Misic, a general deep learning-based method for the high-throughput cell segmentation of complex bacterial communities.
Ontology highlight
ABSTRACT:
SUBMITTER: Panigrahi S
PROVIDER: S-EPMC8478410 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundThe shape, size, and surface information relating to the glenoid fossae and condyles in temporomandibular joints (TMJ) are essential for diagnosing and treating. Patients with TMJ disease often have surface abrasion which may cause fuzzy edges in computed tomography (CT) imaging, especially for low-dose CT, making TMJ segmentation more difficult.MethodsIn this paper, an automatic segmentation algorithm based on deep learning and post-processing was introduced. First, U-Net was used to divide images into 3 categories: glenoid fossae, condyles, and background. For structural fractures in these divided images, the internal force constraint of a snake model was used to replenish the integrity of the fracture boundary in a post-processing operation, and the initial boundary of the snake was obtained based on the basis of the tracking concept. A total of 206 cases of low-dose CT were used to verify the effectiveness of the algorithm, and such indicators as the Dice coefficient (DC) and mean surface distance (MSD) were used to evaluate the agreement between experimental results and the gold standard.ResultsThe proposed method is tested on a self-collected dataset. The results demonstrate that proposed method achieves state-of-the-art performance in terms of DCs = 0.92±0.03 (condyles) and 0.90±0.04 (glenoid fossae), and MSDs =0.20±0.19 mm (condyles) and 0.19±0.08 mm (glenoid fossae).ConclusionsThis study is the first to focus on the simultaneous segmentation of TMJ glenoid fossae and condyles. The proposed U-Net + tracking-based algorithm showed a relatively high segmentation efficiency, enabling it to achieve sought-after segmentation accuracy.
| S-EPMC8039636 | biostudies-literature
Project description:Robust and automated segmentation of leaves and other backgrounds is a core prerequisite of most approaches in high-throughput field phenotyping. So far, the possibilities of deep learning approaches for this purpose have not been explored adequately, partly due to a lack of publicly available, appropriate datasets. This study presents a workflow based on DeepLab v3+ and on a diverse annotated dataset of 190 RGB (350 x 350 pixels) images. Images of winter wheat plants of 76 different genotypes and developmental stages have been acquired throughout multiple years at high resolution in outdoor conditions using nadir view, encompassing a wide range of imaging conditions. Inconsistencies of human annotators in complex images have been quantified, and metadata information of camera settings has been included. The proposed approach achieves an intersection over union (IoU) of 0.77 and 0.90 for plants and soil, respectively. This outperforms the benchmarked machine learning methods which use Support Vector Classifier and/or Random Forrest. The results show that a small but carefully chosen and annotated set of images can provide a good basis for a powerful segmentation pipeline. Compared to earlier methods based on machine learning, the proposed method achieves better performance on the selected dataset in spite of using a deep learning approach with limited data. Increasing the amount of publicly available data with high human agreement on annotations and further development of deep neural network architectures will provide high potential for robust field-based plant segmentation in the near future. This, in turn, will be a cornerstone of data-driven improvement in crop breeding and agricultural practices of global benefit.
| S-EPMC8765702 | biostudies-literature
Project description:The purpose of this study was to determine whether a deep-learning-based assessment system could facilitate preoperative grading of meningioma. This was a retrospective study conducted at two institutions covering 643 patients. The system, designed with a cascade network structure, was developed using deep-learning technology for automatic tumor detection, visual assessment, and grading prediction. Specifically, a modified U-Net convolutional neural network was first established to segment tumor images. Subsequently, the segmentations were introduced into rendering algorithms for spatial reconstruction and another DenseNet convolutional neural network for grading prediction. The trained models were integrated as a system, and the robustness was tested based on its performance on an external dataset from the second institution involving different magnetic resonance imaging platforms. The results showed that the segment model represented a noteworthy performance with dice coefficients of 0.920 ± 0.009 in the validation group. With accurate segmented tumor images, the rendering model delicately reconstructed the tumor body and clearly displayed the important intracranial vessels. The DenseNet model also achieved high accuracy with an area under the curve of 0.918 ± 0.006 and accuracy of 0.901 ± 0.039 when classifying tumors into low-grade and high-grade meningiomas. Moreover, the system exhibited good performance on the external validation dataset.
