Identification of Neoadjuvant Chemotherapy Response in Muscle-Invasive Bladder Cancer by Fourier-Transform Infrared Micro-Imaging

Abstract

Background: Neoadjuvant chemotherapy (NAC) improves survival in responder patients. However, for non-responders, the treatment represents an ineffective exposure to chemotherapy and its potential adverse events. Predicting the response to treatment is a major issue in the therapeutic management of patients, particularly for patients with muscle-invasive bladder cancer.

Methods: Tissue samples of trans-urethral resection of bladder tumor collected at the diagnosis time, were analyzed by mid-infrared imaging. A sequence of spectral data processing was implemented for automatic recognition of informative pixels and scoring each pixel according to a continuous scale (from 0 to 10) associated with the response to NAC. The ground truth status of the responder or non-responder was based on histopathological examination of the samples.

Results: Although the TMA spots of tumors appeared histologically homogeneous, the infrared approach highlighted spectral heterogeneity. Both the quantification of this heterogeneity and the scoring of the NAC response at the pixel level were used to construct sensitivity and specificity maps from which decision criteria can be extracted to classify cancerous samples.

Conclusions: This proof-of-concept appears as the first to evaluate the potential of the mid-infrared approach for the prediction of response to neoadjuvant chemotherapy in MIBC tissues.

Keywords: chemometric algorithms; mid-infrared imaging; muscle-invasive bladder cancer; neoadjuvant chemotherapy; predictive response to treatment.

Figure 1

Histological images (A,E) and chemometric steps; including individual Kmeans clustering (B,F) for tissue structures recovering; PLS-DA (C,G) for automatic selection of pixels of interest and R/NR PLS scoring (D,H); for two representative calibration samples corresponding to NR and R patients. PLS was run with the infrared images of TMA spots allocated to calibration set as reference inputs; by considering a scale from 0 to 1 with scores of 1 (blue) and 9 (red) for NR and R respectively.

Figure 2

Histology (A,D); PLS scoring (B,E) and histogram (C,F) of test samples from one NR (up) and one R (down) patients. The histograms indicate the number of pixels as function of the R/NR PLS score.

Figure 3

2D map of sensitivity (A) and specificity (B) for test set according to the values of percentage of pixels (x axis) and R/NR PLS score (y axis).

Figure 4

Vibrational infrared features involved in the PLS modeling of the NAC response. The solid line corresponds to the mean of the first twelve PLS latent variables (LV) used in the model and the shaded area represents the minimum to maximum space of variability of these latent variables. The wavenumbers associated with the main spectral features are also indicated.