LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learning
Background: Hepatocellular carcinoma (HCC) is often diagnosed using gadoxetate disodium-enhanced magnetic resonance imaging (EOB-MRI). Standardized reporting according to the Liver Imaging Reporting and Data System (LI-RADS) can improve Gd-MRI interpretation but is rather complex and time-consuming....
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
17 March 2025
|
| In: |
Cancer imaging
Year: 2025, Jahrgang: 25, Pages: 1-17 |
| ISSN: | 1470-7330 |
| DOI: | 10.1186/s40644-025-00844-6 |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.1186/s40644-025-00844-6
|
| Verfasserangaben: | Róbert Stollmayer, Selda Güven, Christian Marcel Heidt, Kai Schlamp, Pál Novák Kaposi, Oyunbileg von Stackelberg, Hans-Ulrich Kauczor, Miriam Klauss and Philipp Mayer |
MARC
| LEADER | 00000naa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1933106581 | ||
| 003 | DE-627 | ||
| 005 | 20250813110927.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 250813s2025 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1186/s40644-025-00844-6 |2 doi | |
| 035 | |a (DE-627)1933106581 | ||
| 035 | |a (DE-599)KXP1933106581 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Stollmayer, Róbert |e VerfasserIn |0 (DE-588)1345106033 |0 (DE-627)1905866100 |4 aut | |
| 245 | 1 | 0 | |a LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learning |c Róbert Stollmayer, Selda Güven, Christian Marcel Heidt, Kai Schlamp, Pál Novák Kaposi, Oyunbileg von Stackelberg, Hans-Ulrich Kauczor, Miriam Klauss and Philipp Mayer |
| 264 | 1 | |c 17 March 2025 | |
| 300 | |b Illustrationen | ||
| 300 | |a 17 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 13.08.2025 | ||
| 520 | |a Background: Hepatocellular carcinoma (HCC) is often diagnosed using gadoxetate disodium-enhanced magnetic resonance imaging (EOB-MRI). Standardized reporting according to the Liver Imaging Reporting and Data System (LI-RADS) can improve Gd-MRI interpretation but is rather complex and time-consuming. These limitations could potentially be alleviated using recent deep learning-based segmentation and classification methods such as nnU-Net. The study aims to create and evaluate an automatic segmentation model for HCC risk assessment, according to LI-RADS v2018 using nnU-Net. Methods: For this single-center retrospective study, 602 patients at risk for HCC were included, who had dynamic EOB-MRI examinations between 05/2005 and 09/2022, containing ≥ LR-3 lesion(s). Manual lesion segmentations in semantic segmentation masks as LR-3, LR-4, LR-5 or LR-M served as ground truth. A set of U-Net models with 14 input channels was trained using the nnU-Net framework for automatic segmentation. Lesion detection, LI-RADS classification, and instance segmentation metrics were calculated by post-processing the semantic segmentation outputs of the final model ensemble. For the external evaluation, a modified version of the LiverHccSeg dataset was used. Results: The final training/internal test/external test cohorts included 383/219/16 patients. In the three cohorts, LI-RADS lesions (≥ LR-3 and LR-M) ≥ 10 mm were detected with sensitivities of 0.41–0.85/0.40–0.90/0.83 (LR-5: 0.85/0.90/0.83) and positive predictive values of 0.70–0.94/0.67–0.88/0.90 (LR-5: 0.94/0.88/0.90). F1 scores for LI-RADS classification of detected lesions ranged between 0.48–0.69/0.47–0.74/0.84 (LR-5: 0.69/0.74/0.84). Median per lesion Sørensen–Dice coefficients were between 0.61–0.74/0.52–0.77/0.84 (LR-5: 0.74/0.77/0.84). Conclusion: Deep learning-based HCC risk assessment according to LI-RADS can be implemented as automatically generated tumor risk maps using out-of-the-box image segmentation tools with high detection performance for LR-5 lesions. Before translation into clinical practice, further improvements in automatic LI-RADS classification, for example through large multi-center studies, would be desirable. | ||
| 650 | 4 | |a Clinical guidelines | |
| 650 | 4 | |a Deep learning | |
| 650 | 4 | |a Hepatocellular carcinoma | |
| 650 | 4 | |a Multiparametric MRI | |
| 700 | 1 | |a Güven, Selda |e VerfasserIn |4 aut | |
| 700 | 1 | |a Heidt, Christian |e VerfasserIn |0 (DE-588)1312342420 |0 (DE-627)187212755X |4 aut | |
| 700 | 1 | |a Schlamp, Kai |d 1976- |e VerfasserIn |0 (DE-588)14182641X |0 (DE-627)631821422 |0 (DE-576)326357254 |4 aut | |
| 700 | 1 | |a Kaposi, Pál Novák |e VerfasserIn |4 aut | |
| 700 | 1 | |a Stackelberg, Oyunbileg von |e VerfasserIn |0 (DE-588)1071738429 |0 (DE-627)826301487 |0 (DE-576)433285168 |4 aut | |
| 700 | 1 | |a Kauczor, Hans-Ulrich |d 1962- |e VerfasserIn |0 (DE-588)139267123 |0 (DE-627)70327113X |0 (DE-576)310955327 |4 aut | |
