to be construed as hmiting of the present invention disclosed herein. While the invention has been described with reference to various embodi- ments, it is understood that the words, which have been used herein, are words of description and illustration, rather than words of limitation. Further, although the invention has been described herein with reference to particular means, ma terials, and embodiments, the invention is not intended to be limited to the par ticulars disclosed herein; rather, the invention extends to all functionally equiva- lent structures, methods and uses, such as are within the scope of the appended claims. Those skilled in the art, having the benefit of the teachings of this specifi cation, may effect numerous modifications thereto and changes may be made without departing from the scope and spirit of the invention in its aspects.