A Fully Transformer Based Multimodal Framework for Explainable Cancer Image Segmentation Using Radiology Reports

• URL: http://arxiv.org/abs/2508.13796v1
• Date: Tue, 19 Aug 2025 12:55:10 GMT
• Title: A Fully Transformer Based Multimodal Framework for Explainable Cancer Image Segmentation Using Radiology Reports
• Abstract summary: We introduce Med-CTX, a fully transformer based framework for explainable breast cancer ultrasound segmentation.<n>We integrate clinical radiology reports to boost both performance and interpretability.<n>On the BUS-BRA dataset, Med-CTX achieves a Dice score of 99% and an IoU of 95%, beating existing baselines U-Net, ViT, and Swin.
• Score: 2.629902609930227
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce Med-CTX, a fully transformer based multimodal framework for explainable breast cancer ultrasound segmentation. We integrate clinical radiology reports to boost both performance and interpretability. Med-CTX achieves exact lesion delineation by using a dual-branch visual encoder that combines ViT and Swin transformers, as well as uncertainty aware fusion. Clinical language structured with BI-RADS semantics is encoded by BioClinicalBERT and combined with visual features utilising cross-modal attention, allowing the model to provide clinically grounded, model generated explanations. Our methodology generates segmentation masks, uncertainty maps, and diagnostic rationales all at once, increasing confidence and transparency in computer assisted diagnosis. On the BUS-BRA dataset, Med-CTX achieves a Dice score of 99% and an IoU of 95%, beating existing baselines U-Net, ViT, and Swin. Clinical text plays a key role in segmentation accuracy and explanation quality, as evidenced by ablation studies that show a -5.4% decline in Dice score and -31% in CIDEr. Med-CTX achieves good multimodal alignment (CLIP score: 85%) and increased confi dence calibration (ECE: 3.2%), setting a new bar for trustworthy, multimodal medical architecture.

