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 more significant detective combination by comparing three methods of antinuclear antibody,extractable nuclear antigen and antinuclear antibodies 3.Methods Three methods were adopted as follows:detecting antinuclear antibody with HEP-2 and prime hepar as antigen media,determining extractable nuclear antigen by EUROASSAY including nRNP/Sm、Sm、SSA、SSB、Scl-70 and Jo-1,using crithidia iuciliae as antigen,to detect ds-DNA antibody with indirect immunofluorescence assay,and to study 15 autoantibodies by EUROLINE.Results To compare positive rates of three dilution(1:10,1:80,1:100)in ANA detection,there existed significant difference(P<0.01)between two dilution of 1:10 and 1:80 only,.In the detection of multiple nuclear types(cytoplasmic pattern,centromere pattern and homegeneous pattern etc),the positive rate of antinucleatr antibodies 3 was higer than that of ENA.IIF was prior to the EUROLINE in the detection of ds-DNA.Conclusion During detecting ANA with IIF,the dilution of 1:80 has advantages in raising positive rate,and ANA3 of 15 antigens provides facilities for clinical diagnosis.

Objective To explore the clinical diagnostic value of CYFRA21-1 in benign lung disease deriving from epithelium cells.Methods CYFRA21-1 level in serum and hydrothorax was determined by electrochemiluminescence immunoassay. The complex sandwich (KS 19.1 monoclonal antibody-CYFRA21-1[Ru(bpy)3]2+ labeled monoclonal antibody BMI 9.21) was fixed to the bead enclosed avidin by means of biotin-avidin combination, then the luminescence under the influence of perfluorotripropylamine and electric field luminous was tested for CYFRA21-1.Results The level of CYFRA21-1 in the group suffering from lung disease accompanied by complications was significantly higher than that of single lung disease group (P<0.01). CYFRA21-1 value in the elder group was significantly higher than that of the younger group (P<0.01).Conclusion The gerontal patients suffering from benign lung disease accompanied by complications should be given symptomatic treatment if their CYFRA21-1 level is elevated but CEA and NES was normal. Recheck the above indices two weeks later so as to identify the benign or malignancy of the disease.