Artificial intelligence-driven real-time 3D surface quantification of Barrett's oesophagus for risk stratification and therapeutic response monitoring
<p><strong>BACKGROUND & AIMS:</strong> Barrett's epithelium measurement using widely accepted Prague C&M criteria is highly operator dependent. By reconstructing the surface of the Barrett's area in 3D from endoscopy video, we propose a novel methodology for measu...
| Главные авторы: | , , , , , , , , |
|---|---|
| Формат: | Working paper |
| Язык: | English |
| Опубликовано: |
Cold Spring Harbor Laboratory Press
2020
|
| _version_ | 1826309954797043712 |
|---|---|
| author | Ali, S Bailey, A East, JE Leedham, SJ Haghighat, M TGU Investigators Lu, X Rittscher, J Braden, B |
| author_facet | Ali, S Bailey, A East, JE Leedham, SJ Haghighat, M TGU Investigators Lu, X Rittscher, J Braden, B |
| author_sort | Ali, S |
| collection | OXFORD |
| description | <p><strong>BACKGROUND & AIMS:</strong> Barrett's epithelium measurement using widely accepted Prague C&M criteria is highly operator dependent. By reconstructing the surface of the Barrett's area in 3D from endoscopy video, we propose a novel methodology for measuring the C&M score automatically. This 3D reconstruction provides an extended field of view and also allows to precisely quantify the Barrett's area including islands. We aim to assess the accuracy of the extracted measurements from phantom and demonstrate their clinical usability.</p>
<p><strong>METHODS:</strong> Advanced deep learning techniques are utilised to design estimators for depth and camera pose required to map standard endoscopy video to a 3D surface model. By segmenting the Barrett's area and locating the position of the gastro-oesophageal junction (GEJ) we measure C&M scores and the Barrett's oesophagus areas (BOA). Experiments using a purpose-built 3D printed oesophagus phantom and high-definition video from 98 patients scored by an expert endoscopist are used for validation.</p>
<p><strong>RESULTS:</strong> Endoscopic phantom video data demonstrated a 95 % accuracy with a marginal +/- 1.8 mm average deviation for C&M and island measurements, while for BOA we achieved nearly 93 % accuracy with only +/- 1.1 sq. cm average deviation compared to the ground-truth measurements. On patient data, the C&M measurements provided by our system concord with the reference provided by expert upper GI endoscopists.</p>
<p><strong>CONCLUSIONS:</strong> The proposed methodology is suitable for extracting Prague C&M scores automatically with a high degree of accuracy. Providing an accurate measurement of the entire Barrett's area provides new opportunities for risk stratification and the assessment of therapy response.</p> |
| first_indexed | 2024-03-07T07:43:25Z |
| format | Working paper |
| id | oxford-uuid:17e0e857-b060-4617-a99c-3ccf309dcffc |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T07:43:25Z |
| publishDate | 2020 |
| publisher | Cold Spring Harbor Laboratory Press |
| record_format | dspace |
| spelling | oxford-uuid:17e0e857-b060-4617-a99c-3ccf309dcffc2023-05-18T12:42:20ZArtificial intelligence-driven real-time 3D surface quantification of Barrett's oesophagus for risk stratification and therapeutic response monitoringWorking paperhttp://purl.org/coar/resource_type/c_8042uuid:17e0e857-b060-4617-a99c-3ccf309dcffcEnglishSymplectic ElementsCold Spring Harbor Laboratory Press2020Ali, SBailey, AEast, JELeedham, SJHaghighat, MTGU InvestigatorsLu, XRittscher, JBraden, B<p><strong>BACKGROUND & AIMS:</strong> Barrett's epithelium measurement using widely accepted Prague C&M criteria is highly operator dependent. By reconstructing the surface of the Barrett's area in 3D from endoscopy video, we propose a novel methodology for measuring the C&M score automatically. This 3D reconstruction provides an extended field of view and also allows to precisely quantify the Barrett's area including islands. We aim to assess the accuracy of the extracted measurements from phantom and demonstrate their clinical usability.