Direct Smear Versus Liquid-Based Cytology in the Diagnosis of Bladder Lesions

Kalantari, Mahmoud Reza; Jahanshahi, Mohammad Ali; Gharib, Masoumeh; Hashemi, Seyedeh‐Sara; Kalantari, Shakiba

doi:10.30699/ijp.2021.528171.2646

Cited by 5 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ThinPrep (Hologic, Inc., United States) and SurePath (Becton Dickinson, Inc., United States) for LBC specimen preparation have been approved by the US Food and Drug Administration (FDA). Compared to the conventional smear cytology, LBC has lower background elements, provides better cell preservation, and has a higher satisfaction rate [9]. As for the sensitivity, it has been reported that LBC achieved at 0.58 (CI: 0.51-0.65) and conventional smear achieved at 0.38 [4,8].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Screening of Urothelial Carcinoma in Whole Slide Images of Liquid-Based Cytology Urine Specimens

Abe¹,

Kanavati²

2022

Preprint

View full text Add to dashboard Cite

Urinary cytology is a useful, essential diagnostic method in routine urological clinical practice. Liquid-based cytology (LBC) for urothelial carcinoma screening is commonly used in the routine clinical cytodiagnosis because of its high cell collection rate. Since conventional screening processes by cytoscreeners and cytopathologists using microscopes is limited in terms of human resources, it is important to integrate new deep learning methods that can automatically and rapidly diagnose a large amount of specimens without delay. The goal of this study was to investigate the use of deep learning models for the classification of urine LBC whole-slide images (WSIs) into neoplastic and non-neoplastic (negative). We trained deep learning models using 786 WSIs by transfer learning, fully supervised, and weakly supervised learning approaches. We evaluated the trained models on two test sets (equal and clinical balance) with a combined total of 750 WSIs, achieving ROC-AUCs for WSI diagnosis in the range of 0.984-0.990 by the best model, demonstrating the promising potential use of our model for aiding urine cytodiagnostic processes.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep Learning-Based Screening of Urothelial Carcinoma in Whole Slide Images of Liquid-Based Cytology Urine Specimens

Abe¹,

Kanavati²

2022

Preprint

View full text Add to dashboard Cite

show abstract

Is prostatic adenocarcinoma detectable by urine cytology—A multicenter retrospective review

Tang,

Li,

Leung

et al. 2024

The Prostate

View full text Add to dashboard Cite

IntroductionUrine cytology is robust for the diagnosis of urothelial lesions, but data on the detection rates of prostatic adenocarcinoma in urine cytology is limited. In this study, a multicenter review was performed to define the clinical role of urine cytology in diagnosis of prostatic adenocarcinoma.MethodsCytologic diagnoses of lower tract urine cytology specimens with histology‐proven prostatic adenocarcinoma from three institutions, from a period of over two decades, were reviewed. Clinicopathological parameters—tumor grade, stage, histologic features, and preanalytical factors—prostate‐specific antigen (PSA) level and lesion size, were retrieved and compared with cytologic diagnoses.ResultsIn total, 2115 urine cytology specimens from 1119 patients were retrieved. The atypia (or above/C3+) and suspicious (or above/C4+) rates were 19.48% and 3.36%. Bilobar and extracapsular involvement, lymphovascular invasion, Gleason score, and International Society of Urological Pathology grade were associated with a positive urine diagnosis (p < 0.05). The atypia (C3+) and suspicious (C4+) rates of urine cytology in patients with a PSA level of ≤4.0 ng/mL was paradoxically higher (p < 0.01), but PSA levels correlated positively with urine diagnosis at higher cutoffs (>10, >20, >50, >100 ng/mL). All these factors remained significant on multivariate analysis (p < 0.05), including a negative correlation with low‐PSA (≤4.0 ng/mL, p = 0.001) and positive correlation with high‐PSA (>20 ng/mL, p = 0.020). Lesion size and multifocality were not associated with urine cytology diagnosis (p > 0.05).ConclusionUrine cytology showed low sensitivity in detection of prostatic adenocarcinoma. Detection rates were largely positively correlated with PSA levels but not for lesion size nor multifocality, limiting its clinical utility.

show abstract

Artificial intelligence algorithms enhance urine cytology reporting confidence in postoperative follow-up for upper urinary tract urothelial carcinoma

Chen,

Yen,

et al. 2024

Int Urol Nephrol

View full text Add to dashboard Cite

Direct Smear Versus Liquid-Based Cytology in the Diagnosis of Bladder Lesions

Cited by 5 publications

References 19 publications

Deep Learning-Based Screening of Urothelial Carcinoma in Whole Slide Images of Liquid-Based Cytology Urine Specimens

Deep Learning-Based Screening of Urothelial Carcinoma in Whole Slide Images of Liquid-Based Cytology Urine Specimens

Is prostatic adenocarcinoma detectable by urine cytology—A multicenter retrospective review

Artificial intelligence algorithms enhance urine cytology reporting confidence in postoperative follow-up for upper urinary tract urothelial carcinoma

Contact Info

Product

Resources

About