María José Carreira Nouche

I am a Professor in Computer Science and Artificial Intelligence at the Universidade de Santiago de Compostela (Spain). Between 2008 and 2012, I was the deputy director of the School of Engineering at this university. From February 2015 to July 2017, I was assistant to the Vice Chancellor of Studies and Educational Innovation in USC. From July 2017 to June 2018, I was Commissioner of the rector for ICT governance and degree strategy. Now, I am the coordinator of the Computer Science and Artificial Intelligence area in my department.

I have participated in 30 research projects, contracts, and research design activities. I was the principal investigator in six of these activities, and nine were contracts/projects with companies. All my work is summarised in more than 90 scientific papers.

My research focuses on medical image intelligent processing, at first in radiographic chest images (PhD) and before my adhesion to CiTIUS, in ophthalmology. After joining CiTIUS, I worked on applications in oncology and neurology, collaborating with specialists from both disciplines. In the field of oncology, we developed a methodology for the 2D and 3D analysis of the evolution of cancer lines in zebrafish, publishing the ZFTool software. In the field of neurology, we developed the ICBrain software for the automatic measurement of tumour volumes in rats from resonance images.

I am currently working in the fields of Dentistry and Bioinformatics. In dentistry, we developed Dentius_Plaque and Dentius_Biofilm, two methodologies for the extraction and objective measurement of bacterial plaque at the macro (plaque) and microscopic (biofilm) level, as well as Dentius_Age for the calculation of dental age from panoramic dental radiographs using deep learning techniques. In bioinformatics, we are working on the development of PrimerEvalPy, a package for the evaluation of primers for analysis of the oral microbiome, and MicroMetaEvaluator, a package for the evaluation of genomic targets in microbial communities for the advancement in clinical metagenomics using machine learning techniques.