MRI-Based Radiomics Approach Predicts Tumor Recurrence in ER + /HER2 - Early Breast Cancer Patients.

Oncotype Dx Recurrence Score (RS) has been validated in patients with ER + /HER2 - invasive breast carcinoma to estimate patient risk of recurrence and guide the use of adjuvant chemotherapy. We investigated the role of MRI-based radiomics features extracted from the tumor and the peritumoral tissues to predict the risk of tumor recurrence. A total of 62 patients with biopsy-proved ER + /HER2 - breast cancer who underwent pre-treatment MRI and Oncotype Dx were included. An RS > 25 was considered discriminant between low-intermediate and high risk of tumor recurrence. Two readers segmented each tumor. Radiomics features were extracted from the tumor and the peritumoral tissues. Partial least square (PLS) regression was used as the multivariate machine learning algorithm. PLS ß-weights of radiomics features included the 5% features with the largest ß-weights in magnitude (top 5%). Leave-one-out nested cross-validation (nCV) was used to achieve hyperparameter optimization and evaluate the generalizable performance of the procedure. The diagnostic performance of the radiomics model was assessed through receiver operating characteristic (ROC) analysis. A null hypothesis probability threshold of 5% was chosen (p < 0.05). The exploratory analysis for the complete dataset revealed an average absolute correlation among features of 0.51. The nCV framework delivered an AUC of 0.76 (p = 1.1∙10-3). When combining "early" and "peak" DCE images of only T or TST, a tendency toward statistical significance was obtained for TST with an AUC of 0.61 (p = 0.05). The 47 features included in the top 5% were balanced between T and TST (23 and 24, respectively). Moreover, 33/47 (70%) were texture-related, and 25/47 (53%) were derived from high-resolution images (1 mm). A radiomics-based machine learning approach shows the potential to accurately predict the recurrence risk in early ER + /HER2 - breast cancer patients.

Incidental detection of pulmonary emboli on routine MDCT of the chest.

OBJECTIVE: The objectives of our study were to assess the prevalence of pulmonary embolism incidentally detected on routine MDCT of the chest and to determine whether the use of wide window settings can improve detection of unsuspected pulmonary embolism. MATERIALS AND METHODS: A retrospective review of routine contrast-enhanced MDCT scans of the chest obtained in 589 patients was undertaken. CT angiograms obtained for suspected pulmonary embolism or thoracic aorta disease were not considered. Image evaluation was performed on a dedicated workstation during two separate review sessions using different window settings: standard, with a width of 400 H and level of 40 H; and wide, with a width of 600 H and level of 100-150 H. The quality of vascular enhancement was recorded. RESULTS: Eight examinations were excluded because of poor quality. Unsuspected pulmonary embolism was present in 20 (3.4%) of 581 patients with an inpatient prevalence of 4.0% (19/474) and outpatient prevalence of 0.9% (1/107). Fourteen patients (70.0%) with unsuspected pulmonary embolism had cancer. The proximal extent of pulmonary embolism involved the main pulmonary artery in five patients, a lobar artery in five, and a segmental artery in 10; isolated subsegmental thrombi were never found. The use of wide window settings allowed detection of pulmonary embolism in two more patients than did the standard settings. CONCLUSION: Unsuspected pulmonary embolism can be found in a significant number of patients undergoing a routine MDCT study of the chest, with a higher prevalence among inpatients with malignancy. The use of wide window settings is recommended when interpreting routine CT scans of the chest to improve detection of unsuspected pulmonary embolism.