Transfer Learning Approach and Nucleus Segmentation with MedCLNet Colon Cancer Database

Colon and lung cancer classification from multi-modal images using resilient and efficient neural network architectures

“… Ram et al [ 8 ] employed a method called GS-PCANet and attained an accuracy of 90.80 % for lung cancer classification, with an AUC (a measure of accuracy) of 0.95. Reis and Turk [ 9 ] utilized DenseNet169 for colon cancer classification and achieved an accuracy of 95.0 %. Sethy et al [ 12 ] combined the AlexNet architecture, wavelet transformations, and support vector machines to achieve an accuracy of 99.3 % and an impressive AUC of 0.99 for lung cancer classification on the LC25000 dataset.…”

“…Reis and Turk [ 9 ] utilized DenseNet169 for colon cancer classification and achieved an accuracy of 95.0 %.…”

“…Reis and Turk [ 9 ] leveraged transfer learning and deep learning for nucleus detection and classification in histopathology datasets. The method achieved a 95.0 % accuracy rate on the MNIST collection of colorectal histopathology data using the DenseNet169 model.…”

Tissue classification and diagnosis of colorectal cancer histopathology images using deep learning algorithms. Is the time ripe for clinical practice implementation?

“…Although the team does not report results before and after the inclusion of the attention model layer, the overall reported accuracy for their model was 95.33% with an AUC of 0.94. It must be noted, however, that both the training and the testing image sets were derived from the same dataset [ 34 – 51 ].…”

“…In Western countries the presence of a cancerous lesion is confirmed by invasion beyond the submucosal tissue (also referred to as Vienna classification), while in the Eastern model the diagnosis is based on inner structural and nucleic abnormalities of the epithelium (also referred to as Japanese classification). Despite the research for which the CRC spectrum is encompassed in its entirety, a unified method has yet to be finalized [ 51 , 52 ].…”