Development of ultrasound-based clinical, radiomics and deep learning fusion models for the diagnosis of benign and malignant soft tissue tumors.

Objectives: The aim of this study is to develop an ultrasound-based fusion model of clinical, radiomics and deep learning (CRDL) for accurate diagnosis of benign and malignant soft tissue tumors (STTs).

Methods: In this retrospective study, ultrasound images and clinical data of patients with STTs from two hospitals were collected between January 2021 and December 2023. Radiomics features and deep learning features were extracted from the ultrasound images, and the optimal features were selected to construct fusion models using support vector machines.

Ultrasound-based artificial intelligence model for prediction of Ki-67 proliferation index in soft tissue tumors.

Rationale And Objectives: To investigate the value of deep learning (DL) combined with radiomics and clinical and imaging features in predicting the Ki-67 proliferation index of soft tissue tumors (STTs).

Materials And Methods: In this retrospective study, a total of 394 patients with STTs admitted from January 2021 to December 2023 in two separate hospitals were collected. Hospital-1 was the training cohort (323 cases, of which 89 and 234 were high and low Ki-67, respectively) and Hospital-2 was the external validation cohort (71 cases, of which 23 and 48 were high and low Ki-67, respectively).

Comparison between combined ultrasounds and magnetic resonance imaging in the differentiation of benign and malignant breast lesions: a cross-sectional study.

Aim: To explore the performance of single or combined ultrasound (US) in diagnosing malignant breast lesions, and then compare the results with a magnetic resonance imaging (MRI) aspect.

Material And Methods: Patients' demographics, tumor markers, and imaging examination were collected. Diagnostic models based on B-mode, color Doppler ultrasounds (CDU), strain elastography (SE), MRI, B-mode US + CDU, B-mode US + SE, and B-mode US + CDU + SE were developed using logistic regression analysis.

[The value of ACR-TIRADS and C-TIRADS in the diagnosis of nodular Hashimoto thyroiditis and papillary thyroid carcinoma with Hashimoto thyroiditis].

To explore the diagnostic value of American Society of Radiology Thyroid Imaging Reporting and Data System（ACR-TIRADS） and Chinese Thyroid Nodule Ultrasound Malignant Risk Stratification（C-TIRADS） in nodular Hashimoto thyroiditis and papillary thyroid carcinoma with Hashimoto thyroiditis. This retrospective analysis included 144 patients（204 thyroid nodules） accompanied by nodular Hashimoto thyroiditis or papillary thyroid carcinoma under the background of Hashimoto thyroiditis confirmed by surgical pathology examination in the First Affiliated Hospital of Hebei North University from August 2018 to May 2021, all nodules were examined by ultrasound, and 204 nodules were scored and graded according to the classification standards of ACR-TIRADS and C-TIRADS. The surgical pathological results were the gold standard.

[Value of e-Flow combined with TI-RADS in qualitative diagnosis of thyroid nodules].

Objective: To investigate the value of combination of thyroid imaging reporting and data system (TI-RADS) and enhanced flow (e-Flow) in the qualitative diagnosis of thyroid nodules; and to compare the diagnostic efficiency between e-Flow and color doppler flow imaging (CDFI.

Method: The study chose 133 patients with 179 nodules (127 benign, 52 malignant nodules) who had per-operative ultrasound examination of their thyroid using grey-scale ultrasound, CDFI, e-Flow, and their noudles were graded by TI-RADS. Then the ultrasound diagnostic value were compared with their surgical pathology results by TI-RADS; TI-RADS and CDFI; TI-RADS and e-Flow, and diagnostic efficiency between e-Flow and CDFI were compared.