Shi Yin1, Qinmu Peng2, Hongming Li3, Zhengqiang Zhang2, Xinge You2, Katherine Fischer4, Susan L Furth5, Yong Fan6, Gregory E Tasian7. 1. School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China; Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA. 2. School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China. 3. Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA. 4. Department of Surgery, Division of Pediatric Urology, The Children's Hospital of Philadelphia, Philadelphia, PA; Center for Pediatric Clinical Effectiveness, The Children's Hospital of Philadelphia, Philadelphia, PA. 5. Department of Pediatrics, Division of Pediatric Nephrology, The Children's Hospital of Philadelphia, Philadelphia, PA. 6. Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA. Electronic address: yong.fan@uphs.upenn.edu. 7. Department of Surgery, Division of Pediatric Urology, The Children's Hospital of Philadelphia, Philadelphia, PA; Center for Pediatric Clinical Effectiveness, The Children's Hospital of Philadelphia, Philadelphia, PA; Department of Biostatistics, Epidemiology, and Informatics, The University of Pennsylvania, Philadelphia, PA.
Abstract
OBJECTIVE: To reliably and quickly diagnose children with posterior urethral valves (PUV), we developed a multi-instance deep learning method to automate image analysis. METHODS: We built a robust pattern classifier to distinguish 86 children with PUV from 71 children with mild unilateral hydronephrosis based on ultrasound images (3504 in sagittal view and 2558 in transverse view) obtained during routine clinical care. RESULTS: The multi-instance deep learning classifier performed better than classifiers built on either single sagittal images or single transverse images. Particularly, the deep learning classifiers built on single images in the sagittal view and single images in the transverse view obtained area under the receiver operating characteristic curve (AUC) values of 0.796 ± 0.064 and 0.815 ± 0.071, respectively. AUC values of the multi-instance deep learning classifiers built on images in the sagittal and transverse views with mean pooling operation were 0.949 ± 0.035 and 0.954 ± 0.033, respectively. The multi-instance deep learning classifiers built on images in both the sagittal and transverse views with a mean pooling operation obtained an AUC of 0.961 ± 0.026 with a classification rate of 0.925 ± 0.060, specificity of 0.986 ± 0.032, and sensitivity of 0.873 ± 0.120, respectively. Discriminative regions of the kidney located using classification activation mapping demonstrated that the deep learning techniques could identify meaningful anatomical features from ultrasound images. CONCLUSION: The multi-instance deep learning method provides an automatic and accurate means to extract informative features from ultrasound images and discriminate infants with PUV from male children with unilateral hydronephrosis.
OBJECTIVE: To reliably and quickly diagnose children with posterior urethral valves (PUV), we developed a multi-instance deep learning method to automate image analysis. METHODS: We built a robust pattern classifier to distinguish 86 children with PUV from 71 children with mild unilateral hydronephrosis based on ultrasound images (3504 in sagittal view and 2558 in transverse view) obtained during routine clinical care. RESULTS: The multi-instance deep learning classifier performed better than classifiers built on either single sagittal images or single transverse images. Particularly, the deep learning classifiers built on single images in the sagittal view and single images in the transverse view obtained area under the receiver operating characteristic curve (AUC) values of 0.796 ± 0.064 and 0.815 ± 0.071, respectively. AUC values of the multi-instance deep learning classifiers built on images in the sagittal and transverse views with mean pooling operation were 0.949 ± 0.035 and 0.954 ± 0.033, respectively. The multi-instance deep learning classifiers built on images in both the sagittal and transverse views with a mean pooling operation obtained an AUC of 0.961 ± 0.026 with a classification rate of 0.925 ± 0.060, specificity of 0.986 ± 0.032, and sensitivity of 0.873 ± 0.120, respectively. Discriminative regions of the kidney located using classification activation mapping demonstrated that the deep learning techniques could identify meaningful anatomical features from ultrasound images. CONCLUSION: The multi-instance deep learning method provides an automatic and accurate means to extract informative features from ultrasound images and discriminate infants with PUV from male children with unilateral hydronephrosis.
Authors: Shi Yin; Qinmu Peng; Hongming Li; Zhengqiang Zhang; Xinge You; Katherine Fischer; Susan L Furth; Gregory E Tasian; Yong Fan Journal: Med Image Anal Date: 2019-11-08 Impact factor: 8.545
Authors: Caleb P Nelson; Richard S Lee; Andrew T Trout; Sabah Servaes; Kate H Kraft; Carol E Barnewolt; Tanya Logvinenko; Jeanne S Chow Journal: J Urol Date: 2019-06 Impact factor: 7.450
Authors: Shi Yin; Zhengqiang Zhang; Hongming Li; Qinmu Peng; Xinge You; Susan L Furth; Gregory E Tasian; Yong Fan Journal: Proc IEEE Int Symp Biomed Imaging Date: 2019-07-11
Authors: Jose E Pulido; Susan L Furth; Stephen A Zderic; Douglas A Canning; Gregory E Tasian Journal: Clin J Am Soc Nephrol Date: 2013-12-05 Impact factor: 8.237
Authors: Jennifer L Dodson; Judith V Jerry-Fluker; Derek K Ng; Marva Moxey-Mims; George J Schwartz; Vikas R Dharnidharka; Bradley A Warady; Susan L Furth Journal: J Urol Date: 2011-10 Impact factor: 7.450