https://scholars.lib.ntu.edu.tw/handle/123456789/559168
標題: | A computer-aided diagnosis system for differentiation and delineation of malignant regions on whole-slide prostate histopathology image using spatial statistics and multidimensional DenseNet | 作者: | Chen, C.-M. Huang, Y.-S. Fang, P.-W. Liang, C.-W. RUEY-FENG CHANG |
關鍵字: | computer-aided diagnosis; deep learning; densely connected network; prostate cancer; whole-slide histopathology image | 公開日期: | 2020 | 卷: | 47 | 期: | 3 | 起(迄)頁: | 1021-1033 | 來源出版物: | Medical Physics | 摘要: | Purpose: Prostate cancer (PCa) is a major health concern in aging males, and proper management of the disease depends on accurately interpreting pathology specimens. However, reading prostatectomy histopathology slides, which is basically for staging, is usually time consuming and differs from reading small biopsy specimens, which is mainly used for diagnosis. Generally, each prostatectomy specimen generates tens of large tissue sections and for each section, the malignant region needs to be delineated to assess the amount of tumor and its burden. With the aim of reducing the workload of pathologists, in this study, we focus on developing a computer-aided diagnosis (CAD) system based on a densely connected convolutional neural network (DenseNet) for whole-slide histopathology images to outline the malignant regions. Methods: We use an efficient color normalization process based on ranklet transformation to automatically correct the intensity of the images. Additionally, we use spatial probability to segment the tissue structure regions for different tissue recognition patterns. Based on the segmentation, we incorporate a multidimensional structure into DenseNet to determine if a particular prostatic region is benign or malignant. Results: As demonstrated by the experimental results with a test set of 2,663 images from 32 whole-slide prostate histopathology images, our proposed system achieved 0.726, 0.6306, and 0.5209 in the average of the Dice coefficient, Jaccard similarity coefficient, and Boundary F1 score measures, respectively. Then, the accuracy, sensitivity, specificity, and the area under the ROC curve (AUC) of the proposed classification method were observed to be 95.0% (2544/2663), 96.7% (1210/1251), 93.9% (1334/1412), and 0.9831, respectively. Discussions: We provide a detailed discussion on how our proposed system demonstrates considerable improvement compared with similar methods considered in previous researches as well as how it can be used for delineating malignant regions. ? 2019 American Association of Physicists in Medicine |
URI: | https://www.scopus.com/inward/record.url?eid=2-s2.0-85077858638&partnerID=40&md5=8c1fb27a6b266682868773813c62a74f https://scholars.lib.ntu.edu.tw/handle/123456789/559168 |
ISSN: | 00942405 | DOI: | 10.1002/mp.13964 | SDG/關鍵字: | Calcium compounds; Computer aided instruction; Computer aided network analysis; Computer networks; Convolutional neural networks; Deep learning; Diseases; Pattern recognition; Phosphorus compounds; Tissue; Urology; Area under the ROC curve; Computer aided diagnosis systems; Computer Aided Diagnosis(CAD); Densely connected networks; Jaccard similarity coefficients; Multi-dimensional structure; Prostate cancers; whole-slide histopathology image; Computer aided diagnosis; Article; cancer classification; cancer epidemiology; computer assisted diagnosis; convolutional neural network; diagnostic test accuracy study; Gleason score; histopathology; human; human tissue; image analysis; male; predictive value; prostate cancer; prostate tumor; prostatectomy; sensitivity and specificity; tissue structure; tumor classification; tumor differentiation; diagnostic imaging; image processing; pathology; procedures; Diagnosis, Computer-Assisted; Humans; Image Processing, Computer-Assisted; Male; Neural Networks, Computer; Prostatic Neoplasms |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。