A Blinded Prospective Evaluation Of Clinical Applicability Of Deep Learning-Based Auto Contouring Of OAR For Head and Neck Radiotherapy

Abstract

Materials/Methods: We retrospectively pooled a large cohort of patients with head and neck cancer treated with definitive radiation from 2008 to 2018 at a single institution. 59 patients were available for analysis (15 patients with LR). Each patient underwent a planning CT scan, an FDG PET scan, and an attenuation corrected (AC) diagnostic CT scan prior to radiotherapy. The gross tumor volume (GTV) was manually drawn on the planning CT. The AC CT scan was diffeomorphically warped to the planning CT using Advanced Normalization Tools (ANTs: http://stnava. github.io/ANTs/), and the transform was applied to the FDG PET scan. 6321 radiomic features (2077 from each of the three scans) from within the GTV mask were extracted using Pyradiomics package. The extracted radiomics features included first order spatial statistics, shape-based volumetrics, and gray level matrix operations on the original image as well as derived images using a variety of spatial filters. Dimensionality reduction was performed using a logistic regression model, reducing the feature dimensions from 6321 to 2754. The remaining features were then fed into a variety of machine learning models to train (N Z 35) and validate (N Z 24) the predictive model with a balanced number of recurrences in the training and validation sets. The model performance was evaluated using receiver operating characteristic (ROC) curve. We further identified the most important features that may affect prognosis. Results: The machine learning models were able to significantly predict locoregional recurrence in our cohort of 59 patients. The classifier performance of the random forests model revealed an area under the curve (AUC) of 0.81 +/-0.13. The top feature weights used a combination of features from all three scans, indicating the need for the multi-modal approach of all three scans. Conclusion: We built machine learning models that can be used to predict locoregional recurrence in patients underwent head and neck radiation using pre-treatment PET and CT scans. This model can be applied to better stratify patients based on pre-treatment images towards personalized treatment. We used automated advanced non-linear registrations and neural networks to improve performance from prior models. The approach can be tailored to optimize medical management using data-driven models.

First experience of autonomous, un-supervised treatment planning integrated in adaptive MR-guided radiotherapy and delivered to a patient with prostate cancer

“…Parameters which only fulfill tolerance are highlighted (criteria for penile bulb and CTVs are only used for evaluation during online adaption, but not during PSO). practice, but a similar workflow was recently proposed for rectal cancer [17] and automation of single processes was also introduced earlier [7][8][9][13][14][15][16].…”

“…Recently, the potentials of artificial intelligence (AI) in healthcare to automatize, standardize and speed-up processes has been discussed extensively [2][3][4][5][6]. In RT, the automation of single workflow steps has recently been investigated by several groups, especially with respect to automatic contouring and plan optimization [7][8][9][10][11][12][13][14][15][16]. For automatic segmentation of organs at risk (OAR), deep learning (DL)-based solutions showed promising results, with first reports on introduction into clinical routine and commercialization [7][8][9][10][11][12].…”

“…In RT, the automation of single workflow steps has recently been investigated by several groups, especially with respect to automatic contouring and plan optimization [7][8][9][10][11][12][13][14][15][16]. For automatic segmentation of organs at risk (OAR), deep learning (DL)-based solutions showed promising results, with first reports on introduction into clinical routine and commercialization [7][8][9][10][11][12]. Solutions for automatic treatment plan optimization were developed and are today partly available for routine planning in commercial treatment planning systems (TPS) [13][14][15][16].…”

Clinical evaluation of autonomous, unsupervised planning integrated in MR-guided radiotherapy for prostate cancer

“…The autonomous workflow consisted of a deep learning-based annotation software (ARTplan 1.7.1, TheraPanacea, Paris, France) [2] and our in-house developed automatic PSO planning tool [21,22]. The planning CT was automatically sent to the annotation software and transferred afterwards to the treatment planning system (TPS) (MonacoÓ 5.40, Elekta AB, Stockholm, Sweden).…”

“…This process is time-consuming and requires human interaction by an experienced user and hence quality can vary significantly [1]. Nevertheless, as process automation and the use of artificial intelligence (AI) for medical applications gained attention in recent years, several approaches were introduced to automate organ segmentation [2][3][4][5][6][7] or RT planning [8][9][10][11][12][13][14][15][16]. Some of these approaches are commercially available and were recently evaluated for clinical usage [9,[11][12][13][14][15][16].…”