Purpose
To compare 2 stereotactic body radiotherapy (SBRT) schedules for medically inoperable early-stage lung cancer to determine which produces the lowest rate of grade ≥ 3 protocol-specified adverse events (psAEs) at 1 year.
Methods
Patients with biopsy-proven peripheral (greater than 2 cm from the central bronchial tree) T1/T2, N0 (clinically node negative by positron emission tomography), M0 tumors were eligible. Patients were randomized to receive either 34 Gy in one fraction (Arm 1) or 48 Gy in 4 consecutive daily fractions (Arm 2). Rigorous central accreditation and quality assurance confirmed treatment per protocol guidelines. This study was designed to detect a psAEs rate > 17% at a 10% significance level (1-sided) and 90% power. Secondary endpoints included rates of primary tumor control (PC), overall survival (OS) and disease-free survival (DFS) at 1 year. Designating the better of the two regimens was based on pre-specified rules of psAEs and PC for each Arm.
Results
Ninety four patients were accrued between September 2009 and March 2011. Median follow up time was 30.2 months. Of 84 analyzable patients, 39 were in Arm 1 and 45 in Arm 2. Patient and tumor characteristics were balanced between Arms. Four (10.3%) patients on Arm 1 (95% confidence interval (CI): 2.9%-24.2%) and six (13.3%) patients on Arm 2 (95% CI: 5.1%-26.8%) experienced psAEs. The 2-year OS rate was 61.3% (95% CI: 44.2%-74.6%) for Arm 1 patients and 77.7% (95% CI: 62.5%-87.3%) for Arm 2. The 2-year DFS was 56.4% (95% 39.6%-70.2%) for Arm 1 and 71.1% (95% CI: 55.5%-82.1%) for Arm 2. The 1-year PC rate was 97.0% (95% CI: 84.2%-99.9%) for Arm 1 and 92.7% (80.1%-98.5%) for Arm 2.
Conclusions
34 Gy in 1 fraction met pre-specified criteria and of the two schedules, warrants further clinical research.
Automated quantification of abnormalities associated with COVID-19 from chest CT could help clinicians evaluate the disease and assess its severity and progression. This study proposes measures of disease severity and a deep learning and deep reinforcement-based method to compute them.
Purpose/Objective(s): To present long-term results of RTOG 0915/NCCTG N0927, a randomized lung stereotactic body radiotherapy (SBRT) trial of 34 Gy in 1 fraction versus 48 Gy in 4 fractions. Materials/Methods: This was a phase II multicenter study of medically inoperable non-small cell lung cancer patients with biopsy-proven peripheral T1 or T2 N0M0 tumors, with 1-year toxicity rates as primary endpoint and selected failure and survival outcomes as secondary endpoints. The study opened in September 2009 and closed in March 2011. Final data were analyzed through May 17, 2018. Results: Eighty four of 94 patients accrued were eligible for analysis: 39 in arm 1 and 45 in arm 2. Median follow-up time was 4.0 years for all patients, and 6.0 years for those alive at analysis. Rates of grade 3 and higher toxicity were 2.6% in arm 1 and 11.1% in arm 2. Median survival times (in years) for 34 Gy and 48 Gy were 4.1 vs. 4.6, respectively. Five-year outcomes as % (95% CI) for 34 Gy and 48 Gy were: primary tumor failure rate of 10.6 (3.3, 23.1) vs. 6.8 (1.7, 16.9); overall survival of 29.6 (16.2, 44.4) vs. 41.1 (26.6, 55.1); and progression-free survival of 19.1 (8.5, 33.0) vs. 33.3 (20.2, 47.0); respectively. Distant failure as the sole failure or a component of first failure occurred in 6 patients (37.5%) in the 34 Gy arm and in 7 (41.2%) in the 48 Gy arm. Conclusions: No excess in late-appearing toxicity was seen in either arm. Primary tumor control rates at 5 years were similar by arm. Median survival times of 4 years for each arm suggest similar efficacy pending any larger studies appropriately powered to detect survival differences.
Objectives
Radiologists’ perception is likely to influence the adoption of artificial intelligence (AI) into clinical practice. We investigated knowledge and attitude towards AI by radiologists and residents in Europe and beyond.
Methods
Between April and July 2019, a survey on fear of replacement, knowledge, and attitude towards AI was accessible to radiologists and residents. The survey was distributed through several radiological societies, author networks, and social media. Independent predictors of fear of replacement and a positive attitude towards AI were assessed using multivariable logistic regression.
Results
The survey was completed by 1,041 respondents from 54 mostly European countries. Most respondents were male (n = 670, 65%), median age was 38 (24–74) years, n = 142 (35%) residents, and n = 471 (45%) worked in an academic center. Basic AI-specific knowledge was associated with fear (adjusted OR 1.56, 95% CI 1.10–2.21, p = 0.01), while intermediate AI-specific knowledge (adjusted OR 0.40, 95% CI 0.20–0.80, p = 0.01) or advanced AI-specific knowledge (adjusted OR 0.43, 95% CI 0.21–0.90, p = 0.03) was inversely associated with fear. A positive attitude towards AI was observed in 48% (n = 501) and was associated with only having heard of AI, intermediate (adjusted OR 11.65, 95% CI 4.25–31.92, p < 0.001), or advanced AI-specific knowledge (adjusted OR 17.65, 95% CI 6.16–50.54, p < 0.001).
Conclusions
Limited AI-specific knowledge levels among radiology residents and radiologists are associated with fear, while intermediate to advanced AI-specific knowledge levels are associated with a positive attitude towards AI. Additional training may therefore improve clinical adoption.
Key Points
• Forty-eight percent of radiologists and residents have an open and proactive attitude towards artificial intelligence (AI), while 38% fear of replacement by AI.
• Intermediate and advanced AI-specific knowledge levels may enhance adoption of AI in clinical practice, while rudimentary knowledge levels appear to be inhibitive.
• AI should be incorporated in radiology training curricula to help facilitate its clinical adoption.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.