Semi-supervised segmentation of ultrasound images based on patch representation and continuous min cut.
Ontology highlight
ABSTRACT:
SUBMITTER: Ciurte A
PROVIDER: S-EPMC4091944 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Prostate segmentation in transrectal ultrasound (TRUS) image is an essential prerequisite for many prostate-related clinical procedures, which, however, is also a long-standing problem due to the challenges caused by the low image quality and shadow artifacts. In this paper, we propose a Shadow-consistent Semi-supervised Learning (SCO-SSL) method with two novel mechanisms, namely shadow augmentation (Shadow-AUG) and shadow dropout (Shadow-DROP), to tackle this challenging problem. Specifically, Shadow-AUG enriches training samples by adding simulated shadow artifacts to the images to make the network robust to the shadow patterns. Shadow-DROP enforces the segmentation network to infer the prostate boundary using the neighboring shadow-free pixels. Extensive experiments are conducted on two large clinical datasets (a public dataset containing 1,761 TRUS volumes and an in-house dataset containing 662 TRUS volumes). In the fully-supervised setting, a vanilla U-Net equipped with our Shadow-AUG&Shadow-DROP outperforms the state-of-the-arts with statistical significance. In the semi-supervised setting, even with only 20% labeled training data, our SCO-SSL method still achieves highly competitive performance, suggesting great clinical value in relieving the labor of data annotation. Source code is released at https://github.com/DIAL-RPI/SCO-SSL.
| S-EPMC9709821 | biostudies-literature
Project description:BackgroundAccurate gastrointestinal (GI) lesion segmentation is crucial in diagnosing digestive tract diseases. An automatic lesion segmentation in endoscopic images is vital to relieving physicians' burden and improving the survival rate of patients. However, pixel-wise annotations are highly intensive, especially in clinical settings, while numerous unlabeled image datasets could be available, although the significant results of deep learning approaches in several tasks heavily depend on large labeled datasets. Limited labeled data also hinder trained models' generalizability under fully supervised learning for computer-aided diagnosis (CAD) systems.MethodsThis work proposes a generative adversarial learning-based semi-supervised segmentation framework for GI lesion diagnosis in endoscopic images to tackle the challenge of limited annotations. The proposed approach leverages limited annotated and large unlabeled datasets in the training networks. We extensively tested the proposed method on 4880 endoscopic images.ResultsCompared with current related works, the proposed method validates better results (Dice similarity coefficient = 89.42 ± 3.92, Intersection over union = 80.04 ± 5.75, Precision = 91.72 ± 4.05, Recall = 90.11 ± 5.64, and Hausdorff distance = 23.28 ± 14.36) on the challenging multi-sited datasets, confirming the effectiveness of the proposed framework.ConclusionWe explore a semi-supervised lesion segmentation method to employ the full use of multiple unlabeled endoscopic images to improve lesion segmentation accuracy. Experimental results confirmed the potential of our method and outperformed promising results compared with the current related works. The proposed CAD system can minimize diagnostic errors.
| S-EPMC9864320 | biostudies-literature
Project description:Deep learning has shown potential in domains with large-scale annotated datasets. However, manual annotation is expensive, time-consuming, and tedious. Pixel-level annotations are particularly costly for semantic segmentation in images with dense irregular patterns of object instances, such as in plant images. In this work, we propose a method for developing high-performing deep learning models for semantic segmentation of such images utilizing little manual annotation. As a use case, we focus on wheat head segmentation. We synthesize a computationally annotated dataset-using a few annotated images, a short unannotated video clip of a wheat field, and several video clips with no wheat-to train a customized U-Net model. Considering the distribution shift between the synthesized and real images, we apply three domain adaptation steps to gradually bridge the domain gap. Only using two annotated images, we achieved a Dice score of 0.89 on the internal test set. When further evaluated on a diverse external dataset collected from 18 different domains across five countries, this model achieved a Dice score of 0.73. To expose the model to images from different growth stages and environmental conditions, we incorporated two annotated images from each of the 18 domains to further fine-tune the model. This increased the Dice score to 0.91. The result highlights the utility of the proposed approach in the absence of large-annotated datasets. Although our use case is wheat head segmentation, the proposed approach can be extended to other segmentation tasks with similar characteristics of irregularly repeating patterns of object instances.
