European radiology
-
To investigate the feasibility of a deep learning-based detection (DLD) system for multiclass lesions on chest radiograph, in comparison with observers. ⋯ • The DLD system was feasible for detection with pattern classification of multiclass lesions on chest radiograph. • The DLD system had high performance of image-wise classification as normal or abnormal chest radiographs (AUROC, 0.985) and showed especially high specificity (99.0%). • In lesion-wise detection of multiclass lesions, the DLD system outperformed all 9 observers (FOM, 0.962 vs. 0.886; p < 0.001).
-
Women in Focus: Be Inspired was a unique programme held at the 2019 European Congress of Radiology that was structured to address a range of topics related to gender and healthcare, including leadership, mentoring and the generational progression of women in medicine. In most countries, women constitute substantially fewer than half of radiologists in academia or private practice despite frequently accounting for at least half of medical school enrolees. Furthermore, the proportion of women decreases at higher academic ranks and levels of leadership, a phenomenon which has been referred to as a "leaky pipeline". ⋯ Strategies for both individuals and institutions to proactively increase the representation of women in academic and leadership positions are suggested. KEY POINTS: • Gender-diverse teams perform better. Thus, gender diversity throughout the radiologic workplace, including in leadership positions, is important for the current and future success of the field. • Though women now make up roughly half of medical students, they remain underrepresented among radiology trainees, faculty and leaders. • Factors leading to the gender gap in academia and leadership positions in Radiology include a lack of role models and mentors, unconscious biases, other societal barriers and generational changes.
-
To develop and evaluate the performance of U-Net for fully automated localization and segmentation of cervical tumors in magnetic resonance (MR) images and the robustness of extracting apparent diffusion coefficient (ADC) radiomics features. ⋯ • U-Net-based deep learning can perform accurate fully automated localization and segmentation of cervical cancer in diffusion-weighted MR images. • Combining b0, b1000, and apparent diffusion coefficient (ADC) images exhibited the highest accuracy in fully automated localization. • First-order radiomics feature extraction from whole tumor volume was robust and could thus potentially be used for longitudinal monitoring of treatment responses.
-
To examine whether the texture analysis of dual-time-point (DTP) F-18-fluorodeoxyglucose (18F-FDG)-PET/CT imaging can differentiate between 18F-FDG-avid benign and malignant pulmonary lesions. ⋯ • Malignant pulmonary lesions showed significantly higher SUV-related (SUVmax and SUVmean) and volumetric (MTV and TLG) parameters than benign pulmonary lesions in both early and delayed images. • Malignant pulmonary lesions showed significantly more heterogeneous18F-FDG uptake than benign pulmonary lesions in both early and delayed images. • Combined use of independent parameters extracted from DTP imaging might yield a high diagnostic accuracy to differentiate between benign and malignant18F-FDG-avid pulmonary lesions.
-
To investigate the efficacy and safety of a new portable ultrasound-guided high-intensity focused ultrasound system (USgHIFU) with advanced targeting and beam steering technology for the treatment of uterine fibroids. ⋯ • A portable compact ultrasound-guided high-intensity focused ultrasound (HIFU) can effectively and safely treat uterine fibroids. • Advanced functions, such as portability, targeted forecasting, electronic beam steering, and interleaved scanning, might be helpful in enhancing the clinical applicability of ultrasound-guided high-intensity focused ultrasound. • In the long-term follow-up of more than 2 years, approximately 80% of those surveyed were satisfied with their HIFU treatment.