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
  • [1] Collaborative Framework for a Whole-Slide Image Viewer
    Lebre, Rui
    Jesus, Rui
    Nunes, Pedro
    Costa, Carlos
    [J]. 2019 IEEE 32ND INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS), 2019, : 221 - 224
  • [2] ScanNet: A Fast and Dense Scanning Framework for Metastastic Breast Cancer Detection from Whole-Slide Image
    Lin, Huangjing
    Chen, Hao
    Dou, Qi
    Wang, Liansheng
    Qin, Jing
    Heng, Pheng-Ann
    [J]. 2018 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2018), 2018, : 539 - 546
  • [3] A generalized deep learning framework for whole-slide image segmentation and analysis
    Khened, Mahendra
    Kori, Avinash
    Rajkumar, Haran
    Krishnamurthi, Ganapathy
    Srinivasan, Balaji
    [J]. SCIENTIFIC REPORTS, 2021, 11 (01)
  • [4] A generalized deep learning framework for whole-slide image segmentation and analysis
    Mahendra Khened
    Avinash Kori
    Haran Rajkumar
    Ganapathy Krishnamurthi
    Balaji Srinivasan
    [J]. Scientific Reports, 11
  • [5] A Fast and Scalable Pipeline for Stain Normalization of Whole-Slide Images in Histopathology
    Stanisavljevic, Milos
    Anghel, Andreea
    Papandreou, Nikolaos
    Andani, Sonali
    Pati, Pushpak
    Ruschoff, Jan Hendrik
    Wild, Peter
    Gabrani, Maria
    Pozidis, Haralampos
    [J]. COMPUTER VISION - ECCV 2018 WORKSHOPS, PT VI, 2019, 11134 : 424 - 436
  • [6] MAMC-Net: an effective deep learning framework for whole-slide image tumor segmentation
    Li Zeng
    Hongzhong Tang
    Wei Wang
    Mingjian Xie
    Zhaoyang Ai
    Lei Chen
    Yongjun Wu
    [J]. Multimedia Tools and Applications, 2023, 82 : 39349 - 39369
  • [7] MAMC-Net: an effective deep learning framework for whole-slide image tumor segmentation
    Zeng, Li
    Tang, Hongzhong
    Wang, Wei
    Xie, Mingjian
    Ai, Zhaoyang
    Chen, Lei
    Wu, Yongjun
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 82 (25) : 39349 - 39369
  • [8] A Digital Pathology Application for Whole-Slide Histopathology Image Analysis based on Genetic Algorithm and Convolutional Networks
    Puerto, Mateo
    Vargas, Tania
    Cruz-Roa, Angel
    [J]. 2016 IEEE LATIN AMERICAN CONFERENCE ON COMPUTATIONAL INTELLIGENCE (LA-CCI), 2016,
  • [9] An Accurate Neural Network for Cytologic Whole-Slide Image Analysis
    Deng, Junwei
    Lu, Yizhou
    Ke, Jing
    [J]. PROCEEDINGS OF THE AUSTRALASIAN COMPUTER SCIENCE WEEK MULTICONFERENCE (ACSW 2020), 2020,
  • [10] Few-shot weakly supervised detection and retrieval in histopathology whole-slide images
    van Rijthoven, Mart
    Balkenhol, Maschenka
    Atzori, Manfredo
    Bult, Peter
    van der Laak, Jeroen
    Ciompi, Francesco
    [J]. MEDICAL IMAGING 2021 - DIGITAL PATHOLOGY, 2021, 11603