Focal Liver Lesion MRI Feature Identification Using Efficientnet and MONAI: A Feasibility Study
Liver tumors constitute a major part of the global disease burden, often making regular imaging follow-up necessary. Recently, deep learning (DL) has increasingly been applied in this research area. How these methods could facilitate report writing is still a question, which our study aims to addres...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Cells |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4409/11/9/1558 |
| _version_ | 1827672854296002560 |
|---|---|
| author | Róbert Stollmayer Bettina Katalin Budai Aladár Rónaszéki Zita Zsombor Ildikó Kalina Erika Hartmann Gábor Tóth Péter Szoldán Viktor Bérczi Pál Maurovich-Horvat Pál Novák Kaposi |
| author_facet | Róbert Stollmayer Bettina Katalin Budai Aladár Rónaszéki Zita Zsombor Ildikó Kalina Erika Hartmann Gábor Tóth Péter Szoldán Viktor Bérczi Pál Maurovich-Horvat Pál Novák Kaposi |
| author_sort | Róbert Stollmayer |
| collection | DOAJ |
| description | Liver tumors constitute a major part of the global disease burden, often making regular imaging follow-up necessary. Recently, deep learning (DL) has increasingly been applied in this research area. How these methods could facilitate report writing is still a question, which our study aims to address by assessing multiple DL methods using the Medical Open Network for Artificial Intelligence (MONAI) framework, which may provide clinicians with preliminary information about a given liver lesion. For this purpose, we collected 2274 three-dimensional images of lesions, which we cropped from gadoxetate disodium enhanced T1w, native T1w, and T2w magnetic resonance imaging (MRI) scans. After we performed training and validation using 202 and 65 lesions, we selected the best performing model to predict features of lesions from our in-house test dataset containing 112 lesions. The model (EfficientNetB0) predicted 10 features in the test set with an average area under the receiver operating characteristic curve (standard deviation), sensitivity, specificity, negative predictive value, positive predictive value of 0.84 (0.1), 0.78 (0.14), 0.86 (0.08), 0.89 (0.08) and 0.71 (0.17), respectively. These results suggest that AI methods may assist less experienced residents or radiologists in liver MRI reporting of focal liver lesions. |
| first_indexed | 2024-03-10T04:16:06Z |
| format | Article |
| id | doaj.art-8329d365809d4588bd0b593f04d8289e |
| institution | Directory Open Access Journal |
| issn | 2073-4409 |
| language | English |
| last_indexed | 2024-03-10T04:16:06Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cells |
| spelling | doaj.art-8329d365809d4588bd0b593f04d8289e2023-11-23T08:00:58ZengMDPI AGCells2073-44092022-05-01119155810.3390/cells11091558Focal Liver Lesion MRI Feature Identification Using Efficientnet and MONAI: A Feasibility StudyRóbert Stollmayer0Bettina Katalin Budai1Aladár Rónaszéki2Zita Zsombor3Ildikó Kalina4Erika Hartmann5Gábor Tóth6Péter Szoldán7Viktor Bérczi8Pál Maurovich-Horvat9Pál Novák Kaposi10Medical Imaging Centre, Department of Radiology, Faculty of Medicine, Semmelweis University, 1083 Budapest, HungaryMedical Imaging Centre, Department of Radiology, Faculty of Medicine, Semmelweis University, 1083 Budapest, HungaryMedical Imaging Centre, Department of Radiology, Faculty of Medicine, Semmelweis University, 1083 Budapest, HungaryMedical Imaging Centre, Department of Radiology, Faculty of Medicine, Semmelweis University, 1083 Budapest, HungaryMedical Imaging Centre, Department of Radiology, Faculty of Medicine, Semmelweis University, 1083 Budapest, HungaryMedical Imaging Centre, Department of Radiology, Faculty of Medicine, Semmelweis University, 1083 Budapest, HungaryMedical Imaging Centre, Department of Radiology, Faculty of Medicine, Semmelweis University, 1083 Budapest, HungaryMedInnoScan Research and Development Ltd., 1112 Budapest, HungaryMedical Imaging Centre, Department of Radiology, Faculty of Medicine, Semmelweis University, 1083 Budapest, HungaryMedical Imaging Centre, Department