Experience in management of cesarean scar pregnancy and outcomes in a single center.

OBJECTIVE: This study aimed to describe our experience of managing cesarean scar pregnancy (CSP) and outcomes depending on ultrasound imaging features. METHODS: A retrospective, cohort observational study was performed on 31 consecutive patients with CSP at 6 to 9 weeks of gestation from April 2015 to January 2021. All patients were evaluated for the residual myometrial thickness (RMT), growth direction of the gestational sac (GS), blood flow, and chorionic parenchyma using ultrasonography. Patients underwent curettage or methotrexate (MTX) combined with curettage in CSP depending on the age of the GS. Blood loss of >500 mL with curettage was considered major bleeding. RESULTS: Twenty-five (80.6%) patients had successful treatment, and six (19.4%) patients had major bleeding. The incidence of major bleeding was significantly higher in patients with >7 weeks of gestation, types II and III CSP, mixed and exogenous types of the growth direction of the GS, an RMT < 2 mm, and multiple lacunae formation in thickened chorionic parenchyma. CONCLUSIONS: The exogenous and mixed types of the GS, an RMT < 2 mm, and multiple lacunae in thickened chorionic parenchyma may be high-risk factors for major hemorrhage by curettage in CSP.

Deep learning-based carotid plaque vulnerability classification with multicentre contrast-enhanced ultrasound video: a comparative diagnostic study.

OBJECTIVES: The aim of this study was to evaluate the performance of deep learning-based detection and classification of carotid plaque (DL-DCCP) in carotid plaque contrast-enhanced ultrasound (CEUS). METHODS AND ANALYSIS: A prospective multicentre study was conducted to assess vulnerability in patients with carotid plaque. Data from 547 potentially eligible patients were prospectively enrolled from 10 hospitals, and 205 patients with CEUS video were finally enrolled for analysis. The area under the receiver operating characteristic curve (AUC) was used to evaluate the effectiveness of DL-DCCP and two experienced radiologists who manually examined the CEUS video (RA-CEUS) in diagnosing and classifying carotid plaque vulnerability. To evaluate the influence of dynamic video input on the performance of the algorithm, a state-of-the-art deep convolutional neural network (CNN) model for static images (Xception) was compared with DL-DCCP for both training and holdout validation cohorts. RESULTS: The AUCs of DL-DCCP were significantly better than those of the experienced radiologists for both the training and holdout validation cohorts (training, DL-DCCP vs RA-CEUS, AUC: 0.85 vs 0.69, p<0.01; holdout validation, DL-DCCP vs RA-CEUS, AUC: 0.87 vs 0.66, p<0.01), that is, also better than the best deep CNN model Xception we had performed, for both the training and holdout validation cohorts (training, DL-DCCP vs Xception, AUC:0.85 vs 0.82, p<0.01; holdout validation, DL-DCCP vs Xception, AUC: 0.87 vs 0.77, p<0.01). CONCLUSION: DL-DCCP shows better overall performance in assessing the vulnerability of carotid atherosclerotic plaques than RA-CEUS. Moreover, with a more powerful network structure and better utilisation of video information, DL-DCCP provided greater diagnostic accuracy than a state-of-the-art static CNN model. TRIAL REGISTRATION NUMBER: ChiCTR1900021846.

Deep learning applied to two-dimensional color Doppler flow imaging ultrasound images significantly improves diagnostic performance in the classification of breast masses: a multicenter study.

BACKGROUND: The current deep learning diagnosis of breast masses is mainly reflected by the diagnosis of benign and malignant lesions. In China, breast masses are divided into four categories according to the treatment method: inflammatory masses, adenosis, benign tumors, and malignant tumors. These categorizations are important for guiding clinical treatment. In this study, we aimed to develop a convolutional neural network (CNN) for classification of these four breast mass types using ultrasound (US) images. METHODS: Taking breast biopsy or pathological examinations as the reference standard, CNNs were used to establish models for the four-way classification of 3623 breast cancer patients from 13 centers. The patients were randomly divided into training and test groups (n = 1810 vs. n = 1813). Separate models were created for two-dimensional (2D) images only, 2D and color Doppler flow imaging (2D-CDFI), and 2D-CDFI and pulsed wave Doppler (2D-CDFI-PW) images. The performance of these three models was compared using sensitivity, specificity, area under receiver operating characteristic curve (AUC), positive (PPV) and negative predictive values (NPV), positive (LR+) and negative likelihood ratios (LR-), and the performance of the 2D model was further compared between masses of different sizes with above statistical indicators, between images from different hospitals with AUC, and with the performance of 37 radiologists. RESULTS: The accuracies of the 2D, 2D-CDFI, and 2D-CDFI-PW models on the test set were 87.9%, 89.2%, and 88.7%, respectively. The AUCs for classification of benign tumors, malignant tumors, inflammatory masses, and adenosis were 0.90, 0.91, 0.90, and 0.89, respectively (95% confidence intervals [CIs], 0.87-0.91, 0.89-0.92, 0.87-0.91, and 0.86-0.90). The 2D-CDFI model showed better accuracy (89.2%) on the test set than the 2D (87.9%) and 2D-CDFI-PW (88.7%) models. The 2D model showed accuracy of 81.7% on breast masses ≤1 cm and 82.3% on breast masses >1 cm; there was a significant difference between the two groups (P < 0.001). The accuracy of the CNN classifications for the test set (89.2%) was significantly higher than that of all the radiologists (30%). CONCLUSIONS: The CNN may have high accuracy for classification of US images of breast masses and perform significantly better than human radiologists. TRIAL REGISTRATION: Chictr.org, ChiCTR1900021375; http://www.chictr.org.cn/showproj.aspx?proj=33139.

