Advancements in Frank’s sign Identification using deep learning on 3D brain MRI
Abstract Frank’s sign (FS) is a diagnostic marker associated with aging and various health conditions. Despite its clinical significance, there lacks a standardized method for its identification. This study aimed to develop a deep learning model for automated FS detection in 3D facial images derived...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-82756-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594764217712640 |
|---|---|
| author | Sungman Jo Jun Sung Kim Min Jeong Kwon Jieun Park Jeong Lan Kim Jin Hyeong Jhoo Eosu Kim Leonard Sunwoo Jae Hyoung Kim Ji Won Han Ki Woong Kim |
| author_facet | Sungman Jo Jun Sung Kim Min Jeong Kwon Jieun Park Jeong Lan Kim Jin Hyeong Jhoo Eosu Kim Leonard Sunwoo Jae Hyoung Kim Ji Won Han Ki Woong Kim |
| author_sort | Sungman Jo |
| collection | DOAJ |
| description | Abstract Frank’s sign (FS) is a diagnostic marker associated with aging and various health conditions. Despite its clinical significance, there lacks a standardized method for its identification. This study aimed to develop a deep learning model for automated FS detection in 3D facial images derived from MRI scans. Four deep learning architectures were evaluated for FS segmentation on a dataset of 400 brain MRI scans. The optimal model was subsequently validated on two external datasets, comprising 300 brain MRI scans each with varying FS presence. Dice similarity coefficient (DSC) and receiver operating characteristic (ROC) analysis were employed to assess model performance. The U-net architecture demonstrated superior performance in terms of accuracy and efficiency. On the validation datasets, the model achieved a DSC of 0.734, an intra-class correlation coefficient of 0.865, and an area under the ROC curve greater than 0.9 for FS detection. Additionally, the model identified optimal voxel thresholds for accurate FS classification, resulting in high sensitivity, specificity, and accuracy metrics. This study successfully developed a deep learning model for automated FS segmentation in MRI scans. This tool has the potential to enhance FS identification in clinical practice and contribute to further research on FS and its associated health implications. |
| format | Article |
| id | doaj-art-60d343c4166f4482b98e871f0a3ef835 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-60d343c4166f4482b98e871f0a3ef8352025-01-19T12:23:12ZengNature PortfolioScientific Reports2045-23222025-01-0115111110.1038/s41598-024-82756-2Advancements in Frank’s sign Identification using deep learning on 3D brain MRISungman Jo0Jun Sung Kim1Min Jeong Kwon2Jieun Park3Jeong Lan Kim4Jin Hyeong Jhoo5Eosu Kim6Leonard Sunwoo7Jae Hyoung Kim8Ji Won Han9Ki Woong Kim10Department of Health Science and Technology, Graduate school of convergence science and technology, Seoul National UniversityDepartment of Neuropsychiatry, Seoul National University Bundang HospitalDepartment of Brain and Cognitive Sciences, Seoul National University of Natural SciencesDepartment of Brain and Cognitive Sciences, Seoul National University of Natural SciencesDepartment of Psychiatry, College of Medicine, Chungnam National UniversityDepartment of Psychiatry, School of Medicine, Kangwon National UniversityGraduate School of Medical Science, Brain Korea 21 Project, Yonsei University College of MedicineDepartment of Radiology, Seoul National University Bundang HospitalDepartment of Radiology, Seoul National University Bundang HospitalDepartment of Neuropsychiatry, Seoul National University Bundang HospitalDepartment of Health Science and Technology, Graduate school of convergence science and technology, Seoul National UniversityAbstract Frank’s sign (FS) is a diagnostic marker associated with aging and various health conditions. Despite its clinical significance, there lacks a standardized method for its identification. This study aimed to develop a deep learning model for automated FS detection in 3D facial images derived from MRI scans. Four deep learning architectures were evaluated for FS segmentation on a dataset of 400 brain MRI scans. The optimal model was subsequently validated on two external datasets, comprising 300 brain MRI scans each with varying FS presence. Dice similarity coefficient (DSC) and receiver operating characteristic (ROC) analysis were employed to assess model performance. The U-net architecture demonstrated superior performance in terms of accuracy and efficiency. On the validation datasets, the model achieved a DSC of 0.734, an intra-class correlation coefficient of 0.865, and an area under the ROC curve greater than 0.9 for FS detection. Additionally, the model identified optimal voxel thresholds for accurate FS classification, resulting in high sensitivity, specificity, and accuracy metrics. This study successfully developed a deep learning model for automated FS segmentation in MRI scans. This tool has the potential to enhance FS identification in clinical practice and contribute to further research on FS and its associated health implications.https://doi.org/10.1038/s41598-024-82756-2Frank’s signDeep learningSegmentationMRI |
| spellingShingle | Sungman Jo Jun Sung Kim Min Jeong Kwon Jieun Park Jeong Lan Kim Jin Hyeong Jhoo Eosu Kim Leonard Sunwoo Jae Hyoung Kim Ji Won Han Ki Woong Kim Advancements in Frank’s sign Identification using deep learning on 3D brain MRI Scientific Reports Frank’s sign Deep learning Segmentation MRI |
| title | Advancements in Frank’s sign Identification using deep learning on 3D brain MRI |
| title_full | Advancements in Frank’s sign Identification using deep learning on 3D brain MRI |
| title_fullStr | Advancements in Frank’s sign Identification using deep learning on 3D brain MRI |
| title_full_unstemmed | Advancements in Frank’s sign Identification using deep learning on 3D brain MRI |
| title_short | Advancements in Frank’s sign Identification using deep learning on 3D brain MRI |
| title_sort | advancements in frank s sign identification using deep learning on 3d brain mri |
| topic | Frank’s sign Deep learning Segmentation MRI |
| url | https://doi.org/10.1038/s41598-024-82756-2 |
| work_keys_str_mv | AT sungmanjo advancementsinfrankssignidentificationusingdeeplearningon3dbrainmri AT junsungkim advancementsinfrankssignidentificationusingdeeplearningon3dbrainmri AT minjeongkwon advancementsinfrankssignidentificationusingdeeplearningon3dbrainmri AT jieunpark advancementsinfrankssignidentificationusingdeeplearningon3dbrainmri AT jeonglankim advancementsinfrankssignidentificationusingdeeplearningon3dbrainmri AT jinhyeongjhoo advancementsinfrankssignidentificationusingdeeplearningon3dbrainmri AT eosukim advancementsinfrankssignidentificationusingdeeplearningon3dbrainmri AT leonardsunwoo advancementsinfrankssignidentificationusingdeeplearningon3dbrainmri AT jaehyoungkim advancementsinfrankssignidentificationusingdeeplearningon3dbrainmri AT jiwonhan advancementsinfrankssignidentificationusingdeeplearningon3dbrainmri AT kiwoongkim advancementsinfrankssignidentificationusingdeeplearningon3dbrainmri |