Related papers

• ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understanding [67.57715989349471]
  Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying them in the medical domain is fundamentally a vision-centric challenge.<n>We introduce ClinFusion, a vision-centric MLLM designed for holistic medical understanding.<n>We show that ClinFusion sets a new state-of-the-art across a comprehensive suite of 2D and 3D multimodal medical benchmarks.
  arXiv  Detail & Related papers  (2026-07-27T17:59:49Z)
• Multimodal Fusion for Fine-Grained Classification of Breast Fibroadenoma and Phyllodes Tumors [7.587937243908819]
  Breast fibroadenoma (FA) and phyllodes tumor (PT) are fibroepithelial breast lesions with highly overlapping appearances on B-mode ultrasound.<n>We propose a clinically guided multimodal framework that integrates visual encoding, CLIP-inspired text encoding, and lightweight clinical encoding.<n>Under patient-level five-fold cross-validation, the proposed method achieves an accuracy of 77.64%, F1-score of 73.38%, and AUC of 89.74%.
  arXiv  Detail & Related papers  (2026-07-02T12:30:08Z)
• Disease-Centric Vision-Language Pretraining with Hybrid Visual Encoding for 3D Computed Tomography [75.7789001619107]
  Vision-language pre-training holds great promise for general-purpose medical AI.<n>We propose a tailored framework featuring three key components.<n>A diagnosis-aware prompt strategy employs real clinical phrases and aggregated disease prototypes to bridge the pre-training-inference gap.
  arXiv  Detail & Related papers  (2026-06-24T08:24:45Z)
• Cerebra: A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment [56.62016795093786]
  Cerebra is an interactive multi-agent AI team that coordinates specialized agents for EHR, clinical notes, and medical imaging analysis.<n>It supports privacy-preserving deployment by operating on structured representations and remains robust when modalities are incomplete.<n>Cerebra significantly improved expert performance, increasing accuracy by 17.5 percentage points in prospective dementia risk estimation.
  arXiv  Detail & Related papers  (2026-03-23T05:46:45Z)
• TGC-Net: A Structure-Aware and Semantically-Aligned Framework for Text-Guided Medical Image Segmentation [56.09179939570486]
  We propose TGC-Net, a CLIP-based framework focusing on parameter-efficient, task-specific adaptations.<n>TGC-Net achieves state-of-the-art performance with substantially fewer trainable parameters, including notable Dice gains on challenging benchmarks.
  arXiv  Detail & Related papers  (2025-12-24T12:06:26Z)
• OncoVision: Integrating Mammography and Clinical Data through Attention-Driven Multimodal AI for Enhanced Breast Cancer Diagnosis [0.7998211927101394]
  OncoVision is a multimodal AI pipeline that combines mammography images and clinical data for better breast cancer diagnosis.<n>It jointly segments four ROIs - masses, calcifications, axillary findings, and breast tissues.<n>It robustly predicts ten structured clinical features: mass morphology, calcification type, ACR breast density, and BI-RADS categories.
  arXiv  Detail & Related papers  (2025-11-24T20:04:26Z)
• Transparent Early ICU Mortality Prediction with Clinical Transformer and Per-Case Modality Attribution [42.85462513661566]
  We present a lightweight, transparent multimodal ensemble that fuses physiological time-series measurements with unstructured clinical notes from the first 48 hours of an ICU stay.<n>A logistic regression model combines predictions from two modality-specific models: a bidirectional LSTM for vitals and a finetuned ClinicalModernBERT transformer for notes.<n>On the MIMIC-III benchmark, our late-fusion ensemble improves discrimination over the best single model while maintaining well-calibrated predictions.
  arXiv  Detail & Related papers  (2025-11-19T20:11:49Z)
• Advancing Chronic Tuberculosis Diagnostics Using Vision-Language Models: A Multi modal Framework for Precision Analysis [0.0]
  This study proposes a Vision-Language Model (VLM) to enhance automated chronic tuberculosis (TB) screening.<n>By integrating chest X-ray images with clinical data, the model addresses the challenges of manual interpretation.<n>The model demonstrated high precision (94 percent) and recall (94 percent) for detecting key chronic TB pathologies.
  arXiv  Detail & Related papers  (2025-03-17T13:49:29Z)
• Towards Interpretable Radiology Report Generation via Concept Bottlenecks using a Multi-Agentic RAG [1.9374282535132377]
  This study enhances interpretability in Chest X-ray (CXR) classification by using concept bottleneck models (CBMs) and a multi-agent Retrieval-Augmented Generation (RAG) system for report generation.<n>By modeling relationships between visual features and clinical concepts, we create interpretable concept vectors that guide a multi-agent RAG system to generate radiology reports.
  arXiv  Detail & Related papers  (2024-12-20T17:33:50Z)
• Bridging the Diagnostic Divide: Classical Computer Vision and Advanced AI methods for distinguishing ITB and CD through CTE Scans [2.900410045439515]
  A consensus among radiologists has recognized the visceral-to-subcutaneous fat ratio as a surrogate biomarker for differentiating between ITB and CD. We propose a novel 2D image computer vision algorithm for auto-segmenting subcutaneous fat to automate this ratio calculation. We trained a ResNet10 model on a dataset of CTE scans with samples from ITB, CD, and normal patients, achieving an accuracy of 75%.
  arXiv  Detail & Related papers  (2024-10-23T17:05:27Z)
• XAI for In-hospital Mortality Prediction via Multimodal ICU Data [57.73357047856416]
  We propose an efficient, explainable AI solution for predicting in-hospital mortality via multimodal ICU data. We employ multimodal learning in our framework, which can receive heterogeneous inputs from clinical data and make decisions. Our framework can be easily transferred to other clinical tasks, which facilitates the discovery of crucial factors in healthcare research.
  arXiv  Detail & Related papers  (2023-12-29T14:28:04Z)
• A Transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics [63.106382317917344]
  We report a Transformer-based representation-learning model as a clinical diagnostic aid that processes multimodal input in a unified manner. The unified model outperformed an image-only model and non-unified multimodal diagnosis models in the identification of pulmonary diseases.
  arXiv  Detail & Related papers  (2023-06-01T16:23:47Z)
• HGT: A Hierarchical GCN-Based Transformer for Multimodal Periprosthetic Joint Infection Diagnosis Using CT Images and Text [0.0]
  Prosthetic Joint Infection (PJI) is a prevalent and severe complication. Currently, a unified diagnostic standard incorporating both computed tomography (CT) images and numerical text data for PJI remains unestablished. This study introduces a diagnostic method, HGT, based on deep learning and multimodal techniques.
  arXiv  Detail & Related papers  (2023-05-29T11:25:57Z)
• Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images [55.83984261827332]
  In this paper, we propose a novel reliable multi-scale wavelet-enhanced transformer network. We develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module. Our proposed method achieves better segmentation accuracy with a high degree of reliability as compared to other state-of-the-art segmentation approaches.
  arXiv  Detail & Related papers  (2022-12-01T07:32:56Z)
• Co-Heterogeneous and Adaptive Segmentation from Multi-Source and Multi-Phase CT Imaging Data: A Study on Pathological Liver and Lesion Segmentation [48.504790189796836]
  We present a novel segmentation strategy, co-heterogenous and adaptive segmentation (CHASe) We propose a versatile framework that fuses appearance based semi-supervision, mask based adversarial domain adaptation, and pseudo-labeling. CHASe can further improve pathological liver mask Dice-Sorensen coefficients by ranges of $4.2% sim 9.4%$.
  arXiv  Detail & Related papers  (2020-05-27T06:58:39Z)

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.