Ultrasound-guided percutaneous needle biopsy skill for peripheral lung lesions and complications prevention.

BACKGROUND: To investigate puncture skills and complications prevention in ultrasound-guided percutaneous needle biopsy for peripheral lung lesions. METHODS: Ninety-two peripheral lung lesions in 92 patients, detected via computed tomography (CT) and also visible on ultrasound, were retrospectively analyzed. All patients underwent percutaneous peripheral lung lesion needle biopsy under traditional ultrasound or contrast enhanced ultrasound (CEUS) guidance paying attention to avoiding necrotic areas and large blood vessels. All the specimens were examined histopathologically. Preprocedure all 92 lesions were performed by traditional ultrasonography to evaluate the size, the echogenecity, liquefaction areas and blood flow on color Doppler imaging, some of which were performed by CEUS for evaluating non-enhanced necrosis areas, contrast agent arrival time (AT) and characteristics of blood perfusion. RESULTS: The histopathologic results of all 92 lesions were as follows: 67 malignant tumors (including 28 adenocarcinomas, 19 squamous cell carcinomas, 6 bronchoalveolar carcinomas, 5 small cell carcinomas, 5 metastatic cancers, 3 poorly differentiated cancers and 1 malignant mesothelioma), 20 benign lesions (including 9 pneumonia, 6 inflammatory pseudotumors and 5 tuberculomas), 5 undetermined lesions. Of 52 lesions by CEUS guidance, 7 lesions showed enhancement in the pulmonary arterial-phase (including 6 pneumonia and 1 malignant tumors), 45 lesions showed enhancement in the bronchial artery phase (including 37 malignant tumors, 3 inflammatory pseudotumors, 4 tuberculomas and 1 undetermined lesion). According to needle insertion angle along linear path, a total of 92 lesions were divided into two groups, 49 lesions at an angle of 70°-80° needle insertion and 43 lesions at an angle of 80°-90° needle insertion. In the study, linear and non-linear two puncture paths were used, we first tried to puncture along linear path in all lesions, if an attempt to insert into the lesions failed due to be blocked by the ribs and then changed to puncture along non-linear path instead. The success rate of biopsy procedure along linear puncture was significantly higher at an angle of 80°-90°group (93.0% vs. 20.4%, P<0.01), and the adoption rate of non-linear path biopsy for solving the puncture needle blocked by the ribs was significantly higher at angle of 70°-80°group (79.6% vs. 7.0%, P<0.01). Of 52 lesions by CEUS guidance, 27 (51.9%) showed non enhanced necrosis areas on CEUS, only 5 showed liquefaction necrosis areas on gray-scale ultrasound. Of 40 lesions by traditional ultrasound guidance, 4 showed necrosis areas on gray-scale ultrasound. There were no significant differences in lesion size, the average number of biopsy attempts and complication rates between CEUS guidance group and traditional ultrasound guidance group (P>0.05), the pathological confirmation rate in CEUS guidance group was higher than that in traditional ultrasound guidance group, but without significant difference (98.1% vs. 90.0%, P>0.05). Of all 92 cases, 3 cases (3.3%) had mild pneumothorax and 4 cases (4.3%) had hemoptysis. CONCLUSIONS: In ultrasound-guided needle biopsy for peripheral lung lesions, using a combination of linear and non-linear puncture techniques and keeping away from necrotic areas and large blood vessels, may help to increase the success rate and reduce the incidence of complications further.