CONVOLUTIONAL NEURAL NETWORKS FOR IDENTIFYING PAPILLARY THYROID CANCER HISTOPATHOLOGICAL IMAGE

Artificial intelligence advancements have significantly sped up the development of specialized algorithms for diagnosing Papillary Thyroid Cancer from digital images. Several studies demonstrate that AI-based approaches provide highly satisfactory performance, with one of them being Convolutional Neural Networks (CNN). However, there is a noticeable gap in research regarding head-to-head comparisons of CNN architectures for identifying thyroid cancer histopathological imaging. This study seeks to address this gap by providing a thorough evaluation of 13 well-known CNN architectures performance using transfer learning. The selected CNN architecture includes CoAtNet-0, ConvNeXt Tiny, DenseNet121, DenseNet201, InceptionV3, InceptionResNetV2, EfficientNetV2B0, ResNet50, ResNet101, ResNet50V2, VGG19, VGG16, and Xception. The model will be assessed using a comprehensive set of metrics widely employed in medical applications, including accuracy, specificity, sensitivity, F1-score, negative predictive value, and positive predictive value in two different patch sizes of 512 × 512 and 256 × 256. ConvNeXt Tiny, ResNet50, and ResNet101 were proven as the leading models and demonstrated optimal performance across all metrics in both image patch sizes. The results emphasize the significance of model selection and appropriate patch size in identifying thyroid histopathological images. © 2025 ICIC International.