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

• DOI: 10.3389/fninf.2021.689675
• Publication Date: 2021-08-13T15:54:27Z
• Authors: Alexandre Routier; Ninon Burgos; Mauricio Díaz; Michael Bacci; Simona Bottani; Omar El-Rifai; Sabrina Fontanella; Pietro Gori; Jérémy Guillon; Alexis Guyot; Ravi Hassanaly; Thomas Jacquemont; Pascal Lu; Arnaud Marcoux; Tristan Moreau; Jorge Samper-Gonz...; Marc Teichmann; Elina Thibeau-Sutre; Ghislain Vaillant; Junhao Wen; Adam Wild; Marie-Odile Habert; Stanley Durrleman; Olivier Colliot
• Keywords: Neuroimaging; Neurosciences. Biological psychiatry. Neuropsychiatry; Quantitative Biology - Quantitative Methods; [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]; 03 medical and health sciences; Multimodal data; 0302 clinical medicine; Pipeline; Machine learning; [INFO.INFO-IM]Computer Science [cs]/Medical Imaging; Quantitative Methods (q-bio.QM); neuroimaging; software; pipeline; Reproducibility; 3. Good health; Data processing; machine learning; FOS: Biological sciences; data processing and analysis; multimodal neuroimaging data; Software; RC321-571; Neuroscience

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