A Few-Shot U-Net Deep Learning Model for COVID-19 Infected Area Segmentation in CT Images.
Ontology highlight
ABSTRACT:
SUBMITTER: Voulodimos A
PROVIDER: S-EPMC8004971 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Coronavirus disease (COVID-19) broke out at the end of 2019, and has resulted in an ongoing global pandemic. Segmentation of pneumonia infections from chest computed tomography (CT) scans of COVID-19 patients is significant for accurate diagnosis and quantitative analysis. Deep learning-based methods can be developed for automatic segmentation and offer a great potential to strengthen timely quarantine and medical treatment. Unfortunately, due to the urgent nature of the COVID-19 pandemic, a systematic collection of CT data sets for deep neural network training is quite difficult, especially high-quality annotations of multi-category infections are limited. In addition, it is still a challenge to segment the infected areas from CT slices because of the irregular shapes and fuzzy boundaries. To solve these issues, we propose a novel COVID-19 pneumonia lesion segmentation network, called Spatial Self-Attention network (SSA-Net), to identify infected regions from chest CT images automatically. In our SSA-Net, a self-attention mechanism is utilized to expand the receptive field and enhance the representation learning by distilling useful contextual information from deeper layers without extra training time, and spatial convolution is introduced to strengthen the network and accelerate the training convergence. Furthermore, to alleviate the insufficiency of labeled multi-class data and the long-tailed distribution of training data, we present a semi-supervised few-shot iterative segmentation framework based on re-weighting the loss and selecting prediction values with high confidence, which can accurately classify different kinds of infections with a small number of labeled image data. Experimental results show that SSA-Net outperforms state-of-the-art medical image segmentation networks and provides clinically interpretable saliency maps, which are useful for COVID-19 diagnosis and patient triage. Meanwhile, our semi-supervised iterative segmentation model can improve the learning ability in small and unbalanced training set and can achieve higher performance.
| S-EPMC9027296 | biostudies-literature
Project description:Deep neural networks have been increasingly proposed for automated screening and diagnosis of retinal diseases from optical coherence tomography (OCT), but often provide high-confidence predictions on out-of-distribution (OOD) cases, compromising their clinical usage. With this in mind, we performed an in-depth comparative analysis of the state-of-the-art uncertainty estimation methods for OOD detection in retinal OCT imaging. The analysis was performed within the use-case of automated screening and staging of age-related macular degeneration (AMD), one of the leading causes of blindness worldwide, where we achieved a macro-average area under the curve (AUC) of 0.981 for AMD classification. We focus on a few-shot Outlier Exposure (OE) method and the detection of near-OOD cases that share pathomorphological characteristics with the inlier AMD classes. Scoring the OOD case based on the Cosine distance in the feature space from the penultimate network layer proved to be a robust approach for OOD detection, especially in combination with the OE. Using Cosine distance and only 8 outliers exposed per class, we were able to improve the near-OOD detection performance of the OE with Reject Bucket method by [Formula: see text] 10% compared to without OE, reaching an AUC of 0.937. The Cosine distance served as a robust metric for OOD detection of both known and unknown classes and should thus be considered as an alternative to the reject bucket class probability in OE approaches, especially in the few-shot scenario. The inclusion of these methodologies did not come at the expense of classification performance, and can substantially improve the reliability and trustworthiness of the resulting deep learning-based diagnostic systems in the context of retinal OCT.
| S-EPMC10533534 | biostudies-literature
Project description:The segmentation of organs at risk is a crucial and time-consuming step in radiotherapy planning. Good automatic methods can significantly reduce the time clinicians have to spend on this task. Due to its variability in shape and low contrast to surrounding structures, segmenting the parotid gland is challenging. Motivated by the recent success of deep learning, we study the use of two-dimensional (2-D), 2-D ensemble, and three-dimensional (3-D) U-Nets for segmentation. The mean Dice similarity to ground truth is ?0.83 for all three models. A patch-based approach for class balancing seems promising for false-positive reduction. The 2-D ensemble and 3-D U-Net are applied to the test data of the 2015 MICCAI challenge on head and neck autosegmentation. Both deep learning methods generalize well onto independent data (Dice 0.865 and 0.88) and are superior to a selection of model- and atlas-based methods with respect to the Dice coefficient. Since appropriate reference annotations are essential for training but often difficult and expensive to obtain, it is important to know how many samples are needed for training. We evaluate the performance after training with different-sized training sets and observe no significant increase in the Dice coefficient for more than 250 training cases.
