A Semantically-aware Relevance Measure For Content-based Medical Image Retrieval Evaluation

Abstract

Performance evaluation for Content-Based Image Retrieval (CBIR) remains a crucial but unsolved problem today especially in the medical domain. Various evaluation metrics have been discussed in the literature to solve this problem. Most of the existing metrics (e.g., precision, recall) are adapted from classification tasks which require manual labels as ground truth. However, such labels are often expensive and unavailable in specific thematic domains. Furthermore, medical images are usually associated with (radiological) case reports or annotated with descriptive captions in literature figures, such text contains information that can help to assess CBIR.Several researchers have argued that the medical concepts hidden in the text can serve as the basis for CBIR evaluation purpose. However, these works often consider these medical concepts as independent and isolated labels while in fact the subtle relationships between various concepts are neglected. In this work, we introduce the use o

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keywei2025a

Related papers

• Advancements In Content-based Image Retrieval: A Comprehensive Survey Of Relevance Feedback Techniques (2023)0.00
• Content-based 3D Image Retrieval And A Colbert-inspired Re-ranking For Tumor Flagging And Staging (2025)0.00
• CBIDR: A Novel Method For Information Retrieval Combining Image And Data By Means Of TOPSIS Applied To Medical Diagnosis (2024)0.00
• Content Based Image Retrieval (CBIR) In Remote Clinical Diagnosis And Healthcare (2016)9.23
• Content-based Image Retrieval For Multi-class Volumetric Radiology Images: A Benchmark Study (2024)5.24
• An Improved Relevance Feedback In CBIR (2020)0.00
• Automatic Feature Weight Determination Using Indexing And Pseudo-relevance Feedback For Multi-feature Content-based Image Retrieval (2018)0.00
• Semi-supervised Lung Nodule Retrieval (2020)0.00