Background: Assessment of lymphovascular invasion (LVI) in breast cancer (BC) primarily relies on preoperative needle biopsy. There is an urgent need to develop a non‐invasive assessment method.Purpose: To develop an effective model to assess the LVI status in patients with BC using magnetic resonance imaging morphological features (MRI‐MF), Radiomics, and deep learning (DL) approaches based on dynamic contrast‐enhanced MRI (DCE‐MRI).Study Type: Cross‐sectional retrospective cohort study.Population: The study included 206 BC patients, with 136 in the training set [97 LVI(−) and 39 LVI(+) cases; median age: 51.5 years] and 70 in the test set [52 LVI(−) and 18 LVI(+) cases; median age: 48 years].Field Strength/Sequence: 1.5 T/T1‐weighted images, fat‐suppressed T2‐weighted images, diffusion‐weighted imaging (DWI), and DCE‐MRI.Assessment: The MRI‐MF model was developed with conventional MR features using logistic analyses. The Radiomic feature extraction process involved collecting data from categorized DCE‐MRI datasets, specifically the first and second post‐contrast images (A1 and A2). Next, a DL model was implemented to determine LVI. Finally, we established a joint diagnosis model by combining the MRI‐MF, Radiomics, and DL approaches.Statistical Tests: Diagnostic performance was compared using receiver operating characteristic curve analysis, confusion matrix, and decision curve analysis.Results: Rim sign and peritumoral edema features were used to develop the MRI‐MF model, while six Radiomics signature from the A1 and A2 images were used for the Radiomics model. The joint model (MRI‐MF + Radiomics + DL models) achieved the highest accuracy (area under the curve [AUC] = 0.857), being significantly superior to the MRI‐MF (AUC = 0.724), Radiomics (AUC = 0.736), or DL (AUC = 0.740) model. Furthermore, it also outperformed the pairwise combination models: Radiomics + MRI‐MF (AUC = 0.796), DL + MRI‐MF (AUC = 0.796), or DL + Radiomics (AUC = 0.826).Data Conclusion: The joint model incorporating MRI‐MF, Radiomics, and DL approaches can effectively determine the LVI status in patients with BC before surgery.Level of Evidence: 4Technical Efficacy: Stage 2

This study aims to quantify intratumoral heterogeneity (ITH) using preoperative CT image and evaluate its ability to predict pathological high-grade patterns, specifically micropapillary and/or solid components (MP/S), in patients diagnosed with clinical stage I solid lung adenocarcinoma (LADC). In this retrospective study, we enrolled 457 patients who were postoperatively diagnosed with clinical stage I solid LADC from two medical centers, assigning them to either a training set (n = 304) or a test set (n = 153). Sub-regions within the tumor were identified using the K-means method. Both intratumoral ecological diversity features (hereafter referred to as ITH) and conventional radiomics (hereafter referred to as C-radiomics) were extracted to generate ITH scores and C-radiomics scores. Next, univariate and multivariate logistic regression analyses were employed to identify clinical-radiological (Clin-Rad) features associated with the MP/S (+) group for constructing the Clin-Rad classification. Subsequently, a hybrid model which presented as a nomogram was developed, integrating the Clin-Rad classification and ITH score. The performance of models was assessed using the receiver operating characteristic (ROC) curves, and the area under the curve (AUC), accuracy, sensitivity, and specificity were determined. The ITH score outperformed both C-radiomics scores and Clin-Rad classification, as evidenced by higher AUC values in the training set (0.820 versus 0.810 and 0.700, p = 0.049 and p = 0.031, respectively) and in the test set (0.805 versus 0.771 and 0.732, p = 0.041 and p = 0.025, respectively). Finally, the hybrid model consistently demonstrated robust predictive capabilities in identifying presence of MP/S components, achieving AUC of 0.830 in the training set and 0.849 in the test set (all p < 0.05). The ITH derived from sub-region within the tumor has been shown to be a reliable predictor for MP/S (+) in clinical stage I solid LADC.

Purpose: To develop a preliminary deep learning model that uses diffusion-weighted imaging (DWI) images to classify the severity of neurological impairment caused by ischemic stroke. Materials and Methods: This retrospective study included 851 ischemic stroke patients (711 patients in the training set and 140 patients in the test set). The patients’ NIHSS scores, which reflect the severity of neurological impairment, were reviewed upon admission and on Day 7 of hospitalization and were classified into two stages (stage 1 for NIHSS < 5 and stage 2 for NIHSS ≥ 5). A 3D-CNN was trained to predict the stage of NIHSS based on different preprocessed DWI images. The performance in predicting the severity of anterior and posterior circulation stroke was also investigated. The AUC, specificity, and sensitivity were calculated to evaluate the performance of the model. Results: Our proposed model obtained better performance in predicting the NIHSS stage on Day 7 of hospitalization than that at admission (best AUC 0.895 vs. 0.846). Model D trained with DWI images (normalized with z-score and resized to 256 × 256 × 64 voxels) achieved the best AUC of 0.846 in predicting the NIHSS stage at admission. Model E rained with DWI images (normalized with maximum–minimum and resized to 128 × 128 × 32 voxels) achieved the best AUC of 0.895 in predicting the NIHSS stage on Day 7 of hospitalization. Our model also showed promising performance in predicting the NIHSS stage on Day 7 of hospitalization for anterior and posterior circulation stroke, with the best AUCs of 0.905 and 0.903, respectively. Conclusions: Our proposed 3D-CNN model can effectively predict the neurological severity of IS using DWI images and performs better in predicting the NIHSS stage on Day 7 of hospitalization. The model also obtained promising performance in subgroup analysis, which can potentially help clinical decision making.