Deep learning prediction of axillary lymph node status using ultrasound images. (April 2022)

• Record Type: Journal Article
• Authors: Sun, Shawn; Mutasa, Simukayi; Liu, Michael Z; Nemer, John; Sun, Mary; Siddique, Maham; Desperito, Elise; Jambawalikar, Sachin; Ha, Richard S.
• Is Part Of: Computers in biology and medicine. Volume 143(2022)
• Publication Date: 2022-04
• Subjects: Deep learning -- Axillary lymph nodes -- Ultrasound imaging; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.105250
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Objective: To investigate the ability of our convolutional neural network (CNN) to predict axillary lymph node metastasis using primary breast cancer ultrasound (US) images. Methods: In this IRB-approved study, 338 US images (two orthogonal images) from 169 patients from 1/2014–12/2016 were used. Suspicious lymph nodes were seen on US and patients subsequently underwent core-biopsy. 64 patients had metastatic lymph nodes. A custom CNN was utilized on 248 US images from 124 patients in the training dataset and tested on 90 US images from 45 patients. The CNN was implemented entirely of 3 × 3 convolutional kernels and linear layers. The 9 convolutional kernels consisted of 6 residual layers, totaling 12 convolutional layers. Feature maps were down-sampled using strided convolutions. Dropout with a 0.5 keep probability and L2 normalization was utilized. Training was implemented by using the Adam optimizer and a final SoftMax score threshold of 0.5 from the average of raw logits from each pixel was used for two class classification (metastasis or not). Results: Our CNN achieved an AUC of 0.72 (SD ± 0.08) in predicting axillary lymph node metastasis from US images in the testing dataset. The model had an accuracy of 72.6% (SD ± 8.4) with a sensitivity and specificity of 65.5% (SD ± 28.6) and 78.9% (SD ± 15.1) respectively. Our algorithm is available to be shared for research use. (https://github.com/stmutasa/MetUS ). Conclusion: It's feasible to predict axillary lymph node metastasis from US images using a deep learning technique. This can potentially aid nodal staging in patients with breast cancer. Highlights: There is a need for non-invasive techniques complementary to sentinel lymph node biopsy for detecting breast cancer axillary metastasis. US in particular has been valuable in assessing axillary disease in breast cancer patients and has the benefit of low cost and zero radiation. AI and DL algorithms can bring the potential of axillary imaging to the next level to predict axillary lymph node metastasis from US images.