Joaquín De Ferrari

• A Framework for Extraction of Clinical Information from Radiological Mammography Reports Using Large Language Models and Retrieval Augmented Generation

  Godoy, E.*, De Ferrari, J.*, Lazo, S., Pacheco, C., Mellado, D., Saez, A., Chabert, S., Salas, R.

  BMC Medical Informatics and Decision Making, Vol. 26, Article 345, 2026.

  Co-first authorWoS Q1DOI: 10.1186/s12911-026-03633-8

• Assessing GPT as a Weak Oracle for Annotating Radiological Studies

  De Ferrari, J., Ñanculef, R., Benoit, D., Araya, M., Solar, M.

  Artificial Intelligence in Medicine (AIME 2025), Pavia, Italy, LNCS vol. 15734, pp. 98–109, Springer, 2025.

  First authorOral presentationDOI: 10.1007/978-3-031-95838-0_10

• Automatic detection of contextual laterality in Mammography Reports using Large Language Models

  Godoy, E.*, De Ferrari, J.*, Chabert, S., Mellado, D., Salas, R.

  IEEE International Conference on Pattern Recognition Systems (ICPRS 2024), London, UK, pp. 1–6, 2024.

  Co-first authorDOI: 10.1109/ICPRS62101.2024.10677842

Study notes from my courses, with interactive figures you can play with.

• 1Homogeneous coordinates

  Three numbers for every point and every line of the plane, so that joining two points and crossing two lines each take one cross product.

  Computer Vision · Geometry

• 1Multi-armed bandits

  How to choose again and again among options whose payoffs can only be learned by trying them, estimating what each is worth and balancing trying the others against using the best one found so far.

  Reinforcement Learning · Multi-armed bandits

• 1The laws of text: Zipf and Heaps

  How often words appear and how fast a vocabulary grows, and why a few words fill about a quarter of a long text while new words never stop coming.

  Natural Language Processing · Laws of text, resources and NLP tasks