Centro Hospitalar de São João Porto, Porto, Portugal
Award: Presidential Poster Award
Joao Afonso, MD1, Miguel Mascarenhas, MD1, Tiago Ribeiro, MD1, João Ferreira, PhD2, Filipe Vilas Boas, MD1, Marco Parente, PhD2, Renato Natal, PhD2, Pedro Pereira, MD1, Guilherme Macedo, MD, PhD, FACG1 1Centro Hospitalar de São João, Porto, Porto, Portugal; 2University of Porto, Porto, Porto, Portugal
Introduction: The endoscopic approach to biliary stenosis remains a significative clinical challenge. The introduction of digital single-operator cholangioscopy (D-SOC) allowing direct visual inspection of the bile ducts and guided tissue sampling significantly increased the diagnostic yield in patients with indeterminate biliary strictures. The identification of dilated, irregular and tortuous vessels, often described as tumor vessels, is a frequent element in biliary strictures with a high probability of malignancy.
In recent years, the development of artificial intelligence (AI) algorithms for application to endoscopic practice has been intensely studied. Studies evaluating the application of these algorithms for the interpretation of endoscopic images has provided promising results. However, to date, the impact of these technological advances on cholangioscopy has not been assessed This study aimed to develop and validate a convolutional neural network (CNN) for automatic detection of tumor vessels in D-SOC images.
Methods: A deep learning algorithm was developed and trained for automatic recognition of tumor vessels in D-SOC images. A total of 6475 images from 85 patients who underwent D-SOC (Spyglass™, Boston Scientific, Marlborough, MA, USA). Each frame was classified by two endoscopists with experience in D-SOC (more than 100 exams each) regarding the presence or absence of tumor vessels. The malignancy diagnosis was histologically confirmed. This pool of images was subsequently divided for constitution of two distinct datasets for training (80%) and validation (20%) of the CNN. The performance of the CNN was measured by calculating the area under the receiving operating characteristic curve (AUC), sensitivity, specificity, positive and negative predictive values (PPV and NPV, respectively) – Figure 1.
Results: Our CNN had an overall accuracy of 99.3% for detection of tumor vessels. The sensitivity, specificity, PPV and NPV were 99.3%, 99.4%, 99.6% and 98.7%, respectively. The AUC was 1.00. The CNN had an image processing rate of 20 ms/frame.
Discussion: Our CNN was able to detect tumor vessels with high sensitivity, specificity, and accuracy. The incorporation of AI tools to D-SOC systems may significantly enhance the detection of macroscopic characteristics associated with high probability of biliary malignancy, thus optimizing the diagnostic workup of patients with indeterminate biliary strictures.
Figure: Figure 1: 1a - Output obtained from the application of the CNN. A blue bar represents a correct prediction. 1b - Evolution of the accuracy in predicting the diagnosis of tumor vessels by the CNN during training and validation phases, as the training and validation datasets were repeatedly inputted in the neural network. 1c - ROC analyses of the network’s performance. AUC: area under the curve; CNN: convolutional neural network; B: benign finding; TV: tumor vessels.
Disclosures: Joao Afonso indicated no relevant financial relationships. Miguel Mascarenhas indicated no relevant financial relationships. Tiago Ribeiro indicated no relevant financial relationships. João Ferreira indicated no relevant financial relationships. Filipe Vilas Boas indicated no relevant financial relationships. Marco Parente indicated no relevant financial relationships. Renato Natal indicated no relevant financial relationships. Pedro Pereira indicated no relevant financial relationships. Guilherme Macedo indicated no relevant financial relationships.
Joao Afonso, MD1, Miguel Mascarenhas, MD1, Tiago Ribeiro, MD1, João Ferreira, PhD2, Filipe Vilas Boas, MD1, Marco Parente, PhD2, Renato Natal, PhD2, Pedro Pereira, MD1, Guilherme Macedo, MD, PhD, FACG1. P0629 - Artificial Intelligence and Digital Single-operator Cholangioscopy: Automatic Identification of Tumor Vessels in Patients with Indeterminate Biliary Stenosis, ACG 2021 Annual Scientific Meeting Abstracts. Las Vegas, Nevada: American College of Gastroenterology.