Cancers have been seen to be prevalent worldwide and affect a substantial amount of the global population, where the early and pro-active diagnosis of the disease continues to be a global medical challenge. Endometrial cancer represents a gynecological variant of a cancer that not only is difficult to diagnose but is also produces symptoms of which are not distinct and exclusive to just the cancer itself. Blood spectroscopy has recently prevailed as a means towards high throughput and a largely inexpensive method towards the diagnosis of the endometrial cancer, where, by the post-processing of the accompanying spectra alongside the use of multivariate statistics, an inference can be formed of which gives an indication of the presence and extent of the cancer.

Subsequent work done in this area showed that the prediction results for cancer could be improved with the use of signal decomposition models alongside machine learning prediction machines, thus showing the potential appeal of decomposition models in the processing pipeline of the spectroscopy data. As part of this exploratory study, we employ for the first time, the use of Deep Learning for the processing of acquired FTIR spectra, which allows for a fully unsupervised decomposition and feature extraction of the resulting spectra’s, coupled with prediction machines capable of predicting the presence of the cancer.

The obtained results show that the use of the Deep Learning allows for enhanced predictions of endometrial cancer, whilst allowing for a clinical decision support platform that carries a greater degree of autonomy and therein diagnosis throughput.