Hang Meng, Fei Li, Zhen Yang, Qiang Zhu, Chaogang Fan, Shu Zhan

Proceedings of the 13th International Multi-Conference on Complexity, Informatics and Cybernetics: IMCIC 2022, Vol. II, pp. 146-152 (2022); https://doi.org/10.54808/IMCIC2022.02.146

Hang Meng
Key Laboratory of Knowledge Engineering with Big Data, Ministry of Education, Hefei University of Technology, Hefei City, Anhui Province, China

Fei Li
The Second Affiliated Hospital of Anhui Medical University, Hefei City, Anhui Province, China

Zhen Yang
The Second Affiliated Hospital of Anhui Medical University, Hefei City, Anhui Province, China

Qiang Zhu
Tongcheng Teachers College, Tongcheng City, Anhui Province, China

Chaogang Fan
Department of General Surgery, The Affiliated BenQ Hospital of Nanjing Medical University, Nanjing City, Jiangsu Province, China

Shu Zhan
Key Laboratory of Knowledge Engineering with Big Data, Ministry of Education, Hefei University of Technology, Hefei City, Anhui Province, China

Cite this paper as:
Meng, H., Li, F., Yang, Z., Zhu, Q., Fan, C., Zhan, S. (2022). Salient Patch Based NAS for Grading of Colorectal Cancer Histology Images. In N. Callaos, S. Hashimoto, N. Lace, B. Sánchez, M. Savoie (Eds.), Proceedings of the 13th International Multi-Conference on Complexity, Informatics and Cybernetics: IMCIC 2022, Vol. II, pp. 146-152. International Institute of Informatics and Cybernetics. https://doi.org/10.54808/IMCIC2022.02.146

Digital histopathological tissue images are gold material for cancer diagnosis and grades. Convolutional Neural Networks (CNNs) are state-of-the-art models in many image classification tasks. However, considering the limited computing resources, it is not practical to directly train CNNs on gigapixel resolution histopathological tissue images. Therefore, the entire histopathological image is commonly divided into a grid of patches and then fed each patch to CNNs, but not all patches are necessary for specific tasks. Besides, although CNNs are excellent image classifiers, many pre-trained models are based on natural images. Neural Architecture Search (NAS) can realize automatic search, construction, and training specific problem-oriented networks. We present salient patch based NAS for grading colorectal cancer (CRC) histology images with these motivations. The proposed framework first applies the classic classification network to extract significant patches from the whole image, then use the network obtained by NAS to grade the patches, and finally aggregates the patch-level predictions to generate the entire CRC histological image label. Our experiments on microscopic colorectal tissue images demonstrate that the proposed method is sufficient to obtain more accurate classification results compared to its counterparts. We also conducted a comprehensive analysis of the different scenarios of the proposed method.