Prospective evaluation of a new artificial intelligence system for the classification of colonic polyps.
Ontology highlight
ABSTRACT:
DISEASE(S): Benign Neoplasm Of Colon, Rectum, Anus And Anal Canal,Polyp Of Colon
PROVIDER: 2733414 | ecrin-mdr-crc |
REPOSITORIES: ECRIN MDR
Similar Datasets
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
Project description:Microarray analysis was used to determine the expression of 12,000 genes in a set of 50 gliomas, 28 glioblastomas and 22 anaplastic oligodendrogliomas. Supervised learning approaches were used to build a two-class prediction model based on a subset of 14 glioblastomas and 7 anaplastic oligodendrogliomas with classic histology. A 20-feature k-nearest neighbor model correctly classified 18 of the 21 classic cases in leave-one-out cross-validation when compared with pathological diagnoses. This model was then used to predict the classification of clinically common, histologically nonclassic samples. When tumors were classified according to pathology, the survival of patients with nonclassic glioblastoma and nonclassic anaplastic oligodendroglioma was not significantly different (P = 0.19). However, class distinctions according to the model were significantly associated with survival outcome (P = 0.05). This class prediction model was capable of classifying high-grade, nonclassic glial tumors objectively and reproducibly. Moreover, the model provided a more accurate predictor of prognosis in these nonclassic lesions than did pathological classification. These data suggest that class prediction models, based on defined molecular profiles, classify diagnostically challenging malignant gliomas in a manner that better correlates with clinical outcome than does standard pathology.
2016-05-28 | GSE82009 | GEO
Project description:Interventions: Usual standard of care from the endoscopist doctor, with addition of Endo-AID (Olympus Corporation) AI module to be on during withdrawal phase of colonoscopy.
-Usual standard of care: single colonoscopy, which may take between 3-30 minutes. During withdrawal phase, which may take between 6 and 60 minutes, the AI module will be activated. It is not known if use of this module will increase the withdrawal time (compared to standard of care, without it).
-The nurses will advise the doctor of the randomisation (AI or standard of care), and turn on the AI device once withdrawal has commenced.
-The AI will analyse the video output from the scope to automatically detect suspected polyps in real-time during withdrawal. Polyps would then be further analysed and resected as per usual standard of care.
Primary outcome(s): ADR (Adenoma Detection Rate) - proportion of patients with at least one histologically proven adenoma or carcinoma. Histology will be assessed using standard procedure in the laboratory.
This data will be gathered from colonoscopy reports and lab reports of patients[At time of colonoscopy]
Study Design: Purpose: Diagnosis; Allocation: Randomised controlled trial; Masking: Open (masking not used);Assignment: Parallel;Type of endpoint: Efficacy
| 2737810 | ecrin-mdr-crc
Project description:Microarray analysis was used to determine the expression of 12,000 genes in a set of 50 gliomas, 28 glioblastomas and 22 anaplastic oligodendrogliomas. Supervised learning approaches were used to build a two-class prediction model based on a subset of 14 glioblastomas and 7 anaplastic oligodendrogliomas with classic histology. A 20-feature k-nearest neighbor model correctly classified 18 of the 21 classic cases in leave-one-out cross-validation when compared with pathological diagnoses. This model was then used to predict the classification of clinically common, histologically nonclassic samples. When tumors were classified according to pathology, the survival of patients with nonclassic glioblastoma and nonclassic anaplastic oligodendroglioma was not significantly different (P = 0.19). However, class distinctions according to the model were significantly associated with survival outcome (P = 0.05). This class prediction model was capable of classifying high-grade, nonclassic glial tumors objectively and reproducibly. Moreover, the model provided a more accurate predictor of prognosis in these nonclassic lesions than did pathological classification. These data suggest that class prediction models, based on defined molecular profiles, classify diagnostically challenging malignant gliomas in a manner that better correlates with clinical outcome than does standard pathology. louis-00379 Assay Type: Gene Expression Provider: Affymetrix Array Designs: HG_U95Av2 Organism: Homo sapiens (ncbitax) Material Types: total_RNA, synthetic_RNA, organism_part, whole_organism Disease States: Classic anaplastic oligodendroglioma, Non-classic glioblastoma, Classic glioblastoma, Non-classic anaplastic oligodendroglioma
2016-05-28 | E-GEOD-82009 | biostudies-arrayexpress
Project description:The goal of this substudy is to investigate the accuracy of a computer-aided polyp characterization (CADx) system. The main question[s] it aims to answer are:
• How high is the specificity of the AI system when characterizing colorectal polyps
Participants will receive a standard colonoscopy, assisted by the artificial intelligence (AI) assisted system GI Genius.
Researchers will compare the AI system´s characterization with the histopathology to see how accurate the system is.
| 10350 | ecrin-mdr-crc
Project description:Colorectal cancer (CRC) is a leading cause of cancer-related morbidity and mortality worldwide, with rates of CRC predicted to increase. Colonoscopy is currently the gold standard of screening for CRC. Artificial intelligence (AI) is seen as a solution to bridge this gap in adenoma detection, which is a quality indicator in colonoscopy. AI systems utilize deep neural networks to enable computer-aided detection (CADe) and computer-aided classification (CADx). CADe is concerned with the detection of polyps during colonoscopy, which in turn is postulated to help decrease the adenoma miss-rate.
