Dataset Information

Deep learning-based classification of blue light cystoscopy imaging during transurethral resection of bladder tumors.

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.

SUBMITTER: Ali N

PROVIDER: S-EPMC8172542 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundTransurethral resection of bladder tumor (TURBT) is an essential procedure both for the treatment and staging of bladder cancer, particularly non-muscle invasive bladder cancer (NMIBC). The dissemination of cancer cells during resection and the consequent seeding into the bladder mucosa is the main cause of post-TURBT intravesical recurrence. Although the tumor dissemination is inevitable during conventional TURBT (cTURBT), this drawback can be overcome by tumor resection in one piece with intact surrounding normal tissues, referred to as en bloc resection. We previously described the photodynamic diagnosis (PDD)-assisted en bloc TURBT (EBTUR) technique and its favorable outcomes. Based on our preliminary studies, this randomized controlled trial was designed to evaluate the superiority of PDD-EBTUR to PDD-cTURBT.MethodsThe FLEBER study is a single-center randomized controlled trial in NMIBC patients who require TURBT. The longest diameter of the tumor must be between 6 and 30 mm. A total of 160 eligible patients will be enrolled after screening and randomly allocated to the PDD-EBTUR (experimental) and PDD-cTURBT (control) groups in a 1:1 ratio (80 cases to 80 cases). All patients will be treated using a single, immediate postoperative intravesical chemotherapy with epirubicin. The primary endpoint of this trial is the 2-year recurrence-free survival after surgery in pathologically proven low- or intermediate-risk NMIBC. All patients will be monitored by cystoscopy and urine cytology every 3 months for 2 years. Patient data including adverse events and complications, and data from frequency volume charts, pain scales, and health-related QOL questionnaires will be collected before and after the TURBT at indicated visits.DiscussionThe goal of this trial is to determine the potential benefits of PDD-cTURBT and PDD-EBTUR followed by a single immediate postoperative intravesical chemotherapy in patients with low- or intermediate-risk NMIBC who undergo TURBT. Ultimately, our findings will lead to the development of better interventions and potentially change the standard of care.Trial registrationThis clinical trial was prospectively registered with the UMIN Clinical Trials Registry on 1 August 2020. The reference number is UMIN000041273 , and the Ethics Committee of Nara Medical University Approval ID is 2702.

Dataset Information

Deep learning-based classification of blue light cystoscopy imaging during transurethral resection of bladder tumors.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets