Dataset Information

Deep learning-enabled multi-organ segmentation in whole-body mouse scans.

ABSTRACT: Whole-body imaging of mice is a key source of information for research. Organ segmentation is a prerequisite for quantitative analysis but is a tedious and error-prone task if done manually. Here, we present a deep learning solution called AIMOS that automatically segments major organs (brain, lungs, heart, liver, kidneys, spleen, bladder, stomach, intestine) and the skeleton in less than a second, orders of magnitude faster than prior algorithms. AIMOS matches or exceeds the segmentation quality of state-of-the-art approaches and of human experts. We exemplify direct applicability for biomedical research for localizing cancer metastases. Furthermore, we show that expert annotations are subject to human error and bias. As a consequence, we show that at least two independently created annotations are needed to assess model performance. Importantly, AIMOS addresses the issue of human bias by identifying the regions where humans are most likely to disagree, and thereby localizes and quantifies this uncertainty for improved downstream analysis. In summary, AIMOS is a powerful open-source tool to increase scalability, reduce bias, and foster reproducibility in many areas of biomedical research.

SUBMITTER: Schoppe O

PROVIDER: S-EPMC7648799 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning-enabled multi-organ segmentation in whole-body mouse scans.

Schoppe Oliver O Pan Chenchen C Coronel Javier J Mai Hongcheng H Rong Zhouyi Z Todorov Mihail Ivilinov MI Müskes Annemarie A Navarro Fernando F Li Hongwei H Ertürk Ali A Menze Bjoern H BH

Nature communications 20201106 1

Whole-body imaging of mice is a key source of information for research. Organ segmentation is a prerequisite for quantitative analysis but is a tedious and error-prone task if done manually. Here, we present a deep learning solution called AIMOS that automatically segments major organs (brain, lungs, heart, liver, kidneys, spleen, bladder, stomach, intestine) and the skeleton in less than a second, orders of magnitude faster than prior algorithms. AIMOS matches or exceeds the segmentation qualit ...[more]

PMID: 33159057

Similar Datasets

Project description:Lung cancer is the leading cause of cancer related deaths worldwide. The development of orthotopic mouse models of lung cancer, which recapitulates the disease more realistically compared to the widely used subcutaneous tumor models, is expected to critically aid the development of novel therapies to battle lung cancer or related comorbidities such as cachexia. However, follow-up of tumor take, tumor growth and detection of therapeutic effects is difficult, time consuming and requires a vast number of animals in orthotopic models. Here, we describe a solution for the fully automatic segmentation and quantification of orthotopic lung tumor volume and mass in whole-body mouse computed tomography (CT) scans. The goal is to drastically enhance the efficiency of the research process by replacing time-consuming manual procedures with fast, automated ones. A deep learning algorithm was trained on 60 unique manually delineated lung tumors and evaluated by four-fold cross validation. Quantitative performance metrics demonstrated high accuracy and robustness of the deep learning algorithm for automated tumor volume analyses (mean dice similarity coefficient of 0.80), and superior processing time (69 times faster) compared to manual segmentation. Moreover, manual delineations of the tumor volume by three independent annotators was sensitive to bias in human interpretation while the algorithm was less vulnerable to bias. In addition, we showed that besides longitudinal quantification of tumor development, the deep learning algorithm can also be used in parallel with the previously published method for muscle mass quantification and to optimize the experimental design reducing the number of animals needed in preclinical studies. In conclusion, we implemented a method for fast and highly accurate tumor quantification with minimal operator involvement in data analysis. This deep learning algorithm provides a helpful tool for the noninvasive detection and analysis of tumor take, tumor growth and therapeutic effects in mouse orthotopic lung cancer models.

