1
|
Lucas M, Liem EIML, Savci-Heijink CD, Freund JE, Marquering HA, van Leeuwen TG, de Bruin DM. Toward Automated In Vivo Bladder Tumor Stratification Using Confocal Laser Endomicroscopy. J Endourol 2019; 33:930-937. [PMID: 31657629 DOI: 10.1089/end.2019.0354] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/27/2022] Open
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.
Collapse
Affiliation(s)
- Marit Lucas
- Department of Biomedical Engineering and Physics, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.,Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands
| | - Esmee I M L Liem
- Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.,Department of Urology, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands
| | - C Dilara Savci-Heijink
- Department of Pathology, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands
| | - Jan Erik Freund
- Department of Urology, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.,Department of Pathology, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands
| | - Henk A Marquering
- Department of Biomedical Engineering and Physics, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.,Department of Radiology and Nuclear Medicine, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.,Amsterdam Cardiovascular Sciences, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.,Amsterdam Neuroscience, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands
| | - Ton G van Leeuwen
- Department of Biomedical Engineering and Physics, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.,Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.,Amsterdam Cardiovascular Sciences, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands
| | - Daniel M de Bruin
- Department of Biomedical Engineering and Physics, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.,Cancer Center Amsterdam, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.,Department of Urology, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands.,Amsterdam Cardiovascular Sciences, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands
| |
Collapse
|
2
|
Subiela J, Palou J, Esquinas C, Fernández Gómez J, Rodríguez Faba O. Clinical usefulness of random biopsies in diagnosis and treatment of non-muscle invasive bladder cancer: Systematic review and meta-analysis. Actas Urol Esp 2018; 42:285-298. [PMID: 29169705 DOI: 10.1016/j.acuro.2017.10.001] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2017] [Accepted: 10/10/2017] [Indexed: 11/27/2022]
Abstract
INTRODUCTION AND OBJECTIVE This systematic review of the literature has been focused on determining the clinical usefulness of random bladder biopsies (RB) in the diagnosis of carcinoma in situ. A meta-analysis was performed to establish the clinic and pathological factors associated to positive biopsies. EVIDENCE ACQUISITION A systematic review was performed using Pubmed/Medline database according to the PRISMA guidelines. Thirty-seven articles were included, recruiting a total of 12,657 patients, 10,975 were submitted to RB. EVIDENCE SYNTHESIS The overall incidence of positive RB was 21.91%. Significant differences were found in the incidence of positive RB when patients were stratified according to urine cytology result, tumor multiplicity, tumor appearance, stage and grade. The results of the meta-analysis revealed that the presence of positive cytology, tumor multiplicity, non-papillary appearance tumors, stage T1 and histological grades G2 and G3 represent the risk factors to predict abnormalities in RB. CONCLUSIONS The incidence of positive RB in patients with non-muscle invasive bladder cancer was 21.91%. The maximum usefulness of RB was observed when these are performed in a standardized way. The results of the meta-analysis showed that besides positive cytology and non-papillary appearance tumors, tumor multiplicity and histological grades G2 and G3 represent risk factors associated to positive RB, suggesting that the use of RB might be extensive to the intermediate risk group of the European Organization for Research and Treatment of Cancer (EORTC).
Collapse
|
3
|
Musser JE, O'Shaughnessy MJ, Kim PH, Herr HW. Bladder biopsy of normal-appearing mucosa is not helpful in patients with unexplained positive cytology after nonmuscle invasive bladder cancer. J Urol 2014; 193:48-52. [PMID: 24960468 DOI: 10.1016/j.juro.2014.06.068] [Citation(s) in RCA: 4] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/16/2014] [Indexed: 10/25/2022]
Abstract
PURPOSE Malignant voided cytology with normal endoscopic evaluation represents a diagnostic and therapeutic challenge in many patients with a history of nonmuscle invasive bladder cancer. Bladder biopsy is often advised but its efficacy is unclear. We evaluated the usefulness of bladder biopsy in patients with unexplained positive cytology and describe recurrence patterns in this unique patient subset. MATERIALS AND METHODS From an institutional database we retrospectively identified patients with a history of nonmuscle invasive bladder cancer and surveillance cystoscopy from 2008 to 2012 who had malignant voided urine cytology but normal cystoscopy. Patients underwent systematic bladder biopsy or cystoscopic surveillance and were followed for recurrence and progression. RESULTS Of 444 patients 343 were followed with surveillance only and 101 underwent a total of 118 biopsies of normal-appearing bladder mucosa. Three biopsies (2.5%) showed carcinoma in situ and none revealed invasive carcinoma. During the median 32-month followup recurrence developed in the bladder in 194 patients (44%), in the upper tract in 24 (5%) and in the prostatic urethra in 5 (1%) while 219 (49%) had no recurrence. A previous diagnosis of upper tract urothelial carcinoma and a history of bacillus Calmette-Guérin treatment were associated with an increased recurrence risk on multivariate analysis. Recurrence rates and patterns were similar in the biopsy and surveillance groups. CONCLUSIONS Patients with malignant cytology despite normal cystoscopy have a high recurrence rate. Biopsy of normal-appearing bladder mucosa in this setting is rarely positive and does not alter the recurrence pattern.
