Computer Assisted Detection & Selection of Serrated Adenomas and Neoplastic Polyps - a New Clinical DRAft View Homepage


Ontology type: schema:MedicalStudy     


Clinical Trial Info

YEARS

2018-2019

ABSTRACT

The aim of the study is to develop a computer program which is able to automatically detect colorectal polyps in endoscopic video sequences. Furthermore, the program shall be able to automatically distinguish between adenomas, serrated adenomas and hyperplastic polyps on the basis of optical features of the polyps. Video sequences of polyps will be collected during routine colonoscopy procedures. All polyps will be resected endoscopically so that histopathological diagnoses (gold standard) can be notified. In the validation phase of the study a computer program will be established which aims to distinguish between adenomas, serrated adenomas and hyperplastic polyps on the basis of optical features derived from the videos. A deep learning approach will be used for programming. Afterwards, in the testing phase of the study, videos of 100 polyps (not used in the validation phase) will be presented to the computer program. The establishment of a well- functioning computer program is the primary aim of the study. Detailed Description Adenomas are polyps of the colorectum that have the potential to develop into colon cancer [1]. However, some adenomas never become malignant and if they do, progression from adenoma into cancer usually takes a long time. As a result, screening colonoscopy programs were established in order to detect and resect adenomas at an early stage [2]. After resection, polyps should be sent to pathology in order to make a histological diagnosis. Not every colorectal polyp has adenomatous histology. Approximately 40-50% of all polyps contain other benign histology (e.g. hyperplastic polyps). These polyps do not bear the risk of colon cancer. The implementation of screening programs has led to increasing numbers of colonoscopies in the last years [3]. This approach naturally implies higher amounts of detected polyps. The removal of these polyps and consultation of a pathologist in order to make a diagnosis is time consuming and expensive. An optical- based prediction of polyp histology (adenomatous versus non- adenomatous) would enable endoscopists to save money and to inform patients faster about examination results. The approach of predicting polyp histology on the basis of optical features is called the "optical biopsy" method. The prediction is made by the endoscopists during real-time colonoscopy. The aim of this strategy is to make an optical diagnosis which enables users to resect polyps without sending the specimen to pathology. Narrow Band Imaging (NBI) is a light-filter device which can be switched on during colonoscopy. NBI is useful to better display vascular patterns of the colon mucosa. It has been shown that the use of NBI can facilitate optical classification of colorectal polyps [5]. A NBI- based classification schemes exists which can be used to assign polyps into specific polyp categories (adenomatous versus non- adenomatous) [6]. Prior to the implementation of the optical classification approach for routine use in endoscopy it is necessary to proof its feasibility and accuracy [7]. Otherwise the approach would entail the risk of wrong diagnoses which could lead to wrong recommendations on further diagnostic or therapeutic steps. Until now, some clinical trials have shown good accuracy for the optical biopsy method [5]. However, there is growing evidence that optical biopsy does not yet meet demanded accuracy thresholds [8]. The aim of our study is to create a computer program that is able to distinguish between adenomas, serrated adenomas and hyperplastic polyps. Video sequences of colorectal polyps will be used for machine learning (validation phase). Afterwards a set of 100 videos will be used to test whether the computer program is able to distinguish between adenomatous and non- adenomatous polyps (primary endpoint). Statistical measures (accuracy, sensitivity, specificity) will be calculated. The 100 videos will also be presented to human experts who will also predict polyp diagnoses based on optical features. Comparing the accuracy of optical predictions made by the computer and by human experts will be another endpoint of the study. More... »

URL

https://clinicaltrials.gov/show/NCT03601065

Related SciGraph Publications

JSON-LD is the canonical representation for SciGraph data.

