Toward Automated <i>In Vivo</i> Bladder Tumor Stratification Using Confocal Laser Endomicroscopy

Abstract

<b><i>Purpose:</i></b> Urothelial carcinoma of the bladder (UCB) is the most common urinary cancer. White-light cystoscopy (WLC) forms the corner stone for the diagnosis of UCB. However, histopathological assessment is required for adjuvant treatment selection. Probe-based confocal laser endomicroscopy (pCLE) enables visualization of the microarchitecture of bladder lesions during WLC, which allows for real-time tissue differentiation and grading of UCB. To improve the diagnostic process of UCB, computer-aided classification of pCLE videos of <i>in vivo</i> bladder lesions were evaluated in this study. <b><i>Materials and Methods:</i></b> We implemented preprocessing methods to optimize contrast and to reduce striping artifacts in each individual pCLE frame. Subsequently, a semiautomatic frame selection was performed. The selected frames were used to train a feature extractor based on pretrained ImageNet networks. A recurrent neural network, in specific long short-term memory (LSTM), was used to predict the grade of bladder lesions. Differentiation of lesions was performed at two levels, namely (i) healthy and benign <i>vs</i> malignant tissue and (ii) low-grade <i>vs</i> high-grade papillary UCB. A total of 53 patients with 72 lesions were included in this study, resulting in ∼140,000 pCLE frames. <b><i>Results:</i></b> The semiautomated frame selection reduced the number of frames to ∼66,500 informative frames. The accuracy for differentiation of (i) healthy and benign <i>vs</i> malignant urothelium was 79% and (ii) high-grade and low-grade papillary UCB was 82%. <b><i>Conclusions:</i></b> A feature extractor in combination with LSTM results in proper stratification of pCLE videos of <i>in vivo</i> bladder lesions.