# M3d-CAM: A PyTorch library to generate 3D data attention maps for medical deep learning

arXiv: https://arxiv.org/abs/2007.00453 · HTML: https://mlsanity.com/paper/2007.00453/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2020.

## Built on by (most cited first, 12 of 12)

- [Cascaded Multi-Modal Mixing Transformers for Alzheimer's Disease Classification with Incomplete Data](https://mlsanity.com/paper/2210.00255/) (2022)
- [Faint Features Tell: Automatic Vertebrae Fracture Screening Assisted by Contrastive Learning](https://mlsanity.com/paper/2208.10698/) (2022)
- [Advancing Head and Neck Cancer Survival Prediction via Multi-Label Learning and Deep Model Interpretation](https://mlsanity.com/paper/2405.05488/) (2024)
- [One Wave To Explain Them All: A Unifying Perspective On Feature Attribution](https://mlsanity.com/paper/2410.01482/) (2024)
- [TopoTxR: A topology-guided deep convolutional network for breast parenchyma learning on DCE-MRIs](https://mlsanity.com/paper/2411.03464/) (2024)
- [Multiple Sclerosis Lesions Segmentation using Attention-Based CNNs in FLAIR Images](https://mlsanity.com/paper/2201.01832/) (2022)
- [Domain Aware Multi-Task Pretraining of 3D Swin Transformer for T1-weighted Brain MRI](https://mlsanity.com/paper/2410.00410/) (2024)
- [WoundAmbit: Bridging State-of-the-Art Semantic Segmentation and Real-World Wound Care](https://mlsanity.com/paper/2504.06185/) (2025)
- [Atlas-Based Interpretable Age Prediction In Whole-Body MR Images](https://mlsanity.com/paper/2307.07439/) (2023)
- [Multi-task Learning Approach for Intracranial Hemorrhage Prognosis](https://mlsanity.com/paper/2408.08784/) (2024)
- [Enhancing Trust in Clinically Significant Prostate Cancer Prediction with Multiple Magnetic Resonance Imaging Modalities](https://mlsanity.com/paper/2411.04662/) (2024)
- [Adapting Visualization Techniques for Time-Series Anomaly Detection: From Convolutional Neural Networks to Convolutional-Recurrent Neural Networks](https://mlsanity.com/paper/2411.04707/) (2024)

## Abstract (arXiv)

M3d-CAM is an easy to use library for generating attention maps of CNN-based PyTorch models improving the interpretability of model predictions for humans. The attention maps can be generated with multiple methods like Guided Backpropagation, Grad-CAM, Guided Grad-CAM and Grad-CAM++. These attention maps visualize the regions in the input data that influenced the model prediction the most at a certain layer. Furthermore, M3d-CAM supports 2D and 3D data for the task of classification as well as for segmentation. A key feature is also that in most cases only a single line of code is required for generating attention maps for a model making M3d-CAM basically plug and play.