Transmural healing (TH) is being increasingly recognized for reflecting deep remission in Crohn’s disease (CD). The long-term clinical significance of achieving TH is still not fully known. We aimed to evaluate TH as a predictor of long-term positive outcomes using intestinal ultrasonography (US), with comparison with the established endpoint mucosal healing (MH). CD patients were consecutively recruited from September 2015 to August 2018 at a single tertiary hospital. All patients were evaluated at baseline and followed up at 6 months prospectively with a guideline-based treatment regimen. Achieving TH/MH or not was evaluated by US/colonoscopy at the first follow-up. Long-term outcomes including steroid-free clinical remission (CR), drug escalation, hospitalization, and surgery, were recorded after at least another 12 months. We identified 77 patients with a median age of 30 years (range, 12–73 years). Twenty-five (32%) patients achieved TH, and 31 (40%) patients achieved MH. TH and MH were poorly correlated (Cohen’s κ = 0.387; p < 0.05). Univariate analysis showed that both MH and TH were associated with better long-term outcomes. In multivariate analysis, TH was an independent predictor of steroid-free CR [odds ratio (OR), 52.6; p < 0.001], drug escalation (OR, 0.1; p = 0.002), and hospitalization (OR, 0.05; p = 0.005), while MH was an independent predictor of drug escalation (OR, 0.3; p = 0.05). Smoking habit was the only predictor of surgery (OR, 6.6; p = 0.02). TH is an independent predictor of more favorable long-term outcomes than MH, suggesting that TH could become the potential treatment endpoint in CD.

To develop a deep-learning system for the automatic identification of triple-negative breast cancer (TNBC) solely from ultrasound images. A total of 145 patients and 831 images were retrospectively enrolled at Peking Union College Hospital from April 2018 to March 2019. Ultrasound images and clinical information were collected accordingly. Molecular subtypes were determined from immunohistochemical (IHC) results. A CNN with VGG-based architecture was then used to predict TNBC. The model’s performance was evaluated using randomized k-fold stratified cross-validation. A t-SNE analysis and saliency maps were used for model visualization. TNBC was identified in 16 of 145 (11.03%) patients. One hundred fifteen (80%) patients, 15 (10%) patients, and 15 (10%) patients formed the train, validation, and test set respectively. The deep learning system exhibits good efficacy, with an AUC of 0.86 (95% CI: 0.64, 0.95), an accuracy of 85%, a sensitivity of 86%, a specificity of 86%, and an F1-score of 0.74. In addition, the internal representation features learned by the model showed clear differentiation across molecular subtype groups. Such a deep learning system can automatically predict triple-negative breast cancer preoperatively and accurately. It may help to get to more precise and comprehensive management. Graphical Abstract

Objective: To investigate the feasibility of a CAD system S-detect on a database from a single Chinese medical center. Materials and methods: An experienced radiologist performed breast US examinations and made assessments of 266 consecutive breast lesions in 227 patients. S-detect classified the lesions automatically in a dichotomous form. An in-training resident who was blind to both the US diagnostic results and histological results reviewed the images afterward. The final histological results were considered as the diagnostic gold standard. The diagnostic performances and interrater agreements were analyzed. Results: A total of 266 focal breast lesions (161 benign lesions and 105 malignant lesions) were assessed in this study. S-detect had a lower sensitivity (87.07%) and a higher specificity (72.27%) compared with the experienced radiologist (sensitivity 98.1% and specificity 65.43%). The sensitivity and specificity of S-detect were better than that of the resident (sensitivity 82.86% and specificity 68.94%). The AUC value of S-detect (0.807) showed no significant difference with the experienced radiologist (0.817) and was higher than that of the resident (0.758). S-detect had moderate agreement with the experienced radiologist. Conclusion: In this single-center study, a high level of diagnostic performance of S-detect on 266 breast lesions of Chinese women was observed. S-detect had almost equal diagnostic capacity with an experienced radiologist and performed better than a novice reader. S-detect was also distinguished for its high specificity. These results supported the feasibility of S-detect in aiding the diagnosis of breast lesions on an independent database.

Objective: To develop a nomogram for predicting axillary lymph node (ALN) metastases using the breast imaging reporting and data system (BI-RADS) ultrasound lexicon. Methods: A total of 703 patients from July 2015 to January 2018 were included in this study as a primary cohort for model construction. Moreover, 109 patients including 51 pathologically confirmed N1 patients (TNM staging) and 58 non-metastatic patients were recruited as an external validation cohort from March 2018 to August 2019. Ultrasound images and clinical information of these patients were retrospectively reviewed. The ultrasonic features based on the BI-RADS lexicon were extracted by two radiologists. The features extracted from the primary cohort were used to develop a nomogram using multivariate analysis. Internal and external validations were performed to evaluate the predictive efficacy of the nomogram. Results: The nomogram was based on two features (size, lesion boundary) and showed an area under the curve of 0.75 (95% confidence interval [CI], 0.70–0.79) in the primary cohort and 0.91 (95% CI, 0.84–0.97) in the external validation cohort; it achieved an 88% sensitivity in N1 patients. Conclusion: The nomogram based on BI-RADS ultrasonic features can predict breast cancer ALN status with relatively high accuracy. It has potential clinical value in improving the sensitivity and accuracy of the preoperative diagnosis of ALN metastases, especially for N1 patients.

Objective The aim of the study is to explore the potential value of S-Detect for residents-in-training, a computer-assisted diagnosis system based on deep learning (DL) algorithm. Methods The study was designed as a cross-sectional study. Routine breast ultrasound examinations were conducted by an experienced radiologist. The ultrasonic images of the lesions were retrospectively assessed by five residents-in-training according to the Breast Imaging Report and Data System (BI-RADS) lexicon, and a dichotomic classification of the lesions was provided by S-Detect. The diagnostic performances of S-Detect and the five residents were measured and compared using the pathological results as the gold standard. The category 4a lesions assessed by the residents were downgraded to possibly benign as classified by S-Detect. The diagnostic performance of the integrated results was compared with the original results of the residents. Participants A total of 195 focal breast lesions were consecutively enrolled, including 82 malignant lesions and 113 benign lesions. Results S-Detect presented higher specificity (77.88%) and area under the curve (AUC) (0.82) than the residents (specificity: 19.47%–48.67%, AUC: 0.62–0.74). A total of 24, 31, 38, 32 and 42 identified as BI-RADS 4a lesions by residents 1, 2, 3, 4 and 5 were downgraded to possibly benign lesions by S-Detect, respectively. Among these downgraded lesions, 24, 28, 35, 30 and 40 lesions were proven to be pathologically benign, respectively. After combining the residents' results with the results of the software in category 4a lesions, the specificity and AUC of the five residents significantly improved (specificity: 46.02%–76.11%, AUC: 0.71–0.85, p<0.001). The intraclass correlation coefficient of the five residents also increased after integration (from 0.480 to 0.643). Conclusions With the help of the DL software, the specificity, overall diagnostic performance and interobserver agreement of the residents greatly improved. The software can be used as adjunctive tool for residents-in-training, downgrading 4a lesions to possibly benign and reducing unnecessary biopsies.