ObjectiveDermatofibrosarcoma protuberans is a low-to-intermediate-grade malignancy with high postoperative recurrence risk. It is often misdiagnosed as superficial venous malformation due to nonspecific manifestations and clinical features similar to those of other soft tissue tumors. Ultrasound examination is crucial for dermatofibrosarcoma protuberans evaluation; however, its value in differentiating dermatofibrosarcoma protuberans from superficial venous malformation remains underinvestigated.MethodsThis retrospective study analyzed and compared the clinical and ultrasonographic features between 41 histopathologically confirmed dermatofibrosarcoma protuberans cases and 41 superficial venous malformation cases. Clinical data included sex, age, tumor size, and location. Ultrasound findings were categorized into five types, and the following features were evaluated: shape, boundary, pattern, invasion depth, and vascularity.ResultsThe dermatofibrosarcoma protuberans tissues had significantly larger maximum diameters than superficial venous malformations (p < 0.05). Anatomically, dermatofibrosarcoma protuberans predominantly occurred on the trunk, while superficial venous malformations were more common on the extremities (p < 0.05). Dermatofibrosarcoma protuberans tissues mostly invaded both dermis and hypodermis, whereas superficial venous malformations primarily involved the hypodermis (p < 0.05). Dermatofibrosarcoma protuberans tissues had clearer boundaries (p < 0.05) and were more likely to show hyperechoic cord-like structures (type 4), while superficial venous malformations frequently presented network structures (type 3) (p < 0.05).ConclusionsUltrasound can provide valuable morphological features to assist in the differential diagnosis of dermatofibrosarcoma protuberans and superficial venous malformation, improving preoperative assessment accuracy and guiding treatment planning.

BACKGROUND:Rheumatoid arthritis (RA) is a systemic autoimmune disorder characterized by chronic inflammation and progressive joint destruction. Tenosynovitis is one of the early manifestations of RA. This study aims to develop a machine learning (ML)-based model using ultrasound (US) radiomics to objectively diagnosis tenosynovitis in RA patients, thereby facilitating accurate evaluation of RA. METHODS:This study included a total of 1496 grayscale US images of the wrist extensor tendons, wrist flexor tendons, and finger flexor tendons from 152 patients with RA. Radiomic features were extracted from the US images. The radiomic features and a total of 10 clinically relevant features were selected to train machine learning model. To avoid data leakage, the dataset was partitioned at the patient level with 80% allocated to the training set and 20% to the test set. The model was trained for 100 epochs with an early stopping strategy (halted if no test set performance improvement was observed for 10 consecutive epochs) to prevent overfitting. Comparative experiments were conducted against two conventional ML methods: Support Vector Machine (SVM) and Random Forest (RF). Sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1 score, accuracy, and the area under the receiver operating characteristic curve (AUC) of the model were calculated. Calibration curves and decision curve analysis (DCA) were employed to assess the model's clinical utility, and the average per-case processing time was measured to verify real-time applicability. RESULTS:The dataset comprised 1196 images for training and 300 images for testing. In the training set and the test set, the AUC reached 0.969 and 0.914 respectively. The model demonstrated robust performance on the test set, with a sensitivity of 0.881, specificity of 0.788, PPV of 0.505, NPV of 0.964, F1 score of 0.642 and accuracy of 0.807. The model also outperformed SVM (AUCs: 0.909 and 0.881) and RF (AUCs: 0.955 and 0.880) on the training and test sets, respectively. The average processing time per case was 0.8 s, which meets the real-time operational requirements of clinical settings. Calibration curves indicated excellent agreement between predicted and observed outcomes, while DCA confirmed the model's clinical applicability and predictive accuracy across both training and test datasets. CONCLUSION:The XGBoost-based machine learning model developed in this study could effectively diagnosed tenosynovitis on US imaging for RA patients, outperforming SVM and RF. Owing to its real-time processing capability, the model has potential to facilitate the accurate evaluation of RA.

Objective This study aimed to develop and validate an ultrasound-based model integrating conventional ultrasound and calcification patterns (US-CAL) for distinguishing benign from malignant calcified soft tissue masses. Methods This retrospective study analyzed 101 pathologically confirmed soft tissue masses (78 benign, 23 malignant) that showed calcification on ultrasound. We developed two models: the US-CAL model (combining conventional and calcification features) and a conventional ultrasound (US) model. Their performance was compared using receiver operating characteristic (ROC) and decision curve analysis. Results The US-CAL model outperformed the US model, with a significantly higher area under the curve (AUC) (0.91 [95% CI: 0.85-0.97] vs. 0.85 [0.77-0.93]; p < 0.05). It also demonstrated superior sensitivity (0.91 vs. 0.83), specificity (0.73 vs. 0.71), positive predictive value (PPV) (0.50 vs. 0.45), and negative predictive value (NPV) (0.97 vs. 0.93). DCA confirmed a greater net clinical benefit for the US-CAL model. Conclusion The US-CAL model significantly improves the diagnostic accuracy for calcified soft tissue masses, offering a clinically valuable tool to enhance early detection and diagnostic confidence.

ObjectiveThis study aimed to extract radiomic features from ultrasound (US) images of soft tissue tumors (STTs) and develop a diagnostic model for STTs using radiomic and clinical patient data. MethodsThree hundred and sixty-nine patients were recruited as the training group, with 249 benign and 120 malignant STTs, and 127 patients as the validation group, with 93 benign and 34 malignant STTs. We extracted the radiomic features of the US images using an open-source Python package. We selected the most relevant features using the least absolute shrinkage and selection operator (LASSO) regression. Then we used a combination of clinical indexes, radiomic features, and color-Doppler US to construct a diagnostic model for STTs. The diagnostic performance of the model was evaluated by measuring its sensitivity, specificity, area under the receiver operating curve (AUC), and calibration. ResultsWe selected 20 radiomic features of the US images. The model based on the clinical indexes, radiomic features, and color-Doppler scores showed good diagnostic performances on both the training [AUC: 0.97 (0.95-0.98)] and validation datasets [AUC: 0.93 (0.86-0.99)]. The model also presented good calibration with the original results. DiscussionWe extracted radiomic features of ultrasound images of patients with STTs and constructed a clinical-imaging model for differentiating malignant and benign STT lesions. A nomogram displayed a clinical-imaging model, which showed good diagnostic efficacy and calibration in both the training and validation datasets. The clinical-imaging model has potential value for clinical use. ConclusionThe diagnostic model based on clinical, US radiomic, and imaging features presented a high diagnostic performance in STTs, which can have potential value in further clinical utilization.

BackgroundPresurgical evaluation of the histopathological grade of soft tissue sarcoma (STS) is important for enacting treatment strategies. In this study, we plan to investigate the correlation of high-output ultrasound (US) radiomic features and the histopathological grade of STS.MethodsPatients with STS were retrospectively enrolled. The radiomic features were extracted from the US images of the STS lesions. The lesions were graded according to the Fédération Nationale des Centers de Lutte Contre le Cancer (FNCLCC) histopathological grading system. The correlation of the radiomic features and the FNCLCC grades was evaluated. We used the features correlated with the histopathological grades to build a model for predicting high-grade STS (Grade II and III).ResultsA total of 79 patients with STS were enrolled. And 15 radiomic features were found correlated with the FNCLCC grades of STSs, with the correlation coefficient ranging from 0.22 to 0.38. And 8 features showed significant difference among the three grades. The model for predicting high-grade STS based on the 8 radiomic features had an AUC value of 0.80, a sensitivity of 0.73, and a specificity of 0.78.ConclusionThe US radiomic features were correlated with the FNCLCC grade of STS. The radiomic analysis of US imaging could be potentially helpful for identifying the FNCLCC grades of STS pre-surgically.

