Pradeep Reddy Raamana is a biomedical engineer with a Ph.D. in medical image analysis and machine learning. His research interests are in development of multimodal biomarkers for various neurological and psychiatric disorders, and in characterizing the impact of fundamental methodological choices. He is passionate about bridging the gap between the clinic and computer science, and is developing tools and standards to remove the barriers for predictive modelling and quality control for neuroimagers. He founded the special interest group on neuroimaging quality control (niQC) at the International Neuroinformatics Coordinating Facility. He is an advocate for open science, and is committed to open source software and reproducible science.
As the saying goes “garbage in, garbage out”, the quality of insights produced in any data-driven study depends on the quality of input and intermediate data i.e. how well different stages of the neuroscientific analyses are quality controlled (QC). Multiple issues with neuroimaging data include artefacts, inaccuracies, incompleteness and selective measurement. Due to its resource-intensive nature i.e. demanding excessive manual labour, time, specialized tools and training, QC is not regularly performed. Among the small fraction of those employing it, there is a huge variability in terms of how it is operationalized and reported. This lack of standardization in protocols and reporting greatly reduces the commensurability across different studies. To improve harmonization across the field, we need to develop standards and best practices, which is the focus of my CONP fellowship.