Objectives: To establish a radiomics model for distinguishing between the benign and malignant mammary gland nodules via combining the features from nodule and mammary regions on DCE-MRIMethods: In this retrospective study, a total of 103 cases with mammary gland nodules (malignant/benign = 80/23) underwent DCE-MRI, and was confirmed by biopsy pathology. Features were extracted from both nodule region and mammary region on DCE-MRI. Three SVM classifiers were built for diagnosis of benign and malignant nodules as follows: the model with the features only from nodule region (N model), with the features only from mammary region (M model) and the model combining the features from nodule region and mammary region (NM model). The performance of models was evaluated with the area under the curve of receiver operating characteristic (AUC).Results: One radiomic features is selected from nodule region and 3 radiomic features is selected from mammary region. Compared with N or M model, NM model exhibited the best performance with an AUC of 0.756.Conclusions: Compared with the model only using the features from nodule or mammary region, the radiomics-based model combining the features from nodule and mammary region outperformed in the diagnosis of benign and malignant nodules.
The basilar artery has the most perioperative complications in stenting compared to the other intracranial arteries. We aim to study whether the procedural safety in stenting for basilar stenosis has improved. This study was a single-arm, non-randomized trial that included historically controlled patients for comparison. Between January 2012 and March 2019, 147 consecutive patients with symptomatic basilar stenoses receiving elective stenting treatment were included in current basilar artery stenting (BAS) group. The prospectively collected and registered 120 patients by the same interventional team from September 2001 to November 2011 were set as historical BAS group for control. A total of 267 individuals were included in this study, with a mean age of 59.5 ± 8.1 years. The proportion of patients with lesion length >15 mm was 26.5% (39/147) in the current BAS group versus 4.2% (5/120) in the historical BAS group. We found significant differences between these 2 groups in Mori A (17.7% vs 42.5%) and Mori C patients (42.9% vs 13.3%). The proportion of patients receiving preoperative high-resolution magnetic resonance (HRMRI) evaluation was 83.0% (122/147) in the current BAS group versus 20.8% (25/120) in the historical group (P < .05). Balloon-expendable stent (BES) (n = 1), Wingspan (n = 34), and Enterprise (n = 112) stents were placed in the current BAS group. In contrast, only balloon-expendable stent (BES) (n = 48) and Wingspan (n = 72) were deployed in the historical BAS group. The incidence of the safety endpoint (SE) was 4.1% (involving 6 patients) in the current BAS group versus 11.7% (involving 14 patients) in the historical BAS group (P < .05). In multivariate analysis, no risk factor was associated with the occurrence of the safety endpoint (SE). When BAS cases operated by the surgical team accumulated to 120 to 150, the incidence of complications decreased significantly. This is the largest sample size study to discuss the safety of BAS. The significantly decreased incidence of complications indicates that the improving technical measures and the accumulation of operation experience are necessary.
Breast cancer is one of the most common and deadly diseases that threaten women’s health worldwide, and early and accurate breast nodule segmentation is of great significance for the early detection, diagnosis and treatment of breast cancer. However, due to the limitation of medical annotated data, the training segmentation models for medical images is still challenging. The Segment Anything Model (SAM) is a foundational model that interactively segments target objects. Although significant achievements have been made in natural images, there are still challenges in the application in medical images. In this paper, the effect of SAM on breast nodule segmentation was studied from three aspects: initial weight, organ (breast) mask and prompt box, so as to explore the feasibility of breast nodule segmentation. Through a series of experiments on the data collected in this paper, it is found that the use of MedSAM initial weights and the use of single individual fixed prompt boxes can obtain better segmentation results, and can take into account practical application problems.