RESUMO
The purpose of the study was to assess the performance of readers in diagnosing thoracic anomalies on standard chest radiographs (CXRs) with and without a deep-learning-based AI tool (Rayvolve) and to evaluate the standalone performance of Rayvolve in detecting thoracic pathologies on CXRs. This retrospective multicentric study was conducted in two phases. In phase 1, nine readers independently reviewed 900 CXRs from imaging group A and identified thoracic abnormalities with and without AI assistance. A consensus from three radiologists served as the ground truth. In phase 2, the standalone performance of Rayvolve was evaluated on 1500 CXRs from imaging group B. The average values of AUC across the readers significantly increased by 15.94%, with AI-assisted reading compared to unaided reading (0.88 ± 0.01 vs. 0.759 ± 0.07, p < 0.001). The time taken to read the CXRs decreased significantly, by 35.81% with AI assistance. The average values of sensitivity and specificity across the readers increased significantly by 11.44% and 2.95% with AI-assisted reading compared to unaided reading (0.857 ± 0.02 vs. 0.769 ± 0.02 and 0.974 ± 0.01 vs. 0.946 ± 0.01, p < 0.001). From the standalone perspective, the AI model achieved an average sensitivity, specificity, PPV, and NPV of 0.964, 0.844, 0.757, and 0.9798. The speed and performance of the readers improved significantly with AI assistance.
RESUMO
PURPOSE: The purpose of this study was to assess the feasibility, efficacy and toxicity of fiducial marker implantation and tracking in CyberKnife® stereotactic radiation therapy (SBRT) applied to extracranial locations. MATERIALS AND METHOD: This is a retrospective, single-centre, observational study to collect the data of all patients treated by stereotactic radiation therapy with fiducial marker tracking at extracranial locations, conducted between June 2014 and November 2017. Information regarding the implantation procedure, the types of toxicity related to marker implantation and the number of markers implanted/tracked during treatment were collected. Complication rates were evaluated using the CTCAE v4 [Common Terminology Criteria for Adverse Events] scale. The technical success rate was based on the ability to optimally track the tumor throughout all treatment fractions. RESULTS: Out of 2505 patients treated by stereotactic radiation therapy, 25% received treatment with fiducial marker tracking. The total number of implantation procedures was 616 and 1543 fiducial markers were implanted. The implantation-related complication rate was 3%, with 16 Grade 1 events and 4 Grade 2 events. The number of treated patients and the number of implanted markers has gradually increased since the technique was first implemented. The median treatment time was 27 min (range 10-76). 1295 fiducials were effectively tracked throughout all treatment fractions, corresponding to a technical success rate of 84%. The difference between the number of fiducials implanted and those tracked during treatment decreased significantly as the site's experience increased. CONCLUSION: Fiducial marker implantation and tracking is feasible, well-tolerated, and technically effective technique in SBRT for extracranial tumors.