CDeep3M-Plug-and-Play cloud-based deep learning for image segmentation.
Ontology highlight
ABSTRACT:
SUBMITTER: Haberl MG
PROVIDER: S-EPMC6548193 | biostudies-literature | 2018 Sep
REPOSITORIES: biostudies-literature
Publications
CDeep3M-Plug-and-Play cloud-based deep learning for image segmentation.
Haberl Matthias G MG Churas Christopher C Tindall Lucas L Boassa Daniela D Phan Sébastien S Bushong Eric A EA Madany Matthew M Akay Raffi R Deerinck Thomas J TJ Peltier Steven T ST Ellisman Mark H MH
Nature methods 20180831 9
As biomedical imaging datasets expand, deep neural networks are considered vital for image processing, yet community access is still limited by setting up complex computational environments and availability of high-performance computing resources. We address these bottlenecks with CDeep3M, a ready-to-use image segmentation solution employing a cloud-based deep convolutional neural network. We benchmark CDeep3M on large and complex two-dimensional and three-dimensional imaging datasets from light ...[more]
Similar Datasets
Project description:Background Automated analysis of large image data is highly demanded in high-throughput plant phenotyping. Due to large variability in optical plant appearance and experimental setups, advanced machine and deep learning techniques are required for automated detection and segmentation of plant structures in complex optical scenes. Methods Here, we present a GUI-based software tool (DeepShoot) for efficient, fully automated segmentation and quantitative analysis of greenhouse-grown shoots which is based on pre-trained U-net deep learning models of arabidopsis, maize, and wheat plant appearance in different rotational side- and top-views. Results Our experimental results show that the developed algorithmic framework performs automated segmentation of side- and top-view images of different shoots acquired at different developmental stages using different phenotyping facilities with an average accuracy of more than 90% and outperforms shallow as well as conventional and encoder backbone networks in cross-validation tests with respect to both precision and performance time. Conclusion The DeepShoot tool presented in this study provides an efficient solution for automated segmentation and phenotypic characterization of greenhouse-grown plant shoots suitable also for end-users without advanced IT skills. Primarily trained on images of three selected plants, this tool can be applied to images of other plant species exhibiting similar optical properties.
| S-EPMC9328757 | biostudies-literature
Project description:Accurate segmentation of the jaw (i.e., mandible and maxilla) and the teeth in cone beam computed tomography (CBCT) scans is essential for orthodontic diagnosis and treatment planning. Although various (semi)automated methods have been proposed to segment the jaw or the teeth, there is still a lack of fully automated segmentation methods that can simultaneously segment both anatomic structures in CBCT scans (i.e., multiclass segmentation). In this study, we aimed to train and validate a mixed-scale dense (MS-D) convolutional neural network for multiclass segmentation of the jaw, the teeth, and the background in CBCT scans. Thirty CBCT scans were obtained from patients who had undergone orthodontic treatment. Gold standard segmentation labels were manually created by 4 dentists. As a benchmark, we also evaluated MS-D networks that segmented the jaw or the teeth (i.e., binary segmentation). All segmented CBCT scans were converted to virtual 3-dimensional (3D) models. The segmentation performance of all trained MS-D networks was assessed by the Dice similarity coefficient and surface deviation. The CBCT scans segmented by the MS-D network demonstrated a large overlap with the gold standard segmentations (Dice similarity coefficient: 0.934 ± 0.019, jaw; 0.945 ± 0.021, teeth). The MS-D network-based 3D models of the jaw and the teeth showed minor surface deviations when compared with the corresponding gold standard 3D models (0.390 ± 0.093 mm, jaw; 0.204 ± 0.061 mm, teeth). The MS-D network took approximately 25 s to segment 1 CBCT scan, whereas manual segmentation took about 5 h. This study showed that multiclass segmentation of jaw and teeth was accurate and its performance was comparable to binary segmentation. The MS-D network trained for multiclass segmentation would therefore make patient-specific orthodontic treatment more feasible by strongly reducing the time required to segment multiple anatomic structures in CBCT scans.