Collapse
Affiliation(s)
- John E Musser
- Urology Service, Department of Surgery, Memorial-Sloan Kettering Cancer Center, New York, New York.
| | - Matthew J O'Shaughnessy
- Urology Service, Department of Surgery, Memorial-Sloan Kettering Cancer Center, New York, New York
| | - Philip H Kim
- Urology Service, Department of Surgery, Memorial-Sloan Kettering Cancer Center, New York, New York
| | - Harry W Herr
- Urology Service, Department of Surgery, Memorial-Sloan Kettering Cancer Center, New York, New York
| |
Collapse
|
5
|
Shoshany O, Mano R, Margel D, Baniel J, Yossepowitch O. Presence of detrusor muscle in bladder tumor specimens--predictors and effect on outcome as a measure of resection quality. Urol Oncol 2013; 32:40.e17-22. [PMID: 23911682 DOI: 10.1016/j.urolonc.2013.04.009] [Citation(s) in RCA: 27] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/04/2013] [Revised: 03/31/2013] [Accepted: 04/23/2013] [Indexed: 10/26/2022]
Abstract
OBJECTIVES To identify predictors of the absence of detrusor muscle in bladder tumor specimens and analyze its effect on clinical outcome as an indicator of resection quality. METHODS The bladder cancer database of a tertiary medical center was queried for patients who underwent complete transurethral resection of bladder tumor (TURBT) between 2008 and 2009. Study end points were absence of detrusor muscle in the surgical specimen and its association with disease recurrence/progression. RESULTS Detrusor muscle in the surgical specimen was found in 265 of the 332 study patients (79%). The likelihood of finding muscle increased with higher clinical stage (Odds Ratio [OR]-1.8), higher tumor grade (OR-3), larger tumor size (OR-3.2), multifocal disease (OR-1.7), and nonpapillary morphology (OR-2.3). History of bladder cancer, surgeon's experience, and tumor location in the bladder had no effect. In the whole study population, neither tumor recurrence nor disease progression was associated with absence of detrusor muscle. In patients with T1 tumors, absence of detrusor muscle in the specimen was associated with higher early recurrence rate but not worse long-term outcome. CONCLUSIONS Absence of detrusor muscle in TURBT specimens is not determined by the technical difficulty of the procedure or surgical experience. Surgeons are more prone to obtain deep muscle in large, nonpapillary-appearing tumors, likely reflecting efforts to attain accurate staging in these cases. The presence or absence of detrusor muscle may serve as a surrogate of resection quality in patients with T1 tumors, but its general applicability to the overall population of patients undergoing TURBT remains questionable.
Collapse
Affiliation(s)
- Ohad Shoshany
- Department of Urology, Rabin Medical Center, Beilinson Campus, Petah-Tikva, Israel; Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Roy Mano
- Department of Urology, Rabin Medical Center, Beilinson Campus, Petah-Tikva, Israel; Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - David Margel
- Department of Urology, Rabin Medical Center, Beilinson Campus, Petah-Tikva, Israel; Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Jack Baniel
- Department of Urology, Rabin Medical Center, Beilinson Campus, Petah-Tikva, Israel; Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Ofer Yossepowitch
- Department of Urology, Rabin Medical Center, Beilinson Campus, Petah-Tikva, Israel; Sackler Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.
| |
Collapse
|
6
|
Gudjónsson S, Bläckberg M, Chebil G, Jahnson S, Olsson H, Bendahl PO, Månsson W, Liedberg F. The value of bladder mapping and prostatic urethra biopsies for detection of carcinoma in situ (CIS). BJU Int 2011; 110:E41-5. [PMID: 22035276 DOI: 10.1111/j.1464-410x.2011.10654.x] [Citation(s) in RCA: 11] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
Abstract
UNLABELLED It is well known that CIS is a major risk factor for muscle-invasive bladder cancer and that this entity can be difficult to diagnose. Taking cold-cup mapping biopsies from different areas of the bladder (BMAP) is commonly used in patients at risk of harbouring CIS. The diagnostic accuracy of this approach has not been assessed until now. By using the CIS found in the cystoprostatectomy specimen as an indicator of the true occurrence of CIS and comparing that with the findings of BMAP, it is clear that the sensitivity of BMAP to detect CIS when present is low and that negative findings should be considered unreliable. OBJECTIVES To assess the value of bladder mapping and prostatic urethra biopsies for detection of urothelial carcinoma in situ (CIS). CIS of the urinary bladder is a flat high-grade lesion of the mucosa associated with a significant risk of progression to muscle-invasive disease. CIS is difficult to identify on cystoscopy, and definite diagnosis requires histopathology. Traditionally, if CIS is suspected, multiple cold-cup biopsies are taken from the bladder mucosa, and resection biopsies are obtained from the prostatic urethra in males. This approach is often called bladder mapping (BMAP). The accuracy of BMAP as a diagnostic tool is not known. PATIENTS AND METHODS Male patients with bladder cancer scheduled for cystectomy underwent cold-cup bladder biopsies (sidewalls, posterior wall, dome, trigone), and resection biopsies were taken from the prostatic urethra. After cystectomy, the surgical specimen was investigated in a standardised manner and subsequently compared with the BMAP biopsies for the presence of CIS. RESULTS The histopathology reports of 162 patients were analysed. CIS was detected in 46% of the cystoprostatectomy specimens, and multiple (≥2) CIS lesions were found in 30%. BMAP (cold-cup bladder biopsies + resection biopsies from the prostatic urethra) provided sensitivity of 51% for any CIS, and 55% for multiple CIS lesions. The cold-cup biopsies for CIS in the bladder mucosa showed sensitivity and specificity of 46% and 89%, respectively. CONCLUSION Traditional cold-cup biopsies are unreliable for detecting CIS in bladder mucosa and negative findings must be interpreted with caution.
Collapse
|