Difficulty-aware hierarchical convolutional neural networks for deformable registration of brain MR images.
Ontology highlight
ABSTRACT:
SUBMITTER: Huang Y
PROVIDER: S-EPMC7725910 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Error estimation in nonlinear medical image registration is a nontrivial problem that is important for validation of registration methods. We propose a supervised method for estimation of registration errors in nonlinear registration of three-dimensional (3-D) images. The method is based on a 3-D convolutional neural network that learns to estimate registration errors from a pair of image patches. By applying the network to patches centered around every voxel, we construct registration error maps. The network is trained using a set of representative images that have been synthetically transformed to construct a set of image pairs with known deformations. The method is evaluated on deformable registrations of inhale-exhale pairs of thoracic CT scans. Using ground truth target registration errors on manually annotated landmarks, we evaluate the method's ability to estimate local registration errors. Estimation of full domain error maps is evaluated using a gold standard approach. The two evaluation approaches show that we can train the network to robustly estimate registration errors in a predetermined range, with subvoxel accuracy. We achieved a root-mean-square deviation of 0.51 mm from gold standard registration errors and of 0.66 mm from ground truth landmark registration errors.
| S-EPMC5943620 | biostudies-other
Project description:The extreme complexity of mammalian brains requires a comprehensive deconstruction of neuroanatomical structures. Scientists normally use a brain stereotactic atlas to determine the locations of neurons and neuronal circuits. However, different brain images are normally not naturally aligned even when they are imaged with the same setup, let alone under the differing resolutions and dataset sizes used in mesoscopic imaging. As a result, it is difficult to achieve high-throughput automatic registration without manual intervention. Here, we propose a deep learning-based registration method called DeepMapi to predict a deformation field used to register mesoscopic optical images to an atlas. We use a self-feedback strategy to address the problem of imbalanced training sets (sampling at a fixed step size in nonuniform brains of structures and deformations) and use a dual-hierarchical network to capture the large and small deformations. By comparing DeepMapi with other registration methods, we demonstrate its superiority over a set of ground truth images, including both optical and MRI images. DeepMapi achieves fully automatic registration of mesoscopic micro-optical images, even macroscopic MRI datasets, in minutes, with an accuracy comparable to those of manual annotations by anatomists.
| S-EPMC8004526 | biostudies-literature
Project description:PurposeTo employ deep learning to predict genomic subtypes of lower-grade glioma (LLG) tumors based on their appearance at MRI.Materials and methodsImaging data from The Cancer Imaging Archive and genomic data from The Cancer Genome Atlas from 110 patients from five institutions with lower-grade gliomas (World Health Organization grade II and III) were used in this study. A convolutional neural network was trained to predict tumor genomic subtype based on the MRI of the tumor. Two different deep learning approaches were tested: training from random initialization and transfer learning. Deep learning models were pretrained on glioblastoma MRI, instead of natural images, to determine if performance was improved for the detection of LGGs. The models were evaluated using area under the receiver operating characteristic curve (AUC) with cross-validation. Imaging data and annotations used in this study are publicly available.ResultsThe best performing model was based on transfer learning from glioblastoma MRI. It achieved AUC of 0.730 (95% confidence interval [CI]: 0.605, 0.844) for discriminating cluster-of-clusters 2 from others. For the same task, a network trained from scratch achieved an AUC of 0.680 (95% CI: 0.538, 0.811), whereas a model pretrained on natural images achieved an AUC of 0.640 (95% CI: 0.521, 0.763).ConclusionThese findings show the potential of utilizing deep learning to identify relationships between cancer imaging and cancer genomics in LGGs. However, more accurate models are needed to justify clinical use of such tools, which might be obtained using substantially larger training datasets.Supplemental material is available for this article.© RSNA, 2020.
| S-EPMC8017403 | biostudies-literature
Project description:BACKGROUND:Liver alignment between series/exams is challenged by dynamic morphology or variability in patient positioning or motion. Image registration can improve image interpretation and lesion co-localization. We assessed the performance of a convolutional neural network algorithm to register cross-sectional liver imaging series and compared its performance to manual image registration. METHODS:Three hundred fourteen patients, including internal and external datasets, who underwent gadoxetate disodium-enhanced magnetic resonance imaging for clinical care from 2011 to 2018, were retrospectively selected. Automated registration was applied to all 2,663 within-patient series pairs derived from these datasets. Additionally, 100 within-patient series pairs from the internal dataset were independently manually registered by expert readers. Liver overlap, image correlation, and intra-observation distances for manual versus automated registrations were compared using paired t tests. Influence of patient demographics, imaging characteristics, and liver uptake function was evaluated using univariate and multivariate mixed models. RESULTS:Compared to the manual, automated registration produced significantly lower intra-observation distance (p < 0.001) and higher liver overlap and image correlation (p < 0.001). Intra-exam automated registration achieved 0.88 mean liver overlap and 0.44 mean image correlation for the internal dataset and 0.91 and 0.41, respectively, for the external dataset. For inter-exam registration, mean overlap was 0.81 and image correlation 0.41. Older age, female sex, greater inter-series time interval, differing uptake, and greater voxel size differences independently reduced automated registration performance (p ? 0.020). CONCLUSION:A fully automated algorithm accurately registered the liver within and between examinations, yielding better liver and focal observation co-localization compared to manual registration.
