Extended Invariant Information Clustering Is Effective for Leave-One-Site-Out Cross-Validation in Resting State Functional Connectivity Modeling
Herein, we propose a new deep neural network model based on invariant information clustering (IIC), proposed by Ji et al., to improve the modeling performance of the leave-one-site-out cross-validation (LOSO-CV) for a multi-source dataset. Our Extended IIC (EIIC) is a type of contrastive learning; h...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2021-12-01
|
| Series: | Frontiers in Neuroinformatics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fninf.2021.709179/full |
| _version_ | 1819043330367946752 |
|---|---|
| author | Naoki Okamoto Hiroyuki Akama Hiroyuki Akama |
| author_facet | Naoki Okamoto Hiroyuki Akama Hiroyuki Akama |
| author_sort | Naoki Okamoto |
| collection | DOAJ |
| description | Herein, we propose a new deep neural network model based on invariant information clustering (IIC), proposed by Ji et al., to improve the modeling performance of the leave-one-site-out cross-validation (LOSO-CV) for a multi-source dataset. Our Extended IIC (EIIC) is a type of contrastive learning; however, unlike the original IIC, it is characterized by transfer learning with labeled data pairs, but without the need for a data augmentation technique. Each site in LOSO-CV is left out in turn from the remaining sites used for training and receives a value for modeling evaluation. We applied the EIIC to the resting state functional connectivity magnetic resonance imaging dataset of the Autism Brain Imaging Data Exchange. The challenging nature of brain analysis for autism spectrum disorder (ASD) can be attributed to the variability of subjects, particularly the rapid change in the neural system of children as the target ASD age group. However, EIIC demonstrated higher LOSO-CV classification accuracy for the majority of scanning locations than previously used methods. Particularly, with the adjustment of a mini-batch size, EIIC outperformed other classifiers with an accuracy >0.8 for the sites with highest mean age of the subjects. Considering its effectiveness, our proposed method might be promising for harmonization in other domains, owing to its simplicity and intrinsic flexibility. |
| first_indexed | 2024-12-21T09:55:04Z |
| format | Article |
| id | doaj.art-e42e2713bca34346812a69bfb7b2d8bf |
| institution | Directory Open Access Journal |
| issn | 1662-5196 |
| language | English |
| last_indexed | 2024-12-21T09:55:04Z |
| publishDate | 2021-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroinformatics |
| spelling | doaj.art-e42e2713bca34346812a69bfb7b2d8bf2022-12-21T19:08:06ZengFrontiers Media S.A.Frontiers in Neuroinformatics1662-51962021-12-011510.3389/fninf.2021.709179709179Extended Invariant Information Clustering Is Effective for Leave-One-Site-Out Cross-Validation in Resting State Functional Connectivity ModelingNaoki Okamoto0Hiroyuki Akama1Hiroyuki Akama2School of Life Sciences and Technology, Tokyo Institute of Technology, Tokyo, JapanSchool of Life Sciences and Technology, Tokyo Institute of Technology, Tokyo, JapanInstitute for Liberal Arts, Tokyo Institute of Technology, Tokyo, JapanHerein, we propose a new deep neural network model based on invariant information clustering (IIC), proposed by Ji et al., to improve the modeling performance of the leave-one-site-out cross-validation (LOSO-CV) for a multi-source dataset. Our Extended IIC (EIIC) is a type of contrastive learning; however, unlike the original IIC, it is characterized by transfer learning with labeled data pairs, but without the need for a data augmentation technique. Each site in LOSO-CV is left out in turn from the remaining sites used for training and receives a value for modeling evaluation. We applied the EIIC to the resting state functional connectivity magnetic resonance imaging dataset of the Autism Brain Imaging Data Exchange. The challenging nature of brain analysis for autism spectrum disorder (ASD) can be attributed to the variability of subjects, particularly the rapid change in the neural system of children as the target ASD age group. However, EIIC demonstrated higher LOSO-CV classification accuracy for the majority of scanning locations than previously used methods. Particularly, with the adjustment of a mini-batch size, EIIC outperformed other classifiers with an accuracy >0.8 for the sites with highest mean age of the subjects. Considering its effectiveness, our proposed method might be promising for harmonization in other domains, owing to its simplicity and intrinsic flexibility.https://www.frontiersin.org/articles/10.3389/fninf.2021.709179/fulldeep learningresting functional connectivity MRIharmonizationleave-one-site-out cross-validationABIDE |
| spellingShingle | Naoki Okamoto Hiroyuki Akama Hiroyuki Akama Extended Invariant Information Clustering Is Effective for Leave-One-Site-Out Cross-Validation in Resting State Functional Connectivity Modeling Frontiers in Neuroinformatics deep learning resting functional connectivity MRI harmonization leave-one-site-out cross-validation ABIDE |
| title | Extended Invariant Information Clustering Is Effective for Leave-One-Site-Out Cross-Validation in Resting State Functional Connectivity Modeling |
| title_full | Extended Invariant Information Clustering Is Effective for Leave-One-Site-Out Cross-Validation in Resting State Functional Connectivity Modeling |
| title_fullStr | Extended Invariant Information Clustering Is Effective for Leave-One-Site-Out Cross-Validation in Resting State Functional Connectivity Modeling |
| title_full_unstemmed | Extended Invariant Information Clustering Is Effective for Leave-One-Site-Out Cross-Validation in Resting State Functional Connectivity Modeling |
| title_short | Extended Invariant Information Clustering Is Effective for Leave-One-Site-Out Cross-Validation in Resting State Functional Connectivity Modeling |
| title_sort | extended invariant information clustering is effective for leave one site out cross validation in resting state functional connectivity modeling |
| topic | deep learning resting functional connectivity MRI harmonization leave-one-site-out cross-validation ABIDE |
| url | https://www.frontiersin.org/articles/10.3389/fninf.2021.709179/full |
| work_keys_str_mv | AT naokiokamoto extendedinvariantinformationclusteringiseffectiveforleaveonesiteoutcrossvalidationinrestingstatefunctionalconnectivitymodeling AT hiroyukiakama extendedinvariantinformationclusteringiseffectiveforleaveonesiteoutcrossvalidationinrestingstatefunctionalconnectivitymodeling AT hiroyukiakama extendedinvariantinformationclusteringiseffectiveforleaveonesiteoutcrossvalidationinrestingstatefunctionalconnectivitymodeling |