Search

Background: Bladder cancer (BCa) is the second most common type of cancer in the genitourinary system and causes approximately 165,000 deaths each year. The diagnosis of BCa is primarily done through cystoscopy, which involves visually examining the bladder using an endoscope. Currently, white light cystoscopy is considered the most reliable method for diagnosis. However, it can be challenging to detect and diagnose flat, small, or poorly textured lesions. The study explores the performance of deep learning systems (YOLOv7- tiny, RT-DETR18), originally designed for detecting adenomas in colonoscopy images, when retrained and tested with cystoscopy images. The deep neural network used in the study was pre-trained on 35,699 colonoscopy images (some from Mannheim) and both architectures achieved a F1 score of 0.91 on publicly available colonoscopy datasets. Results: When the adenoma-detection network was tested with cystoscopy images from two sources (Ulm and Erlangen), F1 scores ranging from 0.58 to 0.81 were achieved. Subsequently, the networks were retrained using 12,066 cystoscopy images from Mannheim, resulting in improved F1 scores ranging from 0.77 to 0.85. Conclusion: It could be shown that transformer based networks perform slightly better than YOLOv7-tiny networks, but both network types are feasable for lesion detection in the human bladder. The retraining of the network with additional cystoscopy data led to an improvement in the performance of urinary lesion detection. This suggests that it is possible to achieve a domain-shift with the inclusion of appropriate additional data.

Background: Bladder cancer (BCa) is the second most common genitourinary malignancy and has a mortality of 165,000 deaths p.a. The diagnosis of BCa is mostly carried out using cystoscopy - the visual examination of the urinary bladder with an endoscope. White light cystoscopy is currently considered as gold standard for the diagnosis. Nevertheless, especially flat, small or weakly textured lesions, are very difficult to detect and diagnose. Objective: With the advent of deep learning and already commercially available systems for the detection of adenomas in colonoscopy, it is investigated how such a system - for colonoscopy - performs if retrained and tested with cystoscopy images. Methods: A deep neural network with a YOLOv7-tiny architecture was pre-trained on 35,699 colonoscopy images (partially from Mannheim), yielding a precision = 0.92, sensitivity = 0.90, F1 = 0.91 on public colonoscopy data collections. Results: Testing this adenomadetection network with cystoscopy images from three sources (Ulm, Erlangen, Pforzheim), F1 scores in the range of 0.67 to 0.74 could be achieved. The network was then retrained with 12,066 cystoscopy images (from Mannheim), yielding improved F1 scores in the range of 0.78 to 0.85. Conclusion: It could be shown that a deep learning network for adenoma detection in colonoscopy is ad-hoc able to detect approximately 75% of the lesions in the urinary bladder in cystoscopy images, suggesting that these lesions have a similar appearance. After retraining the network with additional cystoscopy data, the performance for urinary lesion detection could be improved, indicating that a domain-shift with adequate additional data is feasible.

Introduction: Early detection of adenomas and polyps is one central goal of colonoscopic screening programs. As the adenoma detection rate (ADR) depends on the experience of the endoscopist, AI-based polyp detection systems can be used for real-time assistance. Hence, to support the physicians such AI-based systems using deep-convolutional neural networks (DCNNS) have been introduced in the past years. One disadvantage of these techniques is the need of a huge amount of labeled training data. Method: We investigate a "human-in-the-loop approach" to minimize the required time to generate labeled training data. The approach is evaluated within the training a YOLOv4 neural network to detect polyps in colonoscopic image data. The performance metrics of the neural network are evaluated on three public datasets. Results: The performance of the YOLO network increased from a precision of 0.88, recall of 0.83, F1 score of 0.86, and a F2 score of 0.86 to a precision of 0.91, recall of 0.87, F1 = of 0.89, and F2 = of 0.88. The interactive labelling of 1,000 images only takes one hours. Conclusion: The proposed "human-in-theloop approach" is capable of generating labelled image data in a minimum of time while increasing the performance metrics as well. For higher performance increase more data can now be labeled within this new approach.

