文献类型：期刊文献

英文题名：Malignancy-Aware Dual-Task Heatmap Decoupling for thyroid ultrasound nodule detection and classification

作者：Chen, Yining[1];Wang, Xiaxia[2]

第一作者：Chen, Yining

通信作者：Chen, YN[1]

机构：[1]Gansu Minzu Normal Univ, Sch Informat Engn, Hezuo, Peoples R China;[2]Gansu Univ Chinese Med, Sch Basic Med, Lanzhou, Peoples R China

第一机构：Gansu Minzu Normal Univ, Sch Informat Engn, Hezuo, Peoples R China

通信机构：[1]corresponding author), Gansu Minzu Normal Univ, Sch Informat Engn, Hezuo, Peoples R China.

年份：2026

卷号：16

外文期刊名：FRONTIERS IN ONCOLOGY

收录：;Scopus(收录号：2-s2.0-105052279722);WOS:【SCI-EXPANDED(收录号:WOS:001876615800001)】；

基金：The author(s) declared that financial support was received for this work and/or its publication. This study was supported by the National Natural Science Foundation of China (82460897).

语种：英文

外文关键词：anchor-free object detection; feature decoupling; feature orthogonality; receptive field; thyroid nodule detection

摘要：Background Accurate thyroid nodule detection and benign-malignant classification on ultrasound are critical for early cancer diagnosis. Existing deep-learning detectors encode localization and classification in a shared feature space, causing inter-task feature redundancy and limiting task-specific performance.Methods We propose Malignancy-Aware Dual-Task Heatmap Decoupling (MADTHD), a CenterNet-based framework that decouples localization and classification through asymmetric dual heads. A Position Head with small receptive fields captures precise nodule contours, while a Malignancy Head with multi-scale dilated convolutions extracts textural and boundary features indicative of benign-malignant status. A feature orthogonality loss is introduced to enforce complementary channel activation between the two heads, reducing inter-task feature redundancy. Systematic ablation studies were conducted on TN5000, and generalization was assessed via zero-shot transfer to the independent TN3K dataset.Results MADTHD achieves a mean average precision of 0.7840 on TN5000, outperforming the CenterNet baseline by 2.61 percentage points, with the improvement most pronounced for malignant nodules. Ablation experiments demonstrate that the asymmetric dual-head architecture and the feature orthogonality loss are mutually synergistic. On the independent TN3K dataset, MADTHD maintains its relative standing against the baseline without fine-tuning.Conclusion MADTHD provides an interpretable dual-task framework mirroring the clinical localize-then-characterize workflow. The proposed modules are lightweight and backbone-agnostic. Clinical utility remains to be established through prospective validation.