RESUMO
Objective.To develop and benchmark a novel 3D dose verification technique consisting of polymer gel dosimetry (PGD) with cone-beam-CT (CBCT) readout through a two-institution study. The technique has potential for wide and robust applicability through reliance on CBCT readout.Approach. Three treatment plans (3-field, TG119-C-shape spine, 4-target SRS) were created by two independent institutions (Institutions A and B). A Varian Truebeam linear accelerator was used to deliver the plans to NIPAM polymer gel dosimeters produced at both institutions using an identical approach. For readout, a slow CBCT scan mode was used to acquire pre- and post-irradiation images of the gel (1 mm slice thickness). Independent gel analysis tools were used to process the PGD images (A: VistaAce software, B: in-house MATLAB code). Comparing planned and measured doses, the analysis involved a combination of 1D line profiles, 2D contour plots, and 3D global gamma maps (criteria ranging between 2%1 mm and 5%2 mm, with a 10% dose threshold).Main results. For all gamma criteria tested, the 3D gamma pass rates were all above 90% for 3-field and 88% for the SRS plan. For the C-shape spine plan, we benchmarked our 2% 2 mm result against previously published work using film analysis (93.4%). For 2%2 mm, 99.4% (Institution A data), and 89.7% (Institution B data) were obtained based on VistaAce software analysis, 83.7% (Institution A data), and 82.9% (Institution B data) based on MATLAB.Significance. The benchmark data demonstrate that when two institutions follow the same rigorous procedures gamma passing rates up to 99%, for 2%2 mm criteria can be achieved for substantively different treatment plans. The use of different software and calibration techniques may have contributed to the variation in the 3D gamma results. By sharing the data across institutions, we observe the gamma passing rate is more consistent within each pipeline, indicating the need for standardized analysis methods.
Assuntos
Tomografia Computadorizada de Feixe Cônico , Aceleradores de Partículas , Radiometria , Planejamento da Radioterapia Assistida por Computador , Tomografia Computadorizada de Feixe Cônico/métodos , Radiometria/métodos , Humanos , Planejamento da Radioterapia Assistida por Computador/métodos , Dosagem Radioterapêutica , Imageamento Tridimensional/métodos , Polímeros/químicaRESUMO
PURPOSE: Deep learning-based auto-segmentation algorithms can improve clinical workflow by defining accurate regions of interest while reducing manual labor. Over the past decade, convolutional neural networks (CNNs) have become prominent in medical image segmentation applications. However, CNNs have limitations in learning long-range spatial dependencies due to the locality of the convolutional layers. Transformers were introduced to address this challenge. In transformers with self-attention mechanism, even the first layer of information processing makes connections between distant image locations. Our paper presents a novel framework that bridges these two unique techniques, CNNs and transformers, to segment the gross tumor volume (GTV) accurately and efficiently in computed tomography (CT) images of non-small cell-lung cancer (NSCLC) patients. METHODS: Under this framework, input of multiple resolution images was used with multi-depth backbones to retain the benefits of high-resolution and low-resolution images in the deep learning architecture. Furthermore, a deformable transformer was utilized to learn the long-range dependency on the extracted features. To reduce computational complexity and to efficiently process multi-scale, multi-depth, high-resolution 3D images, this transformer pays attention to small key positions, which were identified by a self-attention mechanism. We evaluated the performance of the proposed framework on a NSCLC dataset which contains 563 training images and 113 test images. Our novel deep learning algorithm was benchmarked against five other similar deep learning models. RESULTS: The experimental results indicate that our proposed framework outperforms other CNN-based, transformer-based, and hybrid methods in terms of Dice score (0.92) and Hausdorff Distance (1.33). Therefore, our proposed model could potentially improve the efficiency of auto-segmentation of early-stage NSCLC during the clinical workflow. This type of framework may potentially facilitate online adaptive radiotherapy, where an efficient auto-segmentation workflow is required. CONCLUSIONS: Our deep learning framework, based on CNN and transformer, performs auto-segmentation efficiently and could potentially assist clinical radiotherapy workflow.
Assuntos
Carcinoma Pulmonar de Células não Pequenas , Aprendizado Profundo , Neoplasias Pulmonares , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/radioterapia , Tomografia Computadorizada por Raios X , Redes Neurais de Computação , Algoritmos , Carcinoma Pulmonar de Células não Pequenas/diagnóstico por imagem , Carcinoma Pulmonar de Células não Pequenas/radioterapia , Processamento de Imagem Assistida por Computador/métodosRESUMO
Objective. The development of radiation-induced fibrosis after stereotactic ablative radiotherapy (SABR) can obscure follow-up images and delay detection of a local recurrence in early-stage lung cancer patients. The objective of this study was to develop a radiomics model for computer-assisted detection of local recurrence and fibrosis for an earlier timepoint (<1 year) after the SABR treatment.Approach. This retrospective clinical study included CT images (n= 107) of 66 patients treated with SABR. A z-score normalization technique was used for radiomic feature standardization across scanner protocols. The training set for the radiomics model consisted of CT images (66 patients; 22 recurrences and 44 fibrosis) obtained at 24 months (median) follow-up. The test set included CT-images of 41 patients acquired at 5-12 months follow-up. Combinations of four widely used machine learning techniques (support vector machines, gradient boosting, random forests (RF), and logistic regression) and feature selection methods (Relief feature scoring, maximum relevance minimum redundancy, mutual information maximization, forward feature selection, and LASSO) were investigated. Pyradiomics was used to extract 106 radiomic features from the CT-images for feature selection and classification.Main results. An RF + LASSO model scored the highest in terms of AUC (0.87) and obtained a sensitivity of 75% and a specificity of 88% in identifying a local recurrence in the test set. In the training set, 86% accuracy was achieved using five-fold cross-validation. Delong's test indicated that AUC achieved by the RF+LASSO is significantly better than 11 other machine learning models presented here. The top three radiomic features: interquartile range (first order), Cluster Prominence (GLCM), and Autocorrelation (GLCM), were revealed as differentiating a recurrence from fibrosis with this model.Significance. The radiomics model selected, out of multiple machine learning and feature selection algorithms, was able to differentiate a recurrence from fibrosis in earlier follow-up CT-images with a high specificity rate and satisfactory sensitivity performance.