TIP: You can open this SciGraph record using an external JSON-LD service: JSON-LD Playground Google SDTT

[
  {
    "@context": "https://springernature.github.io/scigraph/jsonld/sgcontext.json", 
    "about": [
      {
        "id": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/2746", 
        "inDefinedTermSet": "http://purl.org/au-research/vocabulary/anzsrc-for/2008/", 
        "type": "DefinedTerm"
      }
    ], 
    "description": "The aim of the study is to develop a computer program which is able to automatically detect colorectal polyps in endoscopic video sequences. Furthermore, the program shall be able to automatically distinguish between adenomas, serrated adenomas and hyperplastic polyps on the basis of optical features of the polyps. Video sequences of polyps will be collected during routine colonoscopy procedures. All polyps will be resected endoscopically so that histopathological diagnoses (gold standard) can be notified. In the validation phase of the study a computer program will be established which aims to distinguish between adenomas, serrated adenomas and hyperplastic polyps on the basis of optical features derived from the videos. A deep learning approach will be used for programming. Afterwards, in the testing phase of the study, videos of 100 polyps (not used in the validation phase) will be presented to the computer program. The establishment of a well- functioning computer program is the primary aim of the study.\n\nDetailed Description\nAdenomas are polyps of the colorectum that have the potential to develop into colon cancer [1]. However, some adenomas never become malignant and if they do, progression from adenoma into cancer usually takes a long time. As a result, screening colonoscopy programs were established in order to detect and resect adenomas at an early stage [2]. After resection, polyps should be sent to pathology in order to make a histological diagnosis. Not every colorectal polyp has adenomatous histology. Approximately 40-50% of all polyps contain other benign histology (e.g. hyperplastic polyps). These polyps do not bear the risk of colon cancer. The implementation of screening programs has led to increasing numbers of colonoscopies in the last years [3]. This approach naturally implies higher amounts of detected polyps. The removal of these polyps and consultation of a pathologist in order to make a diagnosis is time consuming and expensive. An optical- based prediction of polyp histology (adenomatous versus non- adenomatous) would enable endoscopists to save money and to inform patients faster about examination results. The approach of predicting polyp histology on the basis of optical features is called the \"optical biopsy\" method. The prediction is made by the endoscopists during real-time colonoscopy. The aim of this strategy is to make an optical diagnosis which enables users to resect polyps without sending the specimen to pathology. Narrow Band Imaging (NBI) is a light-filter device which can be switched on during colonoscopy. NBI is useful to better display vascular patterns of the colon mucosa. It has been shown that the use of NBI can facilitate optical classification of colorectal polyps [5]. A NBI- based classification schemes exists which can be used to assign polyps into specific polyp categories (adenomatous versus non- adenomatous) [6]. Prior to the implementation of the optical classification approach for routine use in endoscopy it is necessary to proof its feasibility and accuracy [7]. Otherwise the approach would entail the risk of wrong diagnoses which could lead to wrong recommendations on further diagnostic or therapeutic steps. Until now, some clinical trials have shown good accuracy for the optical biopsy method [5]. However, there is growing evidence that optical biopsy does not yet meet demanded accuracy thresholds [8]. The aim of our study is to create a computer program that is able to distinguish between adenomas, serrated adenomas and hyperplastic polyps. Video sequences of colorectal polyps will be used for machine learning (validation phase). Afterwards a set of 100 videos will be used to test whether the computer program is able to distinguish between adenomatous and non- adenomatous polyps (primary endpoint). Statistical measures (accuracy, sensitivity, specificity) will be calculated. The 100 videos will also be presented to human experts who will also predict polyp diagnoses based on optical features. Comparing the accuracy of optical predictions made by the computer and by human experts will be another endpoint of the study.", 