| S-EPMC8293763 | biostudies-literature
Project description:Automatic medical image segmentation plays a critical role in scientific research and medical care. Existing high-performance deep learning methods typically rely on large training datasets with high-quality manual annotations, which are difficult to obtain in many clinical applications. Here, we introduce Annotation-effIcient Deep lEarning (AIDE), an open-source framework to handle imperfect training datasets. Methodological analyses and empirical evaluations are conducted, and we demonstrate that AIDE surpasses conventional fully-supervised models by presenting better performance on open datasets possessing scarce or noisy annotations. We further test AIDE in a real-life case study for breast tumor segmentation. Three datasets containing 11,852 breast images from three medical centers are employed, and AIDE, utilizing 10% training annotations, consistently produces segmentation maps comparable to those generated by fully-supervised counterparts or provided by independent radiologists. The 10-fold enhanced efficiency in utilizing expert labels has the potential to promote a wide range of biomedical applications.
| S-EPMC8501087 | biostudies-literature
Project description:Cell segmentation plays a crucial role in understanding, diagnosing, and treating diseases. Despite the recent success of deep learning-based cell segmentation methods, it remains challenging to accurately segment densely packed cells in 3D cell membrane images. Existing approaches also require fine-tuning multiple manually selected hyperparameters on the new datasets. We develop a deep learning-based 3D cell segmentation pipeline, 3DCellSeg, to address these challenges. Compared to the existing methods, our approach carries the following novelties: (1) a robust two-stage pipeline, requiring only one hyperparameter; (2) a light-weight deep convolutional neural network (3DCellSegNet) to efficiently output voxel-wise masks; (3) a custom loss function (3DCellSeg Loss) to tackle the clumped cell problem; and (4) an efficient touching area-based clustering algorithm (TASCAN) to separate 3D cells from the foreground masks. Cell segmentation experiments conducted on four different cell datasets show that 3DCellSeg outperforms the baseline models on the ATAS (plant), HMS (animal), and LRP (plant) datasets with an overall accuracy of 95.6%, 76.4%, and 74.7%, respectively, while achieving an accuracy comparable to the baselines on the Ovules (plant) dataset with an overall accuracy of 82.2%. Ablation studies show that the individual improvements in accuracy is attributable to 3DCellSegNet, 3DCellSeg Loss, and TASCAN, with the 3DCellSeg demonstrating robustness across different datasets and cell shapes. Our results suggest that 3DCellSeg can serve a powerful biomedical and clinical tool, such as histo-pathological image analysis, for cancer diagnosis and grading.
| S-EPMC8748745 | biostudies-literature
Project description:MotivationThe inherent low contrast of electron microscopy (EM) datasets presents a significant challenge for rapid segmentation of cellular ultrastructures from EM data. This challenge is particularly prominent when working with high-resolution big-datasets that are now acquired using electron tomography and serial block-face imaging techniques. Deep learning (DL) methods offer an exciting opportunity to automate the segmentation process by learning from manual annotations of a small sample of EM data. While many DL methods are being rapidly adopted to segment EM data no benchmark analysis has been conducted on these methods to date.ResultsWe present EM-stellar, a platform that is hosted on Google Colab that can be used to benchmark the performance of a range of state-of-the-art DL methods on user-provided datasets. Using EM-stellar we show that the performance of any DL method is dependent on the properties of the images being segmented. It also follows that no single DL method performs consistently across all performance evaluation metrics.Availability and implementationEM-stellar (code and data) is written in Python and is freely available under MIT license on GitHub (https://github.com/cellsmb/em-stellar).Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC8034537 | biostudies-literature
