CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning

• URL: http://arxiv.org/abs/2504.13820v1
• Date: Fri, 18 Apr 2025 17:50:43 GMT
• Title: CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning
• Authors: Yang Yue, Yulin Wang, Chenxin Tao, Pan Liu, Shiji Song, Gao Huang,
• Abstract summary: We present CheXWorld, the first effort towards a self-supervised world model for radiographic images.<n>Our work develops a unified framework that simultaneously models three aspects of medical knowledge essential for qualified radiologists.
• Score: 76.98039909663756
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Humans can develop internal world models that encode common sense knowledge, telling them how the world works and predicting the consequences of their actions. This concept has emerged as a promising direction for establishing general-purpose machine-learning models in recent preliminary works, e.g., for visual representation learning. In this paper, we present CheXWorld, the first effort towards a self-supervised world model for radiographic images. Specifically, our work develops a unified framework that simultaneously models three aspects of medical knowledge essential for qualified radiologists, including 1) local anatomical structures describing the fine-grained characteristics of local tissues (e.g., architectures, shapes, and textures); 2) global anatomical layouts describing the global organization of the human body (e.g., layouts of organs and skeletons); and 3) domain variations that encourage CheXWorld to model the transitions across different appearance domains of radiographs (e.g., varying clarity, contrast, and exposure caused by collecting radiographs from different hospitals, devices, or patients). Empirically, we design tailored qualitative and quantitative analyses, revealing that CheXWorld successfully captures these three dimensions of medical knowledge. Furthermore, transfer learning experiments across eight medical image classification and segmentation benchmarks showcase that CheXWorld significantly outperforms existing SSL methods and large-scale medical foundation models. Code & pre-trained models are available at https://github.com/LeapLabTHU/CheXWorld.

Related papers

• A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis [48.84443450990355]
  Deep networks have achieved broad success in analyzing natural images, when applied to medical scans, they often fail in unexcepted situations. We investigate this challenge and focus on model sensitivity to domain shifts, such as data sampled from different hospitals or data confounded by demographic variables such as sex, race, etc, in the context of chest X-rays and skin lesion images. Taking inspiration from medical training, we propose giving deep networks a prior grounded in explicit medical knowledge communicated in natural language.
  arXiv  Detail & Related papers  (2024-05-23T17:55:02Z)
• DeViDe: Faceted medical knowledge for improved medical vision-language pre-training [1.6567372257085946]
  Vision-language pre-training for chest X-rays has made significant strides, primarily by utilizing paired radiographs and radiology reports. We propose DeViDe, a transformer-based method that leverages radiographic descriptions from the open web. DeViDe incorporates three key features for knowledge-augmented vision language alignment: First, a large-language model-based augmentation is employed to homogenise medical knowledge from diverse sources. In zero-shot settings, DeViDe performs comparably to fully supervised models on external datasets and achieves state-of-the-art results on three large-scale datasets.
  arXiv  Detail & Related papers  (2024-04-04T17:40:06Z)
• Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Data [66.9359934608229]
  This study aims to initiate the development of Radiology Foundation Model, termed as RadFM. To the best of our knowledge, this is the first large-scale, high-quality, medical visual-language dataset, with both 2D and 3D scans. We propose a new evaluation benchmark, RadBench, that comprises five tasks, including modality recognition, disease diagnosis, visual question answering, report generation and rationale diagnosis.
  arXiv  Detail & Related papers  (2023-08-04T17:00:38Z)
• Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation [38.61227663176952]
  We propose a shift towards universal medical image segmentation, a paradigm aiming to build medical image understanding foundation models. We develop Hermes, a novel context-prior learning approach to address the challenges of data heterogeneity and annotation differences in medical image segmentation.
  arXiv  Detail & Related papers  (2023-06-04T17:39:08Z)
• Act Like a Radiologist: Radiology Report Generation across Anatomical Regions [50.13206214694885]
  X-RGen is a radiologist-minded report generation framework across six anatomical regions. In X-RGen, we seek to mimic the behaviour of human radiologists, breaking them down into four principal phases. We enhance the recognition capacity of the image encoder by analysing images and reports across various regions.
  arXiv  Detail & Related papers  (2023-05-26T07:12:35Z)
• Medical Image Captioning via Generative Pretrained Transformers [57.308920993032274]
  We combine two language models, the Show-Attend-Tell and the GPT-3, to generate comprehensive and descriptive radiology records. The proposed model is tested on two medical datasets, the Open-I, MIMIC-CXR, and the general-purpose MS-COCO.
  arXiv  Detail & Related papers  (2022-09-28T10:27:10Z)
• Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels [54.58539616385138]
  We introduce a novel semi-supervised 2D medical image segmentation framework termed Mine yOur owN Anatomy (MONA) First, prior work argues that every pixel equally matters to the model training; we observe empirically that this alone is unlikely to define meaningful anatomical features. Second, we construct a set of objectives that encourage the model to be capable of decomposing medical images into a collection of anatomical features.
  arXiv  Detail & Related papers  (2022-09-27T15:50:31Z)
• Multi-view Local Co-occurrence and Global Consistency Learning Improve Mammogram Classification Generalisation [23.51938491048481]
  We propose a new multi-view global-local analysis method that mimics the radiologist's reading procedure. Our model outperforms competing methods in terms of classification accuracy and generalisation.
  arXiv  Detail & Related papers  (2022-09-21T16:29:01Z)
• Self-Supervised Representation Learning using Visual Field Expansion on Digital Pathology [7.568373895297608]
  A key challenge in the analysis of such images is their size, which can run into the gigapixels. We propose a novel generative framework that can learn powerful representations for such tiles by learning to plausibly expand their visual field. Our model learns to generate different tissue types with fine details, while simultaneously learning powerful representations that can be used for different clinical endpoints.
  arXiv  Detail & Related papers  (2021-09-07T19:20:01Z)
• Image Embedding and Model Ensembling for Automated Chest X-Ray Interpretation [0.0]
  We present and study several machine learning approaches to develop automated Chest X-ray diagnostic models. In particular, we trained several Convolutional Neural Networks (CNN) on the CheXpert dataset. We used the trained CNNs to compute embeddings of the CXR images, in order to train two sets of tree-based classifiers from them.
  arXiv  Detail & Related papers  (2021-05-05T14:48:59Z)
• CS2-Net: Deep Learning Segmentation of Curvilinear Structures in Medical Imaging [90.78899127463445]
  We propose a generic and unified convolution neural network for the segmentation of curvilinear structures. We introduce a new curvilinear structure segmentation network (CS2-Net), which includes a self-attention mechanism in the encoder and decoder.
  arXiv  Detail & Related papers  (2020-10-15T03:06:37Z)

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.