Abstract
Early detection of any disease assists in reduction of disease progression. In this work, discrimination of the thyroid nodules is studied by employing deep learning architectures. Deep learning algorithm mimics the function of the human cerebral cortex. Thyroid nodule classification is done using Convolutional Neural Network (CNN). It is observed that early detection of any disease will help to reduce the risk of death. In CNN, the output of the input layer is fed the convolutional layer followed by ReLU layer and Max pooling layer and the images are classified into Benign (TI-RADS 2, TI-RADS 3, TI-RADS 4a) and Malignant (TI-RADS 4b, TI-RADS 5, TI-RADS 6). The performance of CNN is compared with the pre-trained networks such as Alexnet, VGG-19 and Resnet-50 using transfer learning. The CNN outperformed the pre-trained networks with an accuracy of 99.17%, sensitivity of 0.98, precision of 0.97 and F1 score of 1.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call