DeepParcellation: A novel deep learning method for robust brain magnetic resonance imaging parcellation in older East Asians
Accurate parcellation of cortical regions is crucial for distinguishing morphometric changes in aged brains, particularly in degenerative brain diseases. Normal aging and neurodegeneration precipitate brain structural changes, leading to distinct tissue contrast and shape in people aged >60 y...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-12-01
|
| Series: | Frontiers in Aging Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnagi.2022.1027857/full |
| _version_ | 1811185068543049728 |
|---|---|
| author | Eun-Cheon Lim Uk-Su Choi Uk-Su Choi Uk-Su Choi Uk-Su Choi Kyu Yeong Choi Jang Jae Lee Yul-Wan Sung Seiji Ogawa Byeong Chae Kim Kun Ho Lee Kun Ho Lee Kun Ho Lee Kun Ho Lee Kun Ho Lee Jungsoo Gim Jungsoo Gim Jungsoo Gim for The Alzheimer’s Disease Neuroimaging Initiative |
| author_facet | Eun-Cheon Lim Uk-Su Choi Uk-Su Choi Uk-Su Choi Uk-Su Choi Kyu Yeong Choi Jang Jae Lee Yul-Wan Sung Seiji Ogawa Byeong Chae Kim Kun Ho Lee Kun Ho Lee Kun Ho Lee Kun Ho Lee Kun Ho Lee Jungsoo Gim Jungsoo Gim Jungsoo Gim for The Alzheimer’s Disease Neuroimaging Initiative |
| author_sort | Eun-Cheon Lim |
| collection | DOAJ |
| description | Accurate parcellation of cortical regions is crucial for distinguishing morphometric changes in aged brains, particularly in degenerative brain diseases. Normal aging and neurodegeneration precipitate brain structural changes, leading to distinct tissue contrast and shape in people aged >60 years. Manual parcellation by trained radiologists can yield a highly accurate outline of the brain; however, analyzing large datasets is laborious and expensive. Alternatively, newly-developed computational models can quickly and accurately conduct brain parcellation, although thus far only for the brains of Caucasian individuals. To develop a computational model for the brain parcellation of older East Asians, we trained magnetic resonance images of dimensions 256 × 256 × 256 on 5,035 brains of older East Asians (Gwangju Alzheimer’s and Related Dementia) and 2,535 brains of Caucasians. The novel N-way strategy combining three memory reduction techniques inception blocks, dilated convolutions, and attention gates was adopted for our model to overcome the intrinsic memory requirement problem. Our method proved to be compatible with the commonly used parcellation model for Caucasians and showed higher similarity and robust reliability in older aged and East Asian groups. In addition, several brain regions showing the superiority of the parcellation suggest that DeepParcellation has a great potential for applications in neurodegenerative diseases such as Alzheimer’s disease. |
| first_indexed | 2024-04-11T13:23:10Z |
| format | Article |
| id | doaj.art-1a222bb25c0b4c628e5e68dbed1a491b |
| institution | Directory Open Access Journal |
| issn | 1663-4365 |
| language | English |
| last_indexed | 2024-04-11T13:23:10Z |
| publishDate | 2022-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Aging Neuroscience |
| spelling | doaj.art-1a222bb25c0b4c628e5e68dbed1a491b2022-12-22T04:22:08ZengFrontiers Media S.A.Frontiers in Aging Neuroscience1663-43652022-12-011410.3389/fnagi.2022.10278571027857DeepParcellation: A novel deep learning method for robust brain magnetic resonance imaging parcellation in older East AsiansEun-Cheon Lim0Uk-Su Choi1Uk-Su Choi2Uk-Su Choi3Uk-Su Choi4Kyu Yeong Choi5Jang Jae Lee6Yul-Wan Sung7Seiji Ogawa8Byeong Chae Kim9Kun Ho Lee10Kun Ho Lee11Kun Ho Lee12Kun Ho Lee13Kun Ho Lee14Jungsoo Gim15Jungsoo Gim16Jungsoo Gim17for The Alzheimer’s Disease Neuroimaging InitiativeGwangju Alzheimer’s and Related Dementia Cohort Research Center, Chosun University, Gwangju, South KoreaGwangju Alzheimer’s and Related Dementia Cohort Research Center, Chosun University, Gwangju, South KoreaBK FOUR Department of Integrative Biological Sciences, Chosun University, Gwangju, South KoreaNeurozen Inc., Seoul, South KoreaMedical Device Development Center, Daegu-Gyeongbuk Medical Innovation Foundation, Daegu, South KoreaGwangju Alzheimer’s and Related Dementia Cohort Research Center, Chosun University, Gwangju, South KoreaGwangju Alzheimer’s and Related Dementia Cohort Research Center, Chosun University, Gwangju, South KoreaKansei Fukushi Research Institute, Tohoku Fukushi University, Sendai, Miyagi, JapanKansei Fukushi Research Institute, Tohoku Fukushi University, Sendai, Miyagi, JapanDepartment of Neurology, Chonnam National University Medical School, Gwangju, South KoreaGwangju Alzheimer’s and Related Dementia Cohort Research Center, Chosun University, Gwangju, South KoreaBK FOUR Department of Integrative Biological Sciences, Chosun University, Gwangju, South KoreaNeurozen Inc., Seoul, South KoreaDepartment of Biomedical Science, Chosun