Lesion Search With Self-supervised Learning

Abstract

Content-based image retrieval (CBIR) with self-supervised learning (SSL) accelerates clinicians' interpretation of similar images without manual annotations. We develop a CBIR from the contrastive learning SimCLR and incorporate a generalized-mean (GeM) pooling followed by L2 normalization to classify lesion types and retrieve similar images before clinicians' analysis. Results have shown improved performance. We additionally build an open-source application for image analysis and retrieval. The application is easy to integrate, relieving manual efforts and suggesting the potential to support clinicians' everyday activities.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyqi2023lesion

Related papers

• A Clinically Motivated Self-supervised Approach For Content-based Image Retrieval Of CT Liver Images (2022)9.76
• Semi-supervised Lung Nodule Retrieval (2020)0.00
• Exploring Content Based Image Retrieval For Highly Imbalanced Melanoma Data Using Style Transfer, Semantic Image Segmentation And Ensemble Learning (2021)0.00
• Content Based Image Retrieval (CBIR) In Remote Clinical Diagnosis And Healthcare (2016)9.23
• Cross-modality Sub-image Retrieval Using Contrastive Multimodal Image Representations (2022)6.32
• Global Learnable Attention For Single Image Super-resolution (2022)11.76
• CBIDR: A Novel Method For Information Retrieval Combining Image And Data By Means Of TOPSIS Applied To Medical Diagnosis (2024)0.00
• Siamese Content-based Search Engine For A More Transparent Skin And Breast Cancer Diagnosis Through Histological Imaging (2024)2.26