Abstract
Bladder cancer is one of the top 10 frequently occurring cancers and leads to most cancer deaths worldwide. Recently, blue light (BL) cystoscopy-based photodynamic diagnosis was introduced as a unique technology to enhance the detection of bladder cancer, particularly for the detection of flat and small lesions. Here, we aim to demonstrate a BL image-based artificial intelligence (AI) diagnostic platform using 216 BL images, that were acquired in four different urological departments and pathologically identified with respect to cancer malignancy, invasiveness, and grading. Thereafter, four pre-trained convolution neural networks were utilized to predict image malignancy, invasiveness, and grading. The results indicated that the classification sensitivity and specificity of malignant lesions are 95.77% and 87.84%, while the mean sensitivity and mean specificity of tumor invasiveness are 88% and 96.56%, respectively. This small multicenter clinical study clearly shows the potential of AI based classification of BL images allowing for better treatment decisions and potentially higher detection rates.
Highlights
Bladder cancer is one of the top 10 frequently occurring cancers and leads to most cancer deaths worldwide
We present the classification results of blue light (BL) images using the previously explained fine-tuned convolutional neural networks (CNNs)
We can see that the numbers of collected images per class are different; class weights were considered to correct the unbalance within the data set while the CNNs were trained
Summary
Bladder cancer is one of the top 10 frequently occurring cancers and leads to most cancer deaths worldwide. A recent study established a classification system based on 233 images of bladder wall lesions that was able to identify cancerous formations with a very high sensitivity, but with a low specificity of 50%21. These preliminary findings are promising, further developments in automated image processing are highly appreciated in urological endoscopy. The aim of this study is to test the classification of a small BL image data set consisting of bladder tumor and healthy urothelium images This test was accomplished using an automated image processing pipelines and deep convolutional neural networks (CNNs) as a first step to implement computer-aided diagnosis in urological endoscopy. A comparison between the implemented CNN models and bladder cancer ratings of two experienced urologists was performed on the basis of the classification sensitivity
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
