Clinica: An Open-Source Software Platform for Reproducible Clinical Neuroscience Studies.

Alexandre Routier,Stanley Durrleman,Olivier Colliot,Pascal Lu,Ravi Hassanaly,Ninon Burgos,Omar El-Rifai,Simona Bottani,Jérémy Guillon,Mauricio Díaz,Michael Bacci,Sabrina Fontanella,Pietro Gori,Ghislain Vaillant,Arnaud Marcoux,Marc Teichmann,Junhao Wen,Adam Wild,Thomas Jacquemont,A Guyot ,T Moreau ,Jorge Samper‐Gonzàlez ,Elina Thibeau–Sutre ,Marie‐Odile Habert

doi:10.3389/fninf.2021.689675

Abstract

We present Clinica (www.clinica.run), an open-source software platform designed to make clinical neuroscience studies easier and more reproducible. Clinica aims for researchers to (i) spend less time on data management and processing, (ii) perform reproducible evaluations of their methods, and (iii) easily share data and results within their institution and with external collaborators. The core of Clinica is a set of automatic pipelines for processing and analysis of multimodal neuroimaging data (currently, T1-weighted MRI, diffusion MRI, and PET data), as well as tools for statistics, machine learning, and deep learning. It relies on the brain imaging data structure (BIDS) for the organization of raw neuroimaging datasets and on established tools written by the community to build its pipelines. It also provides converters of public neuroimaging datasets to BIDS (currently ADNI, AIBL, OASIS, and NIFD). Processed data include image-valued scalar fields (e.g., tissue probability maps), meshes, surface-based scalar fields (e.g., cortical thickness maps), or scalar outputs (e.g., regional averages). These data follow the ClinicA Processed Structure (CAPS) format which shares the same philosophy as BIDS. Consistent organization of raw and processed neuroimaging files facilitates the execution of single pipelines and of sequences of pipelines, as well as the integration of processed data into statistics or machine learning frameworks. The target audience of Clinica is neuroscientists or clinicians conducting clinical neuroscience studies involving multimodal imaging, and researchers developing advanced machine learning algorithms applied to neuroimaging data.

Highlights

Neuroimaging plays an important role in clinical neuroscience studies
The core of Clinica is a set of automatic pipelines for processing and analysis of multimodal neuroimaging data, as well as tools for statistics, machine learning, and deep learning
We proposed a software platform that aims at making clinical neuroscience easier and more reproducible

Summary

INTRODUCTION

Neuroimaging plays an important role in clinical neuroscience studies. While the meaning of clinical neuroscience studies may vary, we use it to refer to studies involving human participants (i.e., patients with neurological and psychiatric diseases, and control subjects) explored with multimodal data (neuroimaging, clinical, and cognitive evaluations, genetic data...) and most often involving longitudinal follow-up. Clinica relies on tools written by the scientific community and provides converters of public neuroimaging datasets to BIDS, processing pipelines, and organization for processed files, statistical analysis, and machine learning algorithms. To help with data management, the clinica iotools category comprises a set of tools that allows the user to handle BIDS and CAPS datasets, including generating lists of subjects or merging all tabular data into a single TSV file for analysis with external statistical software packages. - merge-tsv: This command merges all the tabular data including the clinical data of a BIDS directory and the regional features from a CAPS directory (e.g., mean GM density in AAL2 atlas) into a single TSV file This file can be plugged into machine learning tools via Clinica or other statistical/machine learning software packages. The results of the statistical analysis will be stored in the ADNI_CAPS/groups/group-ADvsHC folder

DISCUSSION

DATA AVAILABILITY STATEMENT