scholarly journals Artificial intelligence for automatic cerebral ventricle segmentation and volume calculation: a clinical tool for the evaluation of pediatric hydrocephalus

2020 ◽  
pp. 1-8
Author(s):  
Jennifer L. Quon ◽  
Michelle Han ◽  
Lily H. Kim ◽  
Mary Ellen Koran ◽  
Leo C. Chen ◽  
...  
Keyword(s):  
Clinical Decision Making ◽  
Cerebral Ventricle ◽  
Dice Similarity Coefficient ◽  
Study Cohort ◽  
Mr Images ◽  
Data Set ◽  
Ground Truth Data ◽  
Volume Calculation ◽  
Pediatric Hydrocephalus ◽  
Ventricle Segmentation

OBJECTIVEImaging evaluation of the cerebral ventricles is important for clinical decision-making in pediatric hydrocephalus. Although quantitative measurements of ventricular size, over time, can facilitate objective comparison, automated tools for calculating ventricular volume are not structured for clinical use. The authors aimed to develop a fully automated deep learning (DL) model for pediatric cerebral ventricle segmentation and volume calculation for widespread clinical implementation across multiple hospitals.METHODSThe study cohort consisted of 200 children with obstructive hydrocephalus from four pediatric hospitals, along with 199 controls. Manual ventricle segmentation and volume calculation values served as “ground truth” data. An encoder-decoder convolutional neural network architecture, in which T2-weighted MR images were used as input, automatically delineated the ventricles and output volumetric measurements. On a held-out test set, segmentation accuracy was assessed using the Dice similarity coefficient (0 to 1) and volume calculation was assessed using linear regression. Model generalizability was evaluated on an external MRI data set from a fifth hospital. The DL model performance was compared against FreeSurfer research segmentation software.RESULTSModel segmentation performed with an overall Dice score of 0.901 (0.946 in hydrocephalus, 0.856 in controls). The model generalized to external MR images from a fifth pediatric hospital with a Dice score of 0.926. The model was more accurate than FreeSurfer, with faster operating times (1.48 seconds per scan).CONCLUSIONSThe authors present a DL model for automatic ventricle segmentation and volume calculation that is more accurate and rapid than currently available methods. With near-immediate volumetric output and reliable performance across institutional scanner types, this model can be adapted to the real-time clinical evaluation of hydrocephalus and improve clinician workflow.

scholarly journals Assignment Flow for Order-Constrained OCT Segmentation

2021 ◽  
Author(s):  
Dmitrij Sitenko ◽  
Bastian Boll ◽  
Christoph Schnörr
Keyword(s):  
Geometric Approach ◽  
Ground Truth ◽  
Retinal Cell ◽  
Dice Similarity Coefficient ◽  
Retinal Layer ◽  
Healthy Human ◽  
Data Set ◽  
Ground Truth Data ◽  
Global Shape ◽  
Layer Segmentation

AbstractAt the present time optical coherence tomography (OCT) is among the most commonly used non-invasive imaging methods for the acquisition of large volumetric scans of human retinal tissues and vasculature. The substantial increase of accessible highly resolved 3D samples at the optic nerve head and the macula is directly linked to medical advancements in early detection of eye diseases. To resolve decisive information from extracted OCT volumes and to make it applicable for further diagnostic analysis, the exact measurement of retinal layer thicknesses serves as an essential task be done for each patient separately. However, manual examination of OCT scans is a demanding and time consuming task, which is typically made difficult by the presence of tissue-dependent speckle noise. Therefore, the elaboration of automated segmentation models has become an important task in the field of medical image processing. We propose a novel, purely data driven geometric approach to order-constrained 3D OCT retinal cell layer segmentation which takes as input data in any metric space and can be implemented using only simple, highly parallelizable operations. As opposed to many established retinal layer segmentation methods, we use only locally extracted features as input and do not employ any global shape prior. The physiological order of retinal cell layers and membranes is achieved through the introduction of a smoothed energy term. This is combined with additional regularization of local smoothness to yield highly accurate 3D segmentations. The approach thereby systematically avoid bias pertaining to global shape and is hence suited for the detection of anatomical changes of retinal tissue structure. To demonstrate its robustness, we compare two different choices of features on a data set of manually annotated 3D OCT volumes of healthy human retina. The quality of computed segmentations is compared to the state of the art in automatic retinal layer segmention as well as to manually annotated ground truth data in terms of mean absolute error and Dice similarity coefficient. Visualizations of segmented volumes are also provided.

