This looks better than that: Better interpretable models with protopnext

F Willard, L Moffett, E Mokel, J Donnelly, S Guo… - arxiv preprint arxiv …, 2024 - arxiv.org
Prototypical-part models are a popular interpretable alternative to black-box deep learning
models for computer vision. However, they are difficult to train, with high sensitivity to …

Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks

J Hou, S Liu, Y Bie, H Wang, A Tan, L Luo… - arxiv preprint arxiv …, 2024 - arxiv.org
The increasing demand for transparent and reliable models, particularly in high-stakes
decision-making areas such as medical image analysis, has led to the emergence of …

Enhancing Interpretability of Vertebrae Fracture Grading using Human-interpretable Prototypes

P Sinhamahapatra, S Shit, A Sekuboyina… - arxiv preprint arxiv …, 2024 - arxiv.org
Vertebral fracture grading classifies the severity of vertebral fractures, which is a challenging
task in medical imaging and has recently attracted Deep Learning (DL) models. Only a few …