{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T09:25:17Z","timestamp":1787045117501,"version":"build-2736575974"},"reference-count":45,"publisher":"IOP Publishing","issue":"16","license":[{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Key Scientific Research Project of the Henan Provincial Department of Science and Technology","award":["252102210081"],"award-info":[{"award-number":["252102210081"]}]},{"name":"Key Scientific Research Project of Higher Education Institutions in Henan Province","award":["26B520060"],"award-info":[{"award-number":["26B520060"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2026,8,28]]},"abstract":"Abstract<\/jats:title>\n \n Objective.<\/jats:italic>\n Chest x-ray (CXR) imaging is widely used for screening thoracic diseases. However, accurate multi-disease detection remains challenging because lesion sizes vary substantially, multiple abnormalities often coexist, and small or low-contrast lesions can be obscured by anatomical structures. This study aims to improve multi-disease detection in CXR images by enhancing multi-scale lesion representation and cross-level feature consistency.\n Approach.<\/jats:italic>\n We propose a CXR multi-disease detection framework based on multi-scale parallel perception and adaptive feature fusion. The Multi-scale Parallel Feature Sensing module captures complementary lesion features under different receptive fields. The Smooth Residual Fusion Block refines lesion-related spatial responses and suppresses irrelevant background interference. The adaptive pyramid feature fusion module dynamically integrates multi-level features to reduce semantic discrepancies and preserve fine-grained lesion details.\n Main results.<\/jats:italic>\n On the VinDr-CXR dataset, the proposed method achieved mean Average Precision scores of 0.389 for\n \n \n \n <\/jats:tex-math>\n \n \n mAP<\/mml:mtext>\n \n @<\/mml:mo>\n <\/mml:mrow>\n 0.5<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n and 0.186 for\n \n \n \n <\/jats:tex-math>\n \n \n mAP<\/mml:mtext>\n \n @<\/mml:mo>\n <\/mml:mrow>\n [<\/mml:mo>\n 0.5<\/mml:mn>\n :<\/mml:mo>\n 0.95<\/mml:mn>\n ]<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n , corresponding to absolute improvements of 5.3% and 1.9% points over the baseline, respectively. The gains were particularly evident for small and subtle abnormalities, such as nodules\/masses and pneumothorax. Additional validation on the bounding-box annotated subset of ChestX-ray8 further confirmed robustness, with\n \n \n \n <\/jats:tex-math>\n \n \n mAP<\/mml:mtext>\n \n @<\/mml:mo>\n <\/mml:mrow>\n 0.5<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n ,\n \n \n \n <\/jats:tex-math>\n \n \n mAP<\/mml:mtext>\n \n @<\/mml:mo>\n <\/mml:mrow>\n [<\/mml:mo>\n 0.5<\/mml:mn>\n :<\/mml:mo>\n 0.95<\/mml:mn>\n ]<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n , and Recall values of 0.186, 0.093, and 0.240, respectively.\n Significance.<\/jats:italic>\n The proposed framework provides an effective solution for structurally consistent multi-disease detection in CXR images. Results on two public datasets suggest that multi-scale parallel perception and adaptive feature fusion improve lesion localization robustness, showing potential as a supportive tool for computer-aided screening workflows.\n <\/jats:p>","DOI":"10.1088\/1361-6560\/ae970f","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T08:32:51Z","timestamp":1787041971000},"page":"165004","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-scale parallel perception and adaptive feature fusion for chest x-ray multi-disease detection"],"prefix":"10.1088","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6470-7736","authenticated-orcid":true,"given":"Chengkang","family":"Liu","sequence":"first","affiliation":[{"name":"Zhengzhou University of Science and Technology"},{"name":"Zhengzhou University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2713-5727","authenticated-orcid":false,"given":"Yubo","family":"Yuan","sequence":"additional","affiliation":[{"name":"Zhengzhou University of Science and Technology"},{"name":"Zhengzhou University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3202-8592","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhengzhou University of Science and Technology"},{"name":"Zhengzhou University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3148-5874","authenticated-orcid":true,"given":"Qingwen","family":"Feng","sequence":"additional","affiliation":[{"name":"Zhengzhou University of Science and Technology"},{"name":"Zhengzhou University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhengzhou University of Science and Technology"},{"name":"Zhengzhou University of Science and Technology"},{"name":"Zhengzhou University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhengzhou University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danhui","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhengzhou University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,8,18]]},"reference":[{"key":"pmbae970fbib1","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1038\/s41746-021-00438-z","type":"journal-article","article-title":"Diagnostic accuracy of deep learning in medical imaging: a systematic review and meta-analysis","volume":"4","author":"Aggarwal","year":"2021","journal-title":"npj Digit. Med."