Simulating Realistic MRI variations to Improve Deep Learning model and visual explanations using GradCAM

TL;DR

This paper introduces a method for improving MRI landmark detection using realistic data augmentation, a modified deep learning model, and visual explanations with Grad-CAM, enhancing interpretability and robustness in medical imaging tasks.

Contribution

The study presents a novel pipeline combining synthetic data generation, a modified HighRes3DNet, and Grad-CAM for improved and interpretable MRI landmark detection.

Findings

Enhanced landmark detection accuracy with augmented data

Effective visual explanations via Grad-CAM

Pipeline adaptable to various landmarks and anatomies

Abstract

In the medical field, landmark detection in MRI plays an important role in reducing medical technician efforts in tasks like scan planning, image registration, etc. First, 88 landmarks spread across the brain anatomy in the three respective views -- sagittal, coronal, and axial are manually annotated, later guidelines from the expert clinical technicians are taken sub-anatomy-wise, for better localization of the existing landmarks, in order to identify and locate the important atlas landmarks even in oblique scans. To overcome limited data availability, we implement realistic data augmentation to generate synthetic 3D volumetric data. We use a modified HighRes3DNet model for solving brain MRI volumetric landmark detection problem. In order to visually explain our trained model on unseen data, and discern a stronger model from a weaker model, we implement Gradient-weighted Class Activation Mapping (Grad-CAM) which produces a coarse localization map highlighting the regions the model is focusing. Our experiments show that the proposed method shows favorable results, and the overall pipeline can be extended to a variable number of landmarks and other anatomies.