University, Gwangju, South KoreaKorea Brain Research Institute, Daegu, South KoreaGwangju Alzheimer’s and Related Dementia Cohort Research Center, Chosun University, Gwangju, South KoreaBK FOUR Department of Integrative Biological Sciences, Chosun University, Gwangju, South KoreaDepartment of Biomedical Science, Chosun University, Gwangju, South KoreaAccurate parcellation of cortical regions is crucial for distinguishing morphometric changes in aged brains, particularly in degenerative brain diseases. Normal aging and neurodegeneration precipitate brain structural changes, leading to distinct tissue contrast and shape in people aged >60 years. Manual parcellation by trained radiologists can yield a highly accurate outline of the brain; however, analyzing large datasets is laborious and expensive. Alternatively, newly-developed computational models can quickly and accurately conduct brain parcellation, although thus far only for the brains of Caucasian individuals. To develop a computational model for the brain parcellation of older East Asians, we trained magnetic resonance images of dimensions 256 × 256 × 256 on 5,035 brains of older East Asians (Gwangju Alzheimer’s and Related Dementia) and 2,535 brains of Caucasians. The novel N-way strategy combining three memory reduction techniques inception blocks, dilated convolutions, and attention gates was adopted for our model to overcome the intrinsic memory requirement problem. Our method proved to be compatible with the commonly used parcellation model for Caucasians and showed higher similarity and robust reliability in older aged and East Asian groups. In addition, several brain regions showing the superiority of the parcellation suggest that DeepParcellation has a great potential for applications in neurodegenerative diseases such as Alzheimer’s disease.https://www.frontiersin.org/articles/10.3389/fnagi.2022.1027857/fulldeep learningbrain3D MRIparcellationDeepParcellation |
| spellingShingle | Eun-Cheon Lim Uk-Su Choi Uk-Su Choi Uk-Su Choi Uk-Su Choi Kyu Yeong Choi Jang Jae Lee Yul-Wan Sung Seiji Ogawa Byeong Chae Kim Kun Ho Lee Kun Ho Lee Kun Ho Lee Kun Ho Lee Kun Ho Lee Jungsoo Gim Jungsoo Gim Jungsoo Gim for The Alzheimer’s Disease Neuroimaging Initiative DeepParcellation: A novel deep learning method for robust brain magnetic resonance imaging parcellation in older East Asians Frontiers in Aging Neuroscience deep learning brain 3D MRI parcellation DeepParcellation |
| title | DeepParcellation: A novel deep learning method for robust brain magnetic resonance imaging parcellation in older East Asians |
| title_full | DeepParcellation: A novel deep learning method for robust brain magnetic resonance imaging parcellation in older East Asians |
| title_fullStr | DeepParcellation: A novel deep learning method for robust brain magnetic resonance imaging parcellation in older East Asians |
| title_full_unstemmed | DeepParcellation: A novel deep learning method for robust brain magnetic resonance imaging parcellation in older East Asians |
| title_short | DeepParcellation: A novel deep learning method for robust brain magnetic resonance imaging parcellation in older East Asians |
| title_sort | deepparcellation a novel deep learning method for robust brain magnetic resonance imaging parcellation in older east asians |
| topic | deep learning brain 3D MRI parcellation DeepParcellation |
| url | https://www.frontiersin.org/articles/10.3389/fnagi.2022.1027857/full |
| work_keys_str_mv | AT euncheonlim deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT uksuchoi deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT uksuchoi deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT uksuchoi deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT uksuchoi deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT kyuyeongchoi deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT jangjaelee deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT yulwansung deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT seijiogawa deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT byeongchaekim deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT kunholee deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT kunholee deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT kunholee deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT kunholee deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT kunholee deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT jungsoogim deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT jungsoogim deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT jungsoogim deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians AT forthealzheimersdiseaseneuroimaginginitiative deepparcellationanoveldeeplearningmethodforrobustbrainmagneticresonanceimagingparcellationinoldereastasians |