    "endDate": "2019-10-01T00:00:00Z", 
    "id": "sg:clinicaltrial.NCT03601065", 
    "keywords": [
      "computer", 
      "selection", 
      "adenoma", 
      "polyp", 
      "draft", 
      "software", 
      "colorectal polyp", 
      "video sequence", 
      "hyperplastic polyp", 
      "feature", 
      "colonoscopy", 
      "diagnosise", 
      "gold", 
      "validation phase", 
      "video", 
      "programming", 
      "afterwards", 
      "testing phase", 
      "establishment", 
      "primary aim", 
      "colorectum", 
      "Colonic Neoplasm", 
      "Neoplasm", 
      "long time", 
      "screening colonoscopy", 
      "early stage", 
      "resection", 
      "pathology", 
      "histological diagnosis", 
      "histology", 
      "risk", 
      "implementation", 
      "screening program", 
      "high amount", 
      "removal", 
      "Referral and Consultation", 
      "pathologist", 
      "diagnosis", 
      "prediction", 
      "endoscopists", 
      "money", 
      "patient", 
      "examination", 
      "optical biopsy", 
      "real time", 
      "user", 
      "resect", 
      "specimen", 
      "narrow band", 
      "filter", 
      "pattern", 
      "colon", 
      "classification", 
      "classification scheme", 
      "category", 
      "routine use", 
      "endoscopy", 
      "proof", 
      "feasibility", 
      "accuracy", 
      "entail", 
      "recommendation", 
      "therapeutic", 
      "clinical trial", 
      "good accuracy", 
      "evidence", 
      "threshold", 
      "machine", 
      "adenomatous polyp", 
      "primary endpoint", 
      "statistical measure", 
      "Sensitivity and Specificity", 
      "human expert"
    ], 
    "name": "Computer Assisted Detection & Selection of Serrated Adenomas and Neoplastic Polyps - a New Clinical DRAft", 
    "sameAs": [
      "https://app.dimensions.ai/details/clinical_trial/NCT03601065"
    ], 
    "sdDataset": "clinical_trials", 
    "sdDatePublished": "2019-03-07T15:27", 
    "sdLicense": "https://scigraph.springernature.com/explorer/license/", 
    "sdPublisher": {
      "name": "Springer Nature - SN SciGraph project", 
      "type": "Organization"
    }, 
    "sdSource": "file:///pack/app/us_ct_data_00027.json", 
    "sponsor": [
      {
        "id": "https://www.grid.ac/institutes/grid.6936.a", 
        "type": "Organization"
      }
    ], 
    "startDate": "2018-08-01T00:00:00Z", 
    "subjectOf": [
      {
        "id": "https://doi.org/10.1016/j.gie.2014.12.022", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1008831543"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.gie.2009.06.018", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1017295955"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1056/nejm198809013190901", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1042576983"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1053/j.gastro.2012.05.006", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1048130936"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1016/j.cgh.2014.08.036", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1051189748"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10620-015-3661-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053037852", 
          "https://doi.org/10.1007/s10620-015-3661-5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "sg:pub.10.1007/s10620-015-3661-5", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1053037852", 
          "https://doi.org/10.1007/s10620-015-3661-5"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.1055/s-0034-1365348", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1057304990"
        ], 
        "type": "CreativeWork"
      }, 
      {
        "id": "https://doi.org/10.3748/wjg.v20.i26.8449", 
        "sameAs": [
          "https://app.dimensions.ai/details/publication/pub.1071371094"
        ], 
        "type": "CreativeWork"
      }
    ], 
    "type": "MedicalStudy", 
    "url": "https://clinicaltrials.gov/show/NCT03601065"
  }
]
 

