Dataset Information

An automated artifact detection and rejection system for body surface gastric mapping.

ABSTRACT:

Background

Body surface gastric mapping (BSGM) is a new clinical tool for gastric motility diagnostics, providing high-resolution data on gastric myoelectrical activity. Artifact contamination was a key challenge to reliable test interpretation in traditional electrogastrography. This study aimed to introduce and validate an automated artifact detection and rejection system for clinical BSGM applications.

Methods

Ten patients with chronic gastric symptoms generated a variety of artifacts according to a standardized protocol (176 recordings) using a commercial BSGM system (Alimetry, New Zealand). An automated artifact detection and rejection algorithm was developed, and its performance was compared with a reference standard comprising consensus labeling by 3 analysis experts, followed by comparison with 6 clinicians (3 untrained and 3 trained in artifact detection). Inter-rater reliability was calculated using Fleiss' kappa.

Key results

Inter-rater reliability was 0.84 (95% CI:0.77-0.90) among experts, 0.76 (95% CI:0.68-0.83) among untrained clinicians, and 0.71 (95% CI:0.62-0.79) among trained clinicians. The sensitivity and specificity of the algorithm against experts was 96% (95% CI:91%-100%) and 95% (95% CI:90%-99%), respectively, vs 77% (95% CI:68%-85%) and 99% (95% CI:96%-100%) against untrained clinicians, and 97% (95% CI:92%-100%) and 88% (95% CI:82%-94%) against trained clinicians.

Conclusions & inferences

An automated artifact detection and rejection algorithm was developed showing >95% sensitivity and specificity vs expert markers. This algorithm overcomes an important challenge in the clinical translation of BSGM and is now being routinely implemented in patient test interpretations.

SUBMITTER: Calder S

PROVIDER: S-EPMC9786272 | biostudies-literature | 2022 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An automated artifact detection and rejection system for body surface gastric mapping.

Calder Stefan S Schamberg Gabriel G Varghese Chris C Waite Stephen S Sebaratnam Gabrielle G Woodhead Jonathan S T JST Du Peng P Andrews Christopher N CN O'Grady Greg G Gharibans Armen A AA

Neurogastroenterology and motility 20220614 11

<h4>Background</h4>Body surface gastric mapping (BSGM) is a new clinical tool for gastric motility diagnostics, providing high-resolution data on gastric myoelectrical activity. Artifact contamination was a key challenge to reliable test interpretation in traditional electrogastrography. This study aimed to introduce and validate an automated artifact detection and rejection system for clinical BSGM applications.<h4>Methods</h4>Ten patients with chronic gastric symptoms generated a variety of ar ...[more]

PMID: 35699347

Similar Datasets

Project description:IntroductionDelayed gastric emptying (DGE) is frequent after pancreaticoduodenectomy (PD). Although often associated with postoperative pancreatic fistula, the precise pathogenesis in patients with no underlying complications remains unclear. There is evidence to suggest that, after surgery, aberrant electrical pathways are formed in the stomach which could contribute to the development of DGE.Gastric Alimetry is a novel technology which measures the electrical activity of the stomach non-invasively using an array of electrodes applied to the skin of the abdomen. This technique, termed body surface gastric mapping (BSGM), has been validated in normal controls and in patients with functional dyspepsia syndromes. This study will investigate the efficacy and feasibility of using BSGM to assess gastric motility in patients who undergo PD.Methods and analysisThis prospective cohort study will be conducted at a single large volume hepatobiliary unit in the UK. 50 patients who are planned to undergo PD will be included. BSGM measurement will be performed at four timepoints viz: preoperatively, day 4 postoperatively, at discharge and 6 months postoperatively. Key parameters of BSGM measurement, including wave amplitude, frequency and directional vector, will be measured at each timepoint and compared between different patient subgroups. Symptoms will be self-reported by patients during the recording using an iPad application designed for this purpose. Quality of life and patient experience will be assessed using standardised questionnaires at the end of the follow-up period.Ethics and disseminationThe protocol has been approved by the research ethics committees of Newcastle University and the Health Research Authority (HRA) of the UK (ethical approval IRAS ID 305302). Findings will be published in peer-reviewed journals and presented at national and international conferences.Trial registration numberThis study will automatically be registered with the ISRCTN registry by the HRA as part of the ethics approval process.

Project description:ObjectivesTo automatically detect MRI artifacts on dynamic contrast-enhanced (DCE) maximum intensity projections (MIPs) of the breast using deep learning.MethodsWomen who underwent clinically indicated breast MRI between October 2015 and December 2019 were included in this IRB-approved retrospective study. We employed two convolutional neural network architectures (ResNet and DenseNet) to detect the presence of artifacts on DCE MIPs of the left and right breasts. Networks were trained on images acquired up to and including the year 2018 using a 5-fold cross-validation (CV). Ensemble classifiers were built with the resulting CV models and applied to an independent holdout test dataset, which was formed by images acquired in 2019.ResultsOur study sample contained 2265 examinations from 1794 patients (median age at first acquisition: 50 years [IQR: 17 years]), corresponding to 1827 examinations of 1378 individuals in the training dataset and 438 examinations of 416 individuals in the holdout test dataset with a prevalence of image-level artifacts of 53% (1951/3654 images) and 43% (381/876 images), respectively. On the holdout test dataset, the ResNet and DenseNet ensembles demonstrated an area under the ROC curve of 0.92 and 0.94, respectively.ConclusionNeural networks are able to reliably detect artifacts that may impede the diagnostic assessment of MIPs derived from DCE subtraction series in breast MRI. Future studies need to further explore the potential of such neural networks to complement quality assurance and improve the application of DCE MIPs in a clinical setting, such as abbreviated protocols.Key points• Deep learning classifiers are able to reliably detect MRI artifacts in dynamic contrast-enhanced protocol-derived maximum intensity projections of the breast. • Automated quality assurance of maximum intensity projections of the breast may be of special relevance for abbreviated breast MRI, e.g., in high-throughput settings, such as cancer screening programs.

Dataset Information

An automated artifact detection and rejection system for body surface gastric mapping.

Background

Methods

Key results

Conclusions & inferences

Publications

An automated artifact detection and rejection system for body surface gastric mapping.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets