RESUMO
Purpose/objectives: Auto-segmentation with artificial intelligence (AI) offers an opportunity to reduce inter- and intra-observer variability in contouring, to improve the quality of contours, as well as to reduce the time taken to conduct this manual task. In this work we benchmark the AI auto-segmentation contours produced by five commercial vendors against a common dataset. Methods and materials: The organ at risk (OAR) contours generated by five commercial AI auto-segmentation solutions (Mirada (Mir), MVision (MV), Radformation (Rad), RayStation (Ray) and TheraPanacea (Ther)) were compared to manually-drawn expert contours from 20 breast, 20 head and neck, 20 lung and 20 prostate patients. Comparisons were made using geometric similarity metrics including volumetric and surface Dice similarity coefficient (vDSC and sDSC), Hausdorff distance (HD) and Added Path Length (APL). To assess the time saved, the time taken to manually draw the expert contours, as well as the time to correct the AI contours, were recorded. Results: There are differences in the number of CT contours offered by each AI auto-segmentation solution at the time of the study (Mir 99; MV 143; Rad 83; Ray 67; Ther 86), with all offering contours of some lymph node levels as well as OARs. Averaged across all structures, the median vDSCs were good for all systems and compared favorably with existing literature: Mir 0.82; MV 0.88; Rad 0.86; Ray 0.87; Ther 0.88. All systems offer substantial time savings, ranging between: breast 14-20 mins; head and neck 74-93 mins; lung 20-26 mins; prostate 35-42 mins. The time saved, averaged across all structures, was similar for all systems: Mir 39.8 mins; MV 43.6 mins; Rad 36.6 min; Ray 43.2 mins; Ther 45.2 mins. Conclusions: All five commercial AI auto-segmentation solutions evaluated in this work offer high quality contours in significantly reduced time compared to manual contouring, and could be used to render the radiotherapy workflow more efficient and standardized.
RESUMO
To achieve clinical impact in daily oncological practice, emerging AI-based cancer imaging research needs to have clearly defined medical focus, AI methods, and outcomes to be estimated. AI-supported cancer imaging should predict major relevant clinical endpoints, aiming to extract associations and draw inferences in a fair, robust, and trustworthy way. AI-assisted solutions as medical devices, developed using multicenter heterogeneous datasets, should be targeted to have an impact on the clinical care pathway. When designing an AI-based research study in oncologic imaging, ensuring clinical impact in AI solutions requires careful consideration of key aspects, including target population selection, sample size definition, standards, and common data elements utilization, balanced dataset splitting, appropriate validation methodology, adequate ground truth, and careful selection of clinical endpoints. Endpoints may be pathology hallmarks, disease behavior, treatment response, or patient prognosis. Ensuring ethical, safety, and privacy considerations are also mandatory before clinical validation is performed. The Artificial Intelligence for Health Imaging (AI4HI) Clinical Working Group has discussed and present in this paper some indicative Machine Learning (ML) enabled decision-support solutions currently under research in the AI4HI projects, as well as the main considerations and requirements that AI solutions should have from a clinical perspective, which can be adopted into clinical practice. If effectively designed, implemented, and validated, cancer imaging AI-supported tools will have the potential to revolutionize the field of precision medicine in oncology.
RESUMO
The three-dimensional iridium-192 (192Ir) high-dose-rate (HDR) brachytherapy manifests itself as a high-precision, hypofractionated, dose-escalating, minimally invasive method in the armamentarium of contemporary radiation oncology clinical applications. In this study, the physical aspects of the 192Ir radionuclide are presented. Its dosimetric application in HDR brachytherapy for different anatomical sites (prostate, gynecological malignancies, liver, and intrathoracic tumors) as well as the corresponding dosimetric comparison with the stereotactic body radiation therapy (SBRT) techniques based on a representative selection of dosimetric publications is reviewed and illustrated.
RESUMO
The feasibility of real-time portal imaging during radiation therapy, through the Cherenkov emission (CE) effect is investigated via a medical linear accelerator (CyberKnife(®)) irradiating a partially-filled water tank with a 60 mm circular beam. A graticule of lead/plywood and a number of tissue equivalent materials were alternatively placed at the beam entrance face while the induced CE at the exit face was imaged using a gated electron-multiplying-intensified-charged-coupled device (emICCD) for both stationary and dynamic scenarios. This was replicated on an Elekta Synergy(®) linear accelerator with portal images acquired using the iViewGT(™) system. Profiles across the acquired portal images were analysed to reveal the potential resolution and contrast limits of this novel CE based portal imaging technique and compared against the current standard. The CE resolution study revealed that using the lead/plywood graticule, separations down to 3.4 ± 0.5 mm can be resolved. A 28 mm thick tissue-equivalent rod with electron density of 1.69 relative to water demonstrated a CE contrast of 15% through air and 14% through water sections, as compared to a corresponding contrast of 19% and 12% using the iViewGT(™) system. For dynamic scenarios, video rate imaging with 30 frames per second was achieved. It is demonstrated that CE-based portal imaging is feasible to identify both stationary and dynamic objects within a CyberKnife(®) radiotherapy treatment field.