Project description:Urban area mapping is an important application of remote sensing which aims at both estimation and change in land cover under the urban area. A major challenge being faced while analyzing Synthetic Aperture Radar (SAR) based remote sensing data is that there is a lot of similarity between highly vegetated urban areas and oriented urban targets with that of actual vegetation. This similarity between some urban areas and vegetation leads to misclassification of the urban area into forest cover. The present work is a precursor study for the dual-frequency L and S-band NASA-ISRO Synthetic Aperture Radar (NISAR) mission and aims at minimizing the misclassification of such highly vegetated and oriented urban targets into vegetation class with the help of deep learning. In this study, three machine learning algorithms Random Forest (RF), K-Nearest Neighbour (KNN), and Support Vector Machine (SVM) have been implemented along with a deep learning model DeepLabv3+ for semantic segmentation of Polarimetric SAR (PolSAR) data. It is a general perception that a large dataset is required for the successful implementation of any deep learning model but in the field of SAR based remote sensing, a major issue is the unavailability of a large benchmark labeled dataset for the implementation of deep learning algorithms from scratch. In current work, it has been shown that a pre-trained deep learning model DeepLabv3+ outperforms the machine learning algorithms for land use and land cover (LULC) classification task even with a small dataset using transfer learning. The highest pixel accuracy of 87.78% and overall pixel accuracy of 85.65% have been achieved with DeepLabv3+ and Random Forest performs best among the machine learning algorithms with overall pixel accuracy of 77.91% while SVM and KNN trail with an overall accuracy of 77.01% and 76.47% respectively. The highest precision of 0.9228 is recorded for the urban class for semantic segmentation task with DeepLabv3+ while machine learning algorithms SVM and RF gave comparable results with a precision of 0.8977 and 0.8958 respectively.
| S-EPMC8319419 | biostudies-literature
Project description:Recent advances in deep learning for medical image segmentation demonstrate expert-level accuracy. However, application of these models in clinically realistic environments can result in poor generalization and decreased accuracy, mainly due to the domain shift across different hospitals, scanner vendors, imaging protocols, and patient populations etc. Common transfer learning and domain adaptation techniques are proposed to address this bottleneck. However, these solutions require data (and annotations) from the target domain to retrain the model, and is therefore restrictive in practice for widespread model deployment. Ideally, we wish to have a trained (locked) model that can work uniformly well across unseen domains without further training. In this paper, we propose a deep stacked transformation approach for domain generalization. Specifically, a series of n stacked transformations are applied to each image during network training. The underlying assumption is that the "expected" domain shift for a specific medical imaging modality could be simulated by applying extensive data augmentation on a single source domain, and consequently, a deep model trained on the augmented "big" data (BigAug) could generalize well on unseen domains. We exploit four surprisingly effective, but previously understudied, image-based characteristics for data augmentation to overcome the domain generalization problem. We train and evaluate the BigAug model (with n=9 transformations) on three different 3D segmentation tasks (prostate gland, left atrial, left ventricle) covering two medical imaging modalities (MRI and ultrasound) involving eight publicly available challenge datasets. The results show that when training on relatively small dataset (n = 10~32 volumes, depending on the size of the available datasets) from a single source domain: (i) BigAug models degrade an average of 11%(Dice score change) from source to unseen domain, substantially better than conventional augmentation (degrading 39%) and CycleGAN-based domain adaptation method (degrading 25%), (ii) BigAug is better than "shallower" stacked transforms (i.e. those with fewer transforms) on unseen domains and demonstrates modest improvement to conventional augmentation on the source domain, (iii) after training with BigAug on one source domain, performance on an unseen domain is similar to training a model from scratch on that domain when using the same number of training samples. When training on large datasets (n = 465 volumes) with BigAug, (iv) application to unseen domains reaches the performance of state-of-the-art fully supervised models that are trained and tested on their source domains. These findings establish a strong benchmark for the study of domain generalization in medical imaging, and can be generalized to the design of highly robust deep segmentation models for clinical deployment.
