Fully automated detection of primary sclerosing cholangitis (PSC)-compatible bile duct changes based on 3D magnetic resonance cholangiopancreatography using machine learning
Autor: | Bertil Schmidt, Henrike Lenzen, Frank Wacker, Kristina Ringe, Hinrich B. Winther, Michael P. Manns, Van Dai Vo Chieu, Christian Hundt |
---|---|
Rok vydání: | 2020 |
Předmět: |
medicine.medical_specialty
Medizin Overfitting Machine learning computer.software_genre 030218 nuclear medicine & medical imaging Primary sclerosing cholangitis 03 medical and health sciences 0302 clinical medicine medicine Radiology Nuclear Medicine and imaging Neuroradiology Magnetic resonance cholangiopancreatography Artificial neural network medicine.diagnostic_test business.industry Deep learning General Medicine medicine.disease 030220 oncology & carcinogenesis Maximum intensity projection Radiology Artificial intelligence Transfer of learning business computer |
Zdroj: | European Radiology. 31:2482-2489 |
ISSN: | 1432-1084 0938-7994 |
Popis: | To develop and evaluate a deep learning algorithm for fully automated detection of primary sclerosing cholangitis (PSC)-compatible cholangiographic changes on three-dimensional magnetic resonance cholangiopancreatography (3D-MRCP) images. The datasets of 428 patients (n = 205 with confirmed diagnosis of PSC; n = 223 non-PSC patients) referred for MRI including MRCP were included in this retrospective IRB-approved study. Datasets were randomly assigned to a training (n = 386) and a validation group (n = 42). For each case, 20 uniformly distributed axial MRCP rotations and a subsequent maximum intensity projection (MIP) were calculated, resulting in a training database of 7720 images and a validation database of 840 images. Then, a pre-trained Inception ResNet was implemented which was conclusively fine-tuned (learning rate 10−3). Applying an ensemble strategy (by binning of the 20 axial projections), the mean absolute error (MAE) of the developed deep learning algorithm for detection of PSC-compatible cholangiographic changes was lowered from 21 to 7.1%. Sensitivity, specificity, positive predictive (PPV), and negative predictive value (NPV) for detection of these changes were 95.0%, 90.9%, 90.5%, and 95.2% respectively. The results of this study demonstrate the feasibility of transfer learning in combination with extensive image augmentation to detect PSC-compatible cholangiographic changes on 3D-MRCP images with a high sensitivity and a low MAE. Further validation with more and multicentric data is now desirable, as it is known that neural networks tend to overfit the characteristics of the dataset. • The described machine learning algorithm is able to detect PSC-compatible cholangiographic changes on 3D-MRCP images with high accuracy. • The generation of 2D projections from 3D datasets enabled the implementation of an ensemble strategy to boost inference performance. |
Databáze: | OpenAIRE |
Externí odkaz: |