| S-EPMC10013790 | biostudies-literature
Project description:Cone-beam computed tomography (CBCT) is an increasingly utilized imaging modality for the diagnosis and treatment planning of the patients with craniomaxillofacial (CMF) deformities. Accurate segmentation of CBCT image is an essential step to generate three-dimensional (3D) models for the diagnosis and treatment planning of the patients with CMF deformities. However, due to the poor image quality, including very low signal-to-noise ratio and the widespread image artifacts such as noise, beam hardening, and inhomogeneity, it is challenging to segment the CBCT images. In this paper, the authors present a new automatic segmentation method to address these problems.To segment CBCT images, the authors propose a new method for fully automated CBCT segmentation by using patch-based sparse representation to (1) segment bony structures from the soft tissues and (2) further separate the mandible from the maxilla. Specifically, a region-specific registration strategy is first proposed to warp all the atlases to the current testing subject and then a sparse-based label propagation strategy is employed to estimate a patient-specific atlas from all aligned atlases. Finally, the patient-specific atlas is integrated into a maximum a posteriori probability-based convex segmentation framework for accurate segmentation.The proposed method has been evaluated on a dataset with 15 CBCT images. The effectiveness of the proposed region-specific registration strategy and patient-specific atlas has been validated by comparing with the traditional registration strategy and population-based atlas. The experimental results show that the proposed method achieves the best segmentation accuracy by comparison with other state-of-the-art segmentation methods.The authors have proposed a new CBCT segmentation method by using patch-based sparse representation and convex optimization, which can achieve considerably accurate segmentation results in CBCT segmentation based on 15 patients.
| S-EPMC3971832 | biostudies-other
Project description:MotivationMetagenomic contig binning is an important computational problem in metagenomic research, which aims to cluster contigs from the same genome into the same group. Unlike classical clustering problem, contig binning can utilize known relationships among some of the contigs or the taxonomic identity of some contigs. However, the current state-of-the-art contig binning methods do not make full use of the additional biological information except the coverage and sequence composition of the contigs.ResultsWe developed a novel contig binning method, Semi-supervised Spectral Normalized Cut for Binning (SolidBin), based on semi-supervised spectral clustering. Using sequence feature similarity and/or additional biological information, such as the reliable taxonomy assignments of some contigs, SolidBin constructs two types of prior information: must-link and cannot-link constraints. Must-link constraints mean that the pair of contigs should be clustered into the same group, while cannot-link constraints mean that the pair of contigs should be clustered in different groups. These constraints are then integrated into a classical spectral clustering approach, normalized cut, for improved contig binning. The performance of SolidBin is compared with five state-of-the-art genome binners, CONCOCT, COCACOLA, MaxBin, MetaBAT and BMC3C on five next-generation sequencing benchmark datasets including simulated multi- and single-sample datasets and real multi-sample datasets. The experimental results show that, SolidBin has achieved the best performance in terms of F-score, Adjusted Rand Index and Normalized Mutual Information, especially while using the real datasets and the single-sample dataset.Availability and implementationhttps://github.com/sufforest/SolidBin.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC6821242 | biostudies-literature
Project description:Accurate water surface elevation estimation is essential for understanding nearshore processes, but it is still challenging due to limitations in measuring water level using in-situ acoustic sensors. This paper presents a vision-based water surface elevation estimation approach using multi-view datasets. Specifically, we propose a visual domain adaptation method to build a water level estimator in spite of a situation in which ocean wave height cannot be measured directly. We also implemented a semi-supervised approach to extract wave height information from long-term sequences of wave height observations with minimal supervision. We performed wave flume experiments in a hydraulic laboratory with two cameras with side and top viewpoints to validate the effectiveness of our approach. The performance of the proposed models were evaluated by comparing the estimated time series of water elevation with the ground-truth wave gauge data at three locations along the wave flume. The estimated time series were in good agreement within the averaged correlation coefficient of 0.98 and 0.90 on the measurement and 0.95 and 0.85 on the estimation for regular and irregular waves, respectively.
