Qingli Zhu

Background: Accurate assessment of hidradenitis suppurativa (HS) severity is crucial for individualized management, yet conventional clinical grading may underestimate disease extent due to subclinical lesions. Ultrasound enables visualization of deep abscesses and tunnels and may provide additional prognostic information. Materials and Methods: Sixty‐eight patients with HS underwent standardized clinical and ultrasonographic evaluation. Disease severity was classified using the International Hidradenitis Suppurativa Severity Score System (IHS4) and the modified Sonographic Scoring of HS (mSOS‐HS). Concordance between the two systems was assessed, and ultrasonographic grading and features were analyzed in relation to achievement of IHS4‐55 at week 12. Results: The mSOS‐HS classified 18 patients (26.5%) as having more severe disease than IHS4. The two grading systems showed statistically significant agreement, with the Kappa value approaching the threshold for moderate agreement (Kappa = 0.395, 95% CI: 0.204–0.586, p < 0.001). Patients with higher mSOS‐HS grades were less likely to achieve IHS4‐55 at week 12 ( p = 0.014). Among specific ultrasonographic features, the railway sign, defined as parallel hyperechoic lines within tunnel‐like structures, was significantly associated with failure to achieve IHS4‐55 ( p = 0.003). Conclusion: Ultrasonography reveals subclinical HS involvement beyond clinical examination and provides prognostic information for treatment response. The mSOS‐HS complements IHS4 for comprehensive disease staging, while the railway sign may serve as an imaging biomarker for unfavorable response across real‐world treatment settings.

The 70-gene signature (70-GS; MammaPrint) assay is useful for prognosis assessment in HR+/HER2− early breast cancer, but limited accessibility motivates development of noninvasive alternatives. We retrospectively enrolled 219 women with preoperative grayscale ultrasound and 70-GS results, including a development cohort (n = 125), an internal validation cohort (n = 53), and a temporally independent validation cohort (n = 41). Radiomic features were extracted from manually delineated ROIs using PyRadiomics, and a radiomics score was derived after LASSO selection. Candidate radiomics-only, clinicopathologic-only, and full clinicoradiomic models were explored. To reduce overfitting, we selected a parsimonious model combining the radiomics score and Ki67 as the primary model. The simplified model achieved AUCs of 0.878, 0.816, and 0.831 in the development, internal validation, and temporally independent validation cohorts, respectively. In 1000 bootstrap resamples, the optimism-corrected AUC was 0.872 and the corrected calibration slope was 0.953. Adding the radiomics score to a Ki67-only model significantly improved model fit (likelihood-ratio chi-square = 17.14, df = 1, p < 0.001). An ultrasound radiomics and Ki67 model may provide a noninvasive reference for estimating MammaPrint risk categorization, but it should be considered only as a supportive adjunct and not as a replacement for genomic testing.

Cronkhite–Canada syndrome is a rare, non-hereditary polyposis syndrome characterized by non-specific gastrointestinal symptoms accompanied by alopecia, cutaneous hyperpigmentation, and nail dystrophy. Characteristic endoscopic findings are diffuse sessile polypoid lesions with edematous mucosa. We report a case of a 44-year-old woman in whom intestinal ultrasound and CT revealed diffuse mucosal thickening and an ileocecal intussusception—findings that may not be pathognomonic but are highly unusual in adults. These imaging features served as critical red flags that directed the clinical suspicion toward Cronkhite–Canada syndrome and prompted timely endoscopic confirmation.

Transabdominal intestinal ultrasound parameters as intermediate treatment targets in a treat-to-target strategy for moderate-to-severe ulcerative colitis

Foundation models have emerged as powerful tools for addressing various tasks in clinical settings. However, their potential development for breast ultrasound analysis remains untapped. Here we present BUSGen, the first foundation generative model designed for breast ultrasound image analysis. Pretrained on over 3.5 million breast ultrasound images, BUSGen has acquired extensive knowledge of breast structures, pathological features and clinical variations. With few-shot adaptation, BUSGen can generate repositories of realistic and informative task-specific data, facilitating the development of models for a wide range of downstream tasks. Extensive experiments highlight BUSGen's exceptional adaptability, significantly exceeding real-data-trained foundation models in breast cancer screening, diagnosis and prognosis. In breast cancer early diagnosis, our approach outperformed all board-certified radiologists (n = 9), achieving an average sensitivity improvement of 16.5% (P < 0.0001). In addition, we characterized the scaling effect of using synthetic data. Finally, BUSGen enabled de-identified data sharing, making progress forward in secure medical data utilization.

Crohn’s disease (CD) is frequently complicated by intestinal strictures, which substantially affect patients quality of life and long-term outcomes. Accurate classification of strictures—as inflammatory, fibrotic, or mixed—is critical for selecting optimal therapeutic strategies. In clinical practice, multidisciplinary team (MDT) consultation is often employed to assess stricture characteristics. However, the accuracy and inter-specialty consistency of stricture evaluation within MDTs remain inadequately characterized. This study aimed to assess the intra-disciplinary consistency and accuracy of decision-making for CD-related strictures, evaluate the accuracy of post MDT decisions, and propose recommendations for stricture nature assessment and MDT workflow optimization. A mixed-methods study was conducted at Peking Union Medical College Hospital involving 42 patients with CD and intestinal strictures. MDT participants—including specialists from gastroenterology, surgery, ultrasound, and MDT meeting chairs—were involved in evaluating intra-disciplinary decision consistency and accuracy. Semi-structured qualitative interviews were also conducted to explore factors influencing clinical decision-making. Gastroenterologists demonstrated the highest intra-team consistency (PABAK = 0.75) and diagnostic accuracy (89.3%). Ultrasound specialists showed improved consistency following targeted training (from 0.46 to 0.93). The overall accuracy of historical MDT decisions was 92.9%. Key factors influencing stricture nature judgment included clinical presentation, laboratory findings, imaging features, and endoscopic evaluation. Seven core components were identified to improve MDT workflow: expert selection, team building, training, pre-meeting preparation, in-meeting procedures, post-meeting actions, and continuous quality improvement. This study reveals variability in decision-making for CD-related strictures across different specialties. To improve diagnostic accuracy and treatment planning, we propose clear stricture classification criteria and a structured MDT workflow to standardize and enhance multidisciplinary management of CD.

Breast ultrasound (BUS) is an essential tool for diagnosing breast lesions, with millions of examinations per year. However, publicly available high-quality BUS benchmarks for AI development are limited in data scale and annotation richness. In this work, we present BUS-CoT, a BUS dataset for chain-of-thought (CoT) reasoning analysis, which contains 11,439 ultrasound images from 11,850 lesions and 4,838 patients, covering all 99 WHO-defined histopathology categories. For model training and evaluation, we provide a curated high-quality subset of 5,163 lesion-focused images annotated by experienced radiologists. To facilitate research on incentivizing CoT reasoning, we construct the reasoning processes based on observation, feature, diagnosis and pathology labels, annotated and verified by experienced experts. Moreover, by covering lesions of all histopathology types, we aim to facilitate robust AI systems in rare cases, which can be error-prone in clinical practice. The data and code are publicly available at https://doi.org/10.6084/m9.figshare.30838715.

To determine a direct method for diagnosing axillary lymph node (ALN) tumor burden preoperatively in cT1-2N0 breast cancer patients, we developed and validated a deep learning (DL) model based on ultrasound (US) images of sentinel lymph nodes (SLNs) detected by contrast-enhanced lymphatic ultrasound (CEUS). Women with cT1-T2N0 breast cancer who received CEUS were enrolled prospectively from Peking Union Medical College Hospital between April 2020 and July 2021 and from Sichuan Cancer Hospital between April 2022 and July 2022. Heavy ALN tumor burden was defined as > 2 metastatic lymph nodes according to the Z0011 criteria. We developed a DL model, the modality-adaptive network with clinicopathological information (MAN + C), using grayscale or color Doppler US images and radioclinicopathological information to predict heavy tumor burden. A total of 595 SLNs from 374 patients met the inclusion criteria. The areas under the receiver operating characteristic curve (AUCs) were calculated to evaluate the predictive performance of the model, yielding values of 0.91[95%CI(confidence interval):0.899–0.943], 0.98[95%CI:0.950-1], 0.89[95%CI:0.850–0.935], and 0.84[95%CI:0.811–0.869] in the training, validation, independent and external test datasets, respectively. Compared to current artificial intelligence (AI) models, this model extends usability by 30%, encompassing patients with multifocal lesions or those who have undergone primary breast cancer lesion therapy. Using this model, 88.9% of patients could safely decide whether they could waive unnecessary SLN biopsy. MAN + C provided a direct and efficient method for accurate preoperative assessment of ALN tumor burden in cT1-2N0 breast cancer patients.

Integrating perspectives on transabdominal intestinal ultrasound in inflammatory bowel disease management: a nationwide cross-sectional survey of physicians and patients in China