</p> <p><strong>METHODS:</strong> Advanced deep learning techniques are utilised to design estimators for depth and camera pose required to map standard endoscopy video to a 3D surface model. By segmenting the Barrett's area and locating the position of the gastro-oesophageal junction (GEJ) we measure C&M scores and the Barrett's oesophagus areas (BOA). Experiments using a purpose-built 3D printed oesophagus phantom and high-definition video from 98 patients scored by an expert endoscopist are used for validation.</p> <p><strong>RESULTS:</strong> Endoscopic phantom video data demonstrated a 95 % accuracy with a marginal +/- 1.8 mm average deviation for C&M and island measurements, while for BOA we achieved nearly 93 % accuracy with only +/- 1.1 sq. cm average deviation compared to the ground-truth measurements. On patient data, the C&M measurements provided by our system concord with the reference provided by expert upper GI endoscopists.</p> <p><strong>CONCLUSIONS:</strong> The proposed methodology is suitable for extracting Prague C&M scores automatically with a high degree of accuracy. Providing an accurate measurement of the entire Barrett's area provides new opportunities for risk stratification and the assessment of therapy response.</p> |
| spellingShingle | Ali, S Bailey, A East, JE Leedham, SJ Haghighat, M TGU Investigators Lu, X Rittscher, J Braden, B Artificial intelligence-driven real-time 3D surface quantification of Barrett's oesophagus for risk stratification and therapeutic response monitoring |
| title | Artificial intelligence-driven real-time 3D surface quantification of Barrett's oesophagus for risk stratification and therapeutic response monitoring |
| title_full | Artificial intelligence-driven real-time 3D surface quantification of Barrett's oesophagus for risk stratification and therapeutic response monitoring |
| title_fullStr | Artificial intelligence-driven real-time 3D surface quantification of Barrett's oesophagus for risk stratification and therapeutic response monitoring |
| title_full_unstemmed | Artificial intelligence-driven real-time 3D surface quantification of Barrett's oesophagus for risk stratification and therapeutic response monitoring |
| title_short | Artificial intelligence-driven real-time 3D surface quantification of Barrett's oesophagus for risk stratification and therapeutic response monitoring |
| title_sort | artificial intelligence driven real time 3d surface quantification of barrett s oesophagus for risk stratification and therapeutic response monitoring |
| work_keys_str_mv | AT alis artificialintelligencedrivenrealtime3dsurfacequantificationofbarrettsoesophagusforriskstratificationandtherapeuticresponsemonitoring AT baileya artificialintelligencedrivenrealtime3dsurfacequantificationofbarrettsoesophagusforriskstratificationandtherapeuticresponsemonitoring AT eastje artificialintelligencedrivenrealtime3dsurfacequantificationofbarrettsoesophagusforriskstratificationandtherapeuticresponsemonitoring AT leedhamsj artificialintelligencedrivenrealtime3dsurfacequantificationofbarrettsoesophagusforriskstratificationandtherapeuticresponsemonitoring AT haghighatm artificialintelligencedrivenrealtime3dsurfacequantificationofbarrettsoesophagusforriskstratificationandtherapeuticresponsemonitoring AT tguinvestigators artificialintelligencedrivenrealtime3dsurfacequantificationofbarrettsoesophagusforriskstratificationandtherapeuticresponsemonitoring AT lux artificialintelligencedrivenrealtime3dsurfacequantificationofbarrettsoesophagusforriskstratificationandtherapeuticresponsemonitoring AT rittscherj artificialintelligencedrivenrealtime3dsurfacequantificationofbarrettsoesophagusforriskstratificationandtherapeuticresponsemonitoring AT bradenb artificialintelligencedrivenrealtime3dsurfacequantificationofbarrettsoesophagusforriskstratificationandtherapeuticresponsemonitoring |