| S-EPMC6165912 | biostudies-literature
Project description:Environmental monitoring of microplastics (MP) contamination has become an area of great research interest, given potential hazards associated with human ingestion of MP. In this context, determination of MP concentration is essential. However, cheap, rapid, and accurate quantification of MP remains a challenge to this date. This study proposes a deep learning-based image segmentation method that properly distinguishes fluorescent MP from other elements in a given microscopy image. A total of nine different deep learning models, six of which are based on U-Net, were investigated. These models were trained using at least 20,000 patches sampled from 99 fluorescence microscopy images of MP and their corresponding binary masks. MP-Net, which is derived from U-Net, was found to be the best performing model, exhibiting the highest mean F1-score (0.736) and mean IoU value (0.617). Test-time augmentation (using brightness, contrast, and HSV) was applied to MP-Net for robust learning. However, compared to the results obtained without augmentation, no clear improvement in predictive performance could be observed. Recovery assessment for both spiked and real images showed that, compared to already existing tools for MP quantification, the MP quantities predicted by MP-Net are those closest to the ground truth. This observation suggests that MP-Net allows creating masks that more accurately reflect the quantitative presence of fluorescent MP in microscopy images. Finally, MAP (Microplastics Annotation Package) is introduced, an integrated software environment for automated MP quantification, offering support for MP-Net, already existing MP analysis tools like MP-VAT, manual annotation, and model fine-tuning.
| S-EPMC9200300 | biostudies-literature
Project description:Semantic segmentation is an important imaging analysis method enabling the identification of tissue structures. Histological image segmentation is particularly challenging, having large structural information while providing only limited training data. Additionally, labeling these structures to generate training data is time consuming. Here, we demonstrate the feasibility of a semantic segmentation using U-Net with a novel sparse labeling technique. The basic U-Net architecture was extended by attention gates, residual and recurrent links, and dropout regularization. To overcome the high class imbalance, which is intrinsic to histological data, under- and oversampling and data augmentation were used. In an ablation study, various architectures were evaluated, and the best performing model was identified. This model contains attention gates, residual links, and a dropout regularization of 0.125. The segmented images show accurate delineations of the vascular structures (with a precision of 0.9088 and an AUC-ROC score of 0.9717), and the segmentation algorithm is robust to images containing staining variations and damaged tissue. These results demonstrate the feasibility of sparse labeling in combination with the modified U-Net architecture.
| S-EPMC10417575 | biostudies-literature
Project description:Automated cellular instance segmentation is a process utilized for accelerating biological research for the past two decades, and recent advancements have produced higher quality results with less effort from the biologist. Most current endeavors focus on completely cutting the researcher out of the picture by generating highly generalized models. However, these models invariably fail when faced with novel data, distributed differently than the ones used for training. Rather than approaching the problem with methods that presume the availability of large amounts of target data and computing power for retraining, in this work we address the even greater challenge of designing an approach that requires minimal amounts of new annotated data as well as training time. We do so by designing specialized contrastive losses that leverage the few annotated samples very efficiently. A large set of results show that 3 to 5 annotations lead to models with accuracy that: 1) significantly mitigate the covariate shift effects; 2) matches or surpasses other adaptation methods; 3) even approaches methods that have been fully retrained on the target distribution. The adaptation training is only a few minutes, paving a path towards a balance between model performance, computing requirements and expert-level annotation needs.
| S-EPMC10760785 | biostudies-literature
Project description:Deep learning (DL)-based analytics has the scope to transform the field of atomic force microscopy (AFM) with regard to fast and bias-free measurement characterization. For example, AFM force-distance curves can help estimate important parameters of binding kinetics, such as the most probable rupture force, binding probability, association, and dissociation constants, as well as receptor density on live cells. Other than the ideal single-rupture event in the force-distance curves, there can be no-rupture, double-rupture, or multiple-rupture events. The current practice is to go through such datasets manually, which can be extremely tedious work for the experimentalists. We address this issue by adopting a few-shot learning approach to build sample-efficient DL models that demonstrate better performance than shallow ML models while matching the performance of moderately trained humans. We also release our AFM force curve dataset and annotations publicly as a benchmark for the research community.
