DCG-Net: Dual Cross-Attention with Concept-Value Graph Reasoning for Interpretable Medical Diagnosis

Getamesay Dagnaw; Xuefei Yin; Muhammad Hassan Maqsood; Yanming Zhu; Alan Wee-Chung Liew

cs.CVMar 20, 2026

DCG-Net: Dual Cross-Attention with Concept-Value Graph Reasoning for Interpretable Medical Diagnosis

Authors: Getamesay Dagnaw, Xuefei Yin, Muhammad Hassan Maqsood, Yanming Zhu, Alan Wee-Chung Liew

Organizations: School of Information and Communication Technology, Griffith University, QLD, Australia

Abstract

Deep learning models have achieved strong performance in medical image analysis, but their internal decision processes remain difficult to interpret. Concept Bottleneck Models (CBMs) partially address this limitation by structuring predictions through human-interpretable clinical concepts. However, existing CBMs typically overlook the contextual dependencies among concepts. To address these issues, we propose an end-to-end interpretable framework DCG-Net that integrates multimodal alignment with structured concept reasoning. DCG-Net introduces a Dual Cross-Attention module that replaces cosine similarity matching with bidirectional attention between visual tokens and canonicalized textual concept-value prototypes, enabling spatially localized evidence attribution. To capture the relational structure inherent to clinical concepts, we develop a Parametric Concept Graph initialized with Positive Pointwise Mutual Information priors and refined through sparsity-controlled message passing. This formulation models inter-concept dependencies in a manner consistent with clinical domain knowledge. Experiments on white blood cell morphology and skin lesion diagnosis demonstrate that DCG-Net achieves state-of-the-art classification performance while producing clinically interpretable diagnostic explanations.

Figures & tables

Fig. 1: Overview of DCG-Net. The CDE generates canonical concept-value prototypes ( $T_{M}$ ). A vision transformer encodes images into patch-level visual tokens ( $V$ ). The DCA module aligns visual and textual representations via bidirectional attention at the concept-value level, generating local evidence and global relevance ( $\boldsymbol{\alpha}_{M}$ ), which are gated to produce the initial node features $\mathbf{H}^{(0)}$ . The PCG models concept-value dependencies using PPMI-initialized edges refined through learnable message passing, resulting in the refined state $H^{(L)}$ that forms the interpretable bottleneck for diagnosis.

Dataset	Method	Diagnosis Metrics		Concept Metrics
Dataset	Method	Acc (%)	F1 (%)	Acc (%)	F1 (%)
Fitzpatrick17k	CBM [ 15 ] (ICML 2020)	$78.37\pm 0.70$	$56.79\pm 0.45$	$78.42\pm 0.50$	$54.46\pm 0.32$
	CEM [ 6 ] (NeurIPS 2022)	$77.07\pm 1.44$	$58.02\pm 0.61$	$78.96\pm 0.50$	$54.95\pm 0.83$
	ProbCBM [ 13 ] (ICML 2023)	$72.13\pm 1.00$	$54.03\pm 0.15$	$88.49\pm 0.97$	$57.01\pm 1.52$
	evi-CEM [ 8 ] (MICCA 2024)	$76.50\pm 2.52$	$58.55\pm 2.27$	$90.33\pm 0.37$	$64.99\pm 0.73$
	Mica [ 4 ] (AAAI 2024)	$75.63\pm 1.07$	$\mathbf{75.43\pm 1.24}$	$91.7\pm--$	$63.8\pm--$

TABLE I: Performance comparison on PBC and SkinCon classification tasks. Bold indicates the best results, and underlined text denotes the second-best. Some compared results are directly reported from the cited paper [ 9 ] . For DCG-Net, concept metrics are computed on the pre-graph concept-value logits, which are directly supervised during training.

Fig. 2: Qualitative explanation of DCG-Net. (A) Input image with predicted diagnosis, concept-value probabilities, and ground-truth labels. (B) Top concept contributions ( $\alpha\times p_{\text{present}}$ ), showing which clinical findings most strongly support the model’s diagnostic decision. (C) PCG-based relational reasoning, showing each top concept and its associated concept-value nodes, reflecting learned dependencies among concept-value pairs.

Fitzpatrick17k	Performance Metrics
Fitzpatrick17k	Diagnosis (Acc/F1)	Concept (Acc/F1)
Full (ours)	83.44 / 72.13	92.18 / 71.05
w/o CDE	82.51 / 71.36	91.95 / 68.87
No PCG	81.66 / 71.63	92.15 / 70.40

TABLE II: Ablation for methodological justification.

Explore similar work

Vision-Language Models Encode Clinical Guidelines for Concept-Based Medical Reasoning
Mar 9, 2026Mohamed Harmanani, Bining Long, Zhuoxin Guo +6Explainable Medical Image Analysis Medical Reasoning
Queen’s University · Vector Institute · McMaster University +1
Beyond Explanation: Debugging Medical Imaging Models via Concept Intervention
Oct 6, 2026Samrajya Thapa, Daniel J. Quest, Timothy L. Kline +3Explainable Medical Image Analysis Concept Bottleneck Models
Iowa State University, Ames IA, USA · Mayo Clinic, Rochester MN, USA
Beyond Heatmaps: Unsupervised Concept-Graph Reasoning for Interpretable Visual Explanation
Jul 1, 2026Md Mohasin Hossain, Anar Amirli, Robert Leist +2Concept Bottleneck Models Concept-Based Explanations
German Research Center for Artificial Intelligence · Saarland University, Saarbrücken, Germany · German Research Center for Artificial Intelligence (DFKI), Saarbrücken, Germany +2

Mar 9, 2026J/K move · Enter open · S save

Vision-Language Models Encode Clinical Guidelines for Concept-Based Medical Reasoning

Mohamed Harmanani, Bining Long, Zhuoxin Guo, Paul F. R. Wilson+5

Queen’s University · Vector Institute · McMaster University+1

Explainable Medical Image Analysis Medical Reasoning Medical VLMs Concept Bottleneck Models Medical Image Classification

Open paper AskPDF arXiv

Concept Bottleneck Models (CBMs) are a prominent framework for interpretable AI that map learned visual features to a set of meaningful concepts for task-specific downstream predictions. Their sequential structure enhances transparency by connecting model predictions to the underlying concepts that support them. In medical imaging, where transparency is essential, CBMs offer an appealing foundation for explainable model design. However, discrete concept representations often overlook broader clinical context such as diagnostic guidelines and expert heuristics, reducing reliability in complex cases. We propose MedCBR, a concept-based reasoning framework that integrates clinical guidelines with vision-language and reasoning models. Labeled clinical descriptors are transformed into guideline-conformant text, and a concept-based model is trained with a multitask objective combining multimodal contrastive alignment, concept supervision, and diagnostic classification to jointly ground image features, concepts, and pathology. A reasoning model then converts these predictions into structured clinical narratives that explain the diagnosis, emulating expert reasoning based on established guidelines. MedCBR achieves superior diagnostic and concept-level performance, with AUROCs of 94.2% on ultrasound and 84.0% on mammography. Further experiments on non-medical datasets achieve 86.1% accuracy. Our framework enhances interpretability and forms an end-to-end bridge from medical image analysis to decision-making.

Abstract

Explore similar work

Vision-Language Models Encode Clinical Guidelines for Concept-Based Medical Reasoning

Beyond Explanation: Debugging Medical Imaging Models via Concept Intervention

Beyond Heatmaps: Unsupervised Concept-Graph Reasoning for Interpretable Visual Explanation