of Radiology, Faculty of Medicine, Semmelweis University, 1083 Budapest, HungaryMedical Imaging Centre, Department of Radiology, Faculty of Medicine, Semmelweis University, 1083 Budapest, HungaryLiver tumors constitute a major part of the global disease burden, often making regular imaging follow-up necessary. Recently, deep learning (DL) has increasingly been applied in this research area. How these methods could facilitate report writing is still a question, which our study aims to address by assessing multiple DL methods using the Medical Open Network for Artificial Intelligence (MONAI) framework, which may provide clinicians with preliminary information about a given liver lesion. For this purpose, we collected 2274 three-dimensional images of lesions, which we cropped from gadoxetate disodium enhanced T1w, native T1w, and T2w magnetic resonance imaging (MRI) scans. After we performed training and validation using 202 and 65 lesions, we selected the best performing model to predict features of lesions from our in-house test dataset containing 112 lesions. The model (EfficientNetB0) predicted 10 features in the test set with an average area under the receiver operating characteristic curve (standard deviation), sensitivity, specificity, negative predictive value, positive predictive value of 0.84 (0.1), 0.78 (0.14), 0.86 (0.08), 0.89 (0.08) and 0.71 (0.17), respectively. These results suggest that AI methods may assist less experienced residents or radiologists in liver MRI reporting of focal liver lesions.https://www.mdpi.com/2073-4409/11/9/1558focal liver lesiondeep learningradiological featurehepatocellular carcinomaliver metastasisgadoxetate disodium |
| spellingShingle | Róbert Stollmayer Bettina Katalin Budai Aladár Rónaszéki Zita Zsombor Ildikó Kalina Erika Hartmann Gábor Tóth Péter Szoldán Viktor Bérczi Pál Maurovich-Horvat Pál Novák Kaposi Focal Liver Lesion MRI Feature Identification Using Efficientnet and MONAI: A Feasibility Study Cells focal liver lesion deep learning radiological feature hepatocellular carcinoma liver metastasis gadoxetate disodium |
| title | Focal Liver Lesion MRI Feature Identification Using Efficientnet and MONAI: A Feasibility Study |
| title_full | Focal Liver Lesion MRI Feature Identification Using Efficientnet and MONAI: A Feasibility Study |
| title_fullStr | Focal Liver Lesion MRI Feature Identification Using Efficientnet and MONAI: A Feasibility Study |
| title_full_unstemmed | Focal Liver Lesion MRI Feature Identification Using Efficientnet and MONAI: A Feasibility Study |
| title_short | Focal Liver Lesion MRI Feature Identification Using Efficientnet and MONAI: A Feasibility Study |
| title_sort | focal liver lesion mri feature identification using efficientnet and monai a feasibility study |
| topic | focal liver lesion deep learning radiological feature hepatocellular carcinoma liver metastasis gadoxetate disodium |
| url | https://www.mdpi.com/2073-4409/11/9/1558 |
| work_keys_str_mv | AT robertstollmayer focalliverlesionmrifeatureidentificationusingefficientnetandmonaiafeasibilitystudy AT bettinakatalinbudai focalliverlesionmrifeatureidentificationusingefficientnetandmonaiafeasibilitystudy AT aladarronaszeki focalliverlesionmrifeatureidentificationusingefficientnetandmonaiafeasibilitystudy AT zitazsombor focalliverlesionmrifeatureidentificationusingefficientnetandmonaiafeasibilitystudy AT ildikokalina focalliverlesionmrifeatureidentificationusingefficientnetandmonaiafeasibilitystudy AT erikahartmann focalliverlesionmrifeatureidentificationusingefficientnetandmonaiafeasibilitystudy AT gabortoth focalliverlesionmrifeatureidentificationusingefficientnetandmonaiafeasibilitystudy AT peterszoldan focalliverlesionmrifeatureidentificationusingefficientnetandmonaiafeasibilitystudy AT viktorberczi focalliverlesionmrifeatureidentificationusingefficientnetandmonaiafeasibilitystudy AT palmaurovichhorvat focalliverlesionmrifeatureidentificationusingefficientnetandmonaiafeasibilitystudy AT palnovakkaposi focalliverlesionmrifeatureidentificationusingefficientnetandmonaiafeasibilitystudy |