Project description:For image-guided small animal irradiations, the whole workflow of imaging, organ contouring, irradiation planning, and delivery is typically performed in a single session requiring continuous administration of anaesthetic agents. Automating contouring leads to a faster workflow, which limits exposure to anaesthesia and thereby, reducing its impact on experimental results and on animal wellbeing. Here, we trained the 2D and 3D U-Net architectures of no-new-Net (nnU-Net) for autocontouring of the thorax in mouse micro-CT images. We trained the models only on native CTs and evaluated their performance using an independent testing dataset (i.e., native CTs not included in the training and validation). Unlike previous studies, we also tested the model performance on an external dataset (i.e., contrast-enhanced CTs) to see how well they predict on CTs completely different from what they were trained on. We also assessed the interobserver variability using the generalized conformity index ([Formula: see text]) among three observers, providing a stronger human baseline for evaluating automated contours than previous studies. Lastly, we showed the benefit on the contouring time compared to manual contouring. The results show that 3D models of nnU-Net achieve superior segmentation accuracy and are more robust to unseen data than 2D models. For all target organs, the mean surface distance (MSD) and the Hausdorff distance (95p HD) of the best performing model for this task (nnU-Net 3d_fullres) are within 0.16 mm and 0.60 mm, respectively. These values are below the minimum required contouring accuracy of 1 mm for small animal irradiations, and improve significantly upon state-of-the-art 2D U-Net-based AIMOS method. Moreover, the conformity indices of the 3d_fullres model also compare favourably to the interobserver variability for all target organs, whereas the 2D models perform poorly in this regard. Importantly, the 3d_fullres model offers 98% reduction in contouring time.

Project description:Whole-body SPECT small animal imaging is used to study cancer, and plays an important role in the development of new drugs. Comparing and exploring whole-body datasets can be a difficult and time-consuming task due to the inherent heterogeneity of the data (high volume/throughput, multi-modality, postural and positioning variability). The goal of this study was to provide a method to align and compare side-by-side multiple whole-body skeleton SPECT datasets in a common reference, thus eliminating acquisition variability that exists between the subjects in cross-sectional and multi-modal studies. Six whole-body SPECT/CT datasets of BALB/c mice injected with bone targeting tracers (99m)Tc-methylene diphosphonate ((99m)Tc-MDP) and (99m)Tc-hydroxymethane diphosphonate ((99m)Tc-HDP) were used to evaluate the proposed method. An articulated version of the MOBY whole-body mouse atlas was used as a common reference. Its individual bones were registered one-by-one to the skeleton extracted from the acquired SPECT data following an anatomical hierarchical tree. Sequential registration was used while constraining the local degrees of freedom (DoFs) of each bone in accordance to the type of joint and its range of motion. The Articulated Planar Reformation (APR) algorithm was applied to the segmented data for side-by-side change visualization and comparison of data. To quantitatively evaluate the proposed algorithm, bone segmentations of extracted skeletons from the correspondent CT datasets were used. Euclidean point to surface distances between each dataset and the MOBY atlas were calculated. The obtained results indicate that after registration, the mean Euclidean distance decreased from 11.5±12.1 to 2.6±2.1 voxels. The proposed approach yielded satisfactory segmentation results with minimal user intervention. It proved to be robust for "incomplete" data (large chunks of skeleton missing) and for an intuitive exploration and comparison of multi-modal SPECT/CT cross-sectional mouse data.

