Automatic detection of cancer metastasis in lymph node using deep learning. (April 2023)

• Record Type: Journal Article
• Authors: Bütün, Ertan; Uçan, Murat; Kaya, Mehmet
• Is Part Of: Biomedical signal processing and control. Volume 82(2023)
• Publication Date: 2023-04
• Subjects: Deep learning -- Convolutional neural network -- Lymph node metastasis -- Cancer detection; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104564
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A promising deep learning based approach was presented to detect cancer metastasis in lymph node images with higher accuracy. The proposed deep learning framework uses ResNet architectures, transfer learning and 1cycle policy. The validity of the proposed approach was evaluated on PCAM dataset consisted of 220, 025 lymph node images. The experiments demonstrated that the presented method outperformed most of the current studies. Abstract: Lymph node metastases are one of the most indicator of some cancer types such as breast, colon and prostate. Breast cancer mostly spreads to lymph nodes in the armpit and it is one of the most common causes of death in women worldwide. Pathologists need more attention and time to diagnose metastasis in digitized lymph node images and also this process tends to be misinterpreted. In this paper, a promising deep learning based approach was presented to detect cancer metastasis in lymph node images with higher accuracy. The proposed deep learning framework uses ResNet architectures, transfer learning and 1cycle policy which is the method of finding the optimal learning rate. The validity of the proposed approach was evaluated on PCAM dataset consisted of 220, 025 lymph node images. The experiments demonstrated that the presented method outperformed most of the current studies, achieving accuracy of 98.60% on the PCAM dataset by using ResNet models and fine-tuning techniques effectively. The burden of diagnosis procedure of metastasis can be lessened with the proposed deep learning framework in the clinical applications.