GS-OCMXM: Towards Parallel and GPU Accelerated Computing on GS-Based Multi-Cross-Modality Learning for Accurate Segmentation of Ultrasonography Thyroid Nodule Cancer Detection with Limited Labels

AI-assisted thyroid nodule evaluation shows promise in improving thyroid nodule detection, which can be missed by ultrasound(US)-guided hand-held transducer due to the complexity of nodules segmentation. this paper proposed the paper proposes an efficient 4-level framework for ultrasound images segmentation, consisting of Dus-KFCM, Patch Learning, One Class Cross Learning, and parallel computing layer. The developed ML-OCX network considers the contributions of patches to predict the final image-level label by using a GS agent. The authors also created a novel ultrasonography dataset with 4 types of thyroid ultrasound scanning images. Extensive experiments demonstrate the effectiveness of the ML-OCX model, which outperforms other learning methods. The paper also presents an effective multi-modality learning framework to enhance segmentation performance by utilizing prior knowledge of one modality and finding a set of reliable positive and negative examples. The parallel algorithm achieves ~50% improvement in computation efficiency compared to the original serial algorithm. The model is trained on FL-TN, TI-RADS, and DDTI datasets and achieves an accuracy of 97.574%, Fmeasure of 86.150%, and precise judgement of GS-thyroid nodules location from ultrasound assessment, demonstrating its generalization ability. This can help endocrinologist more easily find missed atypia and decrease the follicular lesion miss rate. It may be applicable in daily clinical practice to reduce the burden on physicians. The technology also allows high-risk precancerous lumps to be detected, which has the clinical and biological significance analysis on thyroid nodules echotherapy finding. More prospective studies are needed to make AI-aided thyroid ultrasound diagnosis universal in thyroid nodule clinic.