Browse
Submit Data
Databases
API
Help

Dataset Information

33 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Diagnostic Performance of a Convolutional Neural Network for Diminutive Colorectal Polyp Recognition

ABSTRACT: Interventions: None Primary outcome(s): The primary outcome of the study is the accuracy of the CAD-CNN system for predicting histology of diminutive colorectal polyps (1-5mm) compared with the accuracy of the prediction of the endoscopist. Both the CAD-CNN system and the endoscopist will use NBI for their predictions. Accuracy is defined as the percentage of correctly predicted optical diagnoses of the CAD-CNN system and/or endoscopist compared to the gold standard pathology. For the calculation of the accuracy, adenomas and SSLs will be dichotomised as neoplastic polyps, while HPs and other non-neoplastic histology are considered non-neoplastic. Study Design: N/A: single arm study, Open (masking not used), N/A , unknown, Other

DISEASE(S): Colorectal Cancer,Colorectal Polyps

PROVIDER: 2443187 | ecrin-mdr-crc |

REPOSITORIES: ECRIN MDR

ACCESS DATA

Json Xml

Similar Datasets

Prospective evaluation of a new artificial intelligence system for the classification of colonic polyps.

Project description:Interventions: Group 1: colonoscopy with AI System Primary outcome(s): The rate of correctly classified polyps detected by the AI system (accuracy). The polyp classification is documented during the colonoscopy using the case report form(CRF). Later the result is compared with histology(gold standard). Study Design: Allocation: N/A: single arm study; Masking: Open (masking not used); Control: uncontrolled; Assignment: single; Study design purpose: prevention

| 2733414 | ecrin-mdr-crc

Evaluation of CAD-EYE/SCALE-EYE for Detection, Classification, and Measurement of Colorectal Polyps: a Prospective Study

Project description:The investigators hypothesize that the clinical implementation of an AI system is an optimal tool to monitor, audit and improve the detection and classification of polyps during colonoscopy. The purpose of this prospective clinical cohort study is to evaluate the performance of the SCALE-EYE virtual scale for measuring polyp size when used during live colonoscopies. The investigators also wish to evaluate CAD-eye for detection and classification of polyp histology. It is hypothesized that CAD-eye and SCALE-EYE can function in real-time practice with high accuracy.

| 2404446 | ecrin-mdr-crc

Real-Time Characterizations of Diminutive Colorectal Polyps Using Narrow Band Imaging

Project description:Colorectal cancer is the second leading cause of cancer related death in the United States. Colonoscopy is the most commonly performed screening procedure and diminutive polyps (<5mm) are the most commonly found polyps during colonoscopy. Although these polyps have a very low risk of harboring malignancy, they are routinely removed to determine surveillance intervals. Narrow Band Imaging is equipped on widely available colonoscopes and in expert hands can allow accurate real-time optical histologic diagnosis of colorectal polyps. If this practice can be applied widely, there is significant potential for cost savings. This has led to a ‘characterize, resect and discard’ strategy where polyps determined to be hyperplastic (benign with no neoplastic potential) can be left in place and those determined to be adenomatous (have neoplastic potential) can be resected and discarded. It is unclear if endoscopists without prior expertise or training in Narrow Band Imaging can achieve adequate diagnostic accuracy to put ‘characterize, resect and discard’ into wide practice.

| 2189853 | ecrin-mdr-crc

Interest of Artificial Intelligence in Cancer Screening Colonoscopy

Project description:Artificial Intelligence (AI) to predict the histology of polyps per colonoscopy, offers a promising solution to reduce variation in colonoscopy performance. This new and innovative non-invasive technology will improve the quality of screening colonoscopies, and reduce the costs of colorectal cancer screening. The aim of the study is to performed a cross-sectional, multi-center study evaluating the diagnostic performance of the CAD EYE automatic characterization system for the histology of colonic polyps in colorectal cancer screening colonoscopy.

| 2380194 | ecrin-mdr-crc

CAD EYE Detection of Remaining Lesions After EMR

Project description:In the last decade, many innovative systems have been developed to support and improve the diagnosis accuracy during endoscopic studies. CAD-Eye (Fujifilm, Tokyo, Japan) is a computer-assisted diagnostic (CADx) system that uses artificial intelligence for the detection and characterization of polyps during colonoscopy. However, the accuracy of CAD-Eye in the recognition of remaining lesions after endoscopic mucosal resection (EMR) has not been broadly evaluated. Finally, based on the importance of complete resection of the colonic mucosal lesions, namely suspicious high-grade dysplasia or early invasive cancer, the investigators aimed to assess the accuracy of CAD-Eye in the detection of remaining lesions after the procedure.