Background: Bladder cancer (BCa) is the second most common genitourinary malignancy and has a mortality of 165,000 deaths p.a. The diagnosis of BCa is mostly carried out using cystoscopy - the visual examination of the urinary bladder with an endoscope. White light cystoscopy is currently considered as gold standard for the diagnosis. Nevertheless, especially flat, small or weakly textured lesions, are very difficult to detect and diagnose. Objective: With the advent of deep learning and already commercially available systems for the detection of adenomas in colonoscopy, it is investigated how such a system - for colonoscopy - performs if retrained and tested with cystoscopy images. Methods: A deep neural network with a YOLOv7-tiny architecture was pre-trained on 35,699 colonoscopy images (partially from Mannheim), yielding a precision = 0.92, sensitivity = 0.90, F1 = 0.91 on public colonoscopy data collections. Results: Testing this adenomadetection network with cystoscopy images from three sources (Ulm, Erlangen, Pforzheim), F1 scores in the range of 0.67 to 0.74 could be achieved. The network was then retrained with 12,066 cystoscopy images (from Mannheim), yielding improved F1 scores in the range of 0.78 to 0.85. Conclusion: It could be shown that a deep learning network for adenoma detection in colonoscopy is ad-hoc able to detect approximately 75% of the lesions in the urinary bladder in cystoscopy images, suggesting that these lesions have a similar appearance. After retraining the network with additional cystoscopy data, the performance for urinary lesion detection could be improved, indicating that a domain-shift with adequate additional data is feasible. [ABSTRACT FROM AUTHOR]

Abstract Background Despite all benefit provided by established therapies prognosis of gastric cancer remains poor. Targeted inhibition of platelet derived growth factor receptor (PDGFR) by imatinib may influence tumor growth and amplify chemotherapeutic effects. Methods This phase I study evaluated dose limiting toxicity (DLT) of imatinib combinated with chemotherapy according to a 3-patient cohort dose-escalating design. Thirty-five patients received cisplatin (60 mg/m2 d1 q 3w)/ capecitabine (1250 mg/m2 bid d1-14 q 21) or cisplatin (50 mg/m2 d1 q 2w)/ 5-fluoruracil (2 g/m2 d1, q 1w). Imatinib was started d - 4 with dose escalation from 300 to 700 mg QD in 100 mg steps. Results At imatinib dose level 1 (300mg) one DLT was observed, three more patients were enrolled without further DLT. At dose level 5 (700 mg) two gastric perforations occurred, so 600 mg imatinib emerged as the maximum tolerated dose. Major grade 3/4 toxicities were nausea (6%), anemia (6%) and fatigue (3%). Response evaluation revealed partial response in 27% and stable disease in 43% of the assessable patients. Conclusions Combination of imatinib and chemotherapy is well tolerated. Response rates were not superior to those of standard therapy. Further investigations of a larger group of patients are required to confirm the amplification of chemotherapy effects by imatinib. Trial registration European Clinical Trials Database: Eudra-CT2006-005792-17 and Clinical Trials Database: NCT00601510

Background: Large colonic polyps are associated with advanced dysplasia, but prevalence and characteristics of synchronous polyps in patients with large flat colonic polyps are poorly investigated. This study aims to characterize clinicopathological features of large flat colonic polyps and their impact on occurrence and characteristics of synchronous polyps. Methods: A total of 802 patients that underwent endoscopic mucosal resection (EMR) of flat colonic polyps >20 mm from 2003 to 2014 in an academic endoscopy unit were retrospectively analyzed for size, location and histology of large polyps and synchronous polyps. Results: Average size of large polyps was 34.1 mm (range 20-150 mm, standard deviation 16.1 mm). Histology included 52.5 % adenomas with low-grade dysplasia (LGD), 26.7 % with high-grade dysplasia (HGD), 9.6 % serrated polyps and 11.2 % adenocarcinomas. The majority of large polyps were localized in the proximal colon (61 %). 72.2 % of adenocarcinomas were found in the distal colon, while 80.5 % of all serrated polyps were detected in the proximal colon. Increase in polyp size, advanced age and location in the distal colon were associated with presence of HGD/ adenocarcinoma in large polyps, as identified by multivariate analysis. Synchronous polyps were detected in 67.2 % of patients undergoing complete colonoscopy during EMR. Presence of HGD/adenocarcinoma in the large polyp, localization of any synchronous polyp in the rectosigmoid colon and occurrence of multiple synchronous polyps were associated with presence of HGD/adenocarcinoma in synchronous polyps. Conclusions: Synchronous polyps are frequently found in patients with large flat colonic polyps. The prevalence of synchronous polyps with high grade dysplasia is highest in patients with large flat polyps containing HGD/ adenocarcinoma. [ABSTRACT FROM AUTHOR]