2 October 2024 in Diagnostic and Interventional Radiology
Machine learning models for discriminating clinically significant from clinically insignificant prostate cancer using bi-parametric magnetic resonance imaging - Diagnostic and Interventional Radiology
1 May 2023 in Diagnostic and Interventional Radiology
To evaluate the frequency of abdominal computed tomography (CT) findings in patients with coronavirus disease-2019 (COVID-19) and interrogate the relationship between abdominal CT findings and patient demographic features, clinical findings, and laboratory test results as well as the CT atherosclerosis score in the abdominal aorta. This study was designed as a multicenter retrospective study. The abdominal CT findings of 1.181 patients with positive abdominal symptoms from 26 tertiary medical centers with a positive polymerase chain-reaction test for severe acute respiratory syndrome coronavirus 2 were reviewed. The frequency of ischemic and non-ischemic CT findings as well as the association between CT findings, clinical features, and abdominal aortic calcific atherosclerosis score (AA-CAS) were recorded. Ischemic and non-ischemic abdominal CT findings were detected in 240 (20.3%) and 328 (27.7%) patients, respectively. In 147 patients (12.4%), intra-abdominal malignancy was present. The most frequent ischemic abdominal CT findings were bowel wall thickening (n = 120; 10.2%) and perivascular infiltration (n = 40; 3.4%). As for non-ischemic findings, colitis (n = 91; 7.7%) and small bowel inflammation (n = 73; 6.2%) constituted the most frequent disease processes. The duration of hospital stay was found to be higher in patients with abdominal CT findings than in patients without any positive findings (13.8 ± 13 vs. 10.4 ± 12.8 days, P < 0.001). The frequency of abdominal CT findings was significantly higher in patients who did not survive the infection than in patients who were discharged after recovery (41.7% vs. 27.4%, P < 0.001). Increased AA-CAS was found to be associated with a higher risk of ischemic conditions in abdominal CT examinations. Abdominal symptoms in patients with COVID-19 are usually associated with positive CT findings. The presence of ischemic findings on CT correlates with poor COVID-19 outcomes. A high AA-CAS is associated with abdominal ischemic findings in patients with COVID-19.
13 June 2024 in Current Medical Imaging
Introduction:: The aim of the study was to develop deep-learning neural networks to guide treatment decisions and for the accurate evaluation of tumor response to neoadjuvant chemoradiotherapy (nCRT) in rectal cancer using magnetic resonance (MR) images. Methods:: Fifty-nine tumors with stage 2 or 3 rectal cancer that received nCRT were retrospectively evaluated. Pathological tumor regression grading was carried out using the Dworak (Dw-TRG) guidelines and served as the ground truth for response predictions. Imaging-based tumor regression grading was performed according to the MERCURY group guidelines from pre-treatment and post-treatment para-axial T2-weighted MR images (MR-TRG). Tumor signal intensity signatures were extracted by segmenting the tumors volumetrically on the images. Normalized histograms of the signatures were used as input to a deep neural network (DNN) housing long short-term memory (LSTM) units. The output of the network was the tumor regression grading prediction, DNN-TRG. Results:: In predicting complete or good response, DNN-TRG demonstrated modest agreement with Dw-TRG (Cohen’s kappa= 0.79) and achieved 84.6% sensitivity, 93.9% specificity, and 89.8% accuracy. MR-TRG revealed 46.2% sensitivity, 100% specificity, and 76.3% accuracy. In predicting a complete response, DNN-TRG showed slight agreement with Dw-TRG (Cohen’s kappa= 0.75) with 71.4% sensitivity, 97.8% specificity, and 91.5% accuracy. MR-TRG provided 42.9% sensitivity, 100% specificity, and 86.4% accuracy. DNN-TRG benefited from higher sensitivity but lower specificity, leading to higher accuracy than MR-TRG in predicting tumor response. Conclusion:: The use of deep LSTM neural networks is a promising approach for evaluating the tumor response to nCRT in rectal cancer.