Early Classification of Bladder Cancer Using Spectrum-Aided Visual Enhancer (SAVE) and Deep Learning Models: A Non-Invasive Technology for Faster Detection.

BACKGROUND/

OBJECTIVES

Bladder cancer (BC) is a significant global health issue, ranking as the ninth most prevalent cancer with a rising incidence. Conventional diagnostic methods, including cystoscopy and standard imaging techniques, possess limitations in identifying early cancer symptoms and accurately staging bladder cancer.

METHODS

Consequently, this study developed a computer-aided diagnostic (CAD) system utilizing a novel, purely software-driven approach called Spectrum-Aided Vision Enhancer (SAVE) in conjunction with deep learning algorithms.

RESULTS

Our results demonstrate the profound potential of SAVE to expand diagnostic accessibility in medical imaging. While achieving an overall performance comparable to standard WLI (overall p = 0.41, indicating strong non-inferiority), SAVE demonstrated targeted absolute improvements in F1-scores for the most challenging early stage categories without requiring expensive optical equipment. For instance, in the 'Above T1' class, SAVE elevated the F1-score from 65% to 85% utilizing VGG16.

CONCLUSIONS

These findings indicate that SAVE can provide reliable baseline detection while enhancing visual cues for specific complex lesions without requiring expensive optical equipment. For instance, in the 'Above T1' class, SAVE elevated the F1-score from 65% to 85% utilizing VGG16. These findings indicate that SAVE can provide resource-constrained clinical settings with advanced, high-contrast diagnostic capabilities, effectively decentralizing precision urological care.