Deep neural network for water/fat separation: Supervised training, unsupervised training, and no training.
Ontology highlight
ABSTRACT: Purpose
To use a deep neural network (DNN) for solving the optimization problem of water/fat separation and to compare supervised and unsupervised training.Methods
The current T2∗ -IDEAL algorithm for solving water/fat separation is dependent on initialization. Recently, DNN has been proposed to solve water/fat separation without the need for suitable initialization. However, this approach requires supervised training of DNN using the reference water/fat separation images. Here we propose 2 novel DNN water/fat separation methods: 1) unsupervised training of DNN (UTD) using the physical forward problem as the cost function during training, and 2) no training of DNN using physical cost and backpropagation to directly reconstruct a single dataset. The supervised training of DNN, unsupervised training of DNN, and no training of DNN methods were compared with the reference T2∗ -IDEAL.Results
All DNN methods generated consistent water/fat separation results that agreed well with T2∗ -IDEAL under proper initialization.Conclusion
The water/fat separation problem can be solved using unsupervised deep neural networks.
SUBMITTER: Jafari R
PROVIDER: S-EPMC7809709 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Deep learning analysis of images and text unfolds new horizons in medicine. However, analysis of transcriptomic data, the cause of biological and pathological changes, is hampered by structural complexity distinctive from images and text. Here we conduct unsupervised training on more than 20,000 human normal and tumor transcriptomic data and show that the resulting Deep-Autoencoder, DeepT2Vec, has successfully extracted informative features and embedded transcriptomes into 30-dimensional Transcriptomic Feature Vectors (TFVs). We demonstrate that the TFVs could recapitulate expression patterns and be used to track tissue origins. Trained on these extracted features only, a supervised classifier, DeepC, can effectively distinguish tumors from normal samples with an accuracy of 90% for Pan-Cancer and reach an average 94% for specific cancers. Training on a connected network, the accuracy is further increased to 96% for Pan-Cancer. Together, our study shows that deep learning with autoencoder is suitable for transcriptomic analysis, and DeepT2Vec could be successfully applied to distinguish cancers, normal tissues, and other potential traits with limited samples.
| S-EPMC7644700 | biostudies-literature
Project description:Learning from limited exemplars (few-shot learning) is a fundamental, unsolved problem that has been laboriously explored in the machine learning community. However, current few-shot learners are mostly supervised and rely heavily on a large amount of labeled examples. Unsupervised learning is a more natural procedure for cognitive mammals and has produced promising results in many machine learning tasks. In this paper, we propose an unsupervised feature learning method for few-shot learning. The proposed model consists of two alternate processes, progressive clustering and episodic training. The former generates pseudo-labeled training examples for constructing episodic tasks; and the later trains the few-shot learner using the generated episodic tasks which further optimizes the feature representations of data. The two processes facilitate each other, and eventually produce a high quality few-shot learner. In our experiments, our model achieves good generalization performance in a variety of downstream few-shot learning tasks on Omniglot and MiniImageNet. We also construct a new few-shot person re-identification dataset FS-Market1501 to demonstrate the feasibility of our model to a real-world application.
| S-EPMC7592391 | biostudies-literature
Project description:Chemical-shift encoded MRI (CSE-MRI) is a widely used technique for the study of body composition and metabolic disorders, where derived fat and water signals enable the quantification of adipose tissue and muscle. The UK Biobank is acquiring whole-body Dixon MRI (a specific implementation of CSE-MRI) for over 100,000 participants. Current processing methods associated with large whole-body volumes are time intensive and prone to artifacts during fat-water separation performed by the scanner, making quantitative analysis challenging. The most common artifacts are fat-water swaps, where the labels are inverted at the voxel level. It is common for researchers to discard swapped data (generally around 10%), which is wasteful and may lead to unintended biases. Given the large number of whole-body Dixon MRI acquisitions in the UK Biobank, thousands of swaps are expected to be present in the fat and water volumes from image reconstruction performed on the scanner. If they go undetected, errors will propagate into processes such as organ segmentation, and dilute the results in population-based analyses. There is a clear need for a robust method to accurately separate fat and water volumes in big data collections like the UK Biobank. We formulate fat-water separation as a style transfer problem, where swap-free fat and water volumes are predicted from the acquired Dixon MRI data using a conditional generative adversarial network, and introduce a new loss function for the generator model. Our method is able to predict highly accurate fat and water volumes free from artifacts in the UK Biobank. We show that our model separates fat and water volumes using either single input (in-phase only) or dual input (in-phase and opposed-phase) data, with the latter producing superior results. Our proposed method enables faster and more accurate downstream analysis of body composition from Dixon MRI in population studies by eliminating the need for visual inspection or discarding data due to fat-water swaps.Supplementary informationThe online version contains supplementary material available at 10.1186/s40537-022-00677-1.
