Automated Artifact Detection And Annotation

The radiology Artifact Detection aims to create a system that identifies image artifacts on user selected regions of interest. till now the radiologists are manually finding the artifacts . in this project i aim to create a system that helps the radiologists in this process . The scanning reports will contain 100's of scripts and the traditional segmentation models works on pre trained data and breakdowns when it encounters a rare or a completely new data. The solution which i have planned is using an MedSAM model as it classify the scanning reports based on the visual signatures of the user's selection. A 2.5D volumetric tracking in this once an artifact is identified on Slice N, the algorithm prioritizes searching the exact spatial coordinates on Slices N-1 and N+1 which reduces the requirement of computation power. planning of using the human in the loop method in which out of 10 if the 8 predictions are correct and 2 are wrong if the user deletes 2 wrong predictions then the model learns that these two are wrong. i planed of using DICOM for datamanagement. The structure: Frontend -> model -> datainput -> MedSAM model -> loss calculation and scoring -> datamanagement.