OBJECTIVE:To evaluate the availability and reliability of the European League Against Rheumatisms Outcome Measures in Rheumatology Synovitis (EULAR-OMERACT) scoring system among radiologists with different levels of musculoskeletal ultrasound (US) experience in assessing synovitis in patients with rheumatoid arthritis (RA). METHOD:The patients with RA were retrospectively recruited from January 2020 to March 2022. Five radiologists with different levels of US experience were recruited for the reader study (R1-5), which included two parts. The participating radiologists first read 120 gray-scale (GS) and 120 Doppler US images twice, before and after a standard training program. In the first part, they semi-quantitatively scored the images from 0 to 3 based on the EULAR-OMERACT scoring system. In the second part, they read and scored 165 paired GS and Doppler images two times in 1 month using the EULAR-OMERACT scoring system. The correlation between the sum of the GSUS and power Doppler US (PDUS) image scores and the clinical scores was assessed. RESULT:The intra-rater agreement of the five radiologists was good for the EULAR-OMERACT scoring system, with κ ranging from 0.72 to 0.94 for GSUS and from 0.81 to 0.97 for PDUS. The inter-rater agreement among the experts was good to very good in the EULAR-OMERACT scoring system (κ: 0.76-0.94 for GSUS and 0.80-0.96 for PDUS). The sum of the GSUS and PDUS scores in the EULAR-OMERACT scoring system was moderate to highly positively correlated with the clinical scores (ρ of GSUS: 0.58-0.79, ρ of PDUS: 0.57-0.70 for disease activity score in 28 joints C-reactive protein) after training. CONCLUSION:The EULAR-OMERACT scoring system is a reliable method for evaluating synovitis in RA and shows potential for disease assessment and follow-up in patients with RA.

Extraosseous Ewing's sarcoma is a malignant mesenchymal tumor much rarer than skeletal Ewing's sarcoma. The synchronous or metachronous occurrence of advanced breast cancer with retroperitoneal Ewing's sarcoma is extremely rare. To date, only a few cases of extraosseous Ewing's sarcoma with contrast-enhanced ultrasound findings have been reported. This study aims to report a case of a retroperitoneal Ewing's sarcoma in a 39-year-old woman with advanced breast cancer, where grayscale ultrasound, contrast-enhanced ultrasound, and computed tomography findings were included. To our knowledge, this is the first reported case of ultrasound and contrast-enhanced ultrasonography manifestation of retroperitoneal Ewing's sarcoma as a second primary tumor.

Introduction:: Neurolymphomatosis (NL) is a rare disease. Ultrasound (US) plays a crucial role in diagnosing and following up the NL. Case Presentation:: A 59-year-old man was hospitalized with acute pain in the left upper extremity. Ultrasound revealed segmental swelling of multiple nerves around his left elbow with abundant blood flow signals. Contrast-Enhanced Ultrasound (CEUS) showed a rapid, complete and homogenous enhancement in the nerve lesions in the early arterial phase. The NL was confirmed by imaging and flow cytometry, and he accepted chemotherapy. The posttherapeutic ultrasound showed that the nerves in the left upper limb were basically normal. Unfortunately, the patient died of cerebral metastasis in 5 months. Conclusion:: The nerve US and CEUS can show specific manifestations and provide more diagnostic information about NL.

Ultrasound (US) examination is widely used to diagnose carotid artery plaque, which requires the sonographer to guide the probe to scan along a specific path for complete coverage of the carotid artery region. Meanwhile, stable probe-neck interaction is important for high-quality image acquisition. In this study, a robotic system for autonomous carotid US scanning is proposed. To realize the autonomous visual servo movement of the probe, an object tracking method based on improved Siamese network is proposed. Meanwhile, a local quality assessment algorithm is proposed to ensure that carotid ultrasound images are clear and desirable for diagnosis. To address the issue of poor probe-neck contact and loss of carotid object during ultrasound scanning, an automatic recovery control method is proposed to ensure the continuity of the scanning process without the need to stop and restart the scanning. Experimental results show that the robotic system can successfully navigate the probe to move along a path that meets the clinical standard. In addition, the robot can autonomously rediscover the object and return to the normal scanning state if a stuck condition occurs.

