Back

Low-Cost, Label-Free Blue Light Cystoscopy through Digital Staining of White Light Cystoscopy Videos

Chang, S.; Wintergerst, G. A.; Carlson, C. J.; Yin, H.; Scarpato, K. R.; Luckenbaugh, A. N.; Chang, S.; Kolouri, S.; Bowden, A. K.

2024-03-22 urology
10.1101/2024.03.21.24304656 medRxiv
Show abstract

Bladder cancer is 10th most common malignancy and carries the highest treatment cost among all cancers. The high cost of bladder cancer treatment stems from its high recurrence rate, which necessitates frequent surveillance. White light cystoscopy (WLC), the standard of care surveillance tool to examine the bladder for lesions, has limited sensitivity for early-stage bladder cancer. Blue light cystoscopy (BLC) utilizes a fluorescent dye to induce contrast in cancerous regions, improving the sensitivity of detection by 43%. Nevertheless, the added cost and lengthy administration time of the dye limits the availability of BLC for surveillance. Here, we report the first demonstration of digital staining on clinical endoscopy videos collected with standard-of-care clinical equipment to convert WLC images to accurate BLC-like images. We introduce key pre-processing steps to circumvent color and brightness variations in clinical datasets needed for successful model performance; the results show excellent qualitative and quantitative agreement of the digitally stained WLC (dsWLC) images with ground truth BLC images as measured through staining accuracy analysis and color consistency assessment. In short, dsWLC can provide the fluorescent contrast needed to improve the detection sensitivity of bladder cancer, thereby increasing the accessibility of BLC contrast for bladder cancer surveillance use without the cost and time burden associated with the dye and specialized equipment.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.