Introduction

Diagnosis and characterization of biliary strictures are challenging. The introduction of digital single-operator cholangioscopy (D-SOC) significantly improved the diagnostic yield of indeterminate biliary strictures. Pilot studies using artificial intelligence (AI) algorithms applied to D-SOC have shown promising results. We aimed to develop an AI system based on convolutional neural networks (CNN) for the automatic detection and characterization of malignant biliary strictures in D-SOC images.

Aims & Methods

Our group developed, trained, and validated a CNN based on D-SOC images from two centers in Portugal and Spain. Each frame was labeled as normal/benign findings or as a malignant lesion if histopathological evidence of biliary malignancy was available. Also, we evaluated the network's performance for detecting morphologic features, including tumor vessels, papillary projections, and nodules. The image dataset was split for the constitution of training and validation datasets. The performance of the CNN was measured by calculating the area under the curve (AUC), sensitivity, specificity, and positive and negative predictive values (PPV and NPV, respectively).

Results

A total of 84994 images from 130 D-SOC exams were included (44743 of malignant strictures and 40521 of benign findings). The model had an overall accuracy of 98.3%, a sensitivity of 98.3%, a specificity of 98.3%, and an AUROC of 1.00.
Our group evaluated the performance of the CNN for the detection of morphological characteristics associated with malignancy, particularly tumor vessels and papillary projection. The CNN detected tumor vessels with a sensitivity of 95.7%, a specificity of 88.6%, and an overall accuracy of 93.0%. Papillary projections were identified by the CNN with a sensitivity of 74.1%, a specificity of 94.5%, and an overall accuracy of 91.2%.
The CNN completed the reading of the 4250 batches of images (each batch comprising 128 images) in 23 minutes and 16 seconds, which can be translated to an approximate reading rate of 390 frames per second.

Conclusion

The developed deep learning algorithm accurately detected and differentiated malignant strictures from benign biliary conditions. Furthermore, the AI model provided accurate morphological characterization of the biliary strictures.
The potential of deep learning algorithms to impact the care of patients with suspected biliary malignancy is vast. This study assessed the performance of a CNN for detecting and differentiating malignant and benign biliary disorders using a large pool of D-SOC images. The excellent performance of this model lays the foundations for future exploration of AI technologies in this subset of patients, aiming to improve the clinical outcome of patients with suspected biliary malignancy.

References

1 Larghi A, Tringali A, Lecca PG, Giordano M, Costamagna G. Management of hilar biliary strictures. Am J Gastroenterol. 2008;103(2):458-73.
2 Tummala P, Munigala S, Eloubeidi MA, Agarwal B. Patients with obstructive jaundice and biliary stricture ± mass lesion on imaging: prevalence of malignancy and potential role of EUS-FNA. J Clin Gastroenterol. 2013;47(6):532-7.
3 Paranandi B, Oppong KW. Biliary strictures: endoscopic assessment and management. Frontline Gastroenterol. 2017;8(2):133-7.
4 Singhi AD, Slivka A. Evaluation of indeterminate biliary strictures: Is there life on MARS? Gastrointestinal Endoscopy. 2020;92(2):320-2.
5 Burnett AS, Calvert TJ, Chokshi RJ. Sensitivity of endoscopic retrograde cholangiopancreatography standard cytology: 10-y review of the literature. J Surg Res. 2013;184(1):304-11.
6 Navaneethan U, Njei B, Lourdusamy V, Konjeti R, Vargo JJ, Parsi MA. Comparative effectiveness of biliary brush cytology and intraductal biopsy for detection of malignant biliary strictures: a systematic review and meta-analysis. Gastrointest Endosc. 2015;81(1):168-76.
7 Pereira P, Vilas-Boas F, Peixoto A, Andrade P, Lopes J, Macedo G. How SpyGlass™ May Impact Endoscopic Retrograde Cholangiopancreatography Practice and Patient Management. GE Port J Gastroenterol. 2018;25(3):132-7.

Introduction

Type 1 autoimmune pancreatitis (AIP) represents the most common manifestation of IgG4-related disease. Type 1 AIP responds well to glucocorticoids, but relapses are common requiring multiple treatment courses and ultimately leading to end-organ damage and treatment-related morbidity. To date, scant reports exist on the long-term outcomes of these patients. Moreover, the role of maintenance treatment in preventing disease relapse is still debated.

Aims & Methods

We aimed to evaluate the long-term outcomes of a large European cohort of patients with type 1 AIP and to assess the role of maintenance treatment in preventing disease relapse. Patients with type 1 AIP fulfilling ICDC criteria were included in this multicentric retrospective study within the PrescrAIP framework involving 40 European university Hospital. Relapses were defined as new onset of either AIP related symptoms or radiological abnormalities after a successful induction of remission. Patients without either complete or partial remission were excluded. The primary endpoint was time to relapse. Predictors of relapse were identified by multivariable logistic regression. A bootstrapping technique was performed to internally validate the model. Regression coefficients from the multivariable model were employed to develop a score for computing the risk of relapse for each patient. Patients were divided into four categories according to the score, from the lowest to highest risk of relapse.

Results

477 patients were included in this analysis (325 male, 68%). Mean age at baseline was 59 (IQR 40-68). 60% of the patients presented with jaundice while 7% of the patient with acute pancreatitis. Other organs involvement was present in 238 patients (48%), being biliary involvement the most frequent one (40%). At baseline, diabetes mellitus and pancreatic exocrine insufficiency were present in 30% and 27% of patients, respectively. After a mean follow up of 32 months (IQR 13-68), 150 (31%) AIP relapses occurred. After accounting for confounders, biliary tree involvement (OR 1.62 95%CI 1.1-2.2), acute pancreatitis at baseline (OR 2.1 95%CI 1.1-4.2), narrowing of the main pancreatic duct (OR 1.6, 95%CI 1.1-2.1) were independently associated with relapse, while AIP presenting as a focal mass resulted in a protective factor (OR 0.65 95%CI 0.46-0.92). Increased serum IgG4 level (OR 1.2 95%CI 0.9-1.7) pointed to higher relapse rate without reaching statistical significance. Notably, any maintenance treatment reduced the relapse rate after correcting for the above-mentioned risk factors (OR 0.51, 95%CI 0.37-0.72). There was no difference in term of relapse free survival between maintenance treatment with any anti-rheumatic drugs (azathioprine, methotrexate, mycophenolate) and low-dose GCs. Maintenance treatment reduced relapse rate only in patients with higher relapse risk. At the longest follow up, DM and PEI were recorded in 33% and 29% of the patients, respectively. Only one pancreatic cancer was detected.

Conclusion

Several disease features increase the risk of relapse in type 1 AIP. Any of the maintenance treatment reduce relapse rate in type 1 AIP. Patients showing multiple risk factors for relapse benefit the most from maintenance treatment. The development of a score predicting disease relapse enhances a personalized approach toward AIP treatment. In European AIP patients the development of pancreatic cancer during follow up appears rare.