Early neoplasia in Barrett's esophagus is difficult to detect and often overlooked during Barrett's surveillance. An automatic detection system could be beneficial, by assisting endoscopists with ...detection of early neoplastic lesions. The aim of this study was to assess the feasibility of a computer system to detect early neoplasia in Barrett's esophagus.
Based on 100 images from 44 patients with Barrett's esophagus, a computer algorithm, which employed specific texture, color filters, and machine learning, was developed for the detection of early neoplastic lesions in Barrett's esophagus. The evaluation by one endoscopist, who extensively imaged and endoscopically removed all early neoplastic lesions and was not blinded to the histological outcome, was considered the gold standard. For external validation, four international experts in Barrett's neoplasia, who were blinded to the pathology results, reviewed all images.
The system identified early neoplastic lesions on a per-image analysis with a sensitivity and specificity of 0.83. At the patient level, the system achieved a sensitivity and specificity of 0.86 and 0.87, respectively. A trade-off between the two performance metrics could be made by varying the percentage of training samples that showed neoplastic tissue.
The automated computer algorithm developed in this study was able to identify early neoplastic lesions with reasonable accuracy, suggesting that automated detection of early neoplasia in Barrett's esophagus is feasible. Further research is required to improve the accuracy of the system and prepare it for real-time operation, before it can be applied in clinical practice.
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.
Endoscopic techniques such as high-definition and optical-chromoendoscopy have had enormous impact on endoscopy practice. Since these techniques allow assessment of most subtle morphological mucosal ...abnormalities, further improvements in endoscopic practice lay in increasing the detection efficacy of endoscopists. Several new developments could assist in this. First, web based training tools could improve the skills of the endoscopist for enhancing the detection and classification of lesions. Secondly, incorporation of computer aided detection will be the next step to raise endoscopic quality of the captured data. These systems will aid the endoscopist in interpreting the increasing amount of visual information in endoscopic images providing real-time objective second reading. In addition, developments in the field of molecular imaging open opportunities to add functional imaging data, visualizing biological parameters, of the gastrointestinal tract to white-light morphology imaging. For the successful implementation of abovementioned techniques, a true multi-disciplinary approach is of vital importance.
We aimed to develop and validate a deep-learning computer-aided detection (CAD) system, suitable for use in real time in clinical practice, to improve endoscopic detection of early neoplasia in ...patients with Barrett’s esophagus (BE).
We developed a hybrid ResNet-UNet model CAD system using 5 independent endoscopy data sets. We performed pretraining using 494,364 labeled endoscopic images collected from all intestinal segments. Then, we used 1704 unique esophageal high-resolution images of rigorously confirmed early-stage neoplasia in BE and nondysplastic BE, derived from 669 patients. System performance was assessed by using data sets 4 and 5. Data set 5 was also scored by 53 general endoscopists with a wide range of experience from 4 countries to benchmark CAD system performance. Coupled with histopathology findings, scoring of images that contained early-stage neoplasia in data sets 2–5 were delineated in detail for neoplasm position and extent by multiple experts whose evaluations served as the ground truth for segmentation.
The CAD system classified images as containing neoplasms or nondysplastic BE with 89% accuracy, 90% sensitivity, and 88% specificity (data set 4, 80 patients and images). In data set 5 (80 patients and images) values for the CAD system vs those of the general endoscopists were 88% vs 73% accuracy, 93% vs 72% sensitivity, and 83% vs 74% specificity. The CAD system achieved higher accuracy than any of the individual 53 nonexpert endoscopists, with comparable delineation performance. CAD delineations of the area of neoplasm overlapped with those from the BE experts in all detected neoplasia in data sets 4 and 5. The CAD system identified the optimal site for biopsy of detected neoplasia in 97% and 92% of cases (data sets 4 and 5, respectively).
We developed, validated, and benchmarked a deep-learning computer-aided system for primary detection of neoplasia in patients with BE. The system detected neoplasia with high accuracy and near-perfect delineation performance. The Netherlands National Trials Registry, Number: NTR7072
Display omitted
Recently the Endoscopic Reference Score (EREFS) for endoscopic assessment of eosinophilic esophagitis was introduced, with good interobserver agreement for most signs. The EREFS has not yet been ...evaluated by other investigators and intraobserver agreement has not been assessed. The aim of this study was to further validate the EREFS by assessing interobserver and intraobserver agreement of endoscopic signs in patients with eosinophilic esophagitis.