| S-EPMC8571332 | biostudies-literature
Project description:PurposeA semi-supervised two-step methodology is proposed to obtain a volumetric estimation of COVID-19-related lesions on Computed Tomography (CT) images.MethodsFirst, damaged tissue was segmented from CT images using a probabilistic active contours approach. Second, lung parenchyma was extracted using a previously trained U-Net. Finally, volumetric estimation of COVID-19 lesions was calculated considering the lung parenchyma masks.Our approach was validated using a publicly available dataset containing 20 CT COVID-19 images previously labeled and manually segmented. Then, it was applied to 295 COVID-19 patients CT scans admitted to an intensive care unit. We compared the lesion estimation between deceased and survived patients for high and low-resolution images.ResultsA comparable median Dice similarity coefficient of 0.66 for the 20 validation images was achieved. For the 295 images dataset, results show a significant difference in lesion percentages between deceased and survived patients, with a p-value of 9.1 × 10-4 in low-resolution and 5.1 × 10-5 in high-resolution images. Furthermore, the difference in lesion percentages between high and low-resolution images was 10 % on average.ConclusionThe proposed approach could help estimate the lesion size caused by COVID-19 in CT images and may be considered an alternative to getting a volumetric segmentation for this novel disease without the requirement of large amounts of COVID-19 labeled data to train an artificial intelligence algorithm. The low variation between the estimated percentage of lesions in high and low-resolution CT images suggests that the proposed approach is robust, and it may provide valuable information to differentiate between survived and deceased patients.
| S-EPMC10030333 | biostudies-literature
Project description:Mass Spectrometric Imaging (MSI) is a molecular imaging technique that allows the generation of 2D ion density maps for a large complement of the active molecules present in cells and sectioned tissues. Automatic segmentation of such maps according to patterns of co-expression of individual molecules can be used for discovery of novel molecular signatures (molecules that are specifically expressed in particular spatial regions). However, current segmentation techniques are biased toward the discovery of higher abundance molecules and large segments; they allow limited opportunity for user interaction, and validation is usually performed by similarity to known anatomical features. We describe here a novel method, AMASS (Algorithm for MSI Analysis by Semi-supervised Segmentation). AMASS relies on the discriminating power of a molecular signal instead of its intensity as a key feature, uses an internal consistency measure for validation, and allows significant user interaction and supervision as options. An automated segmentation of entire leech embryo data images resulted in segmentation domains congruent with many known organs, including heart, CNS ganglia, nephridia, nephridiopores, and lateral and ventral regions, each with a distinct molecular signature. Likewise, segmentation of a rat brain MSI slice data set yielded known brain features and provided interesting examples of co-expression between distinct brain regions. AMASS represents a new approach for the discovery of peptide masses with distinct spatial features of expression. Software source code and installation and usage guide are available at http://bix.ucsd.edu/AMASS/ .
| S-EPMC3190602 | biostudies-literature
Project description:Action segmentation of behavioral videos is the process of labeling each frame as belonging to one or more discrete classes, and is a crucial component of many studies that investigate animal behavior. A wide range of algorithms exist to automatically parse discrete animal behavior, encompassing supervised, unsupervised, and semi-supervised learning paradigms. These algorithms - which include tree-based models, deep neural networks, and graphical models - differ widely in their structure and assumptions on the data. Using four datasets spanning multiple species - fly, mouse, and human - we systematically study how the outputs of these various algorithms align with manually annotated behaviors of interest. Along the way, we introduce a semi-supervised action segmentation model that bridges the gap between supervised deep neural networks and unsupervised graphical models. We find that fully supervised temporal convolutional networks with the addition of temporal information in the observations perform the best on our supervised metrics across all datasets.
| S-EPMC11302674 | biostudies-literature
Project description:Hyperspectral imaging (HSI) of tissue samples in the mid-infrared (mid-IR) range provides spectro-chemical and tissue structure information at sub-cellular spatial resolution. Disease states can be directly assessed by analyzing the mid-IR spectra of different cell types (e.g., epithelial cells) and sub-cellular components (e.g., nuclei), provided that we can accurately classify the pixels belonging to these components. The challenge is to extract information from hundreds of noisy mid-IR bands at each pixel, where each band is not very informative in itself, making annotations of unstained tissue HSI images particularly tricky. Because the tissue structure is not necessarily identical between the two sections, only a few regions in unstained HSI image can be annotated with high confidence, even when serial (or adjacent) hematoxylin and eosin stained section is used as a visual guide. In order to completely use both labeled and unlabeled pixels in training images, we have developed an HSI pixel classification method that uses semi-supervised learning for both spectral dimension reduction and hierarchical pixel clustering. Compared to the supervised classifiers, the proposed method was able to account for the vast differences in the spectra of sub-cellular components of the same cell type and to achieve an F1 score of 71.18% on twofold cross-validation across 20 tissue images. To generate further interest in this promising modality, we have released our source code and also showed that disease classification is straightforward after HSI image segmentation.
| S-EPMC6548328 | biostudies-literature