Improved Quantitative Parameter Estimation for Prostate T2 Relaxometry using Convolutional Neural Networks.

This work seeks to evaluate multiple methods for quantitative parameter estimation from standard T2 mapping acquisitions in the prostate. The T2 estimation performance of methods based on neural networks (NN) was quantitatively compared to that of conventional curve fitting techniques. Large physics-based synthetic datasets simulating T2 mapping acquisitions were generated for training NNs and for quantitative performance comparisons. Ten combinations of different NN architectures, training strategies, and training corpora were implemented and compared with four different curve fitting strategies. All methods were compared quantitatively using synthetic data with known ground truth, and further compared on in vivo test data, with and without noise augmentation, to evaluate feasibility and noise robustness. In the evaluation on synthetic data, a convolutional neural network (CNN), trained in a supervised fashion using synthetic data generated from naturalistic images, showed the highest overall accuracy and precision amongst all the methods. On in vivo data, this best-performing method produced low-noise T2 maps and showed the least deterioration with increasing input noise levels. This study showed that a CNN, trained with synthetic data in a supervised manner, may provide superior T2 estimation performance compared to conventional curve fitting, especially in low signal-to-noise regions.

Comparison of automatic liver volumetry performance using different types of magnetic resonance images.

Measurements of liver volume from MR images can be valuable for both clinical and research applications. Automated methods using convolutional neural networks have been used successfully for this using a variety of different MR image types as input. In this work, we sought to determine which types of magnetic resonance images give the best performance when used to train convolutional neural networks for liver segmentation and volumetry. Abdominal MRI scans were performed at 3 Tesla on 42 adolescents with obesity. Scans included Dixon imaging (giving water, fat, and T2* images) and low-resolution T2-weighted scout images. Multiple convolutional neural network models using a 3D U-Net architecture were trained with different input images. Whole-liver manual segmentations were used for reference. Segmentation performance was measured using the Dice similarity coefficient (DSC) and 95% Hausdorff distance. Liver volume accuracy was evaluated using bias, precision, intraclass correlation coefficient, normalized root mean square error (NRMSE), and Bland-Altman analyses. The models trained using both water and fat images performed best, giving DSC = 0.94 and NRMSE = 4.2%. Models trained without the water image as input all performed worse, including in participants with elevated liver fat. Models using the T2-weighted scout images underperformed the Dixon-based models, but provided acceptable performance (DSC ≥ 0.92, NMRSE ≤6.6%) for use in longitudinal pediatric obesity interventions. The model using Dixon water and fat images as input gave the best performance, with results comparable to inter-reader variability and state-of-the-art methods.

Training Convolutional Networks for Prostate Segmentation With Limited Data.

Multi-zonal segmentation is a critical component of computer-aided diagnostic systems for detecting and staging prostate cancer. Previously, convolutional neural networks such as the U-Net have been used to produce fully automatic multi-zonal prostate segmentation on magnetic resonance images (MRIs) with performance comparable to human experts, but these often require large amounts of manually segmented training data to produce acceptable results. For institutions that have limited amounts of labeled MRI exams, it is not clear how much data is needed to train a segmentation model, and which training strategy should be used to maximize the value of the available data. This work compares how the strategies of transfer learning and aggregated training using publicly available external data can improve segmentation performance on internal, site-specific prostate MR images, and evaluates how the performance varies with the amount of internal data used for training. Cross training experiments were performed to show that differences between internal and external data were impactful. Using a standard U-Net architecture, optimizations were performed to select between 2D and 3D variants, and to determine the depth of fine-tuning required for optimal transfer learning. With the optimized architecture, the performance of transfer learning and aggregated training were compared for a range of 5-40 internal datasets. The results show that both strategies consistently improve performance and produced segmentation results that are comparable to that of human experts with approximately 20 site-specific MRI datasets. These findings can help guide the development of site-specific prostate segmentation models for both clinical and research applications.

Automated Acquisition Planning for Magnetic Resonance Spectroscopy in Brain Cancer.

In vivo magnetic resonance spectroscopy (MRS) can provide clinically valuable metabolic information from brain tumors that can be used for prognosis and monitoring response to treatment. Unfortunately, this technique has not been widely adopted in clinical practice or even clinical trials due to the difficulty in acquiring and analyzing the data. In this work we propose a computational approach to solve one of the most critical technical challenges: the problem of quickly and accurately positioning an MRS volume of interest (a cuboid voxel) inside a tumor using MR images for guidance. The proposed automated method comprises a convolutional neural network to segment the lesion, followed by a discrete optimization to position an MRS voxel optimally within the lesion. In a retrospective comparison, the novel automated method is shown to provide improved lesion coverage compared to manual voxel placement.