High-quality endoscopic images were made of the esophagus of 30 patients with eosinophilic esophagitis (age 36 years, range 23 - 46 years; 5 female), 6 of whom were in remission. At least three depersonalized images per patient were incorporated into a slideshow. Images were scored by four expert and four trainee endoscopists who were blinded to the patients' conditions. Interobserver agreement was assessed. After 4 weeks, the images were rescored in a different order to assess intraobserver agreement.
Interobserver agreement was substantial for rings (κ 0.70), white exudates (κ 0.63), and crepe paper esophagus (κ 0.62), moderate for furrows (κ 0.49) and strictures (κ 0.54), and slight for edema (κ 0.12). Intraobserver agreement was substantial for rings (median κ 0.64, IQR 0.46 - 0.70), furrows (median κ 0.69, IQR 0.50 - 0.89), and crepe paper esophagus (median κ 0.69, IQR 0.62 - 0.83), moderate for white exudates (median κ 0.58, IQR 0.54 - 0.71) and strictures (median κ 0.54, IQR 0.33 - 0.70), and less than chance for edema (median κ 0.00, IQR 0.00 - 0.29). Inter- and intraobserver agreement was not substantially different between expert and trainee endoscopists.
Using the EREFS, endoscopic signs of eosinophilic esophagitis were scored consistently by expert and trainee endoscopists.
There has been a vast increase in GI literature focused on the use of machine learning in endoscopy. The relative novelty of this field poses a challenge for reviewers and readers of GI journals. To ...appreciate scientific quality and novelty of machine learning studies, understanding of the technical basis and commonly used techniques is required. Clinicians often lack this technical background, while machine learning experts may be unfamiliar with clinical relevance and implications for daily practice. Therefore, there is an increasing need for a multidisciplinary, international evaluation on how to perform high-quality machine learning research in endoscopy. This review aims to provide guidance for readers and reviewers of peer-reviewed GI journals to allow critical appraisal of the most relevant quality requirements of machine learning studies. The paper provides an overview of common trends and their potential pitfalls and proposes comprehensive quality requirements in six overarching themes: terminology, data, algorithm description, experimental setup, interpretation of results and machine learning in clinical practice.
Published data on the natural history of low-grade dysplasia (LGD) in Barrett's esophagus (BE) are inconsistent and difficult to interpret. We investigated the natural history of LGD in a large ...community-based cohort of BE patients after reviewing the original histological diagnosis by an expert panel of pathologists.
Histopathology reports of all patients diagnosed with LGD between 2000 and 2006 in six non-university hospitals were reviewed by two expert pathologists. This panel diagnosis was subsequently compared with the histological outcome during prospective endoscopic follow-up.
A diagnosis of LGD was made in 147 patients. After pathology review, 85% of the patients were downstaged to non-dysplastic BE (NDBE) or to indefinite for dysplasia. In only 15% of the patients was the initial diagnosis LGD. Endoscopic follow-up was carried out in 83.6% of patients, with a mean follow-up of 51.1 months. For patients with a consensus diagnosis of LGD, the cumulative risk of progressing to high-grade dysplasia or carcinoma (HGD or Ca) was 85.0% in 109.1 months compared with 4.6% in 107.4 months for patients downstaged to NDBE (P<0.0001). The incidence rate of HGD or Ca was 13.4% per patient per year for patients in whom the diagnosis of LGD was confirmed. For patients downstaged to NDBE, the corresponding incidence rate was 0.49%.
LGD in BE is an overdiagnosed and yet underestimated entity in general practice. Patients diagnosed with LGD should undergo an expert pathology review to purify this group. In case the diagnosis of LGD is confirmed, patients should undergo strict endoscopic follow-up or should be considered for endoscopic ablation therapy.
We assessed the preliminary diagnostic accuracy of a recently developed computer-aided detection (CAD) system for detection of Barrett’s neoplasia during live endoscopic procedures.
