Detection of early neoplasia in Barrett’s esophagus using lectin-based near-infrared imaging: an ex vivo study on human tissue

Neves, André; Pietro, Massimiliano di; O’Donovan, Maria; Waterhouse, Dale J.; Bohndiek, Sarah E.; Brindle, Kevin M.; Fitzgerald, Rebecca C.

doi:10.1055/s-0043-124080

Cited by 21 publications

(30 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To truly establish the performance of the color-based classification in a clinically realistic scenario, hyperspectral data should in future be acquired from samples in which a more fine grained histopathological ground truth is available, for example, in mapped endoscopic mucosal resections 18,19 . Once available, the CNN could be more thoroughly tested and also further tailored for application in the discrimination of early cancer.…”

Section: Discussionmentioning

confidence: 99%

Deep learning applied to hyperspectral endoscopy for online spectral classification

Grigoroiu

Yoon

Bohndiek

2020

Sci Rep

View full text Add to dashboard Cite

Hyperspectral imaging (HSi) is being explored in endoscopy as a tool to extract biochemical information that may improve contrast for early cancer detection in the gastrointestinal tract. Motion artefacts during medical endoscopy have traditionally limited HSI application, however, recent developments in the field have led to real-time HSI deployments. Unfortunately, traditional HSI analysis methods remain unable to rapidly process the volume of hyperspectral data in order to provide real-time feedback to the operator. Here, a convolutional neural network (CNN) is proposed to enable online classification of data obtained during HSI endoscopy. A five-layered CNN was trained and fine-tuned on a dataset of 300 hyperspectral endoscopy images acquired from a planar Macbeth ColorChecker chart and was able to distinguish between its 18 constituent colors with an average accuracy of 94.3% achieved at 8.8 fps. Performance was then tested on a set of images simulating an endoscopy environment, consisting of color charts warped inside a rigid tube mimicking a lumen. The algorithm proved robust to such variations, with classification accuracies over 90% being obtained despite the variations, with an average drop in accuracy of 2.4% being registered at the points of longest working distance and most inclination. For further validation of the color-based classification system, ex vivo videos of a methylene blue dyed pig esophagus and images of different disease stages in the human esophagus were analyzed, showing spatially distinct color classifications. These results suggest that the CNN has potential to provide color-based classification during real-time HSI in endoscopy.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep learning applied to hyperspectral endoscopy for online spectral classification

Grigoroiu

Yoon

Bohndiek

2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Thus, molecular CLEM is considered to be a novel method for diagnosis of dysplastic Barrett’s lesions that allows for visualization of cellular processes in real-time by combinations of a variety of either molecular probes or peptides with fluorescent items. Moreover, near-infrared imaging endoscopy with fluorescence lectin was reported to be capable of differentiating neoplastic from non-dysplastic BE lesions [ 116 ]. Nagengast WB et al also reported that near-infrared imaging endoscopy with use of topical and systemic tracers of VEGFA were useful for diagnosis of neoplastic lesions in BE cases, as a higher detection rate was demonstrated as compared to not only WLE but also NBI endoscopy [ 117 ].…”

Section: Endoscopic Findings Showing Possible Predictive Biomarkermentioning

confidence: 99%

Is Malignant Potential of Barrett’s Esophagus Predictable by Endoscopy Findings?

Amano

Ishimura

Ishihara

2020

Life

View full text Add to dashboard Cite

Given that endoscopic findings can be used to predict the potential of neoplastic progression in Barrett’s esophagus (BE) cases, the detection rate of dysplastic Barrett’s lesions may become higher even in laborious endoscopic surveillance because a special attention is consequently paid. However, endoscopic findings for effective detection of the risk of neoplastic progression to esophageal adenocarcinoma (EAC) have not been confirmed, though some typical appearances are suggestive. In the present review, endoscopic findings that can be used predict malignant potential to EAC in BE cases are discussed. Conventional results obtained with white light endoscopy, such as length of BE, presence of esophagitis, ulceration, hiatal hernia, and nodularity, are used as indicators of a higher risk of neoplastic progression. However, there are controversies in some of those findings. Absence of palisade vessels may be also a new candidate predictor, as that reveals degree of intense inflammation and of cyclooxygenase-2 protein expression with accelerated cellular proliferation. Furthermore, an open type of mucosal pattern and enriched stromal blood vessels, which can be observed by image-enhanced endoscopy, including narrow band imaging, have been confirmed as factors useful for prediction of neoplastic progression of BE because they indicate more frequent cyclooxygenase-2 protein expression along with accelerated cellular proliferation. Should the malignant potential of BE be shown predictable by these endoscopic findings, that would simplify methods used for an effective surveillance, because patients requiring careful monitoring would be more easily identified. Development in the near future of a comprehensive scoring system for BE based on clinical factors, biomarkers and endoscopic predictors is required.

show abstract

“…FME employs fluorescently labeled probes, administered either topically or systemically, and an endoscopic detection system to visualize specific fluorescence in a range not affected by natural autofluorescence (typically in the near‐infrared range). Examples of molecular probes used so far for Barrett's dysplasia include the antivascular endothelial growth factor A (VEGFA) antibody bevacizumab, wheat germ agglutinin, which probes cancer‐related surface glycoprotein, and a synthetic polypeptide ASYNYDA, which likely binds cyclophilin A . These detection modalities have only been validated ex vivo or in very small and selected patient cohorts and will require further studies to prove their potential in Barrett's dysplasia detection.…”

Section: Surveillancementioning

confidence: 99%

Recent advances in Barrett's esophagus

Inadomi

Alastal

Bonavina

et al. 2018

Annals of the New York Academy of Sciences

Self Cite

View full text Add to dashboard Cite

Barrett's esophagus (BE) is the only known precursor of esophageal adenocarcinoma, one of the few cancers with increasing incidence in developed countries. The pathogenesis of BE is unclear with regard to either the cellular origin of this metaplastic epithelium or the manner in which malignant transformation occurs, although recent data indicate a possible junctional origin of stem cells for BE. Treatment of BE may be achieved using endoscopic eradication therapy; however, there is a lack of discriminatory tools to identify individuals at sufficient risk for cancer development in whom intervention is warranted. Reduction in gastroesophageal reflux of gastric contents including acid is mandatory to achieve remission from BE after endoscopic ablation, and can be achieved using medical or nonmedical interventions. Research topics of greatest interest include the mechanism of BE development and transformation to cancer, risk stratification methods to identify individuals who may benefit from ablation of BE, optimization of eradication therapy, and surveillance methods to ensure that remission is maintained after eradication is achieved.

show abstract

Detection of early neoplasia in Barrett’s esophagus using lectin-based near-infrared imaging: an ex vivo study on human tissue

Cited by 21 publications

References 19 publications

Deep learning applied to hyperspectral endoscopy for online spectral classification

Deep learning applied to hyperspectral endoscopy for online spectral classification

Is Malignant Potential of Barrett’s Esophagus Predictable by Endoscopy Findings?

Recent advances in Barrett's esophagus

Contact Info

Product

Resources

About