Abstract

Anatomical variations in shape and volume metrics make pancreas medical image processing one of the most difficult subjects. Image processing in pancreas Computed Tomography (CT) is required to detect the class of pancreas anomaly accurately, reducing the possibility of a fatal outcome. It is estimated that a misunderstanding of radiology images accounts for 40% to 54% of all negligence claims. Machine learning advancements have created opportunities to train algorithms to learn patterns in pancreas images and use that knowledge to predict the pancreatic ductal adenocarcinoma (PDAC) overall survival rate. This paper performs feature extraction on CT pancreas images using edge detection techniques. Non-Local Means (NLM) are applied to the images to remove noise and smoothen them to highlight the defect. The experiments achieved an Intersection over Union (AOU) of 0.79 and an accuracy of 0.96. The images are then passed through the cropping layer to remove unwanted sections. The new train set is obtained from aggregating features from the edge detection feature extraction techniques and was then pruned to only eight features using the Principal Component Analysis technique. The train set was loaded into Light Gradient-boosting Machine (LGBM) to train the model to segment all the images.

Statistics