Liu Feng-Yu, Chen Chih-Chi, Cheng Chi-Tung, Wu Cheng-Ta, Hsu Chih-Po, Fu Chih-Yuan, Chen Shann-Ching, Liao Chien-Hung, Lee Mel S
Compal Electronics, Smart Device Business Group, Taipei 114, Taiwan.
Department of Physical Medicine and Rehabilitation, Chang Gung Memorial Hospital, Chang Gung University, Linkou, Taoyuan 333, Taiwan.
J Pers Med. 2021 Jun 7;11(6):522. doi: 10.3390/jpm11060522.
Automated detection of the region of interest (ROI) is a critical step in the two-step classification system in several medical image applications. However, key information such as model parameter selection, image annotation rules, and ROI confidence score are essential but usually not reported. In this study, we proposed a practical framework of ROI detection by analyzing hip joints seen on 7399 anteroposterior pelvic radiographs (PXR) from three diverse sources. We presented a deep learning-based ROI detection framework utilizing a single-shot multi-box detector with a customized head structure based on the characteristics of the obtained datasets. Our method achieved average intersection over union (IoU) = 0.8115, average confidence = 0.9812, and average precision with threshold IoU = 0.5 (AP50) = 0.9901 in the independent testing set, suggesting that the detected hip regions appropriately covered the main features of the hip joints. The proposed approach featured flexible loose-fitting labeling, customized model design, and heterogeneous data testing. We demonstrated the feasibility of training a robust hip region detector for PXRs. This practical framework has a promising potential for a wide range of medical image applications.
在多个医学图像应用的两步分类系统中，自动检测感兴趣区域（ROI）是关键步骤。然而，诸如模型参数选择、图像标注规则和ROI置信度得分等关键信息至关重要，但通常未被报告。在本研究中，我们通过分析来自三个不同来源的7399张前后位骨盆X线片（PXR）上的髋关节，提出了一种实用的ROI检测框架。我们提出了一种基于深度学习的ROI检测框架，该框架利用单发多框检测器，并根据所得数据集的特征采用定制的头部结构。在独立测试集中，我们的方法实现了平均交并比（IoU）= 0.8115、平均置信度 = 0.9812以及阈值IoU = 0.5时的平均精度（AP50）= 0.9901，这表明检测到的髋关节区域恰当地覆盖了髋关节的主要特征。所提出的方法具有灵活的宽松标注、定制模型设计和异构数据测试的特点。我们证明了为PXR训练一个强大的髋关节区域检测器的可行性。这个实用框架在广泛的医学图像应用中具有广阔的潜力。