Project description:PurposeTo improve the robustness of deep learning-based glioblastoma segmentation in a clinical setting with sparsified datasets.Materials and methodsIn this retrospective study, preoperative T1-weighted, T2-weighted, T2-weighted fluid-attenuated inversion recovery, and postcontrast T1-weighted MRI from 117 patients (median age, 64 years; interquartile range [IQR], 55-73 years; 76 men) included within the Multimodal Brain Tumor Image Segmentation (BraTS) dataset plus a clinical dataset (2012-2013) with similar imaging modalities of 634 patients (median age, 59 years; IQR, 49-69 years; 382 men) with glioblastoma from six hospitals were used. Expert tumor delineations on the postcontrast images were available, but for various clinical datasets, one or more sequences were missing. The convolutional neural network, DeepMedic, was trained on combinations of complete and incomplete data with and without site-specific data. Sparsified training was introduced, which randomly simulated missing sequences during training. The effects of sparsified training and center-specific training were tested using Wilcoxon signed rank tests for paired measurements.ResultsA model trained exclusively on BraTS data reached a median Dice score of 0.81 for segmentation on BraTS test data but only 0.49 on the clinical data. Sparsified training improved performance (adjusted P < .05), even when excluding test data with missing sequences, to median Dice score of 0.67. Inclusion of site-specific data during sparsified training led to higher model performance Dice scores greater than 0.8, on par with a model based on all complete and incomplete data. For the model using BraTS and clinical training data, inclusion of site-specific data or sparsified training was of no consequence.ConclusionAccurate and automatic segmentation of glioblastoma on clinical scans is feasible using a model based on large, heterogeneous, and partially incomplete datasets. Sparsified training may boost the performance of a smaller model based on public and site-specific data.Supplemental material is available for this article.Published under a CC BY 4.0 license.

Project description:ImportanceConventional segmentation of the retinal nerve fiber layer (RNFL) is prone to errors that may affect the accuracy of spectral-domain optical coherence tomography (SD-OCT) scans in detecting glaucomatous damage.ObjectiveTo develop a segmentation-free deep learning (DL) algorithm for assessment of glaucomatous damage using the entire circle B-scan image from SD-OCT.Design, setting, and participantsThis cross-sectional study at a single institution used data from SD-OCT images of eyes with glaucoma (perimetric and preperimetric) and normal eyes. The data set was randomly split at the patient level into a training (50%), validation (20%), and test data set (30%). Data were collected from March 2008 to April 2019, and analysis began April 2018.ExposuresA convolutional neural network was trained to discriminate glaucomatous from normal eyes using the SD-OCT circle B-scan without segmentation lines.Main outcomes and measuresThe ability to discriminate glaucoma from healthy eyes was evaluated by comparing the area under the receiver operating characteristic curve and sensitivity at 80% or 95% specificity for the DL algorithm's predicted probability of glaucoma vs conventional RNFL thickness parameters given by SD-OCT software. The performance was also assessed in preperimetric glaucoma, as well as by visual field severity using Hodapp-Parrish-Anderson criteria.ResultsA total of 20 806 SD-OCT images from 1154 eyes of 635 individuals (612 [53%] with glaucoma and 542 normal eyes [47%]) were included. The mean (SD) age at SD-OCT scan was 70.8 (10.4) years in individuals with glaucoma and 55.8 (14.1) years in controls. There were 187 women (53.3%) in the glaucoma group and 165 (59.8%) in the control group. Of 612 eyes with glaucoma, 432 (70.4%) had perimetric and 180 (29.6%) had preperimetric glaucoma. The DL algorithm had a significantly higher area under the receiver operating characteristic curve than global RNFL thickness (0.96 vs 0.87; difference = 0.08 [95% CI, 0.04-0.12]) and each RNFL thickness sector for discriminating between glaucoma and controls (all P < .001). At 95% specificity, the DL algorithm (81%; 95% CI, 64%-97%) was more sensitive than global RNFL thickness (67%; 95% CI, 58%-76%). The areas under the receiver operating characteristic curve were also significantly greater for the DL algorithm compared with RNFL thickness at each stage of disease, especially preperimetric and mild perimetric glaucoma.Conclusions and relevanceA segmentation-free DL algorithm performed better than conventional RNFL thickness parameters for diagnosing glaucomatous damage on OCT scans, especially in early disease. Future studies should investigate how such an approach contributes to diagnostic decisions when combined with other relevant clinical information, such as risk factors and perimetry results.

Dataset Information

Deep learning-enabled multi-organ segmentation in whole-body mouse scans.

Publications

Deep learning-enabled multi-organ segmentation in whole-body mouse scans.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets