Advanced liver fibrosis detection using a two-stage deep learning approach on standard T2-weighted MRI.
Objectives: To develop and validate a deep learning model for automated detection of advanced liver fibrosis using standard T2-weighted MRI. Methods: We utilized two datasets: the public CirrMRI600 + dataset (n = 374) containing T2-weighted MRI scans from patients with cirrhosis (n = 318) and health...
| Published in: | Abdominal Radiology Vol. 51; no. 4; pp. 1770 - 1783 |
|---|---|
| Main Authors: | , , , , , , , , , , |
| Format: | Journal Article |
| Published: |
Springer Nature
Apr2026
|
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=192481145&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 192481145 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 2366004X JT14 jtl: Abdominal Radiology issn: 2366004X maglogo: N pubinfo: dt: Apr2026 vid: 51 iid: 4 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 192481145 187426031 10.1007/s00261-025-05160-y 192481145 ppf: 1770 ppct: 13 formats: fmt: – @attributes: type: T – @attributes: type: P tig: atl: Advanced liver fibrosis detection using a two-stage deep learning approach on standard T2-weighted MRI. aug: au: Gupta, Pankaj Singh, Shravya Gulati, Ajay Dutta, Niharika Aggarwal, Yashika Kalra, Naveen Premkumar, Madhumita Taneja, Sunil Verma, Nipun De, Arka Duseja, Ajay affil: Institute of Medical Education and Research, Chandigarh, India sug: ab: Objectives: To develop and validate a deep learning model for automated detection of advanced liver fibrosis using standard T2-weighted MRI. Methods: We utilized two datasets: the public CirrMRI600 + dataset (n = 374) containing T2-weighted MRI scans from patients with cirrhosis (n = 318) and healthy subjects (n = 56), and an in-house dataset of chronic liver disease patients (n = 187). A two-stage deep learning pipeline was developed: first, an automated liver segmentation model using nnU-Net architecture trained on CirrMRI600 + and then applied to segment livers in our in-house dataset; second, a Masked Attention ResNet classification model. For classification model training, patients with liver stiffness measurement (LSM) > 12 kPa were classified as advanced fibrosis (n = 104). In contrast, healthy subjects from CirrMRI600 + and patients with LSM ≤ 12 kPa were classified as non-advanced fibrosis (n = 116). Model validation was exclusively performed on a separate test set of 23 patients with histopathological confirmation of the degree of fibrosis (METAVIR ≥ F3 indicating advanced fibrosis). We additionally compared our two-stage approach with direct classification without segmentation, and evaluated alternative architectures including DenseNet121 and SwinTransformer. Results: The liver segmentation model performed excellently on the test set (mean Dice score: 0.960 ± 0.009; IoU: 0.923 ± 0.016). On the pathologically confirmed independent test set (n = 23), our two-stage model achieved strong diagnostic performance (sensitivity: 0.778, specificity: 0.800, AUC: 0.811, accuracy: 0.783), significantly outperforming direct classification without segmentation (AUC: 0.743). Classification performance was highly dependent on segmentation quality, with cases having excellent segmentation (Score 1) showing higher accuracy (0.818) than those with poor segmentation (Score 3, accuracy: 0.625). Alternative architectures with masked attention showed comparable but slightly lower performance (DenseNet121: AUC 0.795; SwinTransformer: AUC 0.782). Conclusions: Our fully automated deep learning pipeline effectively detects advanced liver fibrosis using standard non-contrast T2-weighted MRI, potentially offering a non-invasive alternative to current diagnostic approaches. The segmentation-first approach provides significant performance gains over direct classification. pubtype: Academic Journal doctype: Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|