This study introduces a novel approach proposing self-awareness in detecting manifestation shifts within medical images, designing the challenge as a classification of lesion subtypes. The proposed method achieved competitive performance compared with recent literature utilizing reconstruction thresholds based on histogram analysis.
Recommended citation: FREITAS, Samuel Armbrust; DA COSTA, Cristiano André; DE OLIVEIRA RAMOS, Gabriel. Autoencoders to detect manifestation shift in medical images. In: Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS). SBC, 2025. p. 425-436.