The CAD system ...was tested during endoscopic procedures in 10 patients with nondysplastic Barrett’s esophagus (NDBE) and 10 patients with confirmed Barrett’s neoplasia. White-light endoscopy images were obtained at every 2-cm level of the Barrett’s segment and immediately analyzed by the CAD system, providing instant feedback to the endoscopist. At every level, 3 images were evaluated by the CAD system. Outcome measures were diagnostic performance of the CAD system per level and per patient, defined as accuracy, sensitivity, and specificity (ground truth was established by expert assessment and corresponding histopathology), and concordance of 3 sequential CAD predictions per level.
Accuracy, sensitivity, and specificity of the CAD system in a per-level analyses were 90%, 91%, and 89%, respectively. Nine of 10 neoplastic patients were correctly diagnosed. The single lesion not detected by CAD showed NDBE in the endoscopic resection specimen. In only 1 NDBE patient, the CAD system produced false-positive predictions. In 75% of all levels, the CAD system produced 3 concordant predictions.
This is one of the first studies to evaluate a CAD system for Barrett’s neoplasia during live endoscopic procedures. The system detected neoplasia with high accuracy, with only a small number of false-positive predictions and with a high concordance rate between separate predictions. The CAD system is thereby ready for testing in larger, multicenter trials. (Clinical trial registration number: NL7544.)
The endoscopic evaluation of narrow-band imaging (NBI) zoom imagery in Barrett’s esophagus (BE) is associated with suboptimal diagnostic accuracy and poor interobserver agreement. Computer-aided ...diagnosis (CAD) systems may assist endoscopists in the characterization of Barrett’s mucosa. Our aim was to demonstrate the feasibility of a deep-learning CAD system for tissue characterization of NBI zoom imagery in BE.
The CAD system was first trained using 494,364 endoscopic images of general endoscopic imagery. Next, 690 neoplastic BE and 557 nondysplastic BE (NDBE) white-light endoscopy overview images were used for refinement training. Subsequently, a third dataset of 112 neoplastic and 71 NDBE NBI zoom images with histologic correlation was used for training and internal validation. Finally, the CAD system was further trained and validated with a fourth, histologically confirmed dataset of 59 neoplastic and 98 NDBE NBI zoom videos. Performance was evaluated using fourfold cross-validation. The primary outcome was the diagnostic performance of the CAD system for classification of neoplasia in NBI zoom videos.
The CAD system demonstrated accuracy, sensitivity, and specificity for detection of BE neoplasia using NBI zoom images of 84%, 88%, and 78%, respectively. In total, 30,021 individual video frames were analyzed by the CAD system. Accuracy, sensitivity, and specificity of the video-based CAD system were 83% (95% confidence interval CI, 78%-89%), 85% (95% CI, 76%-94%), and 83% (95% CI, 76%-90%), respectively. The mean assessment speed was 38 frames per second.
We have demonstrated promising diagnostic accuracy of predicting the presence/absence of Barrett’s neoplasia on histologically confirmed unaltered NBI zoom videos with fast corresponding assessment time.
Reported malignant progression rates for low-grade dysplasia (LGD) in Barrett's oesophagus (BO) vary widely. Expert histological review of LGD is advised, but limited data are available on its ...clinical value. This retrospective cohort study aimed to determine the value of an expert pathology panel organised in the Dutch Barrett's Advisory Committee (BAC) by investigating the incidence rates of high-grade dysplasia (HGD) and oesophageal adenocarcinoma (OAC) after expert histological review of LGD.
We included all BO cases referred to the BAC for histological review of LGD diagnosed between 2000 and 2011. The diagnosis of the expert panel was related to the histological outcome during endoscopic follow-up. Primary endpoint was development of HGD or OAC.
293 LGD patients (76% men; mean 63 years±11.9) were included. Following histological review, 73% was downstaged to non-dysplastic BO (NDBO) or indefinite for dysplasia (IND). In 27% the initial LGD diagnosis was confirmed. Endoscopic follow-up was performed in 264 patients (90%) with a median follow-up of 39 months (IQR 16-72). For confirmed LGD, the risk of HGD/OAC was 9.1% per patient-year. Patients downstaged to NDBO or IND had a malignant progression risk of 0.6% and 0.9% per patient-year, respectively.
Confirmed LGD in BO has a markedly increased risk of malignant progression. However, the vast majority of patients with community LGD will be downstaged after expert review and have a low progression risk. Therefore, all BO patients with LGD should undergo expert histological review of the diagnosis for adequate risk stratification.