Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Mar 20.
doi: 10.1097/HEP.0000000000001314. Online ahead of print.

Deep learning analysis of MRI accurately detects early-stage perihilar cholangiocarcinoma in patients with primary sclerosing cholangitis

Yashbir Singh  1 , John E Eaton  2 , Sudhakar K Venkatesh  1 , Christopher L Welle  1 , Byron Smith  3 , Shahriar Faghani  1 , Mette Vesterhus  4 , Tom H Karlsen  5 , Kristin K Jorgensen  5   6   7 , Trine Folseraas  5 , Kosta Petrovic  8 , Anne Negard  9 , Ida Bjoerk  10 , Andreas Abildgaard  10 , Aliya F Gulamhusein  11 , Kartik Jhaveri  12 , Gregory J Gores  2 , Sumera I Ilyas  2 , Timucin Taner  13 , Julie K Heimbach  13 , Ty S Diwan  13 , Nicholas F LaRusso  2 , Konstantinos N Lazaridis  2 , Bradley J Erickson  1
Affiliations

Deep learning analysis of MRI accurately detects early-stage perihilar cholangiocarcinoma in patients with primary sclerosing cholangitis

Yashbir Singh et al. Hepatology. .

Abstract

Background and aims: Among those with primary sclerosing cholangitis (PSC), perihilar cholangiocarcinoma (pCCA) is often diagnosed at a late stage and is a leading source of mortality. Detection of pCCA in PSC when curative action can be taken is challenging. Our aim was to create a deep learning model that analyzed MRI to detect early-stage pCCA and compare its diagnostic performance with expert radiologists.

Approach and results: We conducted a multicenter, international, retrospective cohort study involving adults with large duct PSC who underwent contrast-enhanced MRI. Senior abdominal radiologists reviewed the images. All patients with pCCA had early-stage cancer and were registered for liver transplantation. We trained a 3D DenseNet-121 model, a form of deep learning, using MRI images and assessed its performance in a separate test cohort. The study included 398 patients (training cohort n=150; test cohort n=248). pCCA was present in 230 individuals (training cohort n=64; test cohort n=166). In the test cohort, the respective performances of the model compared to the radiologists were: sensitivity 87.9% versus 50.0%, p <0.001; specificity 84.1% versus 100.0%, p <0.001; area under receiving operating curve 86.0% versus 75.0%, p <0.001. Even when a mass was absent, the model had a higher sensitivity for pCCA than radiologists (91.6% vs. 50.6%, p <0.001) and maintained good specificity (84.1%).

Conclusions: The 3D DenseNet-121 MRI model effectively detects early-stage pCCA in PSC patients. Compared to expert radiologists, the model missed fewer cases of cancer.

Keywords: artificial intelligence; cancer; convolutional neural network; deep learning; diagnosis.

PubMed Disclaimer

References

    1. Eaton JE, Talwalkar JA, Lazaridis KN, Gores GJ, Lindor KD. Pathogenesis of primary sclerosing cholangitis and advances in diagnosis and management. Gastroenterology. 2013;145:521–536.
    1. Eaton JE, Welle CL, Bakhshi Z, Sheedy SP, Idilman IS, Gores GJ, et al. Early cholangiocarcinoma detection with magnetic resonance imaging versus ultrasound in primary sclerosing cholangitis. Hepatology. 2021;73:1868–1881.
    1. Venkatesh SK, Welle CL, Miller FH, Jhaveri K, Ringe KI, Eaton JE, et al. Reporting standards for primary sclerosing cholangitis using MRI and MR cholangiopancreatography: Guidelines from MR Working Group of the International Primary Sclerosing Cholangitis Study Group. Eur Radiol. 2022;32:923–937.
    1. Bowlus CL, Arrive L, Bergquist A, Deneau M, Forman L, Ilyas SI, et al. AASLD practice guidance on primary sclerosing cholangitis and cholangiocarcinoma. Hepatology. 2023;77:659–702.
    1. Ali AH, Tabibian JH, Naser-Ghodsi N, Lennon RJ, DeLeon T, Borad MJ, et al. Surveillance for hepatobiliary cancers in patients with primary sclerosing cholangitis. Hepatology. 2018;67:2338–2351.

LinkOut - more resources