Optimizing Thyroid Nodule Segmentation in Thermal Imaging With Temporal Sequences and Advanced Deep Learning Backbones Publisher



Etehadtavakol M ; Etehadtavakol M ; Ng EYK
Source: Expert Systems with Applications Published:2026

Abstract

This study investigates methods to improve the segmentation of thyroid nodules in thermal imaging using deep learning models, with a focus on enhancing the Dice coefficient, a critical metric for model performance. We explore the integration of sequential image data through Long Short-Term Memory (LSTM) networks, hypothesizing that leveraging temporal features can significantly improve segmentation accuracy. Four novel deep learning models—U-Net with VGG16_A, VGG16_B, VGG19, and MobileNet backbones—were developed and evaluated. The research consisted of four studies: (1) analyzing the impact of sequence length (5, 10, and 20 images), which demonstrated a meaningful Dice improvement from 31.5 % to 36.6 % with longer sequences; (2) comparing feature-engineered versus raw data, revealing a tradeoff between sensitivity and precision; (3) assessing transfer learning approaches with VGG16 variants, where VGG16_B achieved a 4 % Dice improvement over VGG16_A; (4) exploring alternative backbones (VGG19 and MobileNet) without substantial performance gains; and (5) conducting ablation experiments across all models and compared single-frame and multi-frame LSTM inputs. Sensitivity analysis highlighted the importance of reducing false negatives for better segmentation accuracy. Despite GPU and dataset limitations, our results indicate that LSTM-based sequential models significantly enhance segmentation performance, offering potential advancements in early thyroid nodule diagnosis and management. Future work will focus on multi-input designs and external validation to ensure generalizability and clinical applicability. © 2025 Elsevier B.V., All rights reserved.