SAIL: Structure-Aware Interpretable Learning for Anatomy-Aligned Post-hoc Explanations in OCT

• URL: http://arxiv.org/abs/2605.02707v1
• Date: Mon, 04 May 2026 15:13:47 GMT
• Title: SAIL: Structure-Aware Interpretable Learning for Anatomy-Aligned Post-hoc Explanations in OCT
• Abstract summary: Deep learning (DL) has achieved expert-level accuracy in OCT-based retinal disease detection, but its "black box" nature poses challenges for clinical adoption.<n>Existing post-hoc explainable AI (XAI) methods often struggle to delineate fine-grained lesion structures, respect anatomical boundaries, or suppress noise.<n>We propose a Structure-Aware Interpretable Learning framework that integrates retinal anatomical priors at the representation level and couples them with semantic features.
• Score: 14.34264989195413
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Optical coherence tomography (OCT), a commonly used retinal imaging modality, plays a central role in retinal disease diagnosis by providing high-resolution visualization of retinal layers. While deep learning (DL) has achieved expert-level accuracy in OCT-based retinal disease detection, its "black box" nature poses challenges for clinical adoption, where explainability is essential for clinical trust and regulatory approval. Existing post-hoc explainable AI (XAI) methods often struggle to delineate fine-grained lesion structures, respect anatomical boundaries, or suppress noise, limiting the trustworthiness of their explanations. To bridge these gaps, we propose a Structure-Aware Interpretable Learning (SAIL) framework that integrates retinal anatomical priors at the representation level and couples them with semantic features via a fusion design. Without modifying standard post-hoc explainability methods, this representation yields sharper and more anatomically aligned attribution maps. Comprehensive experiments on diverse OCT datasets demonstrate that our structure-aware method consistently enhances interpretability, producing clinically meaningful and anatomy-aware explanations. Ablation studies further show that strong interpretability requires both structural priors and semantic features, and that properly fusing the two is critical to achieve the best explanation quality. Together, these results highlight structure-aware representations as a key step toward reliable explainability in OCT.

