Methods and systems for processing medical images

1 . A method of processing a medical image, the method comprising:

receiving, by a processing unit, the medical image, wherein the medical image comprises a plurality of objects, and wherein the medical image is a low-resolution image;

segmenting, by the processing unit, at least one object from the plurality of objects from the medical image comprising: generating a hue, saturation, value (HSV) image from a red, green, blue (RGB) image, wherein the medical image is a RGB image; generating a binary mask from the HSV image by applying a threshold associated with the HSV image, wherein the threshold is applied to at least one channel of HSV color space associated with the HSV image; and segmenting the at least one object from the binary mask obtained from the HSV image;

identifying, by the processing unit, at least one region of interest in the medical image, wherein the region of interest comprises the at least one object, and wherein the at least one object is a clinically relevant object;

generating, by the processing unit, a high-resolution image of the region of interest, wherein the high-resolution image of the region of interest has a higher resolution than the low-resolution image; and

displaying, by the processing unit, the high-resolution image of the region of interest on a display unit.

2 . The method of claim 1 , wherein the clinically relevant object comprises white blood cells, urine sediments, cancerous cells, circulating tumor cells, pathogens, or combinations thereof.

3 . The method of claim 1 , wherein the identifying of the at least one region of interest comprises:

performing a morphological erosion of the binary mask generated from the HSV image;

performing a morphological dilation of the binary mask generated from the HSV image;

determining a set of characteristics associated with the at least one object from the morphologically dilated binary mask of the HSV image;

determining when the set of characteristics associated with the at least one object meet a pre-defined criteria; and

identifying the at least one region of interest associated with the at least one object when the set of characteristics associated with the at least one object meets the pre-defined criteria.

4 . The method of claim 3 , wherein the set of characteristics associated with the at least one object comprises a perimeter associated with the at least one object, a convex area of the at least one object, an eccentricity of the at least one object, or a combination thereof.

5 . The method of claim 1 , wherein the generating of the high-resolution image of the region of interest comprises performing a Fourier ptychographic microscopy reconstruction of the region of interest.

6 . The method of claim 1 , wherein the medical image is a brightfield image associated with a clinical sample.

7 . The method of claim 1 , further comprising:

fusing the high-resolution image of the region of interest with the low-resolution image.

8 . A system for processing a medical image, the system comprising:

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; and

a memory coupled to the one or more processing units, the memory and the one or more processing units configured to:

receive a medical image comprising a plurality of objects, wherein the medical image is a low-resolution image;

segment at least one object from the plurality of objects from the medical image by: generation of a hue, saturation, value (HSV) image from a red, green, blue (RGB) image, wherein the medical image is a RGB image; generation of a binary mask from the HSV image by application of a threshold associated with the HSV image, wherein the threshold is applied to at least one channel of HSV color space associated with the HSV image; and segmentation of the at least one object from the binary mask obtained from the HSV image;

identify at least one region of interest in the medical image, wherein the region of interest comprises the at least one object, and wherein the at least one object is a clinically relevant object;

generate a high-resolution image of the region of interest, wherein the high-resolution image of the region of interest has a higher resolution than the low-resolution image; and

display the high-resolution image of the region of interest on a display unit.

9 . The system of claim 8 , wherein the clinically relevant object comprises white blood cells, urine sediments, cancerous cells, circulating tumor cells, pathogens, or combinations thereof.

10 . The system of claim 8 , wherein the medical image is a brightfield image associated with a clinical sample.

11 . The system of claim 8 , wherein the memory and the one or more processing units are further configured to:

fuse the high-resolution image of the region of interest with the low-resolution image.

12 . A non-transitory storage medium having a computer program product comprising machine readable instructions, that when executed by one or more processing units, cause the one or more processing units to:

receive a medical image comprising a plurality of objects, wherein the medical image is a low-resolution image;

segment at least one object from the plurality of objects from the medical image by: generation of a hue, saturation, value (HSV) image from a red, green, blue (RGB) image, wherein the medical image is a RGB image; generation of a binary mask from the HSV image by application of a threshold associated with the HSV image, wherein the threshold is applied to at least one channel of HSV color space associated with the HSV image; and segmentation of the at least one object from the binary mask obtained from the HSV image;

identify at least one region of interest in the medical image, wherein the region of interest comprises the at least one object, and wherein the at least one object is a clinically relevant object;

generate a high-resolution image of the region of interest, wherein the high-resolution image of the region of interest has a higher resolution than the low-resolution image; and

display the high-resolution image of the region of interest on a display unit.