Computer-Aided Diagnosis System for Accurate Thyroid Disease Detection and Classification

Thyroid diseases represent one of the most common endocrine disorders affecting millions of individuals globally. The thyroid gland plays a critical role in regulating metabolism, body temperature, heart rate, and hormonal balance. Disorders such as hypothyroidism, hyperthyroidism, thyroid nodules, and thyroid cancer can significantly impact human health if not diagnosed and treated at an early stage. Early and accurate diagnosis is therefore essential to reduce complications and improve patient outcomes. Traditional diagnostic procedures for thyroid diseases involve clinical examination, blood tests, ultrasound imaging, computed tomography (CT), and fine-needle aspiration biopsy. However, these methods rely heavily on physician expertise and interpretation of imaging results. Human interpretation may lead to diagnostic variability, delayed detection, or misclassification of thyroid conditions. Computer-Aided Diagnosis (CAD) systems have emerged as an effective technological solution to assist healthcare professionals in diagnosing diseases using artificial intelligence and machine learning techniques.With the advancement of deep learning and data mining techniques, CAD systems are increasingly being used in medical fields such as cancer detection, radiology analysis, and disease prediction. This research paper presents a computer-driven diagnostic system designed for accurate detection and classification of thyroid diseases. The proposed system uses machine learning algorithms and image processing techniques to analyze thyroid ultrasound images and medical datasets. The system consists of several stages including data collection. such as Support Vector Machine (SVM), Random ForestVarious machine learning algorithms,Decision Trees, and Convolutional Neural Networks (CNN) are used to classify thyroid diseases based on extracted features. Deep learning models are capable of automatically extracting complex patterns from medical images and have shown significant improvements in classification accuracy. The proposed CAD system aims to improve diagnostic accuracy, reduce human error, and assist medical professionals in clinical decision-making. Experimental results from existing research studies indicate that machine learning-based thyroid disease detection systems can achieve classification accuracy greater than 95%. This demonstrates the potential of computer-driven diagnosis systems to transform healthcare diagnostics. Subsequently, the boosting final results are obtained through majority voting mechanism. Furthermore, the proposed method is utilized to diagnose sequence images (the images extracted by frame from videos) to solve the poor results caused by slight differences. Finally, better final results are obtained for both of the normal dataset and the sequence dataset (consisting of sequence images). Compared with the accuracies obtained by only training deep learning models with small datasets, the diagnostic accuracies of the above two datasets are improved to 92.11% and 92.54% respectively by utilizing the proposed method.