| 2748485 | ecrin-mdr-crc

MicroRNA signatures of colonic adenomas according to histology

Project description:Adenomatous polyps adjacent to colorectal cancer (CRC) were found to exhibit two distinct microRNAs (miRs) patterns from normal mucosa to low- and separately, to high-grade dysplasia; presence in screen-detected adenoma of non-cancer patients is unknown. Global miR expression was performed on biopsies obtained from 109 healthy patients undergoing screening/surveillance colonoscopy. Included were normal mucosa (NM); hyperplastic polyp (HP); tubular adenoma (TA), tubulovillous adenoma, with or without, high-grade dysplasia (TVHG) and serrated-polyps; sessile serrated adenoma (SSA) and traditional serrated adenoma (TSA). Logistic regression was used to model miRs predictive of histology and CRC risk. We identified 99 miRs that differed across five histologic groups (FDR=0.05) and that accurately separated on histology (Concordance Index (CI)=0.96). In HPNM, miRs-145, -143, -107a, -23b, and -24 were upregulated whereas miRs-663, -1268, -320b, -1275, and -671 where overexpressed in TVHGs (FDR P<0 .05). The expression of miR-145 and -30a showed high accuracy to separate low from high-risk polyps independent of serrated status (CI= 97.1%; AUC 93.4%). For TSAs, miR-125b and -199a were uniquely downregulated relative to HPNMs and miR-335 discriminated between non-serrated and serrated histology. Histologically advanced polyps from non-cancer patients share miR alterations with those reported for CRC and high-grade adenoma adjacent to tumor including downregulation of immune regulatory miRs-125 and -199a in TSAs; polyp that frequently present with in situ carcinoma. These data extend evidence that miR patterns of high-risk adenoma are detectable in subset of screen-detected adenoma for which measurement may be useful in in adenoma risk stratification.

2015-09-29 | GSE73487 | GEO

Artificial Intelligence for Diminutive Polyp Characterization

Project description:Artificial intelligence is a promising tool that may have a role in characterizing colon epithelial lesions (CADx), helping to get a reliable optical diagnosis regardless of the endoscopist experience. Performances of the different CADx systems are variable but it seems that, in most cases, high accuracy and sensitivities are achieved. However, these CADx systems have been developed and validated using still pictures or videos, and a real-world accurate test is lacking. No clinical trials have tested this technology in clinical practice and, therefore, performance in real colonoscopies, practical problems, applicability, and cost are unknown.

| 2731946 | ecrin-mdr-crc

RNA sequencing human monocytes

Project description:Aim: To improve risk stratification in patients with stable coronary artery disease (CAD), we aimed to identify genes in monocytes predictive of new ischemic events in patients with CAD and determine to what extent expression of these transcripts resembles expression in acute myocardial infarction (AMI). Results: COX10 and ZNF484 distinguished between AMI and the whole group of stable CAD patients with an accuracy of 90%. COX10 and ZNF484 together with MT-COI and WNK1 distinguished AMI patients from stable CAD patients with and without a new event with a sensitivity of 89% and a specificity of 98%. MT-COI and COX10 increased the accuracy for separating stable CAD patients with and without a new coronary event from 68 to 80% in addition to age, gender, BMI, diabetes, lipids, blood pressure and hs-CRP. Interestingly, expression of MT-COI, COX10 and WNK1 (but not ZNF484) in PBMCs paired with that in monocytes; COX10 in whole blood was similar to that in monocytes. Conclusions: This work showed that COX10 and ZNF484, eventually combined with MT-COI and WNK1 have the potential to accurately discriminate between AMI and stable CAD patients, and may improve the risk assessment of stable CAD patients.

2019-08-13 | GSE129935 | GEO

Impact of Computer-Aided Detection (CAD) as Second Reader in CT Colonography

Project description:RATIONALE: CT colonography accurately detects large polyps and masses. However, the test is less accurate in identifying lesions between 6 and 9 mm.Use of computer-aided detection (CAD) has shown promising results in providing uniform accuracy and improving CT colonography sensitivity. PURPOSE:This clinical trial compared the performance of CT colonography with unassisted and CAD-assisted reading in detecting patients with colorectal lesions.

| 2110180 | ecrin-mdr-crc

Generating automated kidney transplant biopsy reports combining molecular measurements with ensembles of machine learning classifiers

Project description:We previously reported a system for assessing rejection in kidney transplant biopsies using microarray-based gene expression data, the Molecular Microscope® Diagnostic System (MMDx). Ensembles generated diagnoses that were both more accurate than the best individual classifiers, and nearly as stable as the best, consistent with expectations from the machine learning literature. Human experts had ~93% agreement (balanced accuracy) signing out the reports, and random forest-based automated sign-outs showed similar levels of agreement with the human experts (92% and 94% for predicting the expert MMDx sign-outs for T cell-mediated (TCMR) and antibody-mediated rejection (ABMR) respectively). In most cases disagreements, whether between experts or between experts and automated sign-outs, were in biopsies near diagnostic thresholds. Considerable disagreement with histology persisted. The balanced accuracies of MMDx sign-outs for histology diagnoses of TCMR and ABMR were 73% and 78% respectively. Disagreement with histology is largely due to the known noise in histology assessments (ClinicalTrials.gov NCT01299168).

2019-11-07 | GSE124203 | GEO

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data