Lesion Analysis and Diagnosis with Mask-RCNN
arXiv:1807.05979v213 citations
Originality Synthesis-oriented
AI Analysis
This work addresses medical image analysis for skin lesion diagnosis, but it is incremental as it applies an existing method to a known dataset.
The project tackled lesion analysis and diagnosis by applying Mask R-CNN to the ISIC 2018 challenge, achieving results for segmentation, detection, and diagnosis tasks, with a simple voting procedure used for diagnosis.
This project applies Mask R-CNN method to ISIC 2018 challenge tasks: lesion boundary segmentation (task1), lesion attributes detection (task 2), lesion diagnosis (task 3), a solution to the latter is using a trained model for task 1 and a simple voting procedure.