Transfer Learning Approach and Nucleus Segmentation with MedCLNet Colon Cancer Database

• Published in: Journal of digital imaging 2023-02, Vol.36 (1), p.306-325
• Main Authors: Reis, Hatice Catal, Turk, Veysel
• Format: Article
• Language: English
• Subjects: Abstract machines; Algorithms; Artificial neural networks; Cell Nucleus; Classification; Colon; Colon cancer; Colonic Neoplasms; Colorectal cancer; Datasets; Deep learning; Disease detection; Empirical analysis; Graph theory; Histology; Histopathology; Humans; Imaging; Machine Learning; Medicine; Medicine & Public Health; Neural networks; Neural Networks, Computer; Nuclei; Performance measurement; Radiology; Segmentation; Transfer learning
• ISSN: 1618-727X; 0897-1889; 1618-727X
• DOI: 10.1007/s10278-022-00701-z

Machine learning has been recently used especially in the medical field. In the diagnosis of serious diseases such as cancer, deep learning techniques can be used to reduce the workload of experts and to produce quick solutions. The nuclei found in the histopathology dataset are an essential parameter in disease detection. The nucleus segmentation was performed using the colorectal histology MNIST dataset for nucleus detection in this study. The graph theory, PSO, watershed, and random walker algorithms were used for the segmentation process. In addition, we present the 10-class MedCLNet visual dataset consisting of the NCT-CRC-HE-100 K dataset, LC25000 dataset, and GlaS dataset that can be used in transfer learning studies from deep learning techniques. The study proposes a transfer learning technique using the MedCLNet database. Deep neural networks pre-trained with the proposed transfer learning method were used in the classification with the colorectal histology MNIST dataset in the experimental process. DenseNet201, DenseNet169, InceptionResNetV2, InceptionV3, ResNet152V2, ResNet101V2, and Xception deep learning algorithms were used in transfer learning and the classification studies. The proposed approach was analyzed before and after transfer learning with different methods (DenseNet169 + SVM, DenseNet169 + GRU). In the performance measurement, using the colorectal histology MNIST dataset, 94.29% accuracy was obtained in the DenseNet169 model, which was initiated with random weights in the multi-classification study, and 95.00% accuracy after transfer learning was applied. In comparison with the results obtained from empirical studies, it was demonstrated that the proposed method produced satisfactory outcomes. The application is expected to provide a secondary evaluation for physicians in colon cancer detection and the segmentation. Graphical Abstract