Temporal trends in surgical procedures for pediatric hydrocephalus: an analysis of the Hydrocephalus Clinical Research Network Core Data Project

2020 ◽  
pp. 1-8
Author(s):  
Mandeep S. Tamber ◽  
John R. W. Kestle ◽  
Ron W. Reeder ◽  
Richard Holubkov ◽  
Jessica Alvey ◽  
...  
Keyword(s):  
Clinical Research ◽  
Temporal Trends ◽  
Patient Characteristics ◽  
Research Network ◽  
Third Ventriculostomy ◽  
Study Cohort ◽  
Core Data ◽  
Pediatric Hydrocephalus ◽  
Short Period ◽  
New Procedures

OBJECTIVEAnalysis of temporal trends in patient populations and procedure types may provide important information regarding the evolution of hydrocephalus treatment. The purpose of this study was to use the Hydrocephalus Clinical Research Network’s Core Data Project to identify meaningful trends in patient characteristics and the surgical management of pediatric hydrocephalus over a 9-year period.METHODSThe Core Data Project prospectively collected patient and procedural data on the study cohort from 9 centers between 2008 and 2016. Logistic and Poisson regression were used to test for significant temporal trends in patient characteristics and new and revision hydrocephalus procedures.RESULTSThe authors analyzed 10,149 procedures in 5541 patients. New procedures for hydrocephalus (shunt or endoscopic third ventriculostomy [ETV]) decreased by 1.5%/year (95% CI −3.1%, +0.1%). During the study period, new shunt insertions decreased by 6.5%/year (95% CI −8.3%, −4.6%), whereas new ETV procedures increased by 12.5%/year (95% CI 9.3%, 15.7%). Revision procedures for hydrocephalus (shunt or ETV) decreased by 4.2%/year (95% CI −5.2%, −3.1%), driven largely by a decrease of 5.7%/year in shunt revisions (95% CI −6.8%, −4.6%). Concomitant with the observed increase in new ETV procedures was an increase in ETV revisions (13.4%/year, 95% CI 9.6%, 17.2%). Because revisions decreased at a faster rate than new procedures, the Revision Quotient (ratio of revisions to new procedures) for the Network decreased significantly over the study period (p = 0.0363). No temporal change was observed in the age or etiology characteristics of the cohort, although the proportion of patients with one or more complex chronic conditions significantly increased over time (p = 0.0007).CONCLUSIONSOver a relatively short period, important changes in hydrocephalus care have been observed. A significant temporal decrease in revision procedures amid the backdrop of a more modest change in new procedures appears to be the most notable finding and may be indicative of an improvement in the quality of surgical care for pediatric hydrocephalus. Further studies will be directed at elucidation of the possible drivers of the observed trends.

scholarly journals IMG-22. A DEEP LEARNING MODEL FOR AUTOMATIC POSTERIOR FOSSA PEDIATRIC BRAIN TUMOR SEGMENTATION: A MULTI-INSTITUTIONAL STUDY

2020 ◽  
Vol 22 (Supplement_3) ◽  
pp. iii359-iii359
Author(s):  
Lydia Tam ◽  
Edward Lee ◽  
Michelle Han ◽  
Jason Wright ◽  
Leo Chen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Posterior Fossa ◽  
Ground Truth ◽  
Learning Model ◽  
Tumor Segmentation ◽  
Dice Similarity Coefficient ◽  
Study Cohort ◽  
Navigation Systems ◽  
Tumor Types ◽  
Deep Learning Model

Abstract BACKGROUND Brain tumors are the most common solid malignancies in childhood, many of which develop in the posterior fossa (PF). Manual tumor measurements are frequently required to optimize registration into surgical navigation systems or for surveillance of nonresectable tumors after therapy. With recent advances in artificial intelligence (AI), automated MRI-based tumor segmentation is now feasible without requiring manual measurements. Our goal was to create a deep learning model for automated PF tumor segmentation that can register into navigation systems and provide volume output. METHODS 720 pre-surgical MRI scans from five pediatric centers were divided into training, validation, and testing datasets. The study cohort comprised of four PF tumor types: medulloblastoma, diffuse midline glioma, ependymoma, and brainstem or cerebellar pilocytic astrocytoma. Manual segmentation of the tumors by an attending neuroradiologist served as “ground truth” labels for model training and evaluation. We used 2D Unet, an encoder-decoder convolutional neural network architecture, with a pre-trained ResNet50 encoder. We assessed ventricle segmentation accuracy on a held-out test set using Dice similarity coefficient (0–1) and compared ventricular volume calculation between manual and model-derived segmentations using linear regression. RESULTS Compared to the ground truth expert human segmentation, overall Dice score for model performance accuracy was 0.83 for automatic delineation of the 4 tumor types. CONCLUSIONS In this multi-institutional study, we present a deep learning algorithm that automatically delineates PF tumors and outputs volumetric information. Our results demonstrate applied AI that is clinically applicable, potentially augmenting radiologists, neuro-oncologists, and neurosurgeons for tumor evaluation, surveillance, and surgical planning.

Abstract WP406: Training and Validation of Deepmedic Machine Learning Tool for Automated Hematoma Segmentation and Volume Analysis on CT Using Multicenter Data

Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Sean Nurmsoo ◽  
Alessandro Guida ◽  
Alex Wong ◽  
Richard I Aviv ◽  
Andrew Demchuk ◽  
...  
Keyword(s):  
Machine Learning ◽  
Validation Cohort ◽  
Learning Algorithm ◽  
Intraclass Correlation ◽  
Ct Scans ◽  
Dice Similarity Coefficient ◽  
Machine Learning Algorithm ◽  
Manual Segmentation ◽  
Training Cohort ◽  
Volume Calculation

Introduction: We sought to train and validate an automated machine learning algorithm for ICH segmentation and volume calculation using multicenter data. Methods: An open-source 3D deep machine learning algorithm “DeepMedic” was trained using manually segmented ICH from 208 CT scans (129 patients) from the multicenter PREDICT study. The algorithm was then validated with 125 manually segmented CT scans (48 patients) from the SPOTLIGHT study. Manual segmentation was performed with Quantomo semi-automated software. ABC/2 was measured for all studies by two neuroradiologists. Accuracy of DeepMedic segmentation was assessed using the Dice similarity coefficient. Analysis was stratified by presence of IVH. Intraclass correlation (ICC) with 95% confidence intervals (CI) assessed agreement between manual vs. DeepMedic segmentation volume; and manual segmentation and ABC/2 volume. Bland-Altman charts were analyzed for ABC/2 and DeepMedic vs. manual segmentation volumes. Results: DeepMedic demonstrated high segmentation accuracy in the training cohort (median Dice 0.96; IQR 0.95 - 0.97) and in the validation cohort (median Dice 0.91; IQR 0.86 - 0.94). Dice coefficients were not significantly different between patients with IVH in the training cohort; however was significantly worse in the validation cohort in patients with IVH (Wilcoxon p<0.001). Agreement was significantly better between DeepMedic and manual segmentation (PREDICT: ICC 0.99 [95%CI 0.99 -1.00]; SPOTLIGHT: ICC 0.98 [95%CI 0.97 - 0.99]) than between ABC/2 and manual segmentation (PREDICT: ICC 0.92 [95%CI 0.89 - 0.95]; SPOTLIGHT: ICC 0.95 [95%CI 0.93-0.97]). Improved accuracy of DeepMedic was demonstrated in Bland-Altman charts (Fig 1). Conclusion: ICH machine learning segmentation with DeepMedic is feasible and accurate; and demonstrates greater agreement with manual segmentation compared to ABC/2 volumes. Accuracy of the machine learning algorithm however is limited in patients with IVH.

A Comparison of GFR Estimation Formulae in Pediatric Oncology

2018 ◽  
Vol 230 (03) ◽  
pp. 142-150
Author(s):  
Tobias Rechenauer ◽  
Jakob Zierk ◽  
Daniel Gräfe ◽  
Wolfgang Rascher ◽  
Manfred Rauh ◽  
...  
Keyword(s):  
Cystatin C ◽  
Clinical Decision Making ◽  
Estimating Equations ◽  
Clinical Decision ◽  
Chemotherapeutic Agents ◽  
Laboratory Method ◽  
Background Information ◽  
Data Set ◽  
Therapeutic Consequences ◽  
Gfr Estimation

Abstract Background Application of potentially nephrotoxic chemotherapy requires continuous monitoring of renal function for toxicity and dosing. Novel pediatric glomerular filtration rate (GFR) estimating equations including cystatin C have been proposed to enhance the reliability of GFR calculation. Materials and methods We examined a pediatric oncologic data set with a total of 363 GFR measurements. An analysis of distribution characteristics and comparison of medians was performed to compare creatinine and cystatin C-based GFR estimating formulae. Furthermore, we investigated the clinical impact of different equations in regard to therapeutic consequences. Results Significant differences in estimated GFR values were calculated depending on the applied formula (range of median GFR from 94.8 to 180.9 mL/min per 1.73 m2) which may result in different therapeutic consequences for the use of potentially nephrotoxic chemotherapeutic agents. Significant correlation for all examined formulae was identified, however there were large fluctuations among the correlation coefficients ranging from 0.254 to 1.0. Conclusion This study compares proposed pediatric GFR estimating equations in a clinical setting. It underlines the current limitations and difficulties of GFR estimation including potential dosing errors. Cystitis C-based equations can be used as alternatives to creatinine-based estimations when the appropriate laboratory method has been applied. A comparative calculator for pediatric GFR estimating equations along with background information is provided at http://gfr.pedz.de and may support clinical decision-making.

scholarly journals Application of Multi-Scale Fusion Attention U-Net to Segment the Thyroid Gland on CT Localization Images for Radiotherapy

2021 ◽  
Author(s):  
Xiaobo Wen ◽  
Biao Zhao ◽  
Meifang Yuan ◽  
Jinzhi Li ◽  
Mengzhen Sun ◽  
...  
Keyword(s):  
Thyroid Gland ◽  
Clinical Work ◽  
Similarity Coefficient ◽  
Dice Similarity Coefficient ◽  
Training Set ◽  
Data Set ◽  
Test Set ◽  
Noise Interference ◽  
Multi Scale ◽  
Validation Set

Abstract Objectives: To explore the performance of Multi-scale Fusion Attention U-net (MSFA-U-net) in thyroid gland segmentation on CT localization images for radiotherapy. Methods: CT localization images for radiotherapy of 80 patients with breast cancer or head and neck tumors were selected; label images were manually delineated by experienced radiologists. The data set was randomly divided into the training set (n=60), the validation set (n=10), and the test set (n=10). Data expansion was performed in the training set, and the performance of the MSFA-U-net model was evaluated using the evaluation indicators Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), positive predictive value (PPV), sensitivity (SE), and Hausdorff distance (HD). Results: With the MSFA-U-net model, the DSC, JSC, PPV, SE, and HD indexes of the segmented thyroid gland in the test set were 0.8967±0.0935, 0.8219±0.1115, 0.9065±0.0940, 0.8979±0.1104, and 2.3922±0.5423, respectively. Compared with U-net, HR-net, and Attention U-net, MSFA-U-net showed that DSC increased by 0.052, 0.0376, and 0.0346 respectively; JSC increased by 0.0569, 0.0805, and 0.0433, respectively; SE increased by 0.0361, 0.1091, and 0.0831, respectively; and HD increased by −0.208, −0.1952, and −0.0548, respectively. The test set image results showed that the thyroid edges segmented by the MSFA-U-net model were closer to the standard thyroid delineated by the experts, in comparison with those segmented by the other three models. Moreover, the edges were smoother, over-anti-noise interference was stronger, and oversegmentation and undersegmentation were reduced. Conclusion: The MSFA-U-net model can meet basic clinical requirements and improve the efficiency of physicians' clinical work.

scholarly journals Homelessness and health needs in Wales

2019 ◽  
Vol 4 (3) ◽  
Author(s):  
Jiao Song ◽  
Charlotte Grey ◽  
Louise Woodfine ◽  
Alisha Davies
Keyword(s):  
Propensity Score ◽  
Substance Misuse ◽  
National Level ◽  
Health Needs ◽  
Mental Wellbeing ◽  
Study Cohort ◽  
Homeless Individual ◽  
Data Set ◽  
Routinely Collected Health Data ◽  
And Control