BackgroundSoft tissue tumors (STTs) are benign or malignant superficial neoplasms arising from soft tissues throughout the body with versatile pathological types. Although Ultrasonography (US) is one of the most common imaging tools to diagnose malignant STTs, it still has several drawbacks in STT diagnosis that need improving.ObjectivesThe study aims to establish this deep learning (DL) driven Artificial intelligence (AI) system for predicting malignant STTs based on US images and clinical indexes of the patients.MethodsWe retrospectively enrolled 271 malignant and 462 benign masses to build the AI system using 5-fold validation. A prospective dataset of 44 malignant masses and 101 benign masses was used to validate the accuracy of system. A multi-data fusion convolutional neural network, named ultrasound clinical soft tissue tumor net (UC-STTNet), was developed to combine gray scale and color Doppler US images and clinic features for malignant STTs diagnosis. Six radiologists (R1-R6) with three experience levels were invited for reader study.ResultsThe AI system achieved an area under receiver operating curve (AUC) value of 0.89 in the retrospective dataset. The diagnostic performance of the AI system was higher than that of one of the senior radiologists (AUC of AI vs R2: 0.89 vs. 0.84, p=0.022) and all of the intermediate and junior radiologists (AUC of AI vs R3, R4, R5, R6: 0.89 vs 0.75, 0.81, 0.80, 0.63; p <0.01). The AI system also achieved an AUC of 0.85 in the prospective dataset. With the assistance of the system, the diagnostic performances and inter-observer agreement of the radiologists was improved (AUC of R3, R5, R6: 0.75 to 0.83, 0.80 to 0.85, 0.63 to 0.69; p<0.01).ConclusionThe AI system could be a useful tool in diagnosing malignant STTs, and could also help radiologists improve diagnostic performance.

目的 观察高频超声测量盂肱关节囊（GJC）厚度及其差值诊断冻结肩（FS）的价值。方法 纳入215例单侧FS患者（FS组）及211名健康受试者（对照组）,以高频超声测量并比较组间及组内双侧肩关节GJC厚度差异，并计算GJC厚度差值。绘制受试者工作特征曲线，计算曲线下面积（AUC）,评价GJC厚度及双侧GJC厚度差值用于诊断FS的效能。结果 FS组患侧GJC厚度大于对侧及对照组双侧（P均＜0.01）;FS组对侧GJC厚度与对照组双侧差异均无统计学意义（P均＞0.05）;对照组双侧GJC厚度差异无统计学意义（P＞0.05）。FS组双侧GJC厚度差值明显大于对照组（P＜0.01）。以2.65 mm为患侧GJC厚度的截断值，其诊断FS的AUC为0.98,敏感度为94.88%、特异度为89.48%、准确率为84.37%;以GJC厚度差值0.85 mm为截断值，其诊断FS的AUC为0.98,敏感度为92.56%、特异度为97.63%、准确率为90.19%。结论 利用高频超声测量GJC厚度及其双侧差值可有效诊断FS。

目的 探讨超声对腮腺多灶性病变良恶性的鉴别诊断价值.方法 回顾性分析59例行超声检查发现腮腺多灶性病变的患者,以病理为"金标准",记录患者的性别、年龄、病灶的数目、分布位置、腺体内淋巴结和最大病灶的大小、形状、物理性质、实性部分"网格状"形态、纵横比、边界、后方回声改变、血流情况.结果 59例病变中,良性50例,恶性9例.恶性病变患者的中位年龄为41岁,超声多表现不规则和"粗网格状";良性病变患者的中位年龄为57岁,超声多表现为规则和"细网格状".良恶性病变在年龄、形状及实性部分"网格状"形态均有统计学差异(P<0.05).其余指标在良恶性鉴别中均无统计学差异(P>0.05).结论 腮腺多灶性病变的超声表现具有一定特征性,超声对良恶性病变的鉴别具有较高的诊断价值.

