A novel transfer learning approach for the classification of histological images of colorectal cancer

• Published in: The Journal of supercomputing Vol. 77; no. 9; pp. 9494 - 9519
• Main Authors: Ohata, Elene Firmeza, Chagas, João Victor Souza das, Bezerra, Gabriel Maia, Hassan, Mohammad Mehedi, de Albuquerque, Victor Hugo Costa, Filho, Pedro Pedrosa Rebouças
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2021; Springer Nature B.V
• Subjects: Artificial neural networks; Cancer; Colorectal cancer; Compilers; Computer Science; Deep Learning; Evaluation; Feature extraction; Health care facilities; Histology; Image classification; Interpreters; Machine learning; Medical imaging; Multilayer perceptrons; Parallel Computing in Biomed Sciences & Healthcare; Processor Architectures; Programming Languages; Support vector machines; Histological images; Convolutional neural networks; Transfer learning; Colorectal cancer
• ISSN: 0920-8542; 1573-0484
• DOI: 10.1007/s11227-020-03575-6

Colorectal cancer (CRC) is the second most diagnosed cancer in the United States. It is identified by histopathological evaluations of microscopic images of the cancerous region, relying on a subjective interpretation. The Colorectal Histology dataset used in this study contains 5000 images, made available by the University Medical Center Mannheim. This approach proposes the automatic identification of eight types of tissues found in CRC histopathological evaluation. We apply Transfer Learning from architectures of Convolutional Neural Networks (CNNs). We modify the structures of CNNs to extract features from the images and input them to well-known machine learning methods: Naive Bayes, Multilayer Perceptron, k-Nearest Neighbors, Random Forest, and Support Vector Machine (SVM). We evaluated 108 extractor–classifier combinations. The one that achieved the best results is DenseNet169 with SVM (RBF), reaching an Accuracy of 92.083% and F1-Score of 92.117%. Therefore, our approach is capable of distinguishing tissues found in CRC histopathological evaluation.