},{"key":"pmbae970fbib2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.104126","type":"journal-article","article-title":"ALCNN: attention based lightweight convolutional neural network for pneumothorax detection in chest x-rays","volume":"79","author":"Agrawal","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"pmbae970fbib3","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-16422-6","type":"journal-article","article-title":"Dual-model approach for accurate chest disease detection using GViT and swin transformer V2","volume":"15","author":"Ahmad","year":"2025","journal-title":"Sci. Rep."},{"key":"pmbae970fbib4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122810","type":"journal-article","article-title":"Automated and reliable detection of multi-diseases on chest x-ray images using optimized ensemble transfer learning","volume":"246","author":"Balmuri","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"pmbae970fbib5","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2025.108118","type":"journal-article","article-title":"A hybrid deep learning approach using xceptionnet and vision transformer for accurate chest disease detection from x-ray images","volume":"110","author":"Bhuvanya","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"pmbae970fbib6","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/s42600-025-00423-5","type":"journal-article","article-title":"Multi-instanceriemannian residual neural network with mountaineering team-based chest disease detection using chest x-ray images","volume":"41","author":"Egala","year":"2025","journal-title":"Res. Biomed. Eng."},{"key":"pmbae970fbib7","first-page":"pp 1174","type":"conference-proceedings","article-title":"Computer aided diagnosis CAD tool for lung and thoracic pathologies detection from chest x-ray images","author":"Fathallah","year":"2025"},{"key":"pmbae970fbib8","doi-asserted-by":"publisher","first-page":"156003","DOI":"10.1109\/ACCESS.2024.3482102","type":"journal-article","article-title":"YOLO-CXR: a novel detection network for locating multiple small lesions in chest x-ray images","volume":"12","author":"Hao","year":"2024","journal-title":"IEEE Access"},{"key":"pmbae970fbib9","first-page":"pp 7132","type":"conference-proceedings","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018"},{"key":"pmbae970fbib10","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.127929","type":"journal-article","article-title":"Localization and classification of abnormalities on chest x-ray images using a mamba-yolovx model","volume":"284","author":"Khalili","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"pmbae970fbib11","doi-asserted-by":"publisher","first-page":"97417","DOI":"10.1109\/ACCESS.2024.3428446","type":"journal-article","article-title":"Tuberculosis detection from chest x-ray image modalities based on transformer and convolutional neural network","volume":"12","author":"Kotei","year":"2024","journal-title":"IEEE Access"},{"key":"pmbae970fbib12","doi-asserted-by":"publisher","first-page":"14105","DOI":"10.1109\/ACCESS.2023.3243845","type":"journal-article","article-title":"Learning from multiple expert annotators for enhancing anomaly detection in medical image analysis","volume":"11","author":"Le","year":"2023","journal-title":"IEEE Access"},{"key":"pmbae970fbib13","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-97187-w","type":"journal-article","article-title":"Lung nodule detection using a multi-scale convolutional neural network and global channel spatial attention mechanisms","volume":"15","author":"Li","year":"2025","journal-title":"Sci. Rep."},{"key":"pmbae970fbib14","doi-asserted-by":"publisher","first-page":"1489","DOI":"10.1109\/TPAMI.2022.3164083","type":"journal-article","article-title":"Contextual transformer networks for visual recognition","volume":"45","author":"Li","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"pmbae970fbib15","doi-asserted-by":"publisher","first-page":"1730","DOI":"10.3934\/mbe.2023079","type":"journal-article","article-title":"Lesion detection of chest x-ray based on scalable attention residual CNN","volume":"20","author":"Lin","year":"2023","journal-title":"Math. Biosci. Eng."