Xiaoqin Qian

Background: Solid-predominant partially cystic thyroid nodules (PCTNs) present challenges for malignancy risk stratification and fine-needle aspiration (FNA) decision-making. This study aimed to compare a multiparametric ultrasound model integrating conventional ultrasound and strain elastography with the American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS) management strategy for reducing unnecessary FNA in solid-predominant PCTNs. Methods: This multicenter retrospective study included solid-predominant PCTNs evaluated at three tertiary referral hospitals between October 2018 and May 2024. A total of 375 nodules were included, with 264 assigned to the training cohort and 111 to the validation cohort. Two predictive models were constructed: Model 1 incorporated maximum nodule diameter and conventional ultrasound features, and Model 2 additionally included elastography. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis. Results: Among the 375 included nodules, 198 (52.8%) were malignant. In the validation cohort, the AUCs were 0.63 [95% confidence interval (CI): 0.54–0.73] for the ACR TI-RADS management strategy, 0.80 (95% CI: 0.72–0.88) for Model 1, and 0.86 (95% CI: 0.78–0.93) for Model 2. Using the continuous ACR TI-RADS score, Model 2 achieved a higher AUC (0.86 vs. 0.74; paired DeLong P=0.02). Elastographic stiffness was the strongest predictor of malignancy in Model 2 [odds ratio (OR), 10.53; 95% CI: 3.65–30.38; PConclusions: The combination of conventional ultrasound features and strain elastography outperformed the ACR TI-RADS system for FNA triage in solid-predominant PCTNs and may help reduce unnecessary FNA procedures.

Nodal lymphoma requires precise diagnosis and longitudinal monitoring. Ultrasound is now established as a first-line tool for evaluating superficial lymphadenopathy, and the introduction of shear-wave elastography, contrast-enhanced ultrasound, super-resolution contrast-enhanced ultrasound, and artificial-intelligence-based decision support has expanded its role far beyond simple morphological assessment. This updated review outlines the evolving role of multimodal ultrasound and its advanced applications in the comprehensive management of nodal lymphoma, from initial diagnosis and biopsy guidance to treatment evaluation and prognosis stratification, highlighting current evidence, clinical utility, and future research directions.

Organoids, an emerging bioengineering approach, can replicate the structure and function of human organs in vitro, providing valuable tools for biomedical research. Patient-derived organoids (PDOs) retain the histological and genetic characteristics of the original tumor, playing a crucial role in precision oncology. Ultrasound-assisted technology, particularly multimodal ultrasound imaging, facilitates the establishment of PDOs for inoperable or rare tumors by enabling precise tumor localization, minimally invasive tissue sampling, and high-purity cell extraction.This review explores the application of multimodal ultrasound techniques in PDO development across various tumor types, highlighting their advantages in obtaining high-purity tumor cells, improving PDO culture success rates, and advancing personalized cancer treatment. Additionally, we discuss factors influencing PDO establishment, such as tumor type, sampling methods, and bioengineering advancements. By summarizing current progress and challenges, this review provides insights into optimizing ultrasound-assisted PDO construction for clinical and research applications.

Introduction: Papillary thyroid carcinoma is the most common pathological subtype of thyroid cancer in both children/adolescents (TCCA) and adults (TCA). TCCA manifests more aggressive and invasive behaviors than TCA, which may be attributed to specific genomic alterations. Methods: To better understand the specific molecular, pathological and clinical manifestations of TCCA, we retrospectively analyzed a cohort of 60 patients with sporadic papillary thyroid carcinoma, including 20 TCCAs and 40 TCAs. Fine-needle aspiration tissue samples from these cases were analyzed using next-generation sequencing. Demographics, ultrasound features, postoperative pathology and radiation exposure history were compared between TCCAs and TCAs. To validate our findings, we integrated data from 28 prior studies, resulting in a larger cohort of 1,483 sporadic TCCAs. Results: Multiple gene mutations were more prevalent in TCCAs than TCAs (p=0.013), such as BRAF^V600E coexisting with KMT2 family genes or PTEN. Although BRAF^V600E was the most common single nucleotide variant in TCCAs (25%, 5/20), its prevalence was significantly lower than in TCAs (95%, 38/40, pRET oncogenic fusions were detected exclusively in TCCAs, with an incidence of 20% (4/20). Compared with TCAs, TCCAs were associated with larger tumor diameters (pBRAF^V600E alongside other mutations (e.g., ATM, PTEN or KMT2 family genes) exhibited more severe clinical manifestations, including larger tumors and higher rates of lymph node metastasis, compared with those harboring BRAF^V600E alone.Discussion: TCCAs exhibit more aggressive and invasive clinical manifestations than TCAs, particularly in cases with RET fusions or BRAF^V600E coexisting with other point mutations. Targeted comprehensive molecular profiling may aid in the diagnosis and treatment of TCCA.

The purpose of this study was to create and validate an ultrasound-based graph convolutional network (US-based GCN) model for the prediction of axillary lymph node metastasis (ALNM) in patients with breast cancer. A total of 820 eligible patients with breast cancer who underwent preoperative breast ultrasonography (US) between April 2016 and June 2022 were retrospectively enrolled. The training cohort consisted of 621 patients, whereas validation cohort 1 included 112 patients, and validation cohort 2 included 87 patients. A US-based GCN model was built using US deep learning features. In validation cohort 1, the US-based GCN model performed satisfactorily, with an AUC of 0.88 and an accuracy of 0.76. In validation cohort 2, the US-based GCN model performed satisfactorily, with an AUC of 0.84 and an accuracy of 0.75. This approach has the potential to help guide optimal ALNM management in breast cancer patients, particularly by preventing overtreatment. In conclusion, we developed a US-based GCN model to assess the ALN status of breast cancer patients prior to surgery. The US-based GCN model can provide a possible noninvasive method for detecting ALNM and aid in clinical decision-making. High-level evidence for clinical use in later studies is anticipated to be obtained through prospective studies.

This study aimed to develop and validate convolutional neural network (CNN) models for distinguishing follicular thyroid carcinoma (FTC) from follicular thyroid adenoma (FTA). Additionally, this current study compared the performance of CNN models with the American College of Radiology Thyroid Imaging Reporting and Data System (ACR-TIRADS) and Chinese Thyroid Imaging Reporting and Data System (C-TIRADS) ultrasound-based malignancy risk stratification systems. A total of 327 eligible patients with FTC and FTA who underwent preoperative thyroid ultrasound examination were retrospectively enrolled between August 2017, and August 2024. Patients were randomly assigned to a training cohort (n = 263) and a test cohort (n = 64) in an 8:2 ratio using stratified sampling. Five CNN models, including VGG16, ResNet101, MobileNetV2, ResNet152, and ResNet50, pre-trained with ImageNet, were developed and tested to distinguish FTC from FTA. The CNN models exhibited good performance, yielding areas under the receiver operating characteristic curve (AUC) ranging from 0.64 to 0.77. The ResNet152 model demonstrated the highest AUC (0.77; 95% CI, 0.67–0.87) for distinguishing between FTC and FTA. Decision curve and calibration curve analyses demonstrated the models’ favorable clinical value and calibration. Furthermore, when comparing the performance of the developed models with that of the C-TIRADS and ACR-TIRADS systems, the models developed in this study demonstrated superior performance. This can potentially guide appropriate management of FTC in patients with follicular neoplasms.