MyCoView aims to develop innovative, non-invasive mouldy core (MC) detection methodologies improving food safety and security in apple by relating MC lesion with mycotoxin contamination. For the first time, mass spectrometry and hyperspectral imaging with a machine learning (ML) approach will be combined to achieve a novel detection methodology. While the fields of hyperspectral imaging and plant-pathogen interaction are maturing, the integration of these interdisciplinary fields with mycotoxin research and ML is still challenging. Despite these challenges, such ambitious fusion greatly contributes to food safety and food security. MyCoView will increase food safety and food security by preventing the storage of latently infected MC apple fruit and by tackling mycotoxin contamination in apple products, thereby contributing to improved human health. This aim will be address by a multistrategy approach following these research objectives: 1) To investigate the metabolic plant-pathogen interactions and production of secondary metabolites by Alternaria spp. in apple using high resolution mass spectrometry (HRMS). 2) To quantify the production of the main Alternaria mycotoxins in apple and their accumulation over time when causing MC. 3) To develop accurate ML models to prevent the storage of latently infected MC apples and their further processing combining hyperspectral imaging and mass spectrometry.