Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders

• URL: http://arxiv.org/abs/2507.15227v1
• Date: Mon, 21 Jul 2025 03:59:21 GMT
• Title: Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders
• Authors: Krishna Kanth Nakka,
• Abstract summary: Interpretability is critical in high-stakes domains such as medical imaging.<n>We introduce Sparse Autoencoder (SAE)-based interpretability to breast imaging by analyzing Mammo-CLIP<n>We train a patch-level textttMammo-SAE on Mammo-CLIP to identify and probe latent features associated with clinically relevant breast concepts.
• Score: 7.23389716633927
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Interpretability is critical in high-stakes domains such as medical imaging, where understanding model decisions is essential for clinical adoption. In this work, we introduce Sparse Autoencoder (SAE)-based interpretability to breast imaging by analyzing {Mammo-CLIP}, a vision--language foundation model pretrained on large-scale mammogram image--report pairs. We train a patch-level \texttt{Mammo-SAE} on Mammo-CLIP to identify and probe latent features associated with clinically relevant breast concepts such as \textit{mass} and \textit{suspicious calcification}. Our findings reveal that top activated class level latent neurons in the SAE latent space often tend to align with ground truth regions, and also uncover several confounding factors influencing the model's decision-making process. Additionally, we analyze which latent neurons the model relies on during downstream finetuning for improving the breast concept prediction. This study highlights the promise of interpretable SAE latent representations in providing deeper insight into the internal workings of foundation models at every layer for breast imaging.

Related papers

• PathSegDiff: Pathology Segmentation using Diffusion model representations [63.20694440934692]
  We propose PathSegDiff, a novel approach for histopathology image segmentation that leverages Latent Diffusion Models (LDMs) as pre-trained featured extractors.<n>Our method utilizes a pathology-specific LDM, guided by a self-supervised encoder, to extract rich semantic information from H&E stained histopathology images.<n>Our experiments demonstrate significant improvements over traditional methods on the BCSS and GlaS datasets.
  arXiv  Detail & Related papers  (2025-04-09T14:58:21Z)
• Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation [56.87049651707208]
  Few-shot Semantic has evolved into In-context tasks, morphing into a crucial element in assessing generalist segmentation models. Our initial focus lies in understanding how to facilitate interaction between the query image and the support image, resulting in the proposal of a KV fusion method within the self-attention framework. Based on our analysis, we establish a simple and effective framework named DiffewS, maximally retaining the original Latent Diffusion Model's generative framework.
  arXiv  Detail & Related papers  (2024-10-03T10:33:49Z)
• Analyzing the Effect of $k$-Space Features in MRI Classification Models [0.0]
  We have developed an explainable AI methodology tailored for medical imaging. We employ a Convolutional Neural Network (CNN) that analyzes MRI scans across both image and frequency domains. This approach not only enhances early training efficiency but also deepens our understanding of how additional features impact the model predictions.
  arXiv  Detail & Related papers  (2024-09-20T15:43:26Z)
• Interpretable breast cancer classification using CNNs on mammographic images [0.0]
  This research addresses the need to gain insights into the decision-making process of convolutional neural networks (CNNs) for mammogram classification. For CNNs trained on the Mammographic Image Analysis Society (MIAS) dataset, we compared the post-hoc interpretability techniques LIME, Grad-CAM, and Kernel SHAP. The results indicate that Grad-CAM, in particular, provides comprehensive insights into the behavior of the CNN, revealing distinctive patterns in normal, benign, and malignant breast tissue.
  arXiv  Detail & Related papers  (2024-08-23T15:25:42Z)
• SAM-Driven Weakly Supervised Nodule Segmentation with Uncertainty-Aware Cross Teaching [13.5553526185399]
  Automated nodule segmentation is essential for computer-assisted diagnosis in ultrasound images. Recently, segmentation foundation models like SAM have shown impressive generalizability on natural images. In this work, we devise a novel weakly supervised framework that effectively utilizes the segmentation foundation model to generate pseudo-labels.
  arXiv  Detail & Related papers  (2024-07-18T14:27:54Z)
• Enhancing AI Diagnostics: Autonomous Lesion Masking via Semi-Supervised Deep Learning [1.4053129774629076]
  This study presents an unsupervised domain adaptation method aimed at autonomously generating image masks outlining regions of interest (ROIs) for differentiating breast lesions in breast ultrasound (US) imaging. Our semi-supervised learning approach utilizes a primitive model trained on a small public breast US dataset with true annotations. This model is then iteratively refined for the domain adaptation task, generating pseudo-masks for our private, unannotated breast US dataset.
  arXiv  Detail & Related papers  (2024-04-18T18:25:00Z)
• Morphology-Enhanced CAM-Guided SAM for weakly supervised Breast Lesion Segmentation [7.747608350830482]
  We present a novel framework for weakly supervised lesion segmentation in early breast ultrasound images. Our method uses morphological enhancement and class activation map (CAM)-guided localization. This approach does not require pixel-level annotation, thereby reducing the cost of data annotation.
  arXiv  Detail & Related papers  (2023-11-18T22:06:04Z)
• Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models [49.95603725998561]
  We propose a new paradigm to build robust and interpretable medical image classifiers with natural language concepts. Specifically, we first query clinical concepts from GPT-4, then transform latent image features into explicit concepts with a vision-language model.
  arXiv  Detail & Related papers  (2023-10-04T21:57:09Z)
• BI-RADS-Net: An Explainable Multitask Learning Approach for Cancer Diagnosis in Breast Ultrasound Images [69.41441138140895]
  This paper introduces BI-RADS-Net, a novel explainable deep learning approach for cancer detection in breast ultrasound images. The proposed approach incorporates tasks for explaining and classifying breast tumors, by learning feature representations relevant to clinical diagnosis. Explanations of the predictions (benign or malignant) are provided in terms of morphological features that are used by clinicians for diagnosis and reporting in medical practice.
  arXiv  Detail & Related papers  (2021-10-05T19:14:46Z)
• Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding [60.89561661441736]
  We propose a novel method for few-shot medical image segmentation. We construct our few-shot image segmentor using a deep convolutional network trained episodically. We enhance discriminability of deep embedding to encourage clustering of the feature domains of the same class.
  arXiv  Detail & Related papers  (2020-12-10T04:01:07Z)
• Explaining Clinical Decision Support Systems in Medical Imaging using Cycle-Consistent Activation Maximization [112.2628296775395]
  Clinical decision support using deep neural networks has become a topic of steadily growing interest. clinicians are often hesitant to adopt the technology because its underlying decision-making process is considered to be intransparent and difficult to comprehend. We propose a novel decision explanation scheme based on CycleGAN activation which generates high-quality visualizations of classifier decisions even in smaller data sets.
  arXiv  Detail & Related papers  (2020-10-09T14:39:27Z)
• Interpretable Deep Models for Cardiac Resynchronisation Therapy Response Prediction [8.152884957975354]
  We propose a novel framework for image-based classification based on a variational autoencoder (VAE) The VAE disentangles the latent space based on explanations' drawn from existing clinical knowledge. We demonstrate our framework on the problem of predicting response of patients with cardiomyopathy to cardiac resynchronization therapy (CRT) from cine cardiac magnetic resonance images.
  arXiv  Detail & Related papers  (2020-06-24T15:35:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.