| S-EPMC7393676 | biostudies-literature
Project description:The rice seed setting rate (RSSR) is an important component in calculating rice yields and a key phenotype for its genetic analysis. Automatic calculations of RSSR through computer vision technology have great significance for rice yield predictions. The basic premise for calculating RSSR is having an accurate and high throughput identification of rice grains. In this study, we propose a method based on image segmentation and deep learning to automatically identify rice grains and calculate RSSR. By collecting information on the rice panicle, our proposed image automatic segmentation method can detect the full grain and empty grain, after which the RSSR can be calculated by our proposed rice seed setting rate optimization algorithm (RSSROA). Finally, the proposed method was used to predict the RSSR during which process, the average identification accuracy reached 99.43%. This method has therefore been proven as an effective, non-invasive method for high throughput identification and calculation of RSSR. It is also applicable to soybean yields, as well as wheat and other crops with similar characteristics.
| S-EPMC8712771 | biostudies-literature
Project description:Convolutional neural network (CNN) models obtain state of the art performance on image classification, localization, and segmentation tasks. Limitations in computer hardware, most notably memory size in deep learning accelerator cards, prevent relatively large images, such as those from medical and satellite imaging, from being processed as a whole in their original resolution. A fully convolutional topology, such as U-Net, is typically trained on down-sampled images and inferred on images of their original size and resolution, by simply dividing the larger image into smaller (typically overlapping) tiles, making predictions on these tiles, and stitching them back together as the prediction for the whole image. In this study, we show that this tiling technique combined with translationally-invariant nature of CNNs causes small, but relevant differences during inference that can be detrimental in the performance of the model. Here we quantify these variations in both medical (i.e., BraTS) and non-medical (i.e., satellite) images and show that training a 2D U-Net model on the whole image substantially improves the overall model performance. Finally, we compare 2D and 3D semantic segmentation models to show that providing CNN models with a wider context of the image in all three dimensions leads to more accurate and consistent predictions. Our results suggest that tiling the input to CNN models-while perhaps necessary to overcome the memory limitations in computer hardware-may lead to undesirable and unpredictable errors in the model's output that can only be adequately mitigated by increasing the input of the model to the largest possible tile size.
| S-EPMC7020775 | biostudies-literature
Project description:Histopathology tissue analysis is considered the gold standard in cancer diagnosis and prognosis. Whole-slide imaging (WSI), i.e., the scanning and digitization of entire histology slides, are now being adopted across the world in pathology labs. Trained histopathologists can provide an accurate diagnosis of biopsy specimens based on WSI data. Given the dimensionality of WSIs and the increase in the number of potential cancer cases, analyzing these images is a time-consuming process. Automated segmentation of tumorous tissue helps in elevating the precision, speed, and reproducibility of research. In the recent past, deep learning-based techniques have provided state-of-the-art results in a wide variety of image analysis tasks, including the analysis of digitized slides. However, deep learning-based solutions pose many technical challenges, including the large size of WSI data, heterogeneity in images, and complexity of features. In this study, we propose a generalized deep learning-based framework for histopathology tissue analysis to address these challenges. Our framework is, in essence, a sequence of individual techniques in the preprocessing-training-inference pipeline which, in conjunction, improve the efficiency and the generalizability of the analysis. The combination of techniques we have introduced includes an ensemble segmentation model, division of the WSI into smaller overlapping patches while addressing class imbalances, efficient techniques for inference, and an efficient, patch-based uncertainty estimation framework. Our ensemble consists of DenseNet-121, Inception-ResNet-V2, and DeeplabV3Plus, where all the networks were trained end to end for every task. We demonstrate the efficacy and improved generalizability of our framework by evaluating it on a variety of histopathology tasks including breast cancer metastases (CAMELYON), colon cancer (DigestPath), and liver cancer (PAIP). Our proposed framework has state-of-the-art performance across all these tasks and is ranked within the top 5 currently for the challenges based on these datasets. The entire framework along with the trained models and the related documentation are made freely available at GitHub and PyPi. Our framework is expected to aid histopathologists in accurate and efficient initial diagnosis. Moreover, the estimated uncertainty maps will help clinicians to make informed decisions and further treatment planning or analysis.
| S-EPMC8172839 | biostudies-literature