Related papers

• Beyond Classification: Structured Supervision Aligns Visual Evidence with Medical Semantics [7.711063174717135]
  Vision Transformers (ViTs) have shown immense potential in medical image analysis.<n>Standard pre-training via global image classification suffers from spatial collapse.<n>We investigate alternative pre-training paradigms to align visual evidence with precise medical semantics.
  arXiv  Detail & Related papers  (2026-09-05T07:03:08Z)
• EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive Alignment [15.371433625713232]
  EndoVLM is a novel vision-language FM pre-trained on over 348K endoscopic examinations.<n>An Anatomy-Guided Sparse Pooling mechanism utilizes textual descriptions as queries to drive sparse attention.<n>A Progressive Semantic-Aware Alignment strategy models clinical taxonomy (anatomy and pathological status) via structured soft targets.<n>A Semantic-Concentrated Masked Autoencoder is applied exclusively to these semantic-rich frames, integrating low-level visual precision with robust high-level semantic representation.
  arXiv  Detail & Related papers  (2026-08-05T05:56:41Z)
• Anatomy-Anchored Self-Supervision: Distilling Vision Foundation Models for Invariant Ultrasound Representation [29.61647712180762]
  Self-supervised pre-training paradigm has gained increasing prominence for learning transferable representations in medical imaging.<n>We propose an anatomy-anchored ultrasound self-supervision framework ANAUS that shifts representation learning from generic visual regions to clinically meaningful anatomical structures.
  arXiv  Detail & Related papers  (2026-05-25T03:52:58Z)
• Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs [63.535652574541764]
  Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in medical image analysis.<n>Their application in gastrointestinal endoscopy is currently hindered by two critical limitations.<n>We propose a novel Clinical-Cognitive-Aligned (CogAlign) framework to address these challenges.
  arXiv  Detail & Related papers  (2026-03-21T07:47:37Z)
• Vision-Language Models Encode Clinical Guidelines for Concept-Based Medical Reasoning [3.2723884637302443]
  Concept Bottleneck Models (CBMs) are a prominent framework for interpretable AI.<n>We propose MedCBR, a concept-based reasoning framework that integrates clinical guidelines with vision-language and reasoning models.<n>Our framework achieves interpretability and forms an end-to-end bridge from medical image analysis to decision-making.
  arXiv  Detail & Related papers  (2026-03-09T20:39:46Z)
• Deep Expert Injection for Anchoring Retinal VLMs with Domain-Specific Knowledge [66.67024684187915]
  Large Vision Language Models (LVLMs) show immense potential for automated ophthalmic diagnosis.<n>Their clinical deployment is severely hindered by lacking domain-specific knowledge.<n>EyExIn is a framework designed to anchor retinal VLMs with expert knowledge via a Deep Expert Injection mechanism.
  arXiv  Detail & Related papers  (2026-03-07T09:43:49Z)
• Structure Observation Driven Image-Text Contrastive Learning for Computed Tomography Report Generation [51.509572354327986]
  This work introduces a novel two-stage (structure- and report-learning) framework tailored for Computed Tomography Report Generation (CTRG)<n>In the first stage, a set of learnable structure-specific visual queries observe corresponding structures in a CT image. The resulting observation tokens are contrasted with structure-specific textual features extracted from the accompanying radiology report with a structure-wise image-text contrastive loss.<n>In the second stage, the visual structure queries are frozen and used to select the critical image patch embeddings depicting each anatomical structure, minimizing distractions from irrelevant areas while reducing memory consumption.
  arXiv  Detail & Related papers  (2026-03-05T07:07:07Z)
• Structure-constrained Language-informed Diffusion Model for Unpaired Low-dose Computed Tomography Angiography Reconstruction [72.80209358480424]
  overdose of iodinated contrast media (ICM) can cause kidney damage and life-threatening allergic reactions.<n>Deep learning methods can generate CT images of normal-dose ICM from low-dose ICM, reducing the required dose.<n>We propose a Structure-constrained Language-informed Diffusion Model (SLDM) that integrates structural synergy and spatial intelligence.
  arXiv  Detail & Related papers  (2026-01-28T06:54:06Z)
• A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis [82.01597026329158]
  We introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS) for pathology-specific text-to-image synthesis.<n>CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy.<n>This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations.
  arXiv  Detail & Related papers  (2025-12-15T10:22:43Z)
• Explainable Melanoma Diagnosis with Contrastive Learning and LLM-based Report Generation [6.12668702512286]
  Cross-modal Explainable Framework for Melanoma (CEFM)<n>Uses contrastive learning as the core mechanism for achieving interpretability.<n>Experiments on public datasets demonstrate 92.79% accuracy and an AUC of 0.961.
  arXiv  Detail & Related papers  (2025-12-05T19:19:36Z)
• Anatomy-VLM: A Fine-grained Vision-Language Model for Medical Interpretation [12.39187443971813]
  We introduce Anatomy-VLM, a vision-language model that incorporates multi-scale information.<n>First, we design a model encoder to localize key anatomical features from entire medical images.<n>Second, these regions are enriched with structured knowledge for contextually-aware interpretation.<n>Third, the model encoder aligns multi-scale medical information to generate clinically-interpretable disease prediction.
  arXiv  Detail & Related papers  (2025-11-11T16:18:01Z)
• Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation [61.350584471060756]
  Vision-grounded medical report generation aims to produce clinically accurate descriptions of medical images.<n>We propose Self-Supervised Anatomical Consistency Learning (SS-ACL) to align generated reports with corresponding anatomical regions.<n>SS-ACL constructs a hierarchical anatomical graph inspired by the invariant top-down inclusion structure of human anatomy.
  arXiv  Detail & Related papers  (2025-09-30T08:59:06Z)
• Multi-Modal Learning Using Physicians Diagnostics for Optical Coherence Tomography Classification [0.0]
  We propose a framework that incorporates experts diagnostics and insights into the analysis of Optical Coherence Tomography. We create a medical diagnostic attribute dataset to improve disease classification using OCT.
  arXiv  Detail & Related papers  (2022-03-20T18:37:20Z)

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.