| S-EPMC9835035 | biostudies-literature
Project description:ObjectiveTo accurately estimate liver PDFF from chemical shift-encoded (CSE) MRI using a deep learning (DL)-based Multi-Decoder Water-Fat separation Network (MDWF-Net), that operates over complex-valued CSE-MR images with only 3 echoes.MethodsThe proposed MDWF-Net and a U-Net model were independently trained using the first 3 echoes of MRI data from 134 subjects, acquired with conventional 6-echoes abdomen protocol at 1.5 T. Resulting models were then evaluated using unseen CSE-MR images obtained from 14 subjects that were acquired with a 3-echoes CSE-MR pulse sequence with a shorter duration compared to the standard protocol. Resulting PDFF maps were qualitatively assessed by two radiologists, and quantitatively assessed at two corresponding liver ROIs, using Bland Altman and regression analysis for mean values, and ANOVA testing for standard deviation (STD) (significance level: .05). A 6-echo graph cut was considered ground truth.ResultsAssessment of radiologists demonstrated that, unlike U-Net, MDWF-Net had a similar quality to the ground truth, despite it considered half of the information. Regarding PDFF mean values at ROIs, MDWF-Net showed a better agreement with ground truth (regression slope = 0.94, R2 = 0.97) than U-Net (regression slope = 0.86, R2 = 0.93). Moreover, ANOVA post hoc analysis of STDs showed a statistical difference between graph cuts and U-Net (p < .05), unlike MDWF-Net (p = .53).ConclusionMDWF-Net showed a liver PDFF accuracy comparable to the reference graph cut method, using only 3 echoes and thus allowing a reduction in the acquisition times.Clinical relevance statementWe have prospectively validated that the use of a multi-decoder convolutional neural network to estimate liver proton density fat fraction allows a significant reduction in MR scan time by reducing the number of echoes required by 50%.Key points• Novel water-fat separation neural network allows for liver PDFF estimation by using multi-echo MR images with a reduced number of echoes. • Prospective single-center validation demonstrated that echo reduction leads to a significant shortening of the scan time, compared to standard 6-echo acquisition. • Qualitative and quantitative performance of the proposed method showed no significant differences in PDFF estimation with respect to the reference technique.
| S-EPMC10415440 | biostudies-literature
Project description:Background Automatic cell type identification has been an urgent task for the rapid development of single-cell RNA-seq techniques. Generally, the current approach for cell type identification is to generate cell clusters by unsupervised clustering and later assign labels to each cell cluster with manual annotation. Methods Here, we introduce LIDER (celL embeddIng based Deep nEural netwoRk classifier), a deep supervised learning method that combines cell embedding and deep neural network classifier for automatic cell type identification. Based on a stacked denoising autoencoder with a tailored and reconstructed loss function, LIDER identifies cell embedding and predicts cell types with a deep neural network classifier. LIDER was developed upon a stacked denoising autoencoder to learn encoder-decoder structures for identifying cell embedding. Results LIDER accurately identifies cell types by using stacked denoising autoencoder. Benchmarking against state-of-the-art methods across eight types of single-cell data, LIDER achieves comparable or even superior enhancement performance. Moreover, LIDER suggests comparable robust to batch effects. Our results show a potential in deep supervised learning for automatic cell type identification of single-cell RNA-seq data. The LIDER codes are available at https://github.com/ShiMGLab/LIDER.
| S-EPMC10439717 | biostudies-literature
Project description:Inferior temporal (IT) cortex in human and nonhuman primates serves visual object recognition. Computational object-vision models, although continually improving, do not yet reach human performance. It is unclear to what extent the internal representations of computational models can explain the IT representation. Here we investigate a wide range of computational model representations (37 in total), testing their categorization performance and their ability to account for the IT representational geometry. The models include well-known neuroscientific object-recognition models (e.g. HMAX, VisNet) along with several models from computer vision (e.g. SIFT, GIST, self-similarity features, and a deep convolutional neural network). We compared the representational dissimilarity matrices (RDMs) of the model representations with the RDMs obtained from human IT (measured with fMRI) and monkey IT (measured with cell recording) for the same set of stimuli (not used in training the models). Better performing models were more similar to IT in that they showed greater clustering of representational patterns by category. In addition, better performing models also more strongly resembled IT in terms of their within-category representational dissimilarities. Representational geometries were significantly correlated between IT and many of the models. However, the categorical clustering observed in IT was largely unexplained by the unsupervised models. The deep convolutional network, which was trained by supervision with over a million category-labeled images, reached the highest categorization performance and also best explained IT, although it did not fully explain the IT data. Combining the features of this model with appropriate weights and adding linear combinations that maximize the margin between animate and inanimate objects and between faces and other objects yielded a representation that fully explained our IT data. Overall, our results suggest that explaining IT requires computational features trained through supervised learning to emphasize the behaviorally important categorical divisions prominently reflected in IT.
