Search

Identifying the presence of intravenous contrast material on CT scans is an important component of data curation for medical imaging-based artificial intelligence model development and deployment. Use of intravenous contrast material is often poorly documented in imaging metadata, necessitating impractical manual annotation by clinician experts. Authors developed a convolutional neural network (CNN)-based deep learning platform to identify intravenous contrast enhancement on CT scans. For model development and validation, authors used six independent datasets of head and neck (HN) and chest CT scans, totaling 133 480 axial two-dimensional sections from 1979 scans, which were manually annotated by clinical experts. Five CNN models were trained first on HN scans for contrast enhancement detection. Model performances were evaluated at the patient level on a holdout set and external test set. Models were then fine-tuned on chest CT data and externally validated. This study found that Digital Imaging and Communications in Medicine metadata tags for intravenous contrast material were missing or erroneous for 1496 scans (75.6%). An EfficientNetB4-based model showed the best performance, with areas under the curve (AUCs) of 0.996 and 1.0 in HN holdout (n = 216) and external (n = 595) sets, respectively, and AUCs of 1.0 and 0.980 in the chest holdout (n = 53) and external (n = 402) sets, respectively. This automated, scan-to-prediction platform is highly accurate at CT contrast enhancement detection and may be helpful for artificial intelligence model development and clinical application. Keywords: CT, Head and Neck, Supervised Learning, Transfer Learning, Convolutional Neural Network (CNN), Machine Learning Algorithms, Contrast Material Supplemental material is available for this article. © RSNA, 2022.

Growing evidence suggests that immunotherapy and radiation therapy can be synergistic in the treatment of cancer. This study was performed to determine the effect of the relative timing and type of immune checkpoint therapy on the response of melanoma brain metastases (BrMets) to treatment with stereotactic radiosurgery (SRS).Seventy-five melanoma patients with 566 BrMets were treated with both SRS and immune checkpoint therapy between 2007 and 2015 at a single institution. Immunotherapy and radiosurgery treatment of any single lesion were considered concurrent if SRS was administered within 4 weeks of immunotherapy. The impact of the timing and type of immunotherapy on the lesional response was determined with the Wilcoxon rank-sum test, which was used to compare the median percent lesion volume change 1.5, 3, and 6 months after SRS treatment, with significance determined by P = .0167 according to the Bonferroni correction for multiple comparisons.Concurrent use of immunotherapy and SRS resulted in a significantly greater median percent reduction in the lesion volume at 1.5 (-63.1% vs -43.2%, P .0001), 3 (-83.0% vs -52.8%, P .0001), and 6 months (-94.9% vs -66.2%, P .0001) in comparison with nonconcurrent therapy. The median percent reduction in the lesion volume was also significantly greater for anti-programmed cell death protein 1 (anti-PD-1) than anti-cytotoxic T-lymphocyte-associated protein 4 (anti-CTLA-4) at 1.5 (-71.1% vs -48.2%, P .0001), 3 (-89.3% vs -66.2%, P .0001), and 6 months (-95.1% vs -75.9%, P = .0004).The administration of immunotherapy within 4 weeks of SRS results in an improved lesional response of melanoma BrMets in comparison with treatment separated by longer than 4 weeks. Anti-PD-1 therapy also results in a greater lesional response than anti-CTLA-4 after SRS. Cancer 2016;122:3051-3058. © 2016 American Cancer Society.

Treatment-related imaging changes (TRICs) after stereotactic radiosurgery (SRS) involves the benign transient enlargement of radiographic lesions after treatment. Identifying the radiation dose volumes and conformality metrics associated with TRICs for different post-treatment periods would be helpful and improve clinical decision making.367 metastases in 113 patients were treated using Gamma Knife SRS between 1/1/2007-12/31/2009. Each metastasis was measured at each imaging follow-up to detect TRICs (defined as ≥ 20% increase in volume). Fluctuations in small volume lesions (less than 108 mmFrom 0-6 months, all measures correlated with the incidence of TRICs (p.001), except KARE, which was inversely correlated. During the 6-12 month period all measures except KARE were still correlated. Beyond 12 months, no correlation was found between any of the measures and the development of TRICs.All metrics except KARE were associated with TRICs from 0-12 months only. Additional patient and treatment factors may become dominant at greater times after SRS.

Disclaimer: “UBC SEEDS provides students with the opportunity to share the findings of their studies, as well as their opinions, conclusions and recommendations with the UBC community. The reader should bear in mind that this is a student project/report and is not an official document of UBC. Furthermore readers should bear in mind that these reports may not reflect the current status of activities at UBC. We urge you to contact the research persons mentioned in a report or the SEEDS Coordinator about the current status of the subject matter of a project/report.”

Because humans age at different rates, a person's physical appearance may yield insights into their biological age and physiological health more reliably than their chronological age. In medicine, however, appearance is incorporated into medical judgments in a subjective and non-standardized fashion. In this study, we developed and validated FaceAge, a deep learning system to estimate biological age from easily obtainable and low-cost face photographs. FaceAge was trained on data from 58,851 healthy individuals, and clinical utility was evaluated on data from 6,196 patients with cancer diagnoses from two institutions in the United States and The Netherlands. To assess the prognostic relevance of FaceAge estimation, we performed Kaplan Meier survival analysis. To test a relevant clinical application of FaceAge, we assessed the performance of FaceAge in end-of-life patients with metastatic cancer who received palliative treatment by incorporating FaceAge into clinical prediction models. We found that, on average, cancer patients look older than their chronological age, and looking older is correlated with worse overall survival. FaceAge demonstrated significant independent prognostic performance in a range of cancer types and stages. We found that FaceAge can improve physicians' survival predictions in incurable patients receiving palliative treatments, highlighting the clinical utility of the algorithm to support end-of-life decision-making. FaceAge was also significantly associated with molecular mechanisms of senescence through gene analysis, while age was not. These findings may extend to diseases beyond cancer, motivating using deep learning algorithms to translate a patient's visual appearance into objective, quantitative, and clinically useful measures.