Computer-aided detection of early Barrett’s neoplasia using volumetric laser endomicroscopy

doi:10.1016/j.gie.2017.03.011

Gastrointestinal Endoscopy

Volume 86, Issue 5, November 2017, Pages 839-846

https://doi.org/10.1016/j.gie.2017.03.011 Get rights and content

Background and Aims

Volumetric laser endomicroscopy (VLE) is an advanced imaging system that provides a near-microscopic resolution scan of the esophageal wall layers up to 3-mm deep. VLE has the potential to improve detection of early neoplasia in Barrett’s esophagus (BE). However, interpretation of VLE images is complex because of the large amount of data that need to be interpreted in real time. The aim of this study was to investigate the feasibility of a computer algorithm to identify early BE neoplasia on ex vivo VLE images.

Methods

We used 60 VLE images from a database of high-quality ex vivo VLE-histology correlations, obtained from BE patients ± neoplasia (30 nondysplastic BE [NDBE] and 30 high-grade dysplasia/early adenocarcinoma images). VLE features from a recently developed clinical VLE prediction score for BE neoplasia served as input for the algorithm: (1) higher VLE surface than subsurface signal and (2) lack of layering. With this input, novel clinically inspired algorithm features were developed, based on signal intensity statistics and grayscale correlations. For comparison, generic image analysis methods were examined for their performance to detect neoplasia. For classification of the images in the NDBE or neoplastic group, several machine learning methods were evaluated. Leave-1-out cross-validation was used for algorithm validation.

Results

Three novel clinically inspired algorithm features were developed. The feature “layering and signal decay statistics” showed the optimal performance compared with the other clinically features (“layering” and “signal intensity distribution”) and generic image analyses methods, with an area under the receiver operating characteristic curve (AUC) of .95. Corresponding sensitivity and specificity were 90% and 93%, respectively. In addition, the algorithm showed a better performance than the clinical VLE prediction score (AUC .81).

Conclusions

This is the first study in which a computer algorithm for BE neoplasia was developed based on VLE images with direct histologic correlates. The algorithm showed good performance to detect BE neoplasia in ex vivo VLE images compared with the performance of a recently developed clinical VLE prediction score. This study suggests that an automatic detection algorithm has the potential to assist endoscopists in detecting early neoplasia on VLE. Future studies on in vivo VLE scans are needed to further validate the algorithm.

Section snippets

Patients and image database

The VLE images used in this study were derived from a database of high-quality 1-to-1 VLE-histology correlations. The construction of this database has been described previously.¹⁴ In short, endoscopic resection specimens from patients with BE with and without early neoplasia were used. The fresh specimens were scanned ex vivo with VLE in a custom-made fixture. Guided by previously placed in vivo and ex vivo markers, histologic sectioning was performed. Histology slides and VLE frames were

Patients and VLE-histology database

The previously constructed VLE-histology database consisted of 52 endoscopic resection specimens from 29 BE patients (mean age, 67 years [SD ±8.4]; 22 men). The worst histologic diagnosis per patient was NDBE in 6, low-grade dysplasia in 2, HGD in 5, and EAC in 16. In total, 86 VLE-histology matches containing 200 areas of interest were constructed. For this study 30 NDBE and 30 HGD/EAC areas of interest of sufficient quality were selected. These 60 images were derived from 19 different

Discussion

Our results show that a computer algorithm based on clinically derived features is capable of identifying early BE neoplasia on ex vivo VLE images. In fact, compared with VLE experts who scored the same ex vivo VLE images, the algorithm performed even better in identifying neoplasia (AUC, .89-.95 vs .81 for experts). We envision that an objective and quantitative interpretation of VLE by a computer-aided algorithm, not hindered by interobserver variability, will be an important tool to aid in

References (22)

M.J. Suter et al.
Comprehensive microscopy of the esophagus in human patients with optical frequency domain imaging
Gastrointest Endosc
(2008)
A. Swager et al.
How good are experts in identifying early Barrett’s neoplasia in endoscopic resection specimens using volumetric laser endomicroscopy?
Gastroenterology
(2016)
A. Swager et al.
How good are experts in identifying endoscopically visible early Barrett’s neoplasia on in vivo volumetric laser endomicroscopy [abstract]?
Gastrointest Endosc
(2016)
B.J. Vakoc et al.
Comprehensive esophageal microscopy by using optical frequency-domain imaging (with video)
Gastrointest Endosc
(2007)
W.L. Curvers et al.
A new paradigm shift in endoscopy: from interpretation to automated image analysis?
Gastrointest Endosc
(2016)
H. Pohl et al.
Esophageal adenocarcinoma incidence: Are we reaching the peak?
Cancer Epidemiol Biomarkers Prev
(2010)
R.C. Fitzgerald et al.
British Society of Gastroenterology guidelines on the diagnosis and management of Barrett’s oesophagus
Gut
(2014)
N. Shaheen et al.
ACG Clinical Guideline: diagnosis and management of Barrett’s esophagus
Am J Gastroenterol
(2015)
H.C. Wolfsen et al.
Safety and feasibility of volumetric laser endomicroscopy in patients with Barrett’s esophagus (with videos)
Gastrointest Endosc
(2015)
A. Swager et al.
Identification of volumetric laser endomicroscopy features predictive for early neoplasia in Barrett’s esophagus using high-quality histological correlation
Gastrointest Endosc
(2017)

C.L. Leggett et al.

