{"id":1145,"date":"2022-09-21T00:11:38","date_gmt":"2022-09-20T22:11:38","guid":{"rendered":"https:\/\/www.iberamia.org\/iberamia\/iberamia2022\/?page_id=1145"},"modified":"2022-11-15T09:58:14","modified_gmt":"2022-11-15T08:58:14","slug":"wexplanabledl","status":"publish","type":"page","link":"https:\/\/www.iberamia.org\/iberamia\/iberamia2022\/wexplanabledl\/","title":{"rendered":"Workshop \u00abExplainable Deep Learning for COVID-19 data\u00bb"},"content":{"rendered":"

IBERAMIA 2022 WORKSHOP on<\/h2>\n

\u201cExplainable Deep Learning for COVID-19 data<\/span>\u201d<\/strong><\/h2>\n

Organized by Ra\u00fal Cruz Barbosa<\/em><\/strong>, Technological University of the Mixteca Region, M\u00e9xico and Alfredo Vellido<\/em><\/strong>, Polytechnic University of Catalonia, Spain<\/h3>\n
Sal\u00f3n 213. Claustro de la Merced, Universidad de Cartagena\u00a0 (Google Maps<\/a>).<\/em><\/strong><\/h5>\n
Cartagena de Indias, Colombia. November 23, 2022<\/strong><\/h5>\n
\n

Explainable Artificial Intelligence and Machine Learning (XAI) methods are very important in many human-computer interaction contexts. In the medical applications domain in particular, they become a must. On the other hand, to face some problems related to the coronavirus disease 2019 (COVID-19) pandemic through a data-centred approach, the deep learning and medical image analysis communities have developed and disseminated models and tools for preprocessing, segmentation and classification tasks from COVID-19 imaging data. However, recent review papers have shown that most of them have no potential clinical use due to several flaws (as methodology or underlying biases). To address these problems at least partially, explainability is a key factor that can boost the medical acceptability of deep learning models.<\/p>\n

Therefore, the goal of this workshop is to gather researchers working on the development of deep learning models mainly for COVID-19 detection, diagnosis or prognosis that include an explanation method (using an interpretable-by-design model and\/or post hoc explanation, for instance). We also welcome research that goes beyond COVID to address other epidemiological problems and research that focuses on the medical decision making processes involved in XAI.<\/p>\n

\n

Proceedings<\/strong><\/h4>\n

\"\"<\/a><\/p>\n

\n

Call for\u00a0 Papers<\/h4>\n

We welcome methodological contributions, case studies, position papers and early research reports.WorkshopExplainableDeepLearning<\/a><\/p>\n

The list of topics addressed in the workshop include, but are not limited to:<\/p>\n