Wireless capsule endoscopy (WCE) is a recently developed tool that allows for the painless and non-invasive examination of the entire gastrointestinal (GI) tract. The microcamera captures a large number of redundant frames for each WCE examination such that a video summarization technique is needed to assist in diagnosis. However, prevalent methods of summarizing WCE videos focus only on the representativeness of the frames owing to a lack of high-level information on their importance. This paper develops a Frame Importance-Assisted Sparse Subset Selection model, called FIAS3, to integrate the high-level frame importance from networks into a sparse subset selection model. The FIAS3 is optimized under three constraints: 1) a frame importance matrix to help pay more attention to important frames, 2) a sparsity constraint to make video summaries more compact, and 3) a similarity-inhibiting constraint to reduce redundancy. The results of experiments on a public dataset demonstrated that our FIAS3 outperforms other methods of summarizing WCE videos. Specifically, its coverage and video reconstruction error were 92% and 0.143, respectively, at a 90% compression ratio, recording respective at least 16.9% and 0.031 improvements over other methods. The results of generalization experiments showed that FIAS3 also achieves competitive results on private datasets. INDEX TERMSComputer-aided diagnosis, deep learning, keyframe extraction, video summarization, wireless capsule endoscopy (WCE).

Locating lung field is a critical and fundamental processing stage in the automated analysis of chest radiographs (CXRs) for pulmonary disorders. During the routine examination of CXRs, using both frontal and lateral CXRs can benefit clinical diagnosis of cardiothoracic and lung diseases. However, the accurate segmentation of lung fields on both frontal and lateral CXRs is still challenging due to the blurry boundary of the lung field on lateral CXRs and the poor generalization ability of the models. Existing deep learning-based methods focused on lung field segmentation on frontal CXRs, and the generalization ability of these methods on the different type of CXRs (e.g., pediatric CXRs) and new lung diseases (e.g., COVID-19) has not been tested. In this paper, a view identification assisted fully convolutional network (VI-FCN) is proposed for the segmentation of lung fields on frontal and lateral CXRs simultaneously. The VI-FCN consists of an FCN branch for lung field segmentation and a view identification branch for identification of the frontal and lateral CXRs and for enhancing the lung field segmentation. To improve the generalization ability of VI-FCN, six public datasets and our frontal and lateral CXRs (over 2000 CXRs) were collected for training. The segmentation of lung fields on the Japanese Society of Radiological Technology (JSRT) dataset yields mean dice similarity coefficient (DSC) of 0.979 ± 0.008, mean Jaccard index (Ω) of 0.959 ± 0.016, and mean boundary distance (MBD) of 1.023 ± 0.487mm. Besides, the VI-FCN achieves mean DSC of 0.973 ± 0.010, mean Ω of 0.947 ± 0.018, and mean MBD of 1.923 ± 0.755mm for the segmentation of lung fields on our lateral CXRs. The experiments demonstrate the superior performance of the proposed VI-FCN over most of existing state-of-the-art methods. Moreover, the proposed VI-FCN achieves promising results on untrained pediatric CXRs and COVID-19 datasets.INDEX TERMS Chest radiographs, Lung field segmentation, Generalization ability, COVID-19.YUHUA XI received the Bachelor's degree in Biomedical Engineering from the Southern Medical University, Guangzhou, China, in 2018. She is currently pursuing the master of engineering degree with the Department of Biomedical Engineering, the Southern Medical University. Her research focuses on the segmentation of medical images and bone suppression in CXRs.