Comparative diagnostic performance of volumetric laser endomicroscopy and confocal laser endomicroscopy in the detection of dysplasia associated with Barrett’s esophagus

Gastrointest Endosc

(2016)

Cited by (107)

Development and validation of artificial neural networks model for detection of Barrett's neoplasia: a multicenter pragmatic nonrandomized trial (with video)
2023, Gastrointestinal Endoscopy
The aim of this study was to develop and externally validate a computer-aided detection (CAD) system for the detection and localization of Barrett’s neoplasia and assess its performance compared with that of general endoscopists in a statistically powered multicenter study by using real-time video sequences.
In phase 1, the hybrid visual geometry group 16-SegNet model was trained by the use of 75,198 images and videos (96 patients) of neoplastic and 1,014,973 images and videos (65 patients) of nonneoplastic Barrett’s esophagus. In phase 2, image-based validation was performed on a separate dataset of 107 images (20 patients) of neoplastic and 364 images (14 patients) of nonneoplastic Barrett’s esophagus. In phase 3 (video-based external validation) we designed a real-time video-based study with 32 videos (32 patients) of neoplastic and 43 videos (43 patients) of nonneoplastic Barrett’s esophagus from 4 European centers to compare the performance of the CAD model with that of 6 nonexpert endoscopists. The primary endpoint was the sensitivity of CAD diagnosis of Barrett’s neoplasia.
In phase 2, CAD detected Barrett’s neoplasia with sensitivity, specificity, and accuracy of 95.3%, 94.5%, and 94.7%, respectively. In phase 3, the CAD system detected Barrett’s neoplasia with sensitivity, specificity, negative predictive value, and accuracy of 93.8%, 90.7%, 95.1%, and 92.0%, respectively, compared with the endoscopists’ performance of 63.5%, 77.9%, 74.2%, and 71.8%, respectively (P < .05 in all parameters). The CAD system localized neoplastic lesions with accuracy, mean precision, and mean intersection over union of 100%, 0.62, and 0.54, respectively, when compared with at least 1 of the expert markings. The processing speed of the CAD detection and localization were 5 ms/image and 33 ms/image, respectively.
To our knowledge, this is the first study describing external (multicenter) validation of AI algorithms for the detection of Barrett’s neoplasia on real-time endoscopic videos. The CAD system in this study significantly outperformed nonexpert endoscopists on real-time video-based assessment, achieving >90% sensitivity for neoplasia detection. This result needs to be validated during real-time endoscopic assessment.
Feasibility and Safety of Tethered Capsule Endomicroscopy in Patients With Barrett's Esophagus in a Multi-Center Study
2022, Clinical Gastroenterology and Hepatology
Tethered capsule endomicroscopy (TCE) involves swallowing a small tethered pill that implements optical coherence tomography (OCT) imaging, procuring high resolution images of the whole esophagus. Here, we demonstrate and evaluate the feasibility and safety of TCE and a portable OCT imaging system in patients with Barrett’s esophagus (BE) in a multi-center (5-site) clinical study.
Untreated patients with BE as per endoscopic biopsy diagnosis were eligible to participate in the study. TCE procedures were performed in unsedated patients by either doctors or nurses. After the capsule was swallowed, the device continuously obtained 10-μm-resolution cross-sectional images as it traversed the esophagus. Following imaging, the device was withdrawn through mouth, and disinfected for subsequent reuse. BE lengths were compared to endoscopy findings when available. OCT-TCE images were compared to volumetric laser endomicroscopy (VLE) images from a patient who had undergone VLE on the same day as TCE.
147 patients with BE were enrolled across all sites. 116 swallowed the capsule (79%), 95/114 (83.3%) men and 21/33 (63.6%) women (P = .01). High-quality OCT images were obtained in 104/111 swallowers (93.7%) who completed the procedure. The average imaging duration was 5.55 ± 1.92 minutes. The mean length of esophagus imaged per patient was 21.69 ± 5.90 cm. A blinded comparison of maximum extent of BE measured by OCT-TCE and EGD showed a strong correlation (r = 0.77-0.79). OCT-TCE images were of similar quality to those obtained by OCT-VLE.
The capabilities of TCE to be used across multiple sites, be administered to unsedated patients by either physicians or nurses who are not expert in OCT-TCE, and to rapidly and safely evaluate the microscopic structure of the esophagus make it an emerging tool for screening and surveillance of BE patients. Clinical trial registry website and trial number: NCT02994693 and NCT03459339.
Real-time artificial intelligence for detecting focal lesions and diagnosing neoplasms of the stomach by white-light endoscopy (with videos)
2022, Gastrointestinal Endoscopy
White-light endoscopy (WLE) is the most pivotal tool to detect gastric cancer in an early stage. However, the skill among endoscopists varies greatly. Here, we aim to develop a deep learning–based system named ENDOANGEL-LD (lesion detection) to assist in detecting all focal gastric lesions and predicting neoplasms by WLE.
Endoscopic images were retrospectively obtained from Renmin Hospital of Wuhan University (RHWU) for the development, validation, and internal test of the system. Additional external tests were conducted in 5 other hospitals to evaluate the robustness. Stored videos from RHWU were used for assessing and comparing the performance of ENDOANGEL-LD with that of experts. Prospective consecutive patients undergoing upper endoscopy were enrolled from May 6, 2021 to August 2, 2021 in RHWU to assess clinical practice applicability.
Over 10,000 patients undergoing upper endoscopy were enrolled in this study. The sensitivities were 96.9% and 95.6% for detecting gastric lesions and 92.9% and 91.7% for diagnosing neoplasms in internal and external patients, respectively. In 100 videos, ENDOANGEL-LD achieved superior sensitivity and negative predictive value for detecting gastric neoplasms from that of experts (100% vs 85.5% ± 3.4% [P = .003] and 100% vs 86.4% ± 2.8% [P = .002], respectively). In 2010 prospective consecutive patients, ENDOANGEL-LD achieved a sensitivity of 92.8% for detecting gastric lesions with 3.04 ± 3.04 false positives per gastroscopy and a sensitivity of 91.8% and specificity of 92.4% for diagnosing neoplasms.
Our results show that ENDOANGEL-LD has great potential for assisting endoscopists in screening gastric lesions and suspicious neoplasms in clinical work. (Clinical trial registration number: ChiCTR2100045963.)
Artificial Intelligence and the Future of Gastroenterology and Hepatology
2022, Gastro Hep Advances
The integration of artificial intelligence (AI) into gastroenterology and hepatology (GI) will inevitably transform the practice of GI in the coming decade. While the application of AI in health care is not new, advancements are occurring rapidly, and the future landscape of AI is beginning to come into focus. From endoscopic assistance via computer vision technology to the predictive capabilities of the vast information contained in the electronic health records, AI promises to optimize and expedite clinical and procedural practice and research in GI. The extensive body of literature already available on AI applications in gastroenterology may seem daunting at first; however, this review aims to provide a breakdown of the key studies conducted thus far and demonstrate the many potential ways this technology may impact the field. This review will also take a look into the future and imagine how GI can be transformed over the coming years, as well as potential limitations and pitfalls that must be overcome to realize this future.
Advanced endoscopic imaging for detection of Barrett's esophagus
2024, Clinical Endoscopy
Research progress of artificial intelligence in esophageal diseases
2023, Chinese Journal of Digestive Endoscopy

