Temporal Feature Extraction from DCE-MRI to Identify Poorly Perfused Subvolumes of Tumors Related to Outcomes of Radiation Therapy in Head and Neck Cancer

Abstract

This study aimed to develop an automated model to extract temporal features from DCE-MRI in head-and-neck (HN) cancers to localize significant tumor subvolumes having low blood volume (LBV) for predicting local and regional failure after chemoradiation therapy. Temporal features were extracted from time-intensity curves to build classification model for differentiating voxels with LBV from those with high BV. Support vector machine (SVM) classification was trained on the extracted features for voxel classification. Subvolumes with LBV were then assembled from the classified voxels with LBV. The model was trained and validated on independent datasets created from 456 873 DCE curves. The resultant subvolumes were compared to ones derived by a 2-step method via pharmacokinetic modeling of blood volume, and evaluated for classification accuracy and volumetric similarity by DSC. The proposed model achieved an average voxel-level classification accuracy and DSC of 82% and 0.72, respectively. Also, the model showed tolerance on different acquisition parameters of DCE-MRI. The model could be directly used for outcome prediction and therapy assessment in radiation therapy of HN cancers, or even supporting boost target definition in adaptive clinical trials with further validation. The model is fully automatable, extendable, and scalable to extract temporal features of DCE-MRI in other tumors.

Clinical indications and acquisition protocol for the use of dynamic contrast-enhanced MRI in head and neck cancer squamous cell carcinoma: recommendations from an expert panel

“…Indeed, PWI can identify intratumoral areas of hypoxia, which is one of the most important prognostic factors determining RT failure [ 28 ]. In this setting, artificial intelligence (AI)-based models applied to DCE-MRI were built to identify poorly perfused subvolumes of tumors [ 29 , 30 ]. Considering that RT planning is often made on the basis of different MR images, including both anatomical and functional (e.g., diffusion MR imaging); the recommendation was changed to “May be recommended” after the first round of the Delphi process, achieving a wider consensus among panelists during the second round.…”

Enhancing Radiotherapy Workflow for Head and Neck Cancer with Artificial Intelligence: A Systematic Review

“…ML/DL methodologies may be useful to identify tumor heterogeneity and intrinsic radioresistance or to evaluate normal tissue responsiveness to radiation [ 4 ]. Among several applications, ML/DL has been rapidly adopted to improve the RT workflow for HNC [ 5 , 6 , 7 , 8 , 9 ].…”

Multisite Technical and Clinical Performance Evaluation of Quantitative Imaging Biomarkers from 3D FDG PET Segmentations of Head and Neck Cancer Images

“…In the evolving field of radiomics, large numbers of potentially informative novel and diverse QIBs are extracted and studied for the personalization of disease treatment, particularly in oncology (1,2). Examples of single institution-based studies of imaging biomarkers include brain cancer (3,4), head and neck cancer (5)(6)(7)(8), lung cancer (9-13), nasopharyngeal carcinoma (14), prostate cancer (15,16), and sarcoma (17). Other research has focused on performance of QIBs across multiple institutions, such as the analysis provided by Castelli et al (18) regarding the predictive value of quantitative fluorodeoxyglucose positron emission tomography (FDG PET) in 45 studies of head and neck cancer.…”