},{"key":"pmbae970fbib16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2022\/4182191","type":"journal-article","article-title":"CXR-RefineDet: single-shot refinement neural network for chest x-ray radiograph based on multiple lesions detection","volume":"2022","author":"Lin","year":"2022","journal-title":"J. Healthc. Eng."},{"key":"pmbae970fbib17","doi-asserted-by":"publisher","first-page":"293","DOI":"10.3390\/jimaging11090293","type":"journal-article","article-title":"Colorectal Polyp segmentation based on deep learning methods: a systematic review","volume":"11","author":"Liu","year":"2025","journal-title":"J. Imaging"},{"key":"pmbae970fbib18","first-page":"pp 8786","type":"conference-proceedings","article-title":"A lung lesion detection algorithm based on YOLOv7 and self-attention mechanism","author":"Luo","year":"2023"},{"key":"pmbae970fbib19","doi-asserted-by":"publisher","first-page":"63017","DOI":"10.1007\/s11042-023-18065-z","type":"journal-article","article-title":"Federated learning with deep convolutional neural networks for the detection of multiple chest diseases using chest x-rays","volume":"83","author":"Malik","year":"2024","journal-title":"Multimed. Tools Appl."},{"key":"pmbae970fbib20","first-page":"pp 69","author":"Mohd Redzwan","year":"2024","type":"book"},{"key":"pmbae970fbib21","doi-asserted-by":"publisher","DOI":"10.1016\/j.irbm.2025.100912","type":"journal-article","article-title":"Transformer-based rt-detr framework for accurate chest x-ray disease detection","volume":"46","author":"Mutukuru","year":"2025","journal-title":"IRBM"},{"key":"pmbae970fbib22","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1007\/s00521-022-07258-6","type":"journal-article","article-title":"Tuberculosis detection in chest radiograph using convolutional neural network architecture and explainable artificial intelligence","volume":"36","author":"Nafisah","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"pmbae970fbib23","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1038\/s41597-022-01498-w","type":"journal-article","article-title":"VinDr-CXR: an open dataset of chest x-rays with radiologist\u2019s annotations","volume":"9","author":"Nguyen","year":"2022","journal-title":"Sci. Data"},{"key":"pmbae970fbib24","doi-asserted-by":"publisher","DOI":"10.13026\/3akn-b287","type":"dataset","article-title":"VinDr-CXR: An open dataset of chest X-rays with radiologist annotations","author":"Nguyen","year":"2021","unstructured":"Nguyen Ha Quy Lam Khanh Le Long Tuan Pham Hieu Huy Tran Duy Quang 2021 VinDr-CXR: An open dataset of chest X-rays with radiologist annotations PhysioNet 10.13026\/3akn-b287"},{"key":"pmbae970fbib25","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiolchem.2025.108620","type":"journal-article","article-title":"BM3D filtering with ensemble hilbert-huang transform and spiking neural networks for cardiomegaly detection in chest radiographs","volume":"120","author":"Patel","year":"2026","journal-title":"Comput. Biol. Chem."},{"key":"pmbae970fbib26","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105567","type":"journal-article","article-title":"Hybrid framework for respiratory lung diseases detection based on classical cnn and quantum classifiers from chest x-rays","volume":"88","author":"Rao","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"pmbae970fbib27","first-page":"pp 608","type":"conference-proceedings","article-title":"Multiple disease detection using cnn based model from chest x-rays","author":"Seviappan","year":"2025"},{"key":"pmbae970fbib28","doi-asserted-by":"publisher","DOI":"10.1002\/mp.70003","type":"journal-article","article-title":"Multi-scale nested graph transformer with graph operations: advancing high-resolution chest x-ray classification","volume":"52","author":"Shan","year":"2025","journal-title":"Med. Phys."},{"key":"pmbae970fbib29","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102708","type":"journal-article","article-title":"Image synthesis with disentangled attributes for chest x-ray nodule augmentation and detection","volume":"84","author":"Shen","year":"2023","journal-title":"Med. Image Anal."},{"key":"pmbae970fbib30","doi-asserted-by":"publisher","first-page":"2487","DOI":"10.1038\/s41598-024-52703-2","type":"journal-article","article-title":"Efficient pneumonia detection using vision transformers on chest x-rays","volume":"14","author":"Singh","year":"2024","journal-title":"Sci. Rep."