| S-EPMC8401675 | biostudies-literature
Project description: Not available
| S-BSST732 | biostudies-other
Project description:BackgroundSegmentation of coronavirus disease 2019 (COVID-19) lesions is a difficult task due to high uncertainty in the shape, size and location of the lesions. CT scan image is an important means of diagnosing COVID-19, but it requires doctors to observe a large number of scan images repeatedly to determine the patient's condition. Moreover, the low contrast of CT scan and the presence of tissues such as blood vessels in the background increase the difficulty of diagnosis. To solve this problem, we proposed an improved segmentation model called the residual attention U-shaped network (ResAU-Net).MethodsA novel method to detect and segment coronavirus pneumonia was established based on the deep-learning algorithm. Firstly, the CT scan image was input, and lung segmentation was then realized by U-net. Then, the region of interest was selected by the minimum circumscribed rectangle clipping method. Finally, the proposed ResAU-Net, which includes attention module (AMB), residual module (RBM) and sub-pixel convolution module (SPCBM), was used to segment the infected area and generate the segmentation results.ResultsWe evaluated our model using cross-validation on 100 chest CT scans test images. The experimental results showed that our method achieved start-of-the-art performance on the pneumonia dataset. The mIoU and Dice cofficients of Lesion segmentation were 73.40%±2.24% and 84.5%±2.46%, and realize fast real-time processing.ConclusionsOur model can effectively solve the problems of poor segmentation accuracy in the segmentation of COVID-19 lesions, and the segmentation result image can effectively assist medical staff in the diagnosis and quantitative analysis of infection degree, and improve the screening and diagnosis efficiency of pneumonia.
| S-EPMC8263886 | biostudies-literature
Project description:Rice is a vital food crop that feeds most of the global population. Cultivating high-yielding and superior-quality rice varieties has always been a critical research direction. Rice grain-related traits can be used as crucial phenotypic evidence to assess yield potential and quality. However, the analysis of rice grain traits is still mainly based on manual counting or various seed evaluation devices, which incur high costs in time and money. This study proposed a high-precision phenotyping method for rice panicles based on visible light scanning imaging and deep learning technology, which can achieve high-throughput extraction of critical traits of rice panicles without separating and threshing rice panicles. The imaging of rice panicles was realized through visible light scanning. The grains were detected and segmented using the Faster R-CNN-based model, and an improved Pix2Pix model cascaded with it was used to compensate for the information loss caused by the natural occlusion between the rice grains. An image processing pipeline was designed to calculate fifteen phenotypic traits of the on-panicle rice grains. Eight varieties of rice were used to verify the reliability of this method. The R2 values between the extraction by the method and manual measurements of the grain number, grain length, grain width, grain length/width ratio and grain perimeter were 0.99, 0.96, 0.83, 0.90 and 0.84, respectively. Their mean absolute percentage error (MAPE) values were 1.65%, 7.15%, 5.76%, 9.13% and 6.51%. The average imaging time of each rice panicle was about 60 seconds, and the total time of data processing and phenotyping traits extraction was less than 10 seconds. By randomly selecting one thousand grains from each of the eight varieties and analyzing traits, it was found that there were certain differences between varieties in the number distribution of thousand-grain length, thousand-grain width, and thousand-grain length/width ratio. The results show that this method is suitable for high-throughput, non-destructive, and high-precision extraction of on-panicle grains traits without separating. Low cost and robust performance make it easy to popularize. The research results will provide new ideas and methods for extracting panicle traits of rice and other crops.
| S-EPMC10544938 | biostudies-literature
Project description:The abilities of plant biologists and breeders to characterize the genetic basis of physiological traits are limited by their abilities to obtain quantitative data representing precise details of trait variation, and particularly to collect this data at a high-throughput scale with low cost. Although deep learning methods have demonstrated unprecedented potential to automate plant phenotyping, these methods commonly rely on large training sets that can be time-consuming to generate. Intelligent algorithms have therefore been proposed to enhance the productivity of these annotations and reduce human efforts. We propose a high-throughput phenotyping system which features a Graphical User Interface (GUI) and a novel interactive segmentation algorithm: Semantic-Guided Interactive Object Segmentation (SGIOS). By providing a user-friendly interface and intelligent assistance with annotation, this system offers potential to streamline and accelerate the generation of training sets, reducing the effort required by the user. Our evaluation shows that our proposed SGIOS model requires fewer user inputs compared to the state-of-art models for interactive segmentation. As a case study of the use of the GUI applied for genetic discovery in plants, we present an example of results from a preliminary genome-wide association study (GWAS) of in planta regeneration in Populus trichocarpa (poplar). We further demonstrate that the inclusion of a semantic prior map with SGIOS can accelerate the training process for future GWAS, using a sample of a dataset extracted from a poplar GWAS of in vitro regeneration. The capabilities of our phenotyping system surpass those of unassisted humans to rapidly and precisely phenotype our traits of interest. The scalability of this system enables large-scale phenomic screens that would otherwise be time-prohibitive, thereby providing increased power for GWAS, mutant screens, and other studies relying on large sample sizes to characterize the genetic basis of trait variation. Our user-friendly system can be used by researchers lacking a computational background, thus helping to democratize the use of deep segmentation as a tool for plant phenotyping.
