ToNNO: Tomographic Reconstruction of a Neural Network's Output for Weakly Supervised Segmentation of 3D Medical Images

arXiv:2404.13103v1 Announce Type: cross
Abstract: Annotating lots of 3D medical images for training segmentation models is time-consuming. The goal of weakly supervised semantic segmentation is to train segmentation models without using any ground truth segmentation masks. Our work addresses the case where only image-level categorical labels, indicating the presence or absence of a particular region of interest (such as tumours or lesions), are available. Most existing methods rely on class activation mapping (CAM). We propose a novel approach, ToNNO, which …

abstract arxiv case cs.cv cs.lg eess.iv image images masks medical network neural network segmentation semantic train training truth type work