AME-CAM: Attentive Multiple-Exit CAM for Weakly Supervised Segmentation on MRI Brain Tumor

TL;DR

The paper introduces AME-CAM, a novel hierarchical CAM approach that extracts multi-resolution activation maps to enhance weakly-supervised brain tumor segmentation accuracy in MRI images.

Contribution

It proposes a new CAM method that leverages multiple resolutions for improved segmentation, addressing low-resolution issues in existing CAM techniques.

Findings

Outperforms state-of-the-art methods on BraTS 2021 dataset

Improves prediction accuracy in weakly-supervised MRI segmentation

Effectively aggregates multi-resolution activation maps

Abstract

Magnetic resonance imaging (MRI) is commonly used for brain tumor segmentation, which is critical for patient evaluation and treatment planning. To reduce the labor and expertise required for labeling, weakly-supervised semantic segmentation (WSSS) methods with class activation mapping (CAM) have been proposed. However, existing CAM methods suffer from low resolution due to strided convolution and pooling layers, resulting in inaccurate predictions. In this study, we propose a novel CAM method, Attentive Multiple-Exit CAM (AME-CAM), that extracts activation maps from multiple resolutions to hierarchically aggregate and improve prediction accuracy. We evaluate our method on the BraTS 2021 dataset and show that it outperforms state-of-the-art methods.