Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEstimation of Tissue Microstructure Using a Deep Network Inspired by a Sparse Reconstruction Framework
69
0
0.0
(
0
)
Added by
Chuyang Ye
Publication date
2017
fields
Informatics Engineering
and research's language is
English
Authors
Chuyang Ye
Ask ChatGPT about the research
No Arabic abstract
Diffusion magnetic resonance imaging (dMRI) provides a unique tool for noninvasively probing the microstructure of the neuronal tissue. The NODDI model has been a popular approach to the estimation of tissue microstructure in many neuroscience studies. It represents the diffusion signals with three types of diffusion in tissue: intra-cellular, extra-cellular, and cerebrospinal fluid compartments. However, the original NODDI method uses a computationally expensive procedure to fit the model and could require a large number of diffusion gradients for accurate microstructure estimation, which may be impractical for clinical use. Therefore, efforts have been devoted to efficient and accurate NODDI microstructure estimation with a reduced number of diffusion gradients. In this work, we propose a deep network based approach to the NODDI microstructure estimation, which is named Microstructure Estimation using a Deep Network (MEDN). Motivated by the AMICO algorithm which accelerates the computation of NODDI parameters, we formulate the microstructure estimation problem in a dictionary-based framework. The proposed network comprises two cascaded stages. The first stage resembles the solution to a dictionary-based sparse reconstruction problem and the second stage computes the final microstructure using the output of the first stage. The weights in the two stages are jointly learned from training data, which is obtained from training dMRI scans with diffusion gradients that densely sample the q-space. The proposed method was applied to brain dMRI scans, where two shells each with 30 gradient directions (60 diffusion gradients in total) were used. Estimation accuracy with respect to the gold standard was measured and the results demonstrate that MEDN outperforms the competing algorithms.
rate research
Read More
Deep learning affords enormous opportunities to augment the armamentarium of biomedical imaging, albeit its design and implementation have potential flaws. Fundamentally, most deep learning models are driven entirely by data without consideration of any prior knowledge, which dramatically increases the complexity of neural networks and limits the application scope and model generalizability. Here we establish a geometry-informed deep learning framework for ultra-sparse 3D tomographic image reconstruction. We introduce a novel mechanism for integrating geometric priors of the imaging system. We demonstrate that the seamless inclusion of known priors is essential to enhance the performance of 3D volumetric computed tomography imaging with ultra-sparse sampling. The study opens new avenues for data-driven biomedical imaging and promises to provide substantially improved imaging tools for various clinical imaging and image-guided interventions.
Diffusion magnetic resonance imaging (dMRI) is currently the only tool for noninvasively imaging the brains white matter tracts. The fiber orientation (FO) is a key feature computed from dMRI for fiber tract reconstruction. Because the number of FOs in a voxel is usually small, dictionary-based sparse reconstruction has been used to estimate FOs with a relatively small number of diffusion gradients. However, accurate FO estimation in regions with complex FO configurations in the presence of noise can still be challenging. In this work we explore the use of a deep network for FO estimation in a dictionary-based framework and propose an algorithm named Fiber Orientation Reconstruction guided by a Deep Network (FORDN). FORDN consists of two steps. First, we use a smaller dictionary encoding coarse basis FOs to represent the diffusion signals. To estimate the mixture fractions of the dictionary atoms (and thus coarse FOs), a deep network is designed specifically for solving the sparse reconstruction problem. Here, the smaller dictionary is used to reduce the computational cost of training. Second, the coarse FOs inform the final FO estimation, where a larger dictionary encoding dense basis FOs is used and a weighted l1-norm regularized least squares problem is solved to encourage FOs that are consistent with the network output. FORDN was evaluated and compared with state-of-the-art algorithms that estimate FOs using sparse reconstruction on simulated and real dMRI data, and the results demonstrate the benefit of using a deep network for FO estimation.
The calibration of modern radio interferometers is a significant challenge, specifically at low frequencies. In this perspective, we propose a novel iterative calibration algorithm, which employs the popular sparse representation framework, in the regime where the propagation conditions shift dissimilarly the directions of the sources. More precisely, our algorithm is designed to estimate the apparent directions of the calibration sources, their powers, the directional and undirectional complex gains of the array elements and their noise powers, with a reasonable computational complexity. Numerical simulations reveal that the proposed scheme is statistically efficient at low SNR and even with additional non-calibration sources at unknown directions.
Multiplication (e.g., convolution) is arguably a cornerstone of modern deep neural networks (DNNs). However, intensive multiplications cause expensive resource costs that challenge DNNs deployment on resource-constrained edge devices, driving several attempts for multiplication-less deep networks. This paper presented ShiftAddNet, whose main inspiration is drawn from a common practice in energy-efficient hardware implementation, that is, multiplication can be instead performed with additions and logical bit-shifts. We leverage this idea to explicitly parameterize deep networks in this way, yielding a new type of deep network that involves only bit-shift and additive weight layers. This hardware-inspired ShiftAddNet immediately leads to both energy-efficient inference and training, without compromising the expressive capacity compared to standard DNNs. The two complementary operation types (bit-shift and add) additionally enable finer-grained control of the models learning capacity, leading to more flexible trade-off between accuracy and (training) efficiency, as well as improved robustness to quantization and pruning. We conduct extensive experiments and ablation studies, all backed up by our FPGA-based ShiftAddNet implementation and energy measurements. Compared to existing DNNs or other multiplication-less models, ShiftAddNet aggressively reduces over 80% hardware-quantified energy cost of DNNs training and inference, while offering comparable or better accuracies. Codes and pre-trained models are available at https://github.com/RICE-EIC/ShiftAddNet.
Computer-aided detection or decision support systems aim to improve breast cancer screening programs by helping radiologists to evaluate digital mammography (DM) exams. Commonly such methods proceed in two steps: selection of candidate regions for malignancy, and later classification as either malignant or not. In this study, we present a candidate detection method based on deep learning to automatically detect and additionally segment soft tissue lesions in DM. A database of DM exams (mostly bilateral and two views) was collected from our institutional archive. In total, 7196 DM exams (28294 DM images) acquired with systems from three different vendors (General Electric, Siemens, Hologic) were collected, of which 2883 contained malignant lesions verified with histopathology. Data was randomly split on an exam level into training (50%), validation (10%) and testing (40%) of deep neural network with u-net architecture. The u-net classifies the image but also provides lesion segmentation. Free receiver operating characteristic (FROC) analysis was used to evaluate the model, on an image and on an exam level. On an image level, a maximum sensitivity of 0.94 at 7.93 false positives (FP) per image was achieved. Similarly, per exam a maximum sensitivity of 0.98 at 7.81 FP per image was achieved. In conclusion, the method could be used as a candidate selection model with high accuracy and with the additional information of lesion segmentation.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
