Background The aim of the study was to develop a deep learning (DL) algorithm to evaluate the pathological complete response (pCR) to neoadjuvant chemotherapy in breast cancer. Methods A total of 302 breast cancer patients in this retrospective study were randomly divided into a training set (n = 244) and a validation set (n = 58). Tumor regions were manually delineated on each slice by two expert radiologists on enhanced T1‐weighted images. Pathological results were used as ground truth. Deep learning network contained five repetitions of convolution and max‐pooling layers and ended with three dense layers. The pre‐NAC model and post‐NAC model inputted six phases of pre‐NAC and post‐NAC images, respectively. The combined model used 12 channels from six phases of pre‐NAC and six phases of post‐NAC images. All models above included three indexes of molecular type as one additional input channel. Results The training set contained 137 non‐pCR and 107 pCR participants. The validation set contained 33 non‐pCR and 25 pCR participants. The area under the receiver operating characteristic (ROC) curve (AUC) of three models was 0.553 for pre‐NAC, 0.968 for post‐NAC and 0.970 for the combined data, respectively. A significant difference was found in AUC between using pre‐NAC data alone and combined data (P < 0.001). The positive predictive value of the combined model was greater than that of the post‐NAC model (100% vs. 82.8%, P = 0.033). Conclusion This study established a deep learning model to predict PCR status after neoadjuvant therapy by combining pre‐NAC and post‐NAC MRI data. The model performed better than using pre‐NAC data only, and also performed better than using post‐NAC data only. Key points Significant findings of the study. It achieved an AUC of 0.968 for pCR prediction. It showed a significantly greater AUC than using pre‐NAC data only. What this study adds This study established a deep learning model to predict PCR status after neoadjuvant therapy by combining pre‐NAC and post‐NAC MRI data.

Objective: We proposed to determine whether the performance of inexperienced radiologists in determining extramural vascular invasion (EMVI) in rectal cancer on MRI can be promoted by means of targeted training. Methods: 230 rectal cancer patients who underwent pre-operative chemoradiotherapy were included. Pre-therapy and post-therapy MR images and pathology EMVI evaluation were available for cases. 230 cases were randomly divided into 150 training cases and 80 testing cases, including 40 testing case A and 40 testing case B. Four radiologists were included for MRI EMVI evaluation, who were divided into targeted training group and non-targeted training group. The two groups evaluated testing case A at baseline, 3 month and 6 month, evaluated testing case B at 6 month. The main outcome was agreement with expert-reference for pre-therapy and post-therapy evaluation, the other outcome was accuracy with pathology for post-therapy evaluation. Results: After 6 months of training, targeted training group showed statistically higher agreement with expert-reference than non-targeted training group for both pre-therapy and post-therapy MRI EMVI evaluation of testing case A and testing case B, all p < 0.05. Targeted training group also showed significantly higher accuracy with pathology than non-targeted training group for post-therapy evaluation of testing case A and testing case B after 6 months of training, all p < 0.05. Conclusion: The diagnostic performance for MRI EMVI evaluation could be promoted by targeted training for inexperienced radiologist. Advances in knowledge: This study provided the first evidence that after 6 month targeted training, inexperienced radiologists demonstrated improved diagnostic performance, with a 20% increase in agreement with expert-reference for both pre-therapy and post-therapy MRI EMVI evaluation and also a 20% increase in or accuracy with pathology for post-therapy evaluation, while inexperienced radiologists could not gain obvious improvement in MRI EMVI evaluation through the same period of regular clinical practice. It indicated that targeted training may be necessary for helping inexperienced radiologist to acquire adequate experience for the MRI EMVI evaluation of rectal cancer, especially for radiologist who works in a medical unit where MRI EMVI diagnosis is uncommon.

No abstract

Background: Computer-aided diagnosis using deep learning algorithms has been initially applied in the field of mammography, but there is no large-scale clinical application.Methods: This study proposed to develop and verify an artificial intelligence model based on mammography. Firstly, retrospectively collected mammograms from six centers were randomized to a training dataset and a validation dataset for establishing the model. Secondly, the model was tested by comparing 12 radiologists’ performance with and without it. Finally, prospectively multicenter mammograms were diagnosed by radiologists with the model. The detection and diagnostic capabilities were evaluated using the free-response receiver operating characteristic (FROC) curve and ROC curve.Results: The sensitivity of model for detecting lesion after matching was 0.908 for false positive rate of 0.25 in unilateral images. The area under ROC curve (AUC) to distinguish the benign from malignant lesions was 0.855 (95% CI: 0.830, 0.880). The performance of 12 radiologists with the model was higher than that of radiologists alone (AUC: 0.852 vs. 0.808, P = 0.005). The mean reading time of with the model was shorter than that of reading alone (80.18 s vs. 62.28 s, P = 0.03). In prospective application, the sensitivity of detection reached 0.887 at false positive rate of 0.25; the AUC of radiologists with the model was 0.983 (95% CI: 0.978, 0.988), with sensitivity, specificity, PPV, and NPV of 94.36%, 98.07%, 87.76%, and 99.09%, respectively.Conclusions: The artificial intelligence model exhibits high accuracy for detecting and diagnosing breast lesions, improves diagnostic accuracy and saves time.Trial registration: NCT, NCT03708978. Registered 17 April 2018, https://register.clinicaltrials.gov/prs/app/ NCT03708978