Automatic Tumor Segmentation With a Convolutional Neural Network in Multiparametric MRI: Influence of Distortion Correction

Abstract

Precise tumor segmentation is a crucial task in radiation therapy planning. Convolutional neural networks (CNNs) are among the highest scoring automatic approaches for tumor segmentation. We investigate the difference in segmentation performance of geometrically distorted and corrected diffusion-weighted data using data of patients with head and neck tumors; 18 patients with head and neck tumors underwent multiparametric magnetic resonance imaging, including T2w, T1w, T2*, perfusion (ktrans), and apparent diffusion coefficient (ADC) measurements. Owing to strong geometrical distortions in diffusion-weighted echo planar imaging in the head and neck region, ADC data were additionally distortion corrected. To investigate the influence of geometrical correction, first 14 CNNs were trained on data with geometrically corrected ADC and another 14 CNNs were trained using data without the correction on different samples of 13 patients for training and 4 patients for validation each. The different sets were each trained from scratch using randomly initialized weights, but the training data distributions were pairwise equal for corrected and uncorrected data. Segmentation performance was evaluated on the remaining 1 test-patient for each of the 14 sets. The CNN segmentation performance scored an average Dice coefficient of 0.40 ± 0.18 for data including distortion-corrected ADC and 0.37 ± 0.21 for uncorrected data. Paired t test revealed that the performance was not significantly different (P = .313). Thus, geometrical distortion on diffusion-weighted imaging data in patients with head and neck tumor does not significantly impair CNN segmentation performance in use.

Automatic segmentation of head and neck primary tumors on MRI using a multi-view CNN

“…Only a limited number of studies are available on primary tumor segmentation in the head and neck area solely using MRI data as input. Although the goal of Bielak et al [ 12 ] was different from this study, the segmentation results can be compared to ours. They evaluated the effect of distortion correction in apparent diffusion coefficient (ADC) measurements on the segmentation performance of CNNs.…”

“…However, in head and neck cancer, MRI is the preferred imaging modality to detect local tumor extent because of its superior soft-tissue contrast without adverse radiation effects [ 11 ]. A few studies with a limited number of patients used single center MRI data that was obtained within a standardized research protocol to automatically segment HNSCC [ 12 , 13 ]. With dice similarity scores (DSC) between 0.30 and 0.40, their performance is not comparable with the segmentation performance when using PET/CT (DSC above 0.70) and should improve to make it useful for the clinic.…”

Predicting Biochemical Failure in Irradiated Patients With Prostate Cancer by Tumour Volume Measured by Multiparametric MRI

“…However, only the expert contour had a significant impact on BRFS as a continuous variable, indicating that the variations in the contours drawn by the novice may lead to fluctuations that mask the correlation between GTV volume and outcome. Future studies should examine whether implementation of automatic GTV segmentation methods based on deep convolutional neuronal networks may improve the robustness of GTV segmentation (31).…”

Evaluation of deep learning-based multiparametric MRI oropharyngeal primary tumor auto-segmentation and investigation of input channel effects: Results from a prospective imaging registry

“…Recent studies of PET/CT HNSCC DL auto-segmentation [11,21,[32][33][34][35][36][37] have demonstrated increased segmentation performance when combining functional and anatomical modalities. However, investigations that combine anatomical with functional MRI in HNSCC to achieve acceptable DL auto-segmentation performance are lacking [38,39].…”