AI improves lung cancer detection on x-rays
December 11, 2020 -- An artificial intelligence (AI) algorithm can catch lung cancers that were initially missed by radiologists on chest radiographs and improve radiologist performance when used as a second reader, according to research published online December 10 in Radiology: Cardiothoracic Imaging.  Discuss
AI body analysis finds lung cancer survival risk factors
December 11, 2020 -- An artificial intelligence (AI) algorithm was able to quickly analyze body composition metrics on abdominal/pelvic CT exams, yielding better prognostic information for survival in lung cancer patients than a patient's body mass index, according to research presented at the virtual RSNA 2020 meeting.  Discuss
AI tool beats traditional breast cancer risk assessments
December 11, 2020 -- A breast cancer risk assessment model based on artificial intelligence (AI) outperformed traditional risk assessment tools in new research presented at the 2020 San Antonio Breast Cancer Symposium meeting. The AI model beat conventional risk models used alone and when combined with breast density data.  Discuss
MRI radiomics predicts axillary lymph node metastasis
December 8, 2020 -- In patients with early-stage breast cancer, "signatures" derived from MRI radiomics and patient clinical risk characteristics can be utilized to preoperatively predict axillary lymph node metastasis as well as disease-free survival, according to research published online December 8 in JAMA Network Open.  Discuss
CT radiomics characterizes complex cystic renal lesions
December 7, 2020 -- A machine-learning algorithm based on CT radiomics analysis can enable better preoperative risk classification of complex cystic renal lesions than relying only on the traditional Bosniak classification criteria, according to an international multicenter study presented Friday at the virtual RSNA 2020 meeting.  Discuss
Machine learning helps find vessel occlusions on CTA
December 7, 2020 -- A 3D convolutional neural network helps find large-vessel occlusions on head and neck CT angiography (CTA) studies -- which could translate to better patient outcomes, according to research presented at the recent virtual RSNA 2020 meeting.  Discuss
Federated learning may boost AI generalizability
December 3, 2020 -- Training deep-learning algorithms with a federated-learning approach could help address the challenge of improving the performance of radiology artificial intelligence (AI) software across institutions, according to a presentation in a scientific session at this week's virtual RSNA 2020 meeting.  Discuss
The 2020 PACSman Awards: Is that all there is?
December 3, 2020 -- What were the hot topics in artificial intelligence and enterprise imaging at RSNA 2020? The PACSman, aka Mike Cannavo, offers his thoughts, as well as the eagerly awaited PACSman Awards for excellence in sales and marketing at this year's virtual conference.  Discuss
Radiology workflow a focus for Philips at RSNA 2020
December 3, 2020 -- A centralized command center that enables healthcare enterprises to more easily manage their far-flung radiology operations is the focus of the virtual booth at RSNA 2020 for Philips Healthcare.  Discuss
Deep-learning algorithm detects free air on CT images
December 3, 2020 -- A deep-learning algorithm was able to detect and quantify regions of free air on CT images, enabling patients with these critical pathologies to be prioritized on the radiology worklist, according to a presentation on Wednesday morning at the virtual RSNA 2020 meeting.  Discuss