U-Net based mitosis detection from H&E-stained images with the semiautomatic annotation using pHH3 IHC-stained images Conference Paper


Authors: Li, J.; Adachi, T.; Takeyama, S.; Yamaguchi, M.; Yagi, Y.
Editors: Colliot, O.; Isgum, I.; Landman, B. A.; Loew, M. H.
Title: U-Net based mitosis detection from H&E-stained images with the semiautomatic annotation using pHH3 IHC-stained images
Conference Title: Medical Imaging 2022: Image Processing
Abstract: We propose a new U-Net-based method for mitosis detection and a semi-automatic image processing algorithm to generate datasets from the H&E- and pHH3- stained tissue images. Instead of manual annotation, which requires not only specialized knowledge but also a lot of labor and time, our dataset generation algorithm is capable of generating precisely labeled datasets that can be easily used as a data expansion for training various kinds of models. Moreover, the proposed U-Net-based mitosis detection model, called GaussUNet, can learn the features of mitotic figures from the images by using novel two-dimensional-Gaussian-distribution-based labels created from the centroid coordinates given by annotations. In addition, we tried to improve the performance of the model by adding false positives obtained from the trained model as the mitosis look-alikes (MLAs) class to the training data. In the experiments, we confirmed the high performance of the proposed method with a simple and efficient model compared to conventional methods. © 2022 SPIE
Keywords: medical imaging; performance; image annotation; tissue images; automatic image processing; generation algorithm; image processing algorithm; manual annotation; mitosis detections; semi-automatic annotation; semi-automatics; specialized knowledge
Journal Title Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume: 12032
Conference Dates: 2022 Feb 20-23
Conference Location: San Diego, CA
ISBN: 1605-7422
Publisher: SPIE  
Date Published: 2022-04-04
Start Page: 120322J
Language: English
DOI: 10.1117/12.2612815
PROVIDER: scopus
DOI/URL:
Notes: Conference Paper -- Export Date: 1 July 2022 -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Yukako Yagi
    75 Yagi