},{"key":"pmbae970fbib31","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122129","type":"journal-article","article-title":"Incremental learning-based cascaded model for detection and localization of tuberculosis from chest x-ray images","volume":"238","author":"Vats","year":"2024a","journal-title":"Expert Syst. Appl."},{"key":"pmbae970fbib32","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124464","type":"journal-article","article-title":"Iterative enhancement fusion-based cascaded model for detection and localization of multiple disease from cxr-images","volume":"255","author":"Vats","year":"2024b","journal-title":"Expert Syst. Appl."},{"key":"pmbae970fbib33","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1186\/s12880-022-00904-4","type":"journal-article","article-title":"Computer-aided diagnostic for classifying chest x-ray images using deep ensemble learning","volume":"22","author":"Visu\u00f1a","year":"2022","journal-title":"BMC Med. Imaging"},{"key":"pmbae970fbib34","first-page":"pp 1","author":"Wang","year":"2024","type":"book"},{"key":"pmbae970fbib35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.369","type":"dataset","article-title":"ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases","author":"Wang","year":"2017","unstructured":"Wang Xiaosong Peng Yifan Lu Le Lu Zhiyong Bagheri Mohammadhadi Summers Ronald M. 2017 ChestX-Ray8: Hospital-Scale Chest X-Ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases NIH Clinical Center 10.1109\/CVPR.2017.369"},{"key":"pmbae970fbib36","first-page":"pp 3462","type":"conference-proceedings","article-title":"ChestX-Ray8: hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases","author":"Wang","year":"2017"},{"key":"pmbae970fbib37","first-page":"pp 3","author":"Woo","year":"2018","type":"book"},{"key":"pmbae970fbib38","doi-asserted-by":"publisher","first-page":"2173","DOI":"10.1038\/s41598-022-06085-y","type":"journal-article","article-title":"Fused feature signatures to probe tumour radiogenomics relationships","volume":"12","author":"Xia","year":"2022","journal-title":"Sci. Rep."},{"key":"pmbae970fbib39","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107742","type":"journal-article","article-title":"DualAttNet: synergistic fusion of image-level and fine-grained disease attention for multi-label lesion detection in chest x-rays","volume":"168","author":"Xu","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"pmbae970fbib40","first-page":"pp 134","author":"Yang","year":"2024","type":"book"},{"key":"pmbae970fbib41","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.129553","type":"journal-article","article-title":"Learning diversified features for pulmonary hypertension detection using chest x-ray","volume":"298","author":"Yu","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"pmbae970fbib42","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0323239","type":"journal-article","article-title":"An optimized transformer model for efficient detection of thoracic diseases in chest x-rays with multi-scale feature fusion","volume":"20","author":"Yu","year":"2025","journal-title":"PLoS One"},{"key":"pmbae970fbib43","first-page":"pp 541","author":"Zhang","year":"2023","type":"book"},{"key":"pmbae970fbib44","first-page":"pp 1","type":"conference-proceedings","article-title":"CPGNet: multimodal graph learning with hierarchical category guidance for multi-label whole slide image classification","author":"Zhao","year":"2025"},{"key":"pmbae970fbib45","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2022.1079240","type":"journal-article","article-title":"Editorial: weakly supervised deep learning-based methods for brain image analysis","volume":"16","author":"Zhu","year":"2022","journal-title":"Front. Neuroinf."}],"container-title":["Physics in Medicine & Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae970f","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae970f\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae970f\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae970f\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T08:32:53Z","timestamp":1787041973000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae970f"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,18]]},"references-count":45,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8,18]]},"published-print":{"date-parts":[[2026,8,28]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ae970f","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,18]]},"assertion":[{"value":"Multi-scale parallel perception and adaptive feature fusion for chest x-ray multi-disease detection","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-04-07","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-08-07","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-08-18","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}