摘要
Inflammatory cells such as lymphocytes and neutrophils are crucial indicators in diagnosing acute inflammation from liver histology images. However, there are several challenges in detecting the inflammatory cells. The inflammatory cells have large variation and also appear similar to other cells. In an often occasion, the inflammatory cells may overlap each other. It is also unavoidable to see the clustery noise in the background. To conquer the above-mentioned problems, this paper proposes a procedure, which implements the detection-then-classification by combining the distance transformation with deep convolutional neural networks for detecting an accurate position of each cell. Then a precise image patch can be extracted for a deep convolutional neural network for classification of the cells into nuclei, lymphocyte, neutrophils and impurity (e.g. Kupffer cell). The experimental results show that the proposed approach can effectively detect the inflammatory cells from H&E Staining liver histopathological images, with an accuracy of 93.7% in inflammatory cells classification.
| 原文 | English |
|---|---|
| 主出版物標題 | New Trends in Computer Technologies and Applications - 23rd International Computer Symposium, ICS 2018, Revised Selected Papers |
| 編輯 | Chuan-Yu Chang, Chien-Chou Lin, Horng-Horng Lin |
| 發行者 | Springer Verlag |
| 頁面 | 665-672 |
| 頁數 | 8 |
| ISBN（列印） | 9789811391897 |
| DOIs | |
| 出版狀態 | Published - 2019 一月 1 |
| 事件 | 23rd International Computer Symposium, ICS 2018 - Yunlin, Taiwan 持續時間: 2018 十二月 20 → 2018 十二月 22 |
出版系列
| 名字 | Communications in Computer and Information Science |
|---|---|
| 卷 | 1013 |
| ISSN（列印） | 1865-0929 |
Conference
| Conference | 23rd International Computer Symposium, ICS 2018 |
|---|---|
| 國家 | Taiwan |
| 城市 | Yunlin |
| 期間 | 18-12-20 → 18-12-22 |
指紋
All Science Journal Classification (ASJC) codes
- Computer Science(all)
- Mathematics(all)
引用此文
}
Inflammatory Cells Detection in H&E Staining Histology Images Using Deep Convolutional Neural Network with Distance Transformation. / Li, Chao Ting; Chung, Pau-Choo; Tsai, Hung Wen; Chow, Nan-Haw; Cheng, Kuo-Sheng.
New Trends in Computer Technologies and Applications - 23rd International Computer Symposium, ICS 2018, Revised Selected Papers. 編輯 / Chuan-Yu Chang; Chien-Chou Lin; Horng-Horng Lin. Springer Verlag, 2019. p. 665-672 (Communications in Computer and Information Science; 卷 1013).研究成果: Conference contribution
TY - GEN
T1 - Inflammatory Cells Detection in H&E Staining Histology Images Using Deep Convolutional Neural Network with Distance Transformation
AU - Li, Chao Ting
AU - Chung, Pau-Choo
AU - Tsai, Hung Wen
AU - Chow, Nan-Haw
AU - Cheng, Kuo-Sheng
PY - 2019/1/1
Y1 - 2019/1/1
N2 - Inflammatory cells such as lymphocytes and neutrophils are crucial indicators in diagnosing acute inflammation from liver histology images. However, there are several challenges in detecting the inflammatory cells. The inflammatory cells have large variation and also appear similar to other cells. In an often occasion, the inflammatory cells may overlap each other. It is also unavoidable to see the clustery noise in the background. To conquer the above-mentioned problems, this paper proposes a procedure, which implements the detection-then-classification by combining the distance transformation with deep convolutional neural networks for detecting an accurate position of each cell. Then a precise image patch can be extracted for a deep convolutional neural network for classification of the cells into nuclei, lymphocyte, neutrophils and impurity (e.g. Kupffer cell). The experimental results show that the proposed approach can effectively detect the inflammatory cells from H&E Staining liver histopathological images, with an accuracy of 93.7% in inflammatory cells classification.
AB - Inflammatory cells such as lymphocytes and neutrophils are crucial indicators in diagnosing acute inflammation from liver histology images. However, there are several challenges in detecting the inflammatory cells. The inflammatory cells have large variation and also appear similar to other cells. In an often occasion, the inflammatory cells may overlap each other. It is also unavoidable to see the clustery noise in the background. To conquer the above-mentioned problems, this paper proposes a procedure, which implements the detection-then-classification by combining the distance transformation with deep convolutional neural networks for detecting an accurate position of each cell. Then a precise image patch can be extracted for a deep convolutional neural network for classification of the cells into nuclei, lymphocyte, neutrophils and impurity (e.g. Kupffer cell). The experimental results show that the proposed approach can effectively detect the inflammatory cells from H&E Staining liver histopathological images, with an accuracy of 93.7% in inflammatory cells classification.
UR - http://www.scopus.com/inward/record.url?scp=85069715775&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85069715775&partnerID=8YFLogxK
U2 - 10.1007/978-981-13-9190-3_73
DO - 10.1007/978-981-13-9190-3_73
M3 - Conference contribution
AN - SCOPUS:85069715775
SN - 9789811391897
T3 - Communications in Computer and Information Science
SP - 665
EP - 672
BT - New Trends in Computer Technologies and Applications - 23rd International Computer Symposium, ICS 2018, Revised Selected Papers
A2 - Chang, Chuan-Yu
A2 - Lin, Chien-Chou
A2 - Lin, Horng-Horng
PB - Springer Verlag
ER -