| S-EPMC9868661 | biostudies-literature
Project description:BackgroundHigh quality 3D information of the microscopic plant tissue morphology-the spatial organization of cells and intercellular spaces in tissues-helps in understanding physiological processes in a wide variety of plants and tissues. X-ray micro-CT is a valuable tool that is becoming increasingly available in plant research to obtain 3D microstructural information of the intercellular pore space and individual pore sizes and shapes of tissues. However, individual cell morphology is difficult to retrieve from micro-CT as cells cannot be segmented properly due to negligible density differences at cell-to-cell interfaces. To address this, deep learning-based models were trained and tested to segment individual cells using X-ray micro-CT images of parenchyma tissue samples from apple and pear fruit with different cell and porosity characteristics.ResultsThe best segmentation model achieved an Aggregated Jaccard Index (AJI) of 0.86 and 0.73 for apple and pear tissue, respectively, which is an improvement over the current benchmark method that achieved AJIs of 0.73 and 0.67. Furthermore, the neural network was able to detect other plant tissue structures such as vascular bundles and stone cell clusters (brachysclereids), of which the latter were shown to strongly influence the spatial organization of pear cells. Based on the AJIs, apple tissue was found to be easier to segment, as the porosity and specific surface area of the pore space are higher and lower, respectively, compared to pear tissue. Moreover, samples with lower pore network connectivity, proved very difficult to segment.ConclusionsThe proposed method can be used to automatically quantify 3D cell morphology of plant tissue from micro-CT instead of opting for laborious manual annotations or less accurate segmentation approaches. In case fruit tissue porosity or pore network connectivity is too low or the specific surface area of the pore space too high, native X-ray micro-CT is unable to provide proper marker points of cell outlines, and one should rely on more elaborate contrast-enhancing scan protocols.
| S-EPMC10799452 | biostudies-literature
Project description:BackgroundDifferential artery-vein (AV) analysis in optical coherence tomography angiography (OCTA) holds promise for the early detection of eye diseases. However, currently available methods for AV analysis are limited for binary processing of retinal vasculature in OCTA, without quantitative information of vascular perfusion intensity. This study is to develop and validate a method for quantitative AV analysis of vascular perfusion intensity.MethodA deep learning network AVA-Net has been developed for automated AV area (AVA) segmentation in OCTA. Seven new OCTA features, including arterial area (AA), venous area (VA), AVA ratio (AVAR), total perfusion intensity density (T-PID), arterial PID (A-PID), venous PID (V-PID), and arterial-venous PID ratio (AV-PIDR), were extracted and tested for early detection of diabetic retinopathy (DR). Each of these seven features was evaluated for quantitative evaluation of OCTA images from healthy controls, diabetic patients without DR (NoDR), and mild DR.ResultsIt was observed that the area features, i.e., AA, VA and AVAR, can reveal significant differences between the control and mild DR. Vascular perfusion parameters, including T-PID and A-PID, can differentiate mild DR from control group. AV-PIDR can disclose significant differences among all three groups, i.e., control, NoDR, and mild DR. According to Bonferroni correction, the combination of A-PID and AV-PIDR can reveal significant differences in all three groups.ConclusionsAVA-Net, which is available on GitHub for open access, enables quantitative AV analysis of AV area and vascular perfusion intensity. Comparative analysis revealed AV-PIDR as the most sensitive feature for OCTA detection of early DR. Ensemble AV feature analysis, e.g., the combination of A-PID and AV-PIDR, can further improve the performance for early DR assessment.
| S-EPMC10110614 | biostudies-literature
Project description:IntroductionThe number of glomeruli and glomerulosclerosis evaluated on kidney biopsy slides constitute standard components of a renal pathology report. Prevailing methods for glomerular assessment remain manual, labor intensive, and nonstandardized. We developed a deep learning framework to accurately identify and segment glomeruli from digitized images of human kidney biopsies.MethodsTrichrome-stained images (n = 275) from renal biopsies of 171 patients with chronic kidney disease treated at the Boston Medical Center from 2009 to 2012 were analyzed. A sliding window operation was defined to crop each original image to smaller images. Each cropped image was then evaluated by at least 3 experts into 3 categories: (i) no glomerulus, (ii) normal or partially sclerosed (NPS) glomerulus, and (iii) globally sclerosed (GS) glomerulus. This led to identification of 751 unique images representing nonglomerular regions, 611 images with NPS glomeruli, and 134 images with GS glomeruli. A convolutional neural network (CNN) was trained with cropped images as inputs and corresponding labels as output. Using this model, an image processing routine was developed to scan the test images to segment the GS glomeruli.ResultsThe CNN model was able to accurately discriminate nonglomerular images from NPS and GS images (performance on test data: Accuracy: 92.67% ± 2.02% and Kappa: 0.8681 ± 0.0392). The segmentation model that was based on the CNN multilabel classifier accurately marked the GS glomeruli on the test data (Matthews correlation coefficient = 0.628).ConclusionThis work demonstrates the power of deep learning for assessing complex histologic structures from digitized human kidney biopsies.
| S-EPMC6612039 | biostudies-literature