WristMIR: Coarse-to-Fine Region-Aware Retrieval of Pediatric Wrist Radiographs with Radiology Report-Driven Learning

• URL: http://arxiv.org/abs/2602.07872v2
• Date: Tue, 10 Feb 2026 11:05:17 GMT
• Title: WristMIR: Coarse-to-Fine Region-Aware Retrieval of Pediatric Wrist Radiographs with Radiology Report-Driven Learning
• Authors: Mert Sonmezer, Serge Vasylechko, Duygu Atasoy, Seyda Ertekin, Sila Kurugol,
• Abstract summary: WristMIR is a region-aware pediatric wrist radiograph retrieval framework.<n>It learns fine-grained, clinically meaningful image representations without any manual image-level annotations.
• Score: 0.39146761527401425
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Retrieving wrist radiographs with analogous fracture patterns is challenging because clinically important cues are subtle, highly localized and often obscured by overlapping anatomy or variable imaging views. Progress is further limited by the scarcity of large, well-annotated datasets for case-based medical image retrieval. We introduce WristMIR, a region-aware pediatric wrist radiograph retrieval framework that leverages dense radiology reports and bone-specific localization to learn fine-grained, clinically meaningful image representations without any manual image-level annotations. Using MedGemma-based structured report mining to generate both global and region-level captions, together with pre-processed wrist images and bone-specific crops of the distal radius, distal ulna, and ulnar styloid, WristMIR jointly trains global and local contrastive encoders and performs a two-stage retrieval process: (1) coarse global matching to identify candidate exams, followed by (2) region-conditioned reranking aligned to a predefined anatomical bone region. WristMIR improves retrieval performance over strong vision-language baselines, raising image-to-text Recall@5 from 0.82% to 9.35%. Its embeddings also yield stronger fracture classification (AUROC 0.949, AUPRC 0.953). In region-aware evaluation, the two-stage design markedly improves retrieval-based fracture diagnosis, increasing mean $F_1$ from 0.568 to 0.753, and radiologists rate its retrieved cases as more clinically relevant, with mean scores rising from 3.36 to 4.35. These findings highlight the potential of anatomically guided retrieval to enhance diagnostic reasoning and support clinical decision-making in pediatric musculoskeletal imaging. The source code is publicly available at https://github.com/quin-med-harvard-edu/WristMIR.

Related papers

• Unsupervised Machine Learning for Osteoporosis Diagnosis Using Singh Index Clustering on Hip Radiographs [0.0]
  Singh Index (SI) provides a straightforward, semi-quantitative means of osteoporosis diagnosis through plain hip radiographs. This study aims to automate SI identification from radiographs using machine learning algorithms.
  arXiv  Detail & Related papers  (2024-11-22T08:44:43Z)
• Content-Based Image Retrieval for Multi-Class Volumetric Radiology Images: A Benchmark Study [0.6249768559720122]
  We benchmark embeddings derived from pre-trained supervised models on medical images against embeddings derived from pre-trained unsupervised models on non-medical images. For volumetric image retrieval, we adopt a late interaction re-ranking method inspired by text matching.
  arXiv  Detail & Related papers  (2024-05-15T13:34:07Z)
• Beyond Images: An Integrative Multi-modal Approach to Chest X-Ray Report Generation [47.250147322130545]
  Image-to-text radiology report generation aims to automatically produce radiology reports that describe the findings in medical images. Most existing methods focus solely on the image data, disregarding the other patient information accessible to radiologists. We present a novel multi-modal deep neural network framework for generating chest X-rays reports by integrating structured patient data, such as vital signs and symptoms, alongside unstructured clinical notes.
  arXiv  Detail & Related papers  (2023-11-18T14:37:53Z)
• Local Contrastive Learning for Medical Image Recognition [0.0]
  Local Region Contrastive Learning (LRCLR) is a flexible fine-tuning framework that adds layers for significant image region selection and cross-modality interaction. Our results on an external validation set of chest x-rays suggest that LRCLR identifies significant local image regions and provides meaningful interpretation against radiology text.
  arXiv  Detail & Related papers  (2023-03-24T17:04:26Z)
• Significantly improving zero-shot X-ray pathology classification via fine-tuning pre-trained image-text encoders [50.689585476660554]
  We propose a new fine-tuning strategy that includes positive-pair loss relaxation and random sentence sampling. Our approach consistently improves overall zero-shot pathology classification across four chest X-ray datasets and three pre-trained models.
  arXiv  Detail & Related papers  (2022-12-14T06:04:18Z)
• 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)
• Radiomics-Guided Global-Local Transformer for Weakly Supervised Pathology Localization in Chest X-Rays [65.88435151891369]
  Radiomics-Guided Transformer (RGT) fuses textitglobal image information with textitlocal knowledge-guided radiomics information. RGT consists of an image Transformer branch, a radiomics Transformer branch, and fusion layers that aggregate image and radiomic information.
  arXiv  Detail & Related papers  (2022-07-10T06:32:56Z)
• Generative Residual Attention Network for Disease Detection [51.60842580044539]
  We present a novel approach for disease generation in X-rays using a conditional generative adversarial learning. We generate a corresponding radiology image in a target domain while preserving the identity of the patient. We then use the generated X-ray image in the target domain to augment our training to improve the detection performance.
  arXiv  Detail & Related papers  (2021-10-25T14:15:57Z)
• VinDr-SpineXR: A deep learning framework for spinal lesions detection and classification from radiographs [0.812774532310979]
  This work aims at developing and evaluating a deep learning-based framework, named VinDr-SpineXR, for the classification and localization of abnormalities from spine X-rays. We build a large dataset, comprising 10,468 spine X-ray images from 5,000 studies, each of which is manually annotated by an experienced radiologist with bounding boxes around abnormal findings in 13 categories. The VinDr-SpineXR is evaluated on a test set of 2,078 images from 1,000 studies, which is kept separate from the training set.
  arXiv  Detail & Related papers  (2021-06-24T11:45:44Z)
• Auxiliary Signal-Guided Knowledge Encoder-Decoder for Medical Report Generation [107.3538598876467]
  We propose an Auxiliary Signal-Guided Knowledge-Decoder (ASGK) to mimic radiologists' working patterns. ASGK integrates internal visual feature fusion and external medical linguistic information to guide medical knowledge transfer and learning.
  arXiv  Detail & Related papers  (2020-06-06T01:00:15Z)

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.