Detection of breast cancer by ATR-FTIR spectroscopy using artificial neural networks

In this study, three (3) neural networks (NN) were designed to discriminate between malignant (n = 78) and benign (n = 88) breast tumors using their respective attenuated total reflection Fourier transform infrared (ATR-FTIR) spectral data. A proposed NN-based sensitivity analysis was performed to determine the most significant IR regions that distinguished benign from malignant samples. The result of the NN-based sensitivity analysis was compared to the obtained results from FTIR visual peak identification. In training each NN models, a 10-fold cross validation was performed and the performance metrics-area under the curve (AUC), accuracy, positive predictive value (PPV), specificity rate (SR), negative predictive value (NPV), and recall rate (RR)-were averaged for comparison. The NN models were compared to six (6) machine learning models-logistic regression (LR), Naive Bayes (NB), decision trees (DT), random forest (RF), support vector machine (SVM) and linear discriminant analysis (LDA)-for benchmarking. The NN models were able to outperform the LR, NB, DT, RF, and LDA for all metrics; while only surpassing the SVM in accuracy, NPV and SR. The best performance metric among the NN models was 90.48% +/- 10.30% for AUC, 96.06% +/- 7.07% for ACC, 92.18 +/- 11.88% for PPV, 94.19 +/- 10.57% for NPV, 89.04% +/- 16.75% for SR, and 94.34% +/- 10.54% for RR. Results from the proposed sensitivity analysis were consistent with the visual peak identification. However, unlike the FTIR visual peak identification method, the NN-based method identified the IR region associated with C-OH C-OH group carbohydrates as significant. IR regions associated with amino acids and amide proteins were also determined as possible sources of variability. In conclusion, results show that ATR-FTIR via NN is a potential diagnostic tool. This study also suggests a possible more specific method in determining relevant regions within a sample's spectrum using NN.