[HTML][HTML] Image harmonization: A review of statistical and deep learning methods for removing batch effects and evaluation metrics for effective harmonization

F Hu, AA Chen, H Horng, V Bashyam, C Davatzikos… - NeuroImage, 2023‏ - Elsevier
Magnetic resonance imaging and computed tomography from multiple batches (eg sites,
scanners, datasets, etc.) are increasingly used alongside complex downstream analyses to …

[HTML][HTML] Harmonization strategies in multicenter MRI-based radiomics

E Stamoulou, C Spanakis, GC Manikis, G Karanasiou… - Journal of …, 2022‏ - mdpi.com
Radiomics analysis is a powerful tool aiming to provide diagnostic and prognostic patient
information directly from images that are decoded into handcrafted features, comprising …

Effects of MRI scanner manufacturers in classification tasks with deep learning models

R Kushol, P Parnianpour, AH Wilman, S Kalra… - Scientific Reports, 2023‏ - nature.com
Deep learning has become a leading subset of machine learning and has been successfully
employed in diverse areas, ranging from natural language processing to medical image …

Increasing diversity in connectomics with the Chinese Human Connectome Project

J Ge, G Yang, M Han, S Zhou, W Men, L Qin… - Nature …, 2023‏ - nature.com
Cultural differences and biological diversity play important roles in sha** human brain
structure and function. To date, most large-scale multimodal neuroimaging datasets have …

HACA3: A unified approach for multi-site MR image harmonization

L Zuo, Y Liu, Y Xue, BE Dewey, SW Remedios… - … Medical Imaging and …, 2023‏ - Elsevier
The lack of standardization and consistency of acquisition is a prominent issue in magnetic
resonance (MR) imaging. This often causes undesired contrast variations in the acquired …

Addressing multi‐site functional MRI heterogeneity through dual‐expert collaborative learning for brain disease identification

Y Fang, GG Potter, D Wu, H Zhu, M Liu - Human Brain Map**, 2023‏ - Wiley Online Library
Several studies employ multi‐site rs‐fMRI data for major depressive disorder (MDD)
identification, with a specific site as the to‐be‐analyzed target domain and other site (s) as …

The status of MRI databases across the world focused on psychiatric and neurological disorders

SC Tanaka, K Kasai, Y Okamoto… - Psychiatry and …, 2024‏ - Wiley Online Library
Neuroimaging databases for neuro‐psychiatric disorders enable researchers to implement
data‐driven research approaches by providing access to rich data that can be used to study …

Deepcombat: A statistically motivated, hyperparameter‐robust, deep learning approach to harmonization of neuroimaging data

F Hu, A Lucas, AA Chen, K Coleman… - Human brain …, 2024‏ - Wiley Online Library
Neuroimaging data acquired using multiple scanners or protocols are increasingly
available. However, such data exhibit technical artifacts across batches which introduce …

[HTML][HTML] IGUANe: A 3D generalizable CycleGAN for multicenter harmonization of brain MR images

V Roca, G Kuchcinski, JP Pruvo, D Manouvriez… - Medical Image …, 2025‏ - Elsevier
In MRI studies, the aggregation of imaging data from multiple acquisition sites enhances
sample size but may introduce site-related variabilities that hinder consistency in …

Segmentation-guided domain adaptation and data harmonization of multi-device retinal optical coherence tomography using cycle-consistent generative adversarial …

S Chen, D Ma, S Lee, TL Timothy, G Xu, D Lu… - Computers in Biology …, 2023‏ - Elsevier
Background Medical images such as Optical Coherence Tomography (OCT) images
acquired from different devices may show significantly different intensity profiles. An …