Revisiting Integration of Image and Metadata for DICOM Series Classification: Cross-Attention and Dictionary Learning

• URL: http://arxiv.org/abs/2602.23833v1
• Date: Fri, 27 Feb 2026 09:12:24 GMT
• Title: Revisiting Integration of Image and Metadata for DICOM Series Classification: Cross-Attention and Dictionary Learning
• Authors: Tuan Truong, Melanie Dohmen, Sara Lorio, Matthias Lenga,
• Abstract summary: DICOM series classification remains challenging due to heterogeneous slice content, variable series length, and entirely missing, incomplete or inconsistent DICOM metadata.<n>We propose an end-to-end multimodal framework for DICOM series classification that jointly models image content and acquisition metadata.<n>We evaluate the proposed approach on the publicly available Duke Liver MRI dataset and a large multi-institutional in-house cohort.
• Score: 1.4430021185664905
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automated identification of DICOM image series is essential for large-scale medical image analysis, quality control, protocol harmonization, and reliable downstream processing. However, DICOM series classification remains challenging due to heterogeneous slice content, variable series length, and entirely missing, incomplete or inconsistent DICOM metadata. We propose an end-to-end multimodal framework for DICOM series classification that jointly models image content and acquisition metadata while explicitly accounting for all these challenges. (i) Images and metadata are encoded with modality-aware modules and fused using a bi-directional cross-modal attention mechanism. (ii) Metadata is processed by a sparse, missingness-aware encoder based on learnable feature dictionaries and value-conditioned modulation. By design, the approach does not require any form of imputation. (iii) Variability in series length and image data dimensions is handled via a 2.5D visual encoder and attention operating on equidistantly sampled slices. We evaluate the proposed approach on the publicly available Duke Liver MRI dataset and a large multi-institutional in-house cohort, assessing both in-domain performance and out-of-domain generalization. Across all evaluation settings, the proposed method consistently outperforms relevant image only, metadata-only and multimodal 2D/3D baselines. The results demonstrate that explicitly modeling metadata sparsity and cross-modal interactions improves robustness for DICOM series classification.

