Conference proceeding
SAMLFDiag: SAM generated latent segmentation features for disease diagnosis
Ninth International Workshop on Pattern Recognition, Vol.13399, pp.1339906-1339906-5
10/21/2024
DOI: 10.1117/12.3054460
Abstract
Numerous studies have demonstrated significant correlations between segmented pathological objects in various medical imaging modalities and disease-related pathology. While previous investigations have employed handcrafted features for disease prediction, those approaches neglect the vast potential of leveraging latent features from deep learning (DL) models, which could potentially enhance the overall accuracy of differential diagnosis. Recently, the Segment Anything Model (SAM) has demonstrated remarkable zero-shot segmentation capabilities for natural images and garnered significant attention for its potential applications in medical image segmentation. However, to the best of our knowledge, no studies have explored leveraging the latent features extracted through SAM’s encoder for medical image classification. In this paper, we propose the novel SAMLF Diag method, which harnesses the latent features generated by MedSAM for benign and malignant breast cancer classification. Our proposed model leverages the encoded features from MedSAM’s Vision Transformer (ViT) to maximize the attribute-related information contained within the image features. By exploiting the powerful segmentation capabilities of SAM, our approach aims to extract and utilize the most informative and discriminative features for breast cancer classification. Experiments on a public ultrasound breast cancer dataset were conducted to validate the effectiveness of SAMLF Diag, demonstrating its ability to outperform baseline deep learning models for breast cancer classification. Our work highlights the potential of leveraging state-of-the-art foundation segmentation models for enhancing disease diagnosis through latent feature extraction and zero-shot learning.
Details
- Title: Subtitle
- SAMLFDiag: SAM generated latent segmentation features for disease diagnosis
- Creators
- Tarun Kanti Roy - University of IowaFahim Ahamed Zaman - University of IowaXiaodong Wu - University of Iowa
- Contributors
- Hui Tian (Editor) - Huaqiao University
- Resource Type
- Conference proceeding
- Publication Details
- Ninth International Workshop on Pattern Recognition, Vol.13399, pp.1339906-1339906-5
- Publisher
- SPIE
- DOI
- 10.1117/12.3054460
- ISSN
- 0277-786X
- Language
- English
- Date published
- 10/21/2024
- Academic Unit
- The Iowa Institute for Biomedical Imaging; Electrical and Computer Engineering; Iowa Technology Institute; Radiation Oncology
- Record Identifier
- 9984742656902771
Metrics
5 Record Views