| S-EPMC6815316 | biostudies-literature
Project description:Recently, deep convolutional neural networks (DCNNs) have attained human-level performances on challenging object recognition tasks owing to their complex internal representation. However, it remains unclear how objects are represented in DCNNs with an overwhelming number of features and non-linear operations. In parallel, the same question has been extensively studied in primates' brain, and three types of coding schemes have been found: one object is coded by the entire neuronal population (distributed coding), or by one single neuron (local coding), or by a subset of neuronal population (sparse coding). Here we asked whether DCNNs adopted any of these coding schemes to represent objects. Specifically, we used the population sparseness index, which is widely-used in neurophysiological studies on primates' brain, to characterize the degree of sparseness at each layer in representative DCNNs pretrained for object categorization. We found that the sparse coding scheme was adopted at all layers of the DCNNs, and the degree of sparseness increased along the hierarchy. That is, the coding scheme shifted from distributed-like coding at lower layers to local-like coding at higher layers. Further, the degree of sparseness was positively correlated with DCNNs' performance in object categorization, suggesting that the coding scheme was related to behavioral performance. Finally, with the lesion approach, we demonstrated that both external learning experiences and built-in gating operations were necessary to construct such a hierarchical coding scheme. In sum, our study provides direct evidence that DCNNs adopted a hierarchically-evolved sparse coding scheme as the biological brain does, suggesting the possibility of an implementation-independent principle underling object recognition.
| S-EPMC7755594 | biostudies-literature
Project description:Machine learning algorithms are currently being implemented in an escalating manner to classify and/or predict the onset of some neurodegenerative diseases; including Alzheimer's Disease (AD); this could be attributed to the fact of the abundance of data and powerful computers. The objective of this work was to deliver a robust classification system for AD and Mild Cognitive Impairment (MCI) against healthy controls (HC) in a low-cost network in terms of shallow architecture and processing. In this study, the dataset included was downloaded from the Alzheimer's disease neuroimaging initiative (ADNI). The classification methodology implemented was the convolutional neural network (CNN), where the diffusion maps, and gray-matter (GM) volumes were the input images. The number of scans included was 185, 106, and 115 for HC, MCI and AD respectively. Ten-fold cross-validation scheme was adopted and the stacked mean diffusivity (MD) and GM volume produced an AUC of 0.94 and 0.84, an accuracy of 93.5% and 79.6%, a sensitivity of 92.5% and 62.7%, and a specificity of 93.9% and 89% for AD/HC and MCI/HC classification respectively. This work elucidates the impact of incorporating data from different imaging modalities; i.e. structural Magnetic Resonance Imaging (MRI) and Diffusion Tensor Imaging (DTI), where deep learning was employed for the aim of classification. To the best of our knowledge, this is the first study assessing the impact of having more than one scan per subject and propose the proper maneuver to confirm the robustness of the system. The results were competitive among the existing literature, which paves the way for improving medications that could slow down the progress of the AD or prevent it.
| S-EPMC7092978 | biostudies-literature
Project description:BackgroundA colonoscopy can detect colorectal diseases, including cancers, polyps, and inflammatory bowel diseases. A computer-aided diagnosis (CAD) system using deep convolutional neural networks (CNNs) that can recognize anatomical locations during a colonoscopy could efficiently assist practitioners. We aimed to construct a CAD system using a CNN to distinguish colorectal images from parts of the cecum, ascending colon, transverse colon, descending colon, sigmoid colon, and rectum.MethodWe constructed a CNN by training of 9,995 colonoscopy images and tested its performance by 5,121 independent colonoscopy images that were categorized according to seven anatomical locations: the terminal ileum, the cecum, ascending colon to transverse colon, descending colon to sigmoid colon, the rectum, the anus, and indistinguishable parts. We examined images taken during total colonoscopy performed between January 2017 and November 2017 at a single center. We evaluated the concordance between the diagnosis by endoscopists and those by the CNN. The main outcomes of the study were the sensitivity and specificity of the CNN for the anatomical categorization of colonoscopy images.ResultsThe constructed CNN recognized anatomical locations of colonoscopy images with the following areas under the curves: 0.979 for the terminal ileum; 0.940 for the cecum; 0.875 for ascending colon to transverse colon; 0.846 for descending colon to sigmoid colon; 0.835 for the rectum; and 0.992 for the anus. During the test process, the CNN system correctly recognized 66.6% of images.ConclusionWe constructed the new CNN system with clinically relevant performance for recognizing anatomical locations of colonoscopy images, which is the first step in constructing a CAD system that will support us during colonoscopy and provide an assurance of the quality of the colonoscopy procedure.