Related papers

• Self-supervised Multiplex Consensus Mamba for General Image Fusion [34.041756423040184]
  We propose SMC-Mamba, a Self-supervised Multiplex Consensus Mamba framework for general image fusion.<n> Modality-Agnostic Feature Enhancement (MAFE) module preserves fine details through adaptive gating.<n>Cross-modal scanning within MCCM strengthens feature interactions across modalities.<n>Bi-level Self-supervised Contrastive Learning Loss (BSCL) preserves high-frequency information without increasing computational overhead.
  arXiv  Detail & Related papers  (2025-12-24T03:57:21Z)
• Exploring a Unified Vision-Centric Contrastive Alternatives on Multi-Modal Web Documents [99.62178668680578]
  We propose Vision-Centric Contrastive Learning (VC2L), a unified framework that models text, images, and their combinations using a single vision transformer.<n> VC2L operates entirely in pixel space by rendering all inputs, whether textual, visual, or combined, as images.<n>To capture complex cross-modal relationships in web documents, VC2L employs a snippet-level contrastive learning objective that aligns consecutive multimodal segments.
  arXiv  Detail & Related papers  (2025-10-21T14:59:29Z)
• A Hybrid AI-based and Rule-based Approach to DICOM De-identification: A Solution for the MIDI-B Challenge [4.40986569501073]
  This paper presents a hybrid de-identification framework designed to process Digital Imaging and Communications in Medicine (DICOM) files.<n>Our framework adopts a modified, pre-built rule-based component, updated with The Cancer Imaging Archive (TCIA)'s best practices guidelines.<n>It incorporates PaddleOCR, a robust Optical Character Recognition (OCR) system for extracting text from images, and RoBERTa, a fine-tuned transformer-based model for identifying Personally Identifiable Information (PII) and Protected Health Information (PHI)
  arXiv  Detail & Related papers  (2025-08-30T09:52:15Z)
• DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data [67.99373622902827]
  DIPO is a framework for controllable generation of articulated 3D objects from a pair of images.<n>We propose a dual-image diffusion model that captures relationships between the image pair to generate part layouts and joint parameters.<n>We propose PM-X, a large-scale dataset of complex articulated 3D objects, accompanied by rendered images, URDF annotations, and textual descriptions.
  arXiv  Detail & Related papers  (2025-05-26T18:55:14Z)
• AuxDet: Auxiliary Metadata Matters for Omni-Domain Infrared Small Target Detection [49.81255045696323]
  We present the Auxiliary Metadata Driven Infrared Small Target Detector (AuxDet)<n>AuxDet integrates metadata semantics with visual features, guiding adaptive representation learning for each sample.<n>Experiments on the challenging WideIRSTD-Full benchmark demonstrate that AuxDet consistently outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-05-21T07:02:05Z)
• CoLLM: A Large Language Model for Composed Image Retrieval [76.29725148964368]
  Composed Image Retrieval (CIR) is a complex task that aims to retrieve images based on a multimodal query.<n>We present CoLLM, a one-stop framework that generates triplets on-the-fly from image-caption pairs.<n>We leverage Large Language Models (LLMs) to generate joint embeddings of reference images and modification texts.
  arXiv  Detail & Related papers  (2025-03-25T17:59:50Z)
• A Mutual Inclusion Mechanism for Precise Boundary Segmentation in Medical Images [2.9137615132901704]
  We present a novel deep learning-based approach, MIPC-Net, for precise boundary segmentation in medical images. We introduce the MIPC module, which enhances the focus on channel information when extracting position features. We also propose the GL-MIPC-Residue, a global residual connection that enhances the integration of the encoder and decoder.
  arXiv  Detail & Related papers  (2024-04-12T02:14:35Z)
• Rotated Multi-Scale Interaction Network for Referring Remote Sensing Image Segmentation [63.15257949821558]
  Referring Remote Sensing Image (RRSIS) is a new challenge that combines computer vision and natural language processing. Traditional Referring Image (RIS) approaches have been impeded by the complex spatial scales and orientations found in aerial imagery. We introduce the Rotated Multi-Scale Interaction Network (RMSIN), an innovative approach designed for the unique demands of RRSIS.
  arXiv  Detail & Related papers  (2023-12-19T08:14:14Z)
• A Simple and Robust Framework for Cross-Modality Medical Image Segmentation applied to Vision Transformers [0.0]
  We propose a simple framework to achieve fair image segmentation of multiple modalities using a single conditional model. We show that our framework outperforms other cross-modality segmentation methods on the Multi-Modality Whole Heart Conditional Challenge.
  arXiv  Detail & Related papers  (2023-10-09T09:51:44Z)
• Unified Frequency-Assisted Transformer Framework for Detecting and Grounding Multi-Modal Manipulation [109.1912721224697]
  We present the Unified Frequency-Assisted transFormer framework, named UFAFormer, to address the DGM4 problem. By leveraging the discrete wavelet transform, we decompose images into several frequency sub-bands, capturing rich face forgery artifacts. Our proposed frequency encoder, incorporating intra-band and inter-band self-attentions, explicitly aggregates forgery features within and across diverse sub-bands.
  arXiv  Detail & Related papers  (2023-09-18T11:06:42Z)
• VERITE: A Robust Benchmark for Multimodal Misinformation Detection Accounting for Unimodal Bias [17.107961913114778]
  multimodal misinformation is a growing problem on social media platforms. In this study, we investigate and identify the presence of unimodal bias in widely-used MMD benchmarks. We introduce a new method -- termed Crossmodal HArd Synthetic MisAlignment (CHASMA) -- for generating realistic synthetic training data.
  arXiv  Detail & Related papers  (2023-04-27T12:28:29Z)
• UNetFormer: A Unified Vision Transformer Model and Pre-Training Framework for 3D Medical Image Segmentation [14.873473285148853]
  We introduce a unified framework consisting of two architectures, dubbed UNetFormer, with a 3D Swin Transformer-based encoder and Conal Neural Network (CNN) and transformer-based decoders. In the proposed model, the encoder is linked to the decoder via skip connections at five different resolutions with deep supervision. We present a methodology for self-supervised pre-training of the encoder backbone via learning to predict randomly masked tokens.
  arXiv  Detail & Related papers  (2022-04-01T17:38:39Z)

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.