INCloud: integrated neuroimaging cloud for data collection, management, analysis and clinical translations

Abstract

BackgroundNeuroimaging techniques provide rich and accurate measures of brain structure and function, and have become one of the most popular methods in mental health and neuroscience research. Rapidly growing neuroimaging research generates massive amounts of data, bringing new challenges in data collection, large-scale data management, efficient computing requirements and data mining and analyses.AimsTo tackle the challenges and promote the application of neuroimaging technology in clinical practice, we developed an integrated neuroimaging cloud (INCloud). INCloud provides a full-stack solution for the entire process of large-scale neuroimaging data collection, management, analysis and clinical applications.MethodsINCloud consists of data acquisition systems, a data warehouse, automatic multimodal image quality check and processing systems, a brain feature library, a high-performance computing cluster and computer-aided diagnosis systems (CADS) for mental disorders. A unique design of INCloud is the brain feature library that converts the unit of data management from image to image features such as hippocampal volume. Connecting the CADS to the scientific database, INCloud allows the accumulation of scientific data to continuously improve the accuracy of objective diagnosis of mental disorders.ResultsUsers can manage and analyze neuroimaging data on INCloud, without the need to download them to the local device. INCloud users can query, manage, analyze and share image features based on customized criteria. Several examples of 'mega-analyses' based on the brain feature library are shown.ConclusionsCompared with traditional neuroimaging acquisition and analysis workflow, INCloud features safe and convenient data management and sharing, reduced technical requirements for researchers, high-efficiency computing and data mining, and straightforward translations to clinical service. The design and implementation of the system are also applicable to imaging research platforms in other fields.

Pathological Networking of Gray Matter Dendritic Density With Classic Brain Morphometries in OCD

“…Multimodal neuroimaging data were acquired from a Simens VERIO 3T scanner (eMethods 2 in Supplement 1 ) and analyzed per modality 25 (eFigure 1 in Supplement 1 ). Multishell diffusion-weighted images ( b = 1000 s/mm 2 and b = 2000 s/mm 2 ) were used to assess neurite morphology via the NODDI Matlab Toolbox 10 in Matlab version R2019b (MathWorks), which derived neurite density index (NDI) and orientation dispersion index maps that were subsequently skeletonized via the NODDI GM-based spatial statistics (NODDI-GBSS) 24 in FMRIB Software Library version 5.0.10 (eMethods 3 in Supplement 1 ).…”

“…This study included 108 unmedicated patients with OCD (median [IQR] age, 26 [24][25][26][27][28][29][30][31]…”

Deep learning system for brain image-aided diagnosis of multiple major mental disorders

“…The dataset we used is a large-scale dataset covering a wide range of mental disorders and contains data from carefully labeled and quality-controlled studies. The data were enrolled by 10 psychiatric study groups according to strict criteria, using essentially the same scanning process and parameters, undergoing fine quality control, and processed and managed using the same hardware and software platform 66 . Data from the same location has advantages in terms of image quality and consistency in socio-cultural context and understanding of diagnostic criteria, which helps to reduce noise in identifying specific diseases.…”

“…Then we performed skull-stripping using watershed algorithm 84 and a process of manually checking to ensure that the skull was completely removed. All the above processing steps were performed using the same hardware and software platform 66 .…”