Search

Background: This study aimed at investigating the feasibility of developing a deep learning-based auto-segmentation model for the heart trained on clinical delineations. Material and methods: This study included two different datasets. The first dataset contained clinical heart delineations from the DBCG RT Nation study (1,561 patients). The second dataset was smaller (114 patients), but with corrected heart delineations. Before training the model on the clinical delineations an outlier-detection was performed, to remove cases with gross deviations from the delineation guideline. No outlier detection was performed for the dataset with corrected heart delineations. Both models were trained with a 3D full resolution nnUNet. The models were evaluated with the dice similarity coefficient (DSC), 95% Hausdorff distance (HD95) and Mean Surface Distance (MSD). The difference between the models were tested with the Mann-Whitney U-test. The balance of dataset quantity versus quality was investigated, by stepwise reducing the cohort size for the model trained on clinical delineations. Results: During the outlier-detection 137 patients were excluded from the clinical cohort due to noncompliance with delineation guidelines. The model trained on the curated clinical cohort performed with a median DSC of 0.96 (IQR 0.94-0.96), median HD95 of 4.00 mm (IQR 3.00 mm-6.00 mm) and a median MSD of 1.49 mm (IQR 1.12 mm-2.02 mm). The model trained on the dedicated and corrected cohort performed with a median DSC of 0.95 (IQR 0.93-0.96), median HD95 of 5.65 mm (IQR 3.37 mm-8.62 mm) and median MSD of 1.63 mm (IQR 1.35 mm-2.11 mm). The difference between the two models were found non-significant for all metrics (p>0.05). Reduction of cohort size showed no significant difference for all metrics (p>0.05). However, with the smallest cohort size, a few outlier structures were found. Conclusions: This study demonstrated a deep learning-based auto-segmentation model trained on curated clinical delineations which performs on par with a model trained on dedicated delineations, making it easier to develop multi-institutional auto-segmentation models. [ABSTRACT FROM AUTHOR]

Background: Radiation therapy (RT) plays a key role in curative-intent treatment for locally advanced lung cancer. Radiation induced pulmonary toxicity can be significant for some patients and becomes a limiting factor for radiation dose, suitability for treatment, as well as post treatment quality of life and suitability for the newly introduced adjuvant immunotherapy. Modern RT techniques aim to minimise the radiation dose to the lungs, without accounting for regional distribution of lung function. Many lung cancer patients have significant regional differences in pulmonary function due to smoking and chronic lung co-morbidity. Even though reduction of dose to functional lung has shown to be feasible, the method of preferential functional lung avoidance has not been investigated in a randomised clinical trial.Methods: In this study, single photon emission computed tomography (SPECT/CT) imaging technique is used for functional lung definition, in conjunction with advanced radiation dose delivery method in randomised, double-blind trial. The study aims to assess the impact of functional lung avoidance technique on pulmonary toxicity and quality of life in patients receiving chemo-RT for lung cancer. Eligibility criteria are biopsy verified lung cancer, scheduled to receive (chemo)-RT with curative intent. Every patient will undergo a pre-treatment perfusion SPECT/CT to identify functional lung. At radiation dose planning, two plans will be produced for all patients on trial. Standard reference plan, without the use of SPECT imaging data, and functional avoidance plan, will be optimised to reduce the dose to functional lung within the predefined constraints. Both plans will be clinically approved. Patients will then be randomised in a 2:1 ratio to be treated according to either the functional avoidance or the standard plan. This study aims to accrue a total of 200 patients within 3 years. The primary endpoint is symptomatic radiation-induced lung toxicity, measured serially 1-12 months after RT. Secondary endpoints include: a quality of life and patient reported lung symptoms assessment, overall survival, progression-free survival, and loco-regional disease control.Discussion: ASPECT trial will investigate functional avoidance method of radiation delivery in clinical practice, and will establish toxicity outcomes for patients with lung cancer undergoing curative chemo-RT.Trial Registration: Clinicaltrials.gov Identifier: NCT04676828 . Registered 1 December 2020. [ABSTRACT FROM AUTHOR]

Purpose: Proton therapy of esophageal cancer is superior to photon radiation therapy in terms of normal tissue sparing. However, respiratory motion and anatomical changes may compromise target dose coverage owing to density changes, geometric misses, and interplay effects. Here we investigate the combined effect on clinical target volume (CTV) coverage and compare proton therapy with intensity modulated radiation therapy (IMRT).Methods and Materials: This study includes 26 patients with esophageal cancer previously treated with IMRT planned on 4-dimensional computed tomography (4D-CT). For each patient, 7 proton pencil beam scanning (PBS) plans were created with different field configurations and optimization strategies. The effect of respiration was investigated by calculating the phase doses, 4D dose, and 4D dynamic dose (including interplay effects). The effect of anatomical changes was investigated by recalculating all plans on all phases of a 4D-CT surveillance scan.Results: The most robust PBS plans were achieved using 2 posterior beams requiring coverage of planning target volume (PTV) and simultaneously using robust optimization (RO) of CTV (2PAPTVRO), resulting in only 1 patient showing V95%CTV <97% in 1 or more phases of the planning CT. For the least robust PBS plans obtained using lateral + posterior beams and CTV-RO, but not requiring PTV coverage (2LPRO), 10 patients showed underdosage. For IMRT, 2 patients showed underdosage. Interplay effects reduced V95%CTV significantly when delivering only 1 fraction, but the effects generally averaged out after 10 fractions. The effect of interplay was significantly larger for RO-only plans compared with plans optimized with RO combined with PTV coverage. Combining the effect of anatomical changes and respiration on the 4D-CT surveillance scan resulted in V95%CTV <97% for 3 2PAPTVRO, 16 2LPRO, and 8 IMRT patients.Conclusions: PBS using posterior beam angles was more robust to anatomical changes and respiration than IMRT. The effect of respiration was enhanced when anatomical changes were present. Single fraction interplay effects deteriorated the dose distribution but were averaged out after 10 fractions. [ABSTRACT FROM AUTHOR]