| S-EPMC9394117 | biostudies-literature
Project description:The Rhizotrons method is an important means of detecting dynamic growth and development phenotypes of plant roots. However, the segmentation of root images is a critical obstacle restricting further development of this method. At present, researchers mostly use direct manual drawings or software-assisted manual drawings to segment root systems for analysis. Root systems can be segmented from root images obtained by the Rhizotrons method, and then, root system lengths and diameters can be obtained with software. This type of image segmentation method is extremely inefficient and very prone to human error. Here, we investigate the effectiveness of an automated image segmentation method based on the DeepLabv3+ convolutional neural network (CNN) architecture to streamline such measurements. We have improved the upsampling portion of the DeepLabv3+ network and validated it using in situ images of cotton roots obtained with a micro root window root system monitoring system. Segmentation performance of the proposed method utilizing WinRHIZO Tron MF analysis was assessed using these images. After 80 epochs of training, the final verification set F1-score, recall, and precision were 0.9773, 0.9847, and 0.9702, respectively. The Spearman rank correlation between the manually obtained Rhizotrons manual segmentation root length and automated root length was 0.9667 (p < 10-8), with r 2 = 0.9449. Based on the comparison of our segmentation results with those of traditional manual and U-net segmentation methods, this novel method can more accurately segment root systems in complex soil environments. Thus, using the improved DeepLabv3+ to segment root systems based on micro-root images is an effective method for accurately and quickly segmenting root systems in a homogeneous soil environment and has clear advantages over traditional manual segmentation.
| S-EPMC7604297 | biostudies-literature
Project description:Accurate localisation of mandibular canals in lower jaws is important in dental implantology, in which the implant position and dimensions are currently determined manually from 3D CT images by medical experts to avoid damaging the mandibular nerve inside the canal. Here we present a deep learning system for automatic localisation of the mandibular canals by applying a fully convolutional neural network segmentation on clinically diverse dataset of 637 cone beam CT volumes, with mandibular canals being coarsely annotated by radiologists, and using a dataset of 15 volumes with accurate voxel-level mandibular canal annotations for model evaluation. We show that our deep learning model, trained on the coarsely annotated volumes, localises mandibular canals of the voxel-level annotated set, highly accurately with the mean curve distance and average symmetric surface distance being 0.56 mm and 0.45 mm, respectively. These unparalleled accurate results highlight that deep learning integrated into dental implantology workflow could significantly reduce manual labour in mandibular canal annotations.
| S-EPMC7125134 | biostudies-literature
Project description:Delineation of Computed Tomography (CT) abdominal anatomical structure, specifically spleen segmentation, is useful for not only measuring tissue volume and biomarkers but also for monitoring interventions. Recently, segmentation algorithms using deep learning have been widely used to reduce time humans spend to label CT data. However, the computerized segmentation has two major difficulties: managing intermediate results (e.g., resampled scans, 2D sliced image for deep learning), and setting up the system environments and packages for autonomous execution. To overcome these issues, we propose an automated pipeline for the abdominal spleen segmentation. This pipeline provides an end-to-end synthesized process that allows users to avoid installing any packages and to deal with the intermediate results locally. The pipeline has three major stages: pre-processing of input data, segmentation of spleen using deep learning, 3D reconstruction with the generated labels by matching the segmentation results with the original image dimensions, which can then be used later and for display or demonstration. Given the same volume scan, the approach described here takes about 50 s on average whereas the manual segmentation takes about 30 min on the average. Even if it includes all subsidiary processes such as preprocessing and necessary setups, the whole pipeline process requires on the average 20 min from beginning to end.
| S-EPMC7086455 | biostudies-literature