Background Public Health Wales developed its long-term strategy with the purpose of ‘Working to Achieve a Healthier Future for Wales’. This study is motivated by one of the strategic priorities, ‘Influencing the wider determinants of health’ with an emphasis on homelessness prevention. Main AimTo understand health needs of homeless health service users from routinely collected health data in Wales. To quantify the corresponding differences from general population. MethodsScoping work has completed collaborating with academic researchers, third sectors, clinical professionals, Office for National Statistics, and housing stats of Welsh Government. To construct study cohort, we will perform linkage exercise among Annual District Death Extract, Emergency Department Data Set, Outpatient Dataset for Wales, Patient Episode Database for Wales, Substance Misuse Data Set and Welsh Longitudinal General Practice dataset (from 2007 to 2018) stored in Secure Anonymised Information Linkage (SAIL) Databank. Study cohort includes all patients with an indication (i.e. clinical codes) of homelessness in their registration information and/or health records. We propose to adapt propensity score matching to construct matched case and control groups. This method will assign each homeless individual to individual without homeless flag with same or similar propensity score. We will then proceed to test for the significance of the homelessness and each health and wellbeing indicators (i.e. physical health, mental wellbeing and substance misuse) in the presence of confounders, and estimate the effects of homelessness on these indicators. ResultsThis study will demonstrate how linked data provide a more comprehensive review of the health needs of a vulnerable population, the homeless groups in Wales, and be able to explore changes over time. ConclusionThe relationship between homelessness and health issues is bi-directional. Findings from this study will have implications for health, housing, social, and homelessness policy at both local and national level; as well as contributing to the ability to providing tailored health services to targeted homeless populations groups.

scholarly journals Segmentation Method for Magnetic Resonance-Guided High-Intensity Focused Ultrasound Therapy Planning

2017 ◽  
Vol 2017 ◽  
pp. 1-7 ◽  
Author(s):  
A. Vargas-Olivares ◽  
O. Navarro-Hinojosa ◽  
M. Maqueo-Vicencio ◽  
L. Curiel ◽  
M. Alencastre-Miranda ◽  
...  
Keyword(s):  
Magnetic Resonance ◽  
High Intensity ◽  
Focused Ultrasound ◽  
High Intensity Focused Ultrasound ◽  
Segmentation Algorithm ◽  
Focal Region ◽  
Therapy Planning ◽  
Mr Images ◽  
Monitoring Method ◽  
Data Set

High-intensity focused ultrasound (HIFU) is a minimally invasive therapy modality in which ultrasound beams are concentrated at a focal region, producing a rise of temperature and selective ablation within the focal volume and leaving surrounding tissues intact. HIFU has been proposed for the safe ablation of both malignant and benign tissues and as an agent for drug delivery. Magnetic resonance imaging (MRI) has been proposed as guidance and monitoring method for the therapy. The identification of regions of interest is a crucial procedure in HIFU therapy planning. This procedure is performed in the MR images. The purpose of the present research work is to implement a time-efficient and functional segmentation scheme, based on the watershed segmentation algorithm, for the MR images used for the HIFU therapy planning. The achievement of a segmentation process with functional results is feasible, but preliminary image processing steps are required in order to define the markers for the segmentation algorithm. Moreover, the segmentation scheme is applied in parallel to an MR image data set through the use of a thread pool, achieving a near real-time execution and making a contribution to solve the time-consuming problem of the HIFU therapy planning.

Chemical Proportionality within Molecular Networks

2021 ◽  
Author(s):  
Daniel Petras ◽  
Andrés Mauricio Caraballo-Rodríguez ◽  
Alan K. Jarmusch ◽  
Carlos Molina-Santiago ◽  
Julia M. Gauglitz ◽  
...  
Keyword(s):  
Natural Products ◽  
Ground Truth ◽  
Mass Spectrometry Data ◽  
Molecular Networks ◽  
Data Series ◽  
Sequential Data ◽  
Chemical Transformations ◽  
Data Set ◽  
Molecular Networking ◽  
Ground Truth Data

Molecular networking of non-targeted tandem mass spectrometry data connects structurally related molecules based on similar fragmentation spectra. Here we report the Chemical Proportionality contextualization of molecular networks. ChemProp scores the changes of abundance between two connected nodes over sequential data series which can be displayed as a direction within the network to prioritize potential biological and chemical transformations or proportional changes of related compounds. We tested the ChemProp workflow on a ground truth data set of defined mixture and highlighted the utility of the tool to prioritize specific molecules within biological samples, including bacterial transformations of bile acids, human drug metabolism and bacterial natural products biosynthesis. The ChemProp workflow is freely available through the Global Natural Products Social Molecular Networking environment.<br><b> </b>

Sign in / Sign up

Export Citation Format

Share Document