View all citing articles on Scopus

: DISCLOSURE: The following author disclosed financial relationships relevant to this publication: J. J. Bergman: Research support recipient from Ninepoint Medical, Olympus Endoscopy, Erbe, and Fujifilm; consultant for Olympus Endoscopy and Fujifilm. All other authors disclosed no financial relationships relevant to this publication. Research support for this study was provided by an unrestricted grant from NinePoint Medical Inc.

: See CME section; p. 903.

View full text

Original articleClinical endoscopyComputer-aided detection of early Barrett’s neoplasia using volumetric laser endomicroscopy

Background and Aims

Methods

Results

Conclusions

Section snippets

Patients and image database

Patients and VLE-histology database

Discussion

Gastrointest Endosc

Gastroenterology

Gastrointest Endosc

Gastrointest Endosc

Gastrointest Endosc

Esophageal adenocarcinoma incidence: Are we reaching the peak?

Cancer Epidemiol Biomarkers Prev

British Society of Gastroenterology guidelines on the diagnosis and management of Barrett’s oesophagus

Gut

ACG Clinical Guideline: diagnosis and management of Barrett’s esophagus

Am J Gastroenterol

Safety and feasibility of volumetric laser endomicroscopy in patients with Barrett’s esophagus (with videos)

Gastrointest Endosc

Identification of volumetric laser endomicroscopy features predictive for early neoplasia in Barrett’s esophagus using high-quality histological correlation

Gastrointest Endosc

Comparative diagnostic performance of volumetric laser endomicroscopy and confocal laser endomicroscopy in the detection of dysplasia associated with Barrett’s esophagus

Gastrointest Endosc

Original article
Clinical endoscopy
Computer-aided detection of early Barrett’s neoplasia using volumetric laser endomicroscopy