Download the RDF metadata as:  json-ld nt turtle xml License info

HOW TO GET THIS DATA PROGRAMMATICALLY:

JSON-LD is a popular format for linked data which is fully compatible with JSON.

curl -H 'Accept: application/ld+json' 'https://scigraph.springernature.com/clinicaltrial.NCT03601065'

N-Triples is a line-based linked data format ideal for batch operations.

curl -H 'Accept: application/n-triples' 'https://scigraph.springernature.com/clinicaltrial.NCT03601065'

Turtle is a human-readable linked data format.

curl -H 'Accept: text/turtle' 'https://scigraph.springernature.com/clinicaltrial.NCT03601065'

RDF/XML is a standard XML format for linked data.

curl -H 'Accept: application/rdf+xml' 'https://scigraph.springernature.com/clinicaltrial.NCT03601065'


 

This table displays all metadata directly associated to this object as RDF triples.

117 TRIPLES      16 PREDICATES      96 URIs      82 LITERALS      1 BLANK NODES

Subject Predicate Object
1 sg:clinicaltrial.NCT03601065 schema:about anzsrc-for:2746
2 schema:description The aim of the study is to develop a computer program which is able to automatically detect colorectal polyps in endoscopic video sequences. Furthermore, the program shall be able to automatically distinguish between adenomas, serrated adenomas and hyperplastic polyps on the basis of optical features of the polyps. Video sequences of polyps will be collected during routine colonoscopy procedures. All polyps will be resected endoscopically so that histopathological diagnoses (gold standard) can be notified. In the validation phase of the study a computer program will be established which aims to distinguish between adenomas, serrated adenomas and hyperplastic polyps on the basis of optical features derived from the videos. A deep learning approach will be used for programming. Afterwards, in the testing phase of the study, videos of 100 polyps (not used in the validation phase) will be presented to the computer program. The establishment of a well- functioning computer program is the primary aim of the study. Detailed Description Adenomas are polyps of the colorectum that have the potential to develop into colon cancer [1]. However, some adenomas never become malignant and if they do, progression from adenoma into cancer usually takes a long time. As a result, screening colonoscopy programs were established in order to detect and resect adenomas at an early stage [2]. After resection, polyps should be sent to pathology in order to make a histological diagnosis. Not every colorectal polyp has adenomatous histology. Approximately 40-50% of all polyps contain other benign histology (e.g. hyperplastic polyps). These polyps do not bear the risk of colon cancer. The implementation of screening programs has led to increasing numbers of colonoscopies in the last years [3]. This approach naturally implies higher amounts of detected polyps. The removal of these polyps and consultation of a pathologist in order to make a diagnosis is time consuming and expensive. An optical- based prediction of polyp histology (adenomatous versus non- adenomatous) would enable endoscopists to save money and to inform patients faster about examination results. The approach of predicting polyp histology on the basis of optical features is called the "optical biopsy" method. The prediction is made by the endoscopists during real-time colonoscopy. The aim of this strategy is to make an optical diagnosis which enables users to resect polyps without sending the specimen to pathology. Narrow Band Imaging (NBI) is a light-filter device which can be switched on during colonoscopy. NBI is useful to better display vascular patterns of the colon mucosa. It has been shown that the use of NBI can facilitate optical classification of colorectal polyps [5]. A NBI- based classification schemes exists which can be used to assign polyps into specific polyp categories (adenomatous versus non- adenomatous) [6]. Prior to the implementation of the optical classification approach for routine use in endoscopy it is necessary to proof its feasibility and accuracy [7]. Otherwise the approach would entail the risk of wrong diagnoses which could lead to wrong recommendations on further diagnostic or therapeutic steps. Until now, some clinical trials have shown good accuracy for the optical biopsy method [5]. However, there is growing evidence that optical biopsy does not yet meet demanded accuracy thresholds [8]. The aim of our study is to create a computer program that is able to distinguish between adenomas, serrated adenomas and hyperplastic polyps. Video sequences of colorectal polyps will be used for machine learning (validation phase). Afterwards a set of 100 videos will be used to test whether the computer program is able to distinguish between adenomatous and non- adenomatous polyps (primary endpoint). Statistical measures (accuracy, sensitivity, specificity) will be calculated. The 100 videos will also be presented to human experts who will also predict polyp diagnoses based on optical features. Comparing the accuracy of optical predictions made by the computer and by human experts will be another endpoint of the study.
3 schema:endDate 2019-10-01T00:00:00Z
4 schema:keywords Colonic Neoplasm
5 Neoplasm
6 Referral and Consultation
7 Sensitivity and Specificity
8 accuracy
9 adenoma
10 adenomatous polyp
11 afterwards
12 category
13 classification
14 classification scheme
15 clinical trial
16 colon
17 colonoscopy
18 colorectal polyp
19 colorectum
20 computer
21 diagnosis
22 diagnosise
23 draft
24 early stage
25 endoscopists
26 endoscopy
27 entail
28 establishment
29 evidence
30 examination
31 feasibility
32 feature
33 filter
34 gold
35 good accuracy
36 high amount
37 histological diagnosis
38 histology
39 human expert
40 hyperplastic polyp
41 implementation
42 long time
43 machine
44 money
45 narrow band
46 optical biopsy
47 pathologist
48 pathology
49 patient
50 pattern
51 polyp
52 prediction
53 primary aim
54 primary endpoint
55 programming
56 proof
57 real time
58 recommendation
59 removal
60 resect
61 resection
62 risk
63 routine use
64 screening colonoscopy
65 screening program
66 selection
67 software
68 specimen
69 statistical measure
70 testing phase
71 therapeutic
72 threshold
73 user
74 validation phase
75 video
76 video sequence
77 schema:name Computer Assisted Detection & Selection of Serrated Adenomas and Neoplastic Polyps - a New Clinical DRAft
78 schema:sameAs https://app.dimensions.ai/details/clinical_trial/NCT03601065
79 schema:sdDatePublished 2019-03-07T15:27
80 schema:sdLicense https://scigraph.springernature.com/explorer/license/
81 schema:sdPublisher N25565f45d9dd43e5ad145df8695eabf3
82 schema:sponsor https://www.grid.ac/institutes/grid.6936.a
83 schema:startDate 2018-08-01T00:00:00Z
84 schema:subjectOf sg:pub.10.1007/s10620-015-3661-5
85 https://doi.org/10.1016/j.cgh.2014.08.036
86 https://doi.org/10.1016/j.gie.2009.06.018
87 https://doi.org/10.1016/j.gie.2014.12.022
88 https://doi.org/10.1053/j.gastro.2012.05.006
89 https://doi.org/10.1055/s-0034-1365348
90 https://doi.org/10.1056/nejm198809013190901
91 https://doi.org/10.3748/wjg.v20.i26.8449
92 schema:url https://clinicaltrials.gov/show/NCT03601065
93 sgo:license sg:explorer/license/
94 sgo:sdDataset clinical_trials
95 rdf:type schema:MedicalStudy
96 N25565f45d9dd43e5ad145df8695eabf3 schema:name Springer Nature - SN SciGraph project
97 rdf:type schema:Organization
98 anzsrc-for:2746 schema:inDefinedTermSet anzsrc-for:
99 rdf:type schema:DefinedTerm
100 sg:pub.10.1007/s10620-015-3661-5 schema:sameAs https://app.dimensions.ai/details/publication/pub.1053037852
101 https://doi.org/10.1007/s10620-015-3661-5
102 rdf:type schema:CreativeWork
103 https://doi.org/10.1016/j.cgh.2014.08.036 schema:sameAs https://app.dimensions.ai/details/publication/pub.1051189748
104 rdf:type schema:CreativeWork
105 https://doi.org/10.1016/j.gie.2009.06.018 schema:sameAs https://app.dimensions.ai/details/publication/pub.1017295955
106 rdf:type schema:CreativeWork
107 https://doi.org/10.1016/j.gie.2014.12.022 schema:sameAs https://app.dimensions.ai/details/publication/pub.1008831543
108 rdf:type schema:CreativeWork
109 https://doi.org/10.1053/j.gastro.2012.05.006 schema:sameAs https://app.dimensions.ai/details/publication/pub.1048130936
110 rdf:type schema:CreativeWork
111 https://doi.org/10.1055/s-0034-1365348 schema:sameAs https://app.dimensions.ai/details/publication/pub.1057304990
112 rdf:type schema:CreativeWork
113 https://doi.org/10.1056/nejm198809013190901 schema:sameAs https://app.dimensions.ai/details/publication/pub.1042576983
114 rdf:type schema:CreativeWork
115 https://doi.org/10.3748/wjg.v20.i26.8449 schema:sameAs https://app.dimensions.ai/details/publication/pub.1071371094
116 rdf:type schema:CreativeWork
117 https://www.grid.ac/institutes/grid.6936.a schema:Organization
 




Preview window. Press ESC to close (or click here)


...