Enhanced Early Detection of Thyroid Abnormalities Using a Deep Learning Model: A Sequential CNN Approach

Abstract

This research emphasizes on development of novel methodology for effective early detection of thyroid abnormalities nodules using machine learning and deep learning methods. Accordingly the proposed system employed a hybrid approach namely a sequential convolutional neural network (SCNN) to automate feature extraction and focus on detecting thyroid abnormalities. Further, advanced sequential model algorithms were employed to distinguish benign from malignant morphology using ultrasound images. The models performance was assessed using ultrasound and CT scan images from a dataset containing grayscale US and CT scan images. The outcomes of experiments on medical images datasets, featuring both diseased and normal thyroids, demonstrated classification and diagnostic accuracy between 95% and 99%, underscoring its significant clinical utility. In addition, this novel procedure yield better precision and sensitivity of 97.4%, and 83.1% respectively witnessing robust classifying images for benign or malignant.