Lucas Cardoso Lazari, Ghasem Azemi, Livia Rosa-Fernandes, Suely K N Marie, Antonio Di Ieva, Giuseppe Palmisano
Matrix-Assisted Laser Desorption/Ionization Time-of-Flight (MALDI-TOF) mass spectrometry generates rich biochemical fingerprints ideal for disease screening. However, its spectral output is highly complex, requiring advanced processing before clinical use. Machine learning excels in learning patterns within this high-dimensional data, but it depends on effective feature extraction. This chapter presents preprocessing strategies for MALDI-TOF spectra and demonstrates the use of fractal dimension and entropy analysis as a feature generation method.