Med (New York, N.Y.) · 2026
A unified multi-task framework enables interpretable chest radiograph analysis.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Xu Lijian, Ni Ziyu, Liu Xinglong, Wang Xiaosong, Li Hongsheng, Zhang Shaoting
Аннотация
BACKGROUND: While multimodal deep learning has advanced medical imaging analysis, existing black-box systems may remain confined to isolated tasks, often overlooking the trust-sensitive nature of clinical diagnosis as a multi-task process.
METHODS: We propose IMT-CXR (interpretable multi-task transformer for chest X-ray analysis), a framework that emulates radiologists' diagnostic workflow through three evidence-driven stages: (1) disease recognition, (2) attribute characterization (e.g., size, location, and severity quantification), and (3) evidence-integrated report generation with traceable decision pathways. The framework employs a unified transformer architecture optimized via medical-domain instruction tuning, which sequentially executes four clinical tasks: multi-label disease classification, lesion localization, anatomical segmentation, and radiology report generation.
FINDINGS: Experimental validation demonstrates competitive performance on ten CXR benchmarks under direct inference and fine-tuning settings. In a blinded evaluation of 160 historical reports from four medical centers, three radiologists rated 66% of artificial intelligence (AI)-generated reports as comparable to or surpassing original clinical reports in diagnostic clarity, highlighting the framework's translational potential.
CONCLUSIONS: By establishing traceable diagnostic pathways from anatomical findings to conclusions, this work bridges the gap between AI technical metrics and clinical utility, advancing trustworthy AI systems in medical imaging.
FUNDING: This research was partially supported by the Centre for Perceptual and Interactive Intelligence (CPII) Ltd. under the Innovation and Technology Commission (ITC)'s InnoHK.
METHODS: We propose IMT-CXR (interpretable multi-task transformer for chest X-ray analysis), a framework that emulates radiologists' diagnostic workflow through three evidence-driven stages: (1) disease recognition, (2) attribute characterization (e.g., size, location, and severity quantification), and (3) evidence-integrated report generation with traceable decision pathways. The framework employs a unified transformer architecture optimized via medical-domain instruction tuning, which sequentially executes four clinical tasks: multi-label disease classification, lesion localization, anatomical segmentation, and radiology report generation.
FINDINGS: Experimental validation demonstrates competitive performance on ten CXR benchmarks under direct inference and fine-tuning settings. In a blinded evaluation of 160 historical reports from four medical centers, three radiologists rated 66% of artificial intelligence (AI)-generated reports as comparable to or surpassing original clinical reports in diagnostic clarity, highlighting the framework's translational potential.
CONCLUSIONS: By establishing traceable diagnostic pathways from anatomical findings to conclusions, this work bridges the gap between AI technical metrics and clinical utility, advancing trustworthy AI systems in medical imaging.
FUNDING: This research was partially supported by the Centre for Perceptual and Interactive Intelligence (CPII) Ltd. under the Innovation and Technology Commission (ITC)'s InnoHK.