Objective:To evaluate the value of ultrasound radiomics combined with machine learning for early diagnosis of seronegative Hashimoto’s thyroiditis (SN-HT) .Methods:This retrospective study included 164 patients from Liaoning Provincial People’s Hospital , Lixin County People’s Hospital, Linghai Dalinghe Hospital, Fengcheng Phoenix Hospital, who underwent thyroidectomy for solitary nodules with normal thyroid function between Nov. 2016 and Jan. 2024. Postoperative pathology confirmed Hashimoto’s thyroiditis (HT) in some cases, who were further categorized into antibody-positive and antibody-negative groups based on serum antibody status. Patients without Hashimoto’s thyroiditis served as the control group. A total of 298 ultrasound images were analyzed. Radiomics features were extracted from hypoechoic non-nodular areas within 0.5 cm surrounding the tumor. Two senior pathologists and two senior ultrasound physicians independently assessed lymphocytic infiltration, eosinophilic changes of follicular epithelium, and the proportion of hypoechoic areas in pathology and ultrasound images, respectively. A machine learning model, CCH-NET, was developed using linear regression and t-distributed stochastic neighbor embedding (t-SNE) techniques. The dataset was divided into a training set (80%) and a validation set (20%) to compare the diagnostic accuracy of CCH-NET with that of senior ultrasound physicians. Results:In internal validation, CCH-NET achieved a diagnostic accuracy of 88.89% for both antibody-positive and antibody-negative groups, significantly higher than the 66.67% accuracy of senior ultrasound physicians ( P<0.01). In external validation, CCH-NET achieved 75.00% and 66.67% accuracy for the two groups, compared to 50.00% by senior ultrasound physicians. For the control group, both methods achieved 93.33% accuracy. The AUC of CCH-NET was 0.848, outperforming senior ultrasound physicians (0.681) ,demonstrating superior diagnostic performance. Conclusion:The radiomics-based CCH-NET model, using non-nodular hypoechoic areas as a specific indicator, can accurately identify early SN-HT in euthyroid patients. It significantly outperforms senior ultrasound physicians, improving diagnostic accuracy and reducing missed diagnoses.

Objective:To evaluate the value of ultrasound radiomics combined with machine learning for early diagnosis of seronegative Hashimoto’s thyroiditis (SN-HT) .Methods:This retrospective study included 164 patients from Liaoning Provincial People’s Hospital , Lixin County People’s Hospital, Linghai Dalinghe Hospital, Fengcheng Phoenix Hospital, who underwent thyroidectomy for solitary nodules with normal thyroid function between Nov. 2016 and Jan. 2024. Postoperative pathology confirmed Hashimoto’s thyroiditis (HT) in some cases, who were further categorized into antibody-positive and antibody-negative groups based on serum antibody status. Patients without Hashimoto’s thyroiditis served as the control group. A total of 298 ultrasound images were analyzed. Radiomics features were extracted from hypoechoic non-nodular areas within 0.5 cm surrounding the tumor. Two senior pathologists and two senior ultrasound physicians independently assessed lymphocytic infiltration, eosinophilic changes of follicular epithelium, and the proportion of hypoechoic areas in pathology and ultrasound images, respectively. A machine learning model, CCH-NET, was developed using linear regression and t-distributed stochastic neighbor embedding (t-SNE) techniques. The dataset was divided into a training set (80%) and a validation set (20%) to compare the diagnostic accuracy of CCH-NET with that of senior ultrasound physicians. Results:In internal validation, CCH-NET achieved a diagnostic accuracy of 88.89% for both antibody-positive and antibody-negative groups, significantly higher than the 66.67% accuracy of senior ultrasound physicians ( P<0.01). In external validation, CCH-NET achieved 75.00% and 66.67% accuracy for the two groups, compared to 50.00% by senior ultrasound physicians. For the control group, both methods achieved 93.33% accuracy. The AUC of CCH-NET was 0.848, outperforming senior ultrasound physicians (0.681) ,demonstrating superior diagnostic performance. Conclusion:The radiomics-based CCH-NET model, using non-nodular hypoechoic areas as a specific indicator, can accurately identify early SN-HT in euthyroid patients. It significantly outperforms senior ultrasound physicians, improving diagnostic accuracy and reducing missed diagnoses.

Objective To study the immune regulation of Galectin-9 on the active CD4+T cells and demonstrate the mechanisms.Methods Lymphocytes were harvested from wild-type C57BL/6 mouse,from which na(i)ve CD4+T cells were separated via MACS and then stimulated with anti-CD3 antibody(Ab) (2.5 μg/ml),anti-CD28 Ab(5 μg/ml) and IL-2(100 ng/ml) for 3 days.The active CD4+T cells were divided into 3 groups:Control group,Galectin-9 group and Galectin-9+α-lactose group.We detected the cell proliferation level by CFSE fluorescence intensity and then dynamically observed the cell morphological changes.The proportion of CD4+CD69+T cell,Th1,Th2 and Th17 cell was valued; Meanwhile,ELISA was used to detect the cytokine levels of IFN-γ,IL-4,IL-10,IL-12,IL-17A and TGF-β1 secreted by lymphocytes.Also Western blot was used to observe the changes of T cell differentiation regulatory protein such as T-bet,GATA-3 and ROR-γt.Results Compared with control group and Galectin-9+α-lactose group,in Galectin-9 group,the cell morphology began to change at 2 h.Moreover the proportions of CD4+CD69+ T cell,Th1 and Th17 cells decreased (P＜0.05),but no significant differences in Th2 cells.The level of IFN-γ,IL-12,IL-17A and TGF-β1 from the supernatant decreased (P＜0.05),while Th2-type cytokines IL-4 and IL-1O did not change.In addition,the expressions of T-bet and ROR-γt were significantly down-regulated (P＜0.05).Conclusion Galectin-9 inhibited Th1 and Th17-type immune response,while had no effect on Th2-type immune response.The mechanism of the immune regulation may be related to affect the expression of Th1 and Th17 specific transcription factors at transcription level.