1
|
Sun K, Zheng Y, Yang X, Jia W. A novel transformer-based aggregation model for predicting gene mutations in lung adenocarcinoma. Med Biol Eng Comput 2024; 62:1427-1440. [PMID: 38233683 DOI: 10.1007/s11517-023-03004-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/02/2023] [Accepted: 12/11/2023] [Indexed: 01/19/2024]
Abstract
In recent years, predicting gene mutations on whole slide imaging (WSI) has gained prominence. The primary challenge is extracting global information and achieving unbiased semantic aggregation. To address this challenge, we propose a novel Transformer-based aggregation model, employing a self-learning weight aggregation mechanism to mitigate semantic bias caused by the abundance of features in WSI. Additionally, we adopt a random patch training method, which enhances model learning richness by randomly extracting feature vectors from WSI, thus addressing the issue of limited data. To demonstrate the model's effectiveness in predicting gene mutations, we leverage the lung adenocarcinoma dataset from Shandong Provincial Hospital for prior knowledge learning. Subsequently, we assess TP53, CSMD3, LRP1B, and TTN gene mutations using lung adenocarcinoma tissue pathology images and clinical data from The Cancer Genome Atlas (TCGA). The results indicate a notable increase in the AUC (Area Under the ROC Curve) value, averaging 4%, attesting to the model's performance improvement. Our research offers an efficient model to explore the correlation between pathological image features and molecular characteristics in lung adenocarcinoma patients. This model introduces a novel approach to clinical genetic testing, expected to enhance the efficiency of identifying molecular features and genetic testing in lung adenocarcinoma patients, ultimately providing more accurate and reliable results for related studies.
Collapse
Affiliation(s)
- Kai Sun
- School of Information Science and Engineering, Shandong Normal University, Jinan, Shandong, 250014, China
| | - Yuanjie Zheng
- School of Information Science and Engineering, Shandong Normal University, Jinan, Shandong, 250014, China.
| | - Xinbo Yang
- School of Information Science and Engineering, Shandong Normal University, Jinan, Shandong, 250014, China
| | - Weikuan Jia
- School of Information Science and Engineering, Shandong Normal University, Jinan, Shandong, 250014, China.
| |
Collapse
|
2
|
Palermo M, D'Elia C, Trenti E, Comploj E, Mian C, Schwienbacher C, Heidegger I, Clauser S, Pycha A, Vjaters E. Prospective evaluation of the RT-PCR based urinary marker Bladder Epicheck® as a diