Yuan Gao1, Yanhui Ding2, Wei Xiao3, Zhigang Yao3, Xiaoming Zhou3, Xiaodan Sui1, Yanna Zhao4, Yuanjie Zheng1. 1. School of Information Science and Engineering, Shandong Normal University, Jinan, 250358, People's Republic of China. 2. School of Information Science and Engineering, Shandong Normal University, Jinan, 250358, People's Republic of China. yanhuiding@126.com. 3. Shandong Provincial Hospital, Jinan, 250013, People's Republic of China. 4. School of Information Science and Engineering, Shandong Normal University, Jinan, 250358, People's Republic of China. yannazhao@sdnu.edu.cn.
Abstract
PURPOSE: Micropapillary adenocarcinoma is a distinctive histological subtype of lung adenocarcinoma with poor prognosis. Computer-aided diagnosis method has the potential to provide help for its early diagnosis. But the implementation of the existing methods largely relies on massive manually labeled data and consumes a lot of time and energy. To tackle these problems, we propose a framework that applies semi-supervised learning method to detect micropapillary adenocarcinoma, which aims to utilize labeled and unlabeled data better. METHODS: The framework consists of a teacher model and a student model. The teacher model is first obtained by using the labeled data. Then, it makes predictions on unlabeled data as pseudo-labels for students. Finally, high-quality pseudo-labels are selected and associated with the labeled data to train the student model. During the learning process of the student model, augmentation is added so that the student model generalizes better than the teacher model. RESULTS: Experiments are conducted on our own whole slide micropapillary lung adenocarcinoma histopathology image dataset and we selected 3527 patches for the experiment. In the supervised learning, our detector achieves a precision of 0.762 and recall of 0.884. In the semi-supervised learning, our method achieves a precision of 0.775 and recall of 0.896; it is superior to other methods. CONCLUSION: We proposed a semi-supervised learning framework for micropapillary adenocarcinoma detection, which has better performance in utilizing both labeled and unlabeled data. In addition, the detector we designed improves the detection accuracy and speed and achieves promising results in detecting micropapillary adenocarcinoma.
PURPOSE: Micropapillary adenocarcinoma is a distinctive histological subtype of lung adenocarcinoma with poor prognosis. Computer-aided diagnosis method has the potential to provide help for its early diagnosis. But the implementation of the existing methods largely relies on massive manually labeled data and consumes a lot of time and energy. To tackle these problems, we propose a framework that applies semi-supervised learning method to detect micropapillary adenocarcinoma, which aims to utilize labeled and unlabeled data better. METHODS: The framework consists of a teacher model and a student model. The teacher model is first obtained by using the labeled data. Then, it makes predictions on unlabeled data as pseudo-labels for students. Finally, high-quality pseudo-labels are selected and associated with the labeled data to train the student model. During the learning process of the student model, augmentation is added so that the student model generalizes better than the teacher model. RESULTS: Experiments are conducted on our own whole slide micropapillary lung adenocarcinoma histopathology image dataset and we selected 3527 patches for the experiment. In the supervised learning, our detector achieves a precision of 0.762 and recall of 0.884. In the semi-supervised learning, our method achieves a precision of 0.775 and recall of 0.896; it is superior to other methods. CONCLUSION: We proposed a semi-supervised learning framework for micropapillary adenocarcinoma detection, which has better performance in utilizing both labeled and unlabeled data. In addition, the detector we designed improves the detection accuracy and speed and achieves promising results in detecting micropapillary adenocarcinoma.
Authors: Wouter Bulten; Hans Pinckaers; Hester van Boven; Robert Vink; Thomas de Bel; Bram van Ginneken; Jeroen van der Laak; Christina Hulsbergen-van de Kaa; Geert Litjens Journal: Lancet Oncol Date: 2020-01-08 Impact factor: 41.316
Authors: William D Travis; Elisabeth Brambilla; Masayuki Noguchi; Andrew G Nicholson; Kim R Geisinger; Yasushi Yatabe; David G Beer; Charles A Powell; Gregory J Riely; Paul E Van Schil; Kavita Garg; John H M Austin; Hisao Asamura; Valerie W Rusch; Fred R Hirsch; Giorgio Scagliotti; Tetsuya Mitsudomi; Rudolf M Huber; Yuichi Ishikawa; James Jett; Montserrat Sanchez-Cespedes; Jean-Paul Sculier; Takashi Takahashi; Masahiro Tsuboi; Johan Vansteenkiste; Ignacio Wistuba; Pan-Chyr Yang; Denise Aberle; Christian Brambilla; Douglas Flieder; Wilbur Franklin; Adi Gazdar; Michael Gould; Philip Hasleton; Douglas Henderson; Bruce Johnson; David Johnson; Keith Kerr; Keiko Kuriyama; Jin Soo Lee; Vincent A Miller; Iver Petersen; Victor Roggli; Rafael Rosell; Nagahiro Saijo; Erik Thunnissen; Ming Tsao; David Yankelewitz Journal: J Thorac Oncol Date: 2011-02 Impact factor: 15.609
Authors: Y Makimoto; K Nabeshima; H Iwasaki; T Miyoshi; S Enatsu; T Shiraishi; A Iwasaki; T Shirakusa; M Kikuchi Journal: Histopathology Date: 2005-06 Impact factor: 5.087