In contrast, CADx deals with the interpretation of polyp appearance during colonoscopy to determine the predicted histology. Prediction of polyp histology is crucial in helping Clinicians decide on a "resect and discard" or "diagnose and leave strategy". It is also useful for the Clinician to be aware of the predicted histology of a colorectal polyp in determining the appropriate method of resection in terms of safety and efficacy. While CADe has been studied extensively in randomized controlled trials, there is a lack of prospective data validating the use of CADx in a clinical setting to predict polyp histology.
The investigators plan to conduct a prospective, multi-centre clinical trial to validate the accuracy of CADx support for prediction of polyp histology in real-time colonoscopy.
| 2388863 | ecrin-mdr-crc
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
Project description:Accurate diagnostic discrimination of benign renal oncocytoma (OC) and malignant renal cell carcinomas (RCC) is not only useful for planning appropriate treatment strategies of patients with renal masses but also for estimating prognosis. Classification of renal neoplasms solely by histopathology can often be challenging for a variety of reasons. The aim of this study was to develop and validate a genomic algorithm for molecular classification of renal cortical neoplasms that could be implemented in a routine clinical diagnostic setting. Using TCGA (The Cancer Genome Atlas) copy number profiles of over 600 RCC specimens, prior FISH studies and published literature, a classification algorithm was developed consisting of 15 genomic markers: loss of VHL, 3p21, 8p, and chromosomes 1, 2, 6, 10 and 17, and gain of 5qter, 16p, 17q, 20q, and chromosomes 3, 7, and 12. Criteria for scoring specimens for the presence of each genomic marker were established. As validation, 191 surgically resected formalin-fixed paraffin-embedded renal neoplasms were blindly submitted to targeted array-CGH and were classified according to the algorithm. Upon histologic re-review leading to exclusion of three specimens and using histology as the gold standard, the algorithm correctly classified 58 of 62 (93%) clear cell renal cell carcinoma, 51 of 56 (91%) papillary RCC, and 33 of 34 (97%) chromophobe RCC. Of the 36 OC specimens, 17 were classified as OC, two as a malignant subtype, 14 as benign, and three exhibited alterations not associated with a specific subtype. In ten of the latter two groups, CCND1-rearrangement was detected by fluorescence in situ hybridization, affording a classification as OC. Together, 33 of 36 (92%) OC were classified as OC or benign. For the entire validation cohort, an overall diagnostic sensitivity of 93% and above 97% specificity was achieved, suggesting that the implementation of genome-based molecular classification in a clinical diagnostic setting could impact the overall management and outcome of patients with renal tumors. A total of 191 RCC FFPE samples are analyzed including 63 clear cell RCC (ccRCC), 57 papillary RCC (pRCC), 35 chromophobe RCC (chrRCC) and 36 oncocytoma (OC). Two-color array-comparative genomic hybdrization on custom designed using RCC DNA as test and normal sex-matched DNA as reference.
2015-04-29 | E-GEOD-57162 | biostudies-arrayexpress
Project description:Interventions: colonoscopy with/without AI (computer-aided detection)
colonoscopy without AI (computer-aided detection)
Primary outcome(s): Adenoma detection rate in total colonoscopy
Study Design: Parallel Randomized
| 2739307 | ecrin-mdr-crc
Project description:Accurate diagnostic discrimination of benign renal oncocytoma (OC) and malignant renal cell carcinomas (RCC) is not only useful for planning appropriate treatment strategies of patients with renal masses but also for estimating prognosis. Classification of renal neoplasms solely by histopathology can often be challenging for a variety of reasons. The aim of this study was to develop and validate a genomic algorithm for molecular classification of renal cortical neoplasms that could be implemented in a routine clinical diagnostic setting. Using TCGA (The Cancer Genome Atlas) copy number profiles of over 600 RCC specimens, prior FISH studies and published literature, a classification algorithm was developed consisting of 15 genomic markers: loss of VHL, 3p21, 8p, and chromosomes 1, 2, 6, 10 and 17, and gain of 5qter, 16p, 17q, 20q, and chromosomes 3, 7, and 12. Criteria for scoring specimens for the presence of each genomic marker were established. As validation, 191 surgically resected formalin-fixed paraffin-embedded renal neoplasms were blindly submitted to targeted array-CGH and were classified according to the algorithm. Upon histologic re-review leading to exclusion of three specimens and using histology as the gold standard, the algorithm correctly classified 58 of 62 (93%) clear cell renal cell carcinoma, 51 of 56 (91%) papillary RCC, and 33 of 34 (97%) chromophobe RCC. Of the 36 OC specimens, 17 were classified as OC, two as a malignant subtype, 14 as benign, and three exhibited alterations not associated with a specific subtype. In ten of the latter two groups, CCND1-rearrangement was detected by fluorescence in situ hybridization, affording a classification as OC. Together, 33 of 36 (92%) OC were classified as OC or benign. For the entire validation cohort, an overall diagnostic sensitivity of 93% and above 97% specificity was achieved, suggesting that the implementation of genome-based molecular classification in a clinical diagnostic setting could impact the overall management and outcome of patients with renal tumors.
2015-04-29 | GSE57162 | GEO