| 700 | 1 | |a Klauß, Miriam |d 1978- |e VerfasserIn |0 (DE-588)130870552 |0 (DE-627)506783839 |0 (DE-576)29838728X |4 aut | |
| 700 | 1 | |a Mayer, Philipp |d 1985- |e VerfasserIn |0 (DE-588)1066605440 |0 (DE-627)817714758 |0 (DE-576)426052250 |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Cancer imaging |d London : BioMed Central, 2000 |g 25(2025), Artikel-ID 36, Seite 1-17 |h Online-Ressource |w (DE-627)36374732X |w (DE-600)2104862-9 |w (DE-576)34726624X |x 1470-7330 |7 nnas |a LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learning |
| 773 | 1 | 8 | |g volume:25 |g year:2025 |g elocationid:36 |g pages:1-17 |g extent:17 |a LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learning |
| 856 | 4 | 0 | |u https://doi.org/10.1186/s40644-025-00844-6 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20250813 | ||
| 993 | |a Article | ||
| 994 | |a 2025 | ||
| 998 | |g 1066605440 |a Mayer, Philipp |m 1066605440:Mayer, Philipp |d 910000 |d 911400 |e 910000PM1066605440 |e 911400PM1066605440 |k 0/910000/ |k 1/910000/911400/ |p 9 |y j | ||
| 998 | |g 130870552 |a Klauß, Miriam |m 130870552:Klauß, Miriam |d 910000 |d 911400 |d 50000 |e 910000PK130870552 |e 911400PK130870552 |e 50000PK130870552 |k 0/910000/ |k 1/910000/911400/ |k 0/50000/ |p 8 | ||
| 998 | |g 139267123 |a Kauczor, Hans-Ulrich |m 139267123:Kauczor, Hans-Ulrich |d 910000 |d 911400 |e 910000PK139267123 |e 911400PK139267123 |k 0/910000/ |k 1/910000/911400/ |p 7 | ||
| 998 | |g 1071738429 |a Stackelberg, Oyunbileg von |m 1071738429:Stackelberg, Oyunbileg von |d 60000 |d 62600 |e 60000PS1071738429 |e 62600PS1071738429 |k 0/60000/ |k 1/60000/62600/ |p 6 | ||
| 998 | |g 14182641X |a Schlamp, Kai |m 14182641X:Schlamp, Kai |d 910000 |d 950000 |d 950900 |e 910000PS14182641X |e 950000PS14182641X |e 950900PS14182641X |k 0/910000/ |k 1/910000/950000/ |k 2/910000/950000/950900/ |p 4 | ||
| 998 | |g 1312342420 |a Heidt, Christian |m 1312342420:Heidt, Christian |d 910000 |d 911400 |e 910000PH1312342420 |e 911400PH1312342420 |k 0/910000/ |k 1/910000/911400/ |p 3 | ||
| 998 | |g 1345106033 |a Stollmayer, Róbert |m 1345106033:Stollmayer, Róbert |d 910000 |d 911400 |e 910000PS1345106033 |e 911400PS1345106033 |k 0/910000/ |k 1/910000/911400/ |p 1 |x j | ||
| 999 | |a KXP-PPN1933106581 |e 4756949789 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"recId":"1933106581","person":[{"role":"aut","family":"Stollmayer","given":"Róbert","display":"Stollmayer, Róbert"},{"family":"Güven","role":"aut","display":"Güven, Selda","given":"Selda"},{"given":"Christian","display":"Heidt, Christian","role":"aut","family":"Heidt"},{"display":"Schlamp, Kai","given":"Kai","family":"Schlamp","role":"aut"},{"display":"Kaposi, Pál Novák","given":"Pál Novák","role":"aut","family":"Kaposi"},{"role":"aut","family":"Stackelberg","given":"Oyunbileg von","display":"Stackelberg, Oyunbileg von"},{"display":"Kauczor, Hans-Ulrich","given":"Hans-Ulrich","role":"aut","family":"Kauczor"},{"display":"Klauß, Miriam","given":"Miriam","family":"Klauß","role":"aut"},{"given":"Philipp","display":"Mayer, Philipp","family":"Mayer","role":"aut"}],"note":["Gesehen am 13.08.2025"],"language":["eng"],"name":{"displayForm":["Róbert Stollmayer, Selda Güven, Christian Marcel Heidt, Kai Schlamp, Pál Novák Kaposi, Oyunbileg von Stackelberg, Hans-Ulrich Kauczor, Miriam Klauss and Philipp Mayer"]},"relHost":[{"recId":"36374732X","origin":[{"publisherPlace":"London ; Heidelberg ; New York, NY","dateIssuedKey":"2000","dateIssuedDisp":"2000-","publisher":"BioMed Central ; BMC, part of Springer Nature"}],"physDesc":[{"extent":"Online-Ressource"}],"id":{"zdb":["2104862-9"],"eki":["36374732X"],"issn":["1470-7330"]},"title":[{"subtitle":"the official publication of the International Cancer Imaging Society","title":"Cancer imaging","title_sort":"Cancer imaging"}],"pubHistory":["1.2000 -"],"note":["Gesehen am 20.03.23"],"part":{"volume":"25","year":"2025","pages":"1-17","extent":"17","text":"25(2025), Artikel-ID 36, Seite 1-17"},"language":["eng"],"disp":"LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learningCancer imaging","type":{"bibl":"periodical","media":"Online-Ressource"}}],"origin":[{"dateIssuedKey":"2025","dateIssuedDisp":"17 March 2025"}],"title":[{"title":"LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learning","title_sort":"LI-RADS-based hepatocellular carcinoma risk mapping using contrast-enhanced MRI and self-configuring deep learning"}],"type":{"media":"Online-Ressource","bibl":"article-journal"},"physDesc":[{"extent":"17 S.","noteIll":"Illustrationen"}],"id":{"eki":["1933106581"],"doi":["10.1186/s40644-025-00844-6"]}} | ||
| SRT | |a STOLLMAYERLIRADSBASE1720 | ||