CECT images useful in predicting axillary lymph node metastasis in breast cancer: Study

The researchers carefully designed a new construction called deformable sampling module (DSM) as a plug-and-play sampling module in the proposed deformable attention VGG19 (DA-VGG19). They used a dataset of 800 samples labeled from 800 CECT images of 401 breast cancer patients retrospectively enrolled in the last three years were adopted to train, validate, and test the deep convolutional neural network models. By comparing the accuracy, positive predictive value, negative predictive value, sensitivity, and specificity indices, the performance of the proposed model is analyzed in detail.

The results of the study are as follows:

The best-performing DA-VGG19 model achieved an accuracy of 0.9088, which is higher than that of other classification neural networks.

Thus, the researchers concluded that through this first of its kind research to predict ALN by CECT dataset via deep learning. as such, the proposed intelligent diagnosis algorithm can provide doctors with daily diagnostic assistance and advice and reduce the workload of doctors.

Reference:

A study titled, "Axillary lymph node metastasis prediction by contrast-enhanced computed tomography images for breast cancer patients based on deep learning" by Liu Z et. al published in the Computers in Biology and Medicine.

https://doi.org/10.1016/j.compbiomed.2021.104715