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

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 (k_trans), 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 tumor segmentation in breast ultrasound images using a dilated fully convolutional network combined with an active contour model

PURPOSE

Due to the low contrast, blurry boundaries, and large amount of shadows in breast ultrasound (BUS) images, automatic tumor segmentation remains a challenging task. Deep learning provides a solution to this problem, since it can effectively extract representative features from lesions and the background in BUS images.

METHODS

A novel automatic tumor segmentation method is proposed by combining a dilated fully convolutional network (DFCN) with a phase-based active contour (PBAC) model. The DFCN is an improved fully convolutional neural network with dilated convolution in deeper layers, fewer parameters, and batch normalization techniques; and has a large receptive field that can separate tumors from background. The predictions made by the DFCN are relatively rough due to blurry boundaries and variations in tumor sizes; thus, the PBAC model, which adds both region-based and phase-based energy functions, is applied to further improve segmentation results. The DFCN model is trained and tested in dataset 1 which contains 570 BUS images from 89 patients. In dataset 2, a 10-fold support vector machine (SVM) classifier is employed to verify the diagnostic ability using 460 features extracted from the segmentation results of the proposed method.

RESULTS

Advantages of the present method were compared with three state-of-the-art networks; the FCN-8s, U-net, and dilated residual network (DRN). Experimental results from 170 BUS images show that the proposed method had a Dice Similarity coefficient of 88.97 ± 10.01%, a Hausdorff distance (HD) of 35.54 ± 29.70 pixels, and a mean absolute deviation (MAD) of 7.67 ± 6.67 pixels, which showed the best segmentation performance. In dataset 2, the area under curve (AUC) of the 10-fold SVM classifier was 0.795 which is similar to the classification using the manual segmentation results.

CONCLUSIONS

The proposed automatic method may be sufficiently accurate, robust, and efficient for medical ultrasound applications.

Differential localization of glioblastoma subtype: implications on glioblastoma pathogenesis

INTRODUCTION

The subventricular zone (SVZ) has been implicated in the pathogenesis of glioblastoma. Whether molecular subtypes of glioblastoma arise from unique niches of the brain relative to the SVZ remains largely unknown. Here, we tested whether these subtypes of glioblastoma occupy distinct regions of the cerebrum and examined glioblastoma localization in relation to the SVZ.

METHODS

Pre-operative MR images from 217 glioblastoma patients from The Cancer Imaging Archive were segmented automatically into contrast enhancing (CE) tumor volumes using Iterative Probabilistic Voxel Labeling (IPVL). Probabilistic maps of tumor location were generated for each subtype and distances were calculated from the centroid of CE tumor volumes to the SVZ. Glioblastomas that arose in a Genetically Modified Murine Model (GEMM) model were also analyzed with regard to SVZ distance and molecular subtype.

RESULTS

Classical and mesenchymal glioblastomas were more diffusely distributed and located farther from the SVZ. In contrast, proneural and neural glioblastomas were more likely to be located in closer proximity to the SVZ. Moreover, in a GFAP-CreER; PtenloxP/loxP; Trp53loxP/loxP; Rb1loxP/loxP; Rbl1-/- GEMM model of glioblastoma where tumor can spontaneously arise in different regions of the cerebrum, tumors that arose near the SVZ were more likely to be of proneural subtype (p < 0.0001).

CONCLUSIONS

Glioblastoma subtypes occupy different regions of the brain and vary in proximity to the SVZ. These findings harbor implications pertaining to the pathogenesis of glioblastoma subtypes.