| S-EPMC4222664 | biostudies-literature
Project description:Accurately predicting the brain responses to various stimuli poses a significant challenge in neuroscience. Despite recent breakthroughs in neural encoding using convolutional neural networks (CNNs) in fMRI studies, there remain critical gaps between the computational rules of traditional artificial neurons and real biological neurons. To address this issue, a spiking CNN (SCNN)-based framework is presented in this study to achieve neural encoding in a more biologically plausible manner. The framework utilizes unsupervised SCNN to extract visual features of image stimuli and employs a receptive field-based regression algorithm to predict fMRI responses from the SCNN features. Experimental results on handwritten characters, handwritten digits and natural images demonstrate that the proposed approach can achieve remarkably good encoding performance and can be utilized for "brain reading" tasks such as image reconstruction and identification. This work suggests that SNN can serve as a promising tool for neural encoding.
| S-EPMC10462614 | biostudies-literature
Project description:As single-cell RNA sequencing technologies mature, massive gene expression profiles can be obtained. Consequently, cell clustering and annotation become two crucial and fundamental procedures affecting other specific downstream analyses. Most existing single-cell RNA-seq (scRNA-seq) data clustering algorithms do not take into account the available cell annotation results on the same tissues or organisms from other laboratories. Nonetheless, such data could assist and guide the clustering process on the target dataset. Identifying marker genes through differential expression analysis to manually annotate large amounts of cells also costs labor and resources. Therefore, in this paper, we propose a novel end-to-end cell supervised clustering and annotation framework called scAnCluster, which fully utilizes the cell type labels available from reference data to facilitate the cell clustering and annotation on the unlabeled target data. Our algorithm integrates deep supervised learning, self-supervised learning and unsupervised learning techniques together, and it outperforms other customized scRNA-seq supervised clustering methods in both simulation and real data. It is particularly worth noting that our method performs well on the challenging task of discovering novel cell types that are absent in the reference data.
| S-EPMC7397036 | biostudies-literature
Project description:Deep learning facilitates complex medical data analysis and is increasingly being explored in colorectal cancer diagnostics. However, the training cost of the deep learning model limits its real-world medical utility. In this study, we present a composite network that combines deep learning and unsupervised K-means clustering algorithm (RK-net) for automatic processing of medical images. RK-net was more efficient in image refinement compared with manual screening and annotation. The training of a deep learning model for colorectal cancer diagnosis was accelerated by two times with utilization of RK-net-processed images. Better performance was observed in training loss and accuracy achievement as well. RK-net could be useful to refine medical images of the ever-expanding quantity and assist in subsequent construction of the artificial intelligence model.
| S-EPMC9762730 | biostudies-literature
Project description:PurposeTo perform and evaluate water-fat signal separation of whole-body gradient echo scans using convolutional neural networks.MethodsWhole-body gradient echo scans of 240 subjects, each consisting of 5 bipolar echoes, were used. Reference fat fraction maps were created using a conventional method. Convolutional neural networks, more specifically 2D U-nets, were trained using 5-fold cross-validation with 1 or several echoes as input, using the squared difference between the output and the reference fat fraction maps as the loss function. The outputs of the networks were assessed by the loss function, measured liver fat fractions, and visually. Training was performed using a graphics processing unit (GPU). Inference was performed using the GPU as well as a central processing unit (CPU).ResultsThe loss curves indicated convergence, and the final loss of the validation data decreased when using more echoes as input. The liver fat fractions could be estimated using only 1 echo, but results were improved by use of more echoes. Visual assessment found the quality of the outputs of the networks to be similar to the reference even when using only 1 echo, with slight improvements when using more echoes. Training a network took at most 28.6 h. Inference time of a whole-body scan took at most 3.7 s using the GPU and 5.8 min using the CPU.ConclusionIt is possible to perform water-fat signal separation of whole-body gradient echo scans using convolutional neural networks. Separation was possible using only 1 echo, although using more echoes improved the results.
| S-EPMC6618066 | biostudies-literature