OBJECTIVES:The study was designed to evaluate entheseal sites and anterior chest wall (ACW) of patients with ankylosing spondylitis (AS) using ultrasound (US) and investigate the correlation between disease activity and US score. METHODS:This prospective cross-sectional study included 104 patients with AS and 50 control subjects. Each patient underwent US scanning of 23 entheses and 11 sites of the ACW. The US features, including hypoechogenicity, thickness, erosion, calcification, bursitis, and Doppler signal, were evaluated. Disease activity was assessed based on C reactive protein (CRP), erythrocyte sedimentation rate (ESR), disease activity score-C reactive protein (ASDAS-CRP), and Bath Ankylosing Spondylitis Disease Activity Index (BASDAI). RESULTS:The most commonly involved entheses on US were the Achilles tendon (AT) and quadriceps tendon (QT). The most involved site of ACW was the sternoclavicular joint (SCJ). Compared with the control group, significant differences were observed in the AS group in the rates of US enthesitis and ACW in AT (P = .01), SCJ (P = .00), and costochondral joint (CCJ) (P = .01). Patients with high or very high disease activity had a higher erosion score (P = .02). The erosion score was weakly positively associated with CRP, ESR, BASDAI, ASDAS-CRP, and ASDAS-ESR (correlation coefficient: 0.22-0.45). CONCLUSIONS:The most commonly involved entheseal sites on US were AT and QT, while the site of ACW was SCJ. The US assessment of AS should take the ACW into account. High disease activity might indicate erosion in AS.

BACKGROUND:Nodular fasciitis (NF) has nonspecific clinical manifestations and is often misdiagnosed as sarcoma. The investigations of imaging methods for NF were limited. OBJECTIVE:To analyze the ultrasound (US) features of NF, and to evaluate the diagnostic value of US for NF. MATERIALS AND METHODS:A total of 61 NF patients were recruited retrospectively, and 551 lesions in the subcutaneous fat layer were included for comparison. We evaluated the ultrasound features of the patients and divided the NF cases into three types. Chi-square test or Fisher exact test were conducted to detect the potential difference in the distributions of three types in the two groups. RESULTS:Among the 61 NF cases, 65.6% were in the upper extremities (n = 40). The proportion of type 1, 2, and 3 were 57.4%, 24.6%, and 18.0%, respectively. NF were significantly more likely locating in the upper extremities than the other soft tissue tumors (p < 0.001). Type 1 and type 2 of sonographic features were significantly more commonly observed in NF than other soft tissue tumors among the three types (p < 0.001). CONCLUSION:The type 1 and type 2 of US features can help to distinguish NF from other lesions. US has great potential to improve the diagnostic accuracy and reduce the unnecessary surgery.

Objective:To evaluate the effectiveness of CT-ultrasound comparison as a quality control method for the missed diagnosis of focal liver lesions by ultrasound.Methods:The study subjects were patients who underwent imaging examinations at Peking University Shenzhen Hospital from December 2022 to April 2023. Using the CT examination results as the "gold standard", cases were divided into three groups based on the maximum diameter of the focal lesions suggested by CT: "≤1.0 cm", "1.1-2.0 cm", and "＞2.0 cm". The lesion locations and maximum diameters were analyzed, and the CT-ultrasound comparison results were classified as "weakly inconsistent (≤1.0 cm)", "moderately inconsistent (1.1-2.0 cm)", "strongly inconsistent (＞2.0 cm)", and "possibly consistent". Statistical analysis was then conducted. Based on the chronological order of CT and ultrasound reports, the paired records were categorized into "pre-examination quality control" (CT report before ultrasound report) and "post-examination quality control" (CT report after ultrasound report), and the quantity of records in each category was recorded. Records of "strongly inconsistent" were reviewed, followed by data analysis and quality control feedback.Results:Among the 2397 cases of CT-ultrasound paired focal liver lesions, the "inconsistency rate" was 24.53% (588/2397); the inconsistency rate of the "≤1.0 cm" group was the highest (42.62%, 430/1009), and that of the "＞2.0 cm" group was the lowest (7.66%, 49/640). The proportions of "weakly inconsistent", "moderately inconsistent", and "strongly inconsistent" categories were 17.94% (430/2397), 4.55% (109/2397), and 2.04% (49/2397), respectively. Cases of "strongly inconsistent" were mainly concentrated near the capsule of the left outer lobe of the liver and the diaphragmatic top of the right lobe. Among all inconsistent cases, 47.96% (282/588) were in the "pre-examination quality control" category.Conclusion:The method of CT-ultrasound comparison can serve as a practical quality control strategy to improve the missed diagnosis of focal liver lesions in ultrasound examinations.

