Monitoring brain CT scan image

A system to monitor a brain CT scan image, the system comprises;

• a memory;
• a processor coupled to the memory, wherein the processor is configured to execute a set of instructions stored in the memory to:
• receive a brain CT scan image of a patient;
• resample the brain CT scan image into a plurality of slices, wherein the brain CT scan image is resampled using a bilinear interpolation;
• identify a basal ganglia region and a corona radiata level in the plurality of slices, wherein the basal ganglia region and the corona radiata level are identified in a Middle Cerebral Artery (MCA) territory using a deep learning model;
• segment a plurality of anatomical regions upon identification of the basal ganglia region and the corona radiata level, wherein the plurality of anatomical regions is segmented using deep learning, and wherein the plurality of anatomical regions is segmented on a set of slices associated with the basal ganglia region and the corona radiata level;
• segment a plurality of infarcts in the plurality of slices using the deep learning;
• extract a white matter region and a grey matter region in the plurality of slices using a windowing technique;
• determine a density of the white matter region and a density of the grey matter region on each of the plurality of slices based on an analysis of the plurality of slices using a fast Fourier transform technique;
• segment a plurality of black regions in the plurality of slices based on comparison of the density of the white matter region and the grey matter region with a threshold density;
• determine an overlapping region across the plurality of slices, wherein the overlapping region is determined based on the plurality of anatomical regions, the plurality of infarcts and the plurality of black regions, and wherein the overlapping region indicates an affected area of brain in the brain CT scan image;
• compute an ASPECTS score based on the overlapping region and a predefined threshold, wherein a defined point is deducted from the predefined threshold when the overlapping region is determined;
• and
• recommend a course of action to the patient in real-time based on the ASPECTS score and a threshold score, thereby monitoring a brain CT scan image.

A non-transitory computer program product having embodied thereon a computer program for monitoring a brain CT scan image, the computer program product storing instructions, the instructions comprising instructions for:

• receiving a brain CT scan image of a patient;
• resampling the brain CT scan image into a plurality of slices, wherein the brain CT scan image is resampled using a bilinear interpolation;
• identifying a basal ganglia region and a corona radiata level in the plurality of slices, wherein the basal ganglia region and the corona radiata level are identified in a Middle Cerebral Artery (MCA) territory using a deep learning model;
• segmenting a plurality of anatomical regions upon identification of the basal ganglia region and the corona radiata level, wherein the plurality of anatomical regions is segmented using deep learning, and wherein the plurality of anatomical regions is segmented on a set of slices associated with the basal ganglia region and the corona radiata level;
• segmenting a plurality of infarcts in the plurality of slices using the deep learning;
• extracting a white matter region and a grey matter region in the plurality of slices using a windowing technique;
• determining a density of the white matter region and a density of the grey matter region on each of the plurality of slices based on an analysis of the plurality of slices using a fast Fourier transform technique;
• segmenting a plurality of black regions in the plurality of slices based on comparison of the density of the white matter region and the grey matter region with a threshold density;
• determining an overlapping region across the plurality of slices, wherein the overlapping region is determined based on the plurality of anatomical regions, the plurality of infarcts and the plurality of black regions, and wherein the overlapping region indicates an affected area of brain in the brain CT scan image;
• computing an ASPECTS score based on the overlapping region and a predefined threshold, wherein a defined point is deducted from the predefined threshold when the overlapping region is determined;
• and
• recommending a course of action to the patient in real-time based on the ASPECTS score and a threshold score, thereby monitoring a brain CT scan image.