| S-EPMC8309686 | biostudies-literature
Project description:Our understanding of life is based upon the interpretation of macromolecular structures and their dynamics. Almost 90% of currently known macromolecular models originated from electron density maps constructed using X-ray diffraction images. Even though diffraction images are critical for structure determination, due to their vast amounts and noisy, non-intuitive nature, their quality is rarely inspected. In this paper, we use recent advances in machine learning to automatically detect seven types of anomalies in X-ray diffraction images. For this purpose, we utilize a novel X-ray beam center detection algorithm, propose three different image representations, and compare the predictive performance of general-purpose classifiers and deep convolutional neural networks (CNNs). In benchmark tests on a set of 6,311 X-ray diffraction images, the proposed CNN achieved between 87% and 99% accuracy depending on the type of anomaly. Experimental results show that the proposed anomaly detection system can be considered suitable for early detection of sub-optimal data collection conditions and malfunctions at X-ray experimental stations.
| S-EPMC8341115 | biostudies-literature
Project description:In this paper, we demonstrate the feasibility and performance of deep residual neural networks for volumetric segmentation of irreversibly damaged brain tissue lesions on T1-weighted MRI scans for chronic stroke patients. A total of 239 T1-weighted MRI scans of chronic ischemic stroke patients from a public dataset were retrospectively analyzed by 3D deep convolutional segmentation models with residual learning, using a novel zoom-in&out strategy. Dice similarity coefficient (DSC), average symmetric surface distance (ASSD), and Hausdorff distance (HD) of the identified lesions were measured by using manual tracing of lesions as the reference standard. Bootstrapping was employed for all metrics to estimate 95% confidence intervals. The models were assessed on a test set of 31 scans. The average DSC was 0.64 (0.51-0.76) with a median of 0.78. ASSD and HD were 3.6 mm (1.7-6.2 mm) and 20.4 mm (10.0-33.3 mm), respectively. The latest deep learning architecture and techniques were applied with 3D segmentation on MRI scans and demonstrated effectiveness for volumetric segmentation of chronic ischemic stroke lesions.
| S-EPMC7281812 | biostudies-literature
Project description:This research aims to analyze the effects of different parameter estimation on the recognition performance of satellite modulation signals based on deep learning (DL) under low signal to noise ratio (SNR) or channel non-ideal conditions. In this study, first, the common characteristics of broadband satellite modulation signal and the commonly used signal feature extraction algorithm are introduced. Then, the broadband satellite modulation signal pattern recognition model based on deformable convolutional neural networks (DCNN) is built, and the broadband satellite signal simulation is conducted based on Matlab software. Next, the signal characteristics of binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), 8 phase shift keying (PSK), 16 quadratic amplitude modulation (QAM), 64QAM, and 32 absolute phase shift keying (APSK) are extracted by the constellation map, and the ratio changes of T1 and T2 with SNR are compared. When SNR is given, it is compared with VGG model, AlexNet model, and ResNe model. The results show that the constellation points of satellite signals with different modulations are evenly distributed. T1 of PSK modulation signals increases significantly with the increase of SNR. When SNR is greater than 10, PSK modulation signals can be identified. When T2 is set and SNR is greater than 15dB, 16QAM and 32APSK signals can be distinguished. In the model, the Relu activation function, mini-batch gradient descent (MBGD) algorithm, and Softmax classifier have the best recognition accuracy. PSK modulation signals have the best recognition rate when the SNR is 0dB, and the recognition accuracy of different modulation signals at 20dB is over 98%. When the data length reaches 4000, the recognition accuracy of different modulation signals is higher than 97%. Compared with other algorithms, this algorithm has the highest recognition accuracy (99.83%) and shorter training time (3960s). In conclusion, the broadband satellite modulation signal pattern recognition algorithm of DCNN constructed in this study can effectively identify the patterns of different modulation signals.
| S-EPMC7357751 | biostudies-literature