OBJECTIVE:Ultrasonography (US) is the primary imaging method for soft tissue tumors (STTs), the diagnostic performance of which still requires improvement. To achieve an accurate evaluation of STTs, we built the diagnostic nomogram for STTs using the clinical and US features of patients with STTs. METHODS:A total of 613 patients with 195 malignant and 418 benign STTs were retrospectively recruited. We used a blend of clinical and ultrasonic features, as well as exclusively US features, to develop two distinct diagnostic models for STTs: the clinical-US model and the US-only model, respectively. The two models were evaluated and compared by measuring their areas under the receiver operating characteristic curve (AUC), calibration, integrated discrimination improvement (IDI) and decision curve analysis. The performance of the clinical-US model was also compared with that of two radiologists. RESULTS:The clinical-US model had better diagnostic performance than the model based on US imaging features alone (AUCs of the clinical-US and US-only models: 0.95 [0.93-0.97] vs. 0.89 [0.87-0.92], p < 0.001; IDI of the two models: 0.15 ± 0.03, p < 0.001). The clinical-US model was also superior to the two radiologists in diagnosing STTs (AUCs of clinical-US model and two radiologists: 0.95 [0.93-0.97] vs. 0.79 [0.75-0.82] and 0.83 [0.80-0.85], p < 0.001). CONCLUSION:The diagnostic model based on clinical and US imaging features had high diagnostic performance in STTs, which could help identify malignant STTs for radiologists.

In recent years, studies have shown a close relationship between cardiomyocyte death and ferroptosis. Clioquinol (CQ) can inhibit ferroptosis. Porous lipid-poly (lactic-co-glycolic acid) (PLGA) microbubbles (MBs) were prepared by double emulsification (W1/O/W2) using 1,2-dioctadecanoyl-sn-glycero-3-phophocholine and PLGA as raw materials. Porous lipid-PLGA MBs were used as carriers to prepare CQ/PLGA MBs containing CQ. CQ/PLGA had the advantages of high drug loading, good biocompatibility, and sustained release. Our results showed that CQ/PLGA improved the effect of CQ and reduced its cytotoxicity. Under low-frequency ultrasound with certain parameters, CQ/PLGA showed steady-state cavitation, which increased the membrane permeability of mouse cardiomyocyte HL-1 to a certain extent and further prevented the process of ferroptosis in mouse cardiomyocyte HL-1.

A series of substituted 4H-3,1-benzoxazin-4-ones have been made and assayed as inhibitors of human leukocyte elastase (HLE) and other serine proteases. The benzoxazinones are kinetically competitive, alternate substrate inhibitors that inhibit by acylation and slow deacylation. Two structure-activity relationships have been found which are consistent with this mechanism. First, electron withdrawal at position 2 gives better inhibition (lower Ki values) because acylation rates are increased while deacylation is relatively unaffected. Second, benzoxazinones with methyl or ethyl substitution at position 5 are better inhibitors of HLE because the acyl enzymes formed from these compounds are 2,6-disubstituted benzoic acid esters and their deacylation is sterically hindered.

To evaluate the sonographic features of secondary involvement of skin and subcutaneous tissues by hematologic malignancies.

目的 分析腮腺囊实性肿瘤中良性和恶性病变的声像特征,探讨超声诊断腮腺良恶性病变的可行性.方法 回顾性分析手术或穿刺活检病理结果的76例腮腺囊实性肿瘤的超声图像,分析肿瘤超声特征与良恶性相关性.结果 76例腮腺囊实性肿瘤中,病理证实为良性52例,恶性24例.腮腺囊实性肿瘤良恶性病变的超声表现,在肿瘤形态、整体边界、实性成分主要分布区域、实性成分边界、实性成分与囊壁夹角、囊性成分透声以及彩色多普勒血流信号等指标的差异有统计学意义(P＜0.05).结论 腮腺囊实性肿瘤良恶性病变的超声表现具有一定特征.