Computer Aided Diagnosis for the Characterisation of Dysplasia in Barrett’s Oesophagus with Magnification Endoscopy

Aims There have been significant advances in magnification endoscopic imaging of Barrett’s oesophagus (BE). Magnification endoscopy of mucosal and vascular patterns arising in BE can help predict non-dysplastic from dysplastic mucosa. This can inform sampling and guide endoscopic eradication therapy. We aimed to develop a computer aided detection system that can support the diagnosis of BE dysplasia on magnification endoscopy.

Methods Videos were collected in high definition magnification white light and virtual chromoendoscopy with i-scan (Pentax Hoya, Japan) imaging modes in patients with dysplastic lesions in BE (high grade dysplasia (HGD)/intramucosal adenocarcinoma) and patients with non-dysplastic BE (NDBE). Endoscopic resection margins/targeted biopsy site histology served as the ground truth for dysplasia in videos. Videos were annotated for definite visual presence of dysplasia. We trained a convolutional neural network with a Resnet101 architecture to classify video frames into dysplastic or non-dysplastic using randomly selected frames from annotated videos.

Results 58 patients each with high quality video frames of magnification areas of BE (34 dysplasia, 24 NDBE) were included. Performance was evaluated using a 15-fold cross validation methodology. 76,496 (47,438 dysplasia, 29,058 NDBE) magnification video frames were analysed by the neural network. All dysplastic and non-dysplastic frames were included.

We used an exponentially weighted moving average of consecutive frames to make a diagnosis of dysplasia. The network achieved a per frame sensitivity of 82 %, specificity of 82 %, and Area under the ROC of 90 %. The mean assessment speed per frame was 0.0135 seconds (SD, ± 0.006).

Conclusions The neural network can characterise BE dysplasia with high accuracy and speed on magnification endoscopic images. Whole video frames were used to train and test the data moving it towards real time automated diagnosis. This will potentially aid endoscopists to make key decisions regarding endoscopic sampling and resection in BE during the same endoscopic session.

Citation: Hussein M, Lines D, Puyal JGB et al. OP13 COMPUTER AIDED DIAGNOSIS FOR THE CHARACTERISATION OF DYSPLASIA IN BARRETT’S OESOPHAGUS WITH MAGNIFICATION ENDOSCOPY. Endoscopy 2021; 53: S10.

Publikationsverlauf

Artikel online veröffentlicht:
19. März 2021