A fast and effective detection framework for whole-slide histopathology image analysis

被引:5
|
作者
Ruan, Jun [1 ]
Zhu, Zhikui [1 ]
Wu, Chenchen [1 ]
Ye, Guanglu [1 ]
Zhou, Jingfan [1 ]
Yue, Junqiu [1 ,2 ]
机构
[1] Wuhan Univ Technol, Sch Informat Engn, Wuhan, Peoples R China
[2] Huazhong Univ Sci & Technol, Hubei Canc Hosp, Tongji Med Coll, Dept Pathol, Wuhan, Peoples R China
来源
PLOS ONE | 2021年 / 16卷 / 05期
基金
中国国家自然科学基金;
关键词
COMPUTATIONAL PATHOLOGY; CLASSIFICATION; SEGMENTATION;
D O I
10.1371/journal.pone.0251521
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
Pathologists generally pan, focus, zoom and scan tissue biopsies either under microscopes or on digital images for diagnosis. With the rapid development of whole-slide digital scanners for histopathology, computer-assisted digital pathology image analysis has attracted increasing clinical attention. Thus, the working style of pathologists is also beginning to change. Computer-assisted image analysis systems have been developed to help pathologists perform basic examinations. This paper presents a novel lightweight detection framework for automatic tumor detection in whole-slide histopathology images. We develop the Double Magnification Combination (DMC) classifier, which is a modified DenseNet-40 to make patch-level predictions with only 0.3 million parameters. To improve the detection performance of multiple instances, we propose an improved adaptive sampling method with superpixel segmentation and introduce a new heuristic factor, local sampling density, as the convergence condition of iterations. In postprocessing, we use a CNN model with 4 convolutional layers to regulate the patch-level predictions based on the predictions of adjacent sampling points and use linear interpolation to generate a tumor probability heatmap. The entire framework was trained and validated using the dataset from the Camelyon16 Grand Challenge and Hubei Cancer Hospital. In our experiments, the average AUC was 0.95 in the test set for pixel-level detection.
引用
收藏
页数:22
相关论文
共 50 条
  • [31] Identification of "BRAF-Positive" Cases Based on Whole-Slide Image Analysis
    Popovici, Vlad
    Krenek, Ales
    Budinska, Eva
    [J]. BIOMED RESEARCH INTERNATIONAL, 2017, 2017
  • [32] High-throughput adaptive sampling for whole-slide histopathology image analysis (HASHI) via convolutional neural networks: Application to invasive breast cancer detection
    Cruz-Roa, Angel
    Gilmore, Hannah
    Basavanhally, Ajay
    Feldman, Michael
    Ganesan, Shridar
    Shih, Natalie
    Tomaszewski, John
    Madabhushi, Anant
    Gonzalez, Fabio
    [J]. PLOS ONE, 2018, 13 (05):
  • [33] FAST TUMOR DETECTOR IN WHOLE-SLIDE IMAGE WITH DYNAMIC PROGRAMING BASED MONTE CARLO SAMPLING
    Ke, Jing
    Shen, Yiqing
    Guo, Yi
    Liang, Xiaoyao
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2020, : 2471 - 2475
  • [34] Integration of Deep Learning and Graph Theory for Analyzing Histopathology Whole-slide Images
    Jung, Hyun
    Suloway, Christian
    Miao, Tianyi
    Edmondson, Elijah F.
    Morcock, David R.
    Deleage, Claire
    Liu, Yanling
    Collins, Jack R.
    Lisle, Curtis
    [J]. 2018 IEEE APPLIED IMAGERY PATTERN RECOGNITION WORKSHOP (AIPR), 2018,
  • [35] A Comparative Study of CNN and FCN for Histopathology Whole Slide Image Analysis
    Sun, Shujiao
    Jiang, Bonan
    Zheng, Yushan
    Xie, Fengying
    [J]. IMAGE AND GRAPHICS, ICIG 2019, PT II, 2019, 11902 : 558 - 567
  • [36] Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learning
    Chan, Tsai Hor
    Cendra, Fernando Julio
    Ma, Lan
    Yin, Guosheng
    Yu, Lequan
    [J]. 2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2023, : 15661 - 15670
  • [37] Accurate diagnosis of lymphoma on whole-slide histopathology images using deep learning
    Syrykh, Charlotte
    Abreu, Arnaud
    Amara, Nadia
    Siegfried, Aurore
    Maisongrosse, Veronique
    Frenois, Francois X.
    Martin, Laurent
    Rossi, Cedric
    Laurent, Camille
    Brousset, Pierre
    [J]. NPJ DIGITAL MEDICINE, 2020, 3 (01)
  • [38] Accurate diagnosis of lymphoma on whole-slide histopathology images using deep learning
    Charlotte Syrykh
    Arnaud Abreu
    Nadia Amara
    Aurore Siegfried
    Véronique Maisongrosse
    François X. Frenois
    Laurent Martin
    Cédric Rossi
    Camille Laurent
    Pierre Brousset
    [J]. npj Digital Medicine, 3
  • [39] The whole slide breast histopathology image detection based on a fused model and heatmaps
    Zhang, Xueqin
    Liu, Chang
    Li, Tianren
    Zhou, Yunlan
    [J]. BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2023, 82
  • [40] Privacy risks of whole-slide image sharing in digital pathology
    Petr Holub
    Heimo Müller
    Tomáš Bíl
    Luca Pireddu
    Markus Plass
    Fabian Prasser
    Irene Schlünder
    Kurt Zatloukal
    Rudolf Nenutil
    Tomáš Brázdil
    [J]. Nature Communications, 14