Marit Lucas1,2, Esmee I M L Liem2,3, C Dilara Savci-Heijink4, Jan Erik Freund3,4, Henk A Marquering1,5,6,7, Ton G van Leeuwen1,2,6, Daniel M de Bruin1,2,3,6. 1. Department of Biomedical Engineering and Physics, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands. 2. Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands. 3. Department of Urology, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands. 4. Department of Pathology, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands. 5. Department of Radiology and Nuclear Medicine, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands. 6. Amsterdam Cardiovascular Sciences, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands. 7. Amsterdam Neuroscience, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.
Abstract
Purpose: 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 in vivo bladder lesions were evaluated in this study. Materials and Methods: 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 vs malignant tissue and (ii) low-grade vs high-grade papillary UCB. A total of 53 patients with 72 lesions were included in this study, resulting in ∼140,000 pCLE frames. Results: The semiautomated frame selection reduced the number of frames to ∼66,500 informative frames. The accuracy for differentiation of (i) healthy and benign vs malignant urothelium was 79% and (ii) high-grade and low-grade papillary UCB was 82%. Conclusions: A feature extractor in combination with LSTM results in proper stratification of pCLE videos of in vivo bladder lesions.
Purpose: 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 in vivo bladder lesions were evaluated in this study. Materials and Methods: 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 vs malignant tissue and (ii) low-grade vs high-grade papillary UCB. A total of 53 patients with 72 lesions were included in this study, resulting in ∼140,000 pCLE frames. Results: The semiautomated frame selection reduced the number of frames to ∼66,500 informative frames. The accuracy for differentiation of (i) healthy and benign vs malignant urothelium was 79% and (ii) high-grade and low-grade papillary UCB was 82%. Conclusions: A feature extractor in combination with LSTM results in proper stratification of pCLE videos of in vivo bladder lesions.
Entities:
Keywords:
bladder tumor; classification; confocal laser endomicroscopy; deep learning; long-short term memory
Authors: Lei Tian; Brady Hunt; Muyinatu A Lediju Bell; Ji Yi; Jason T Smith; Marien Ochoa; Xavier Intes; Nicholas J Durr Journal: Lasers Surg Med Date: 2021-05-20