TY - GEN
T1 - Semantic Segmentation of Nuclei from Breast Histopathological Images by Incorporating Attention in U-Net
AU - Rashmi, R.
AU - Prasad, Keerthana
AU - Udupa, Chethana Babu K.
N1 - Publisher Copyright:
© 2021, Springer Nature Singapore Pte Ltd.
PY - 2021
Y1 - 2021
N2 - Breast cancer is a major disease in the world and is detected by histopathological image analysis. The structure and characteristics of nuclei contributes largely in the decision of malignancy of a tumor. There exists several medical image processing techniques based on traditional and CNN methods to segment nuclei from breast histopathological images. However, these algorithms use hand crafted features and depend on availability of large annotated dataset. Moreover, heterogeneous structure and characteristic of nuclei makes it non trivial task. In this context, this paper presents an encoder decoder based CNN architecture to semantically segment nuclei from breast histopathological images. A new attention mechanism is used to extract feature from the nuclei regions at multiple scales. The proposed architecture is evaluated on breast histopathological images and achieved an mIoU of 0.77.
AB - Breast cancer is a major disease in the world and is detected by histopathological image analysis. The structure and characteristics of nuclei contributes largely in the decision of malignancy of a tumor. There exists several medical image processing techniques based on traditional and CNN methods to segment nuclei from breast histopathological images. However, these algorithms use hand crafted features and depend on availability of large annotated dataset. Moreover, heterogeneous structure and characteristic of nuclei makes it non trivial task. In this context, this paper presents an encoder decoder based CNN architecture to semantically segment nuclei from breast histopathological images. A new attention mechanism is used to extract feature from the nuclei regions at multiple scales. The proposed architecture is evaluated on breast histopathological images and achieved an mIoU of 0.77.
UR - http://www.scopus.com/inward/record.url?scp=85107505434&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85107505434&partnerID=8YFLogxK
U2 - 10.1007/978-981-16-1086-8_13
DO - 10.1007/978-981-16-1086-8_13
M3 - Conference contribution
AN - SCOPUS:85107505434
SN - 9789811610851
T3 - Communications in Computer and Information Science
SP - 137
EP - 148
BT - Computer Vision and Image Processing - 5th International Conference, CVIP 2020, Revised Selected Papers
A2 - Singh, Satish Kumar
A2 - Roy, Partha
A2 - Raman, Balasubramanian
A2 - Nagabhushan, P.
PB - Springer Science and Business Media Deutschland GmbH
T2 - 5th International Conference on Computer Vision and Image Processing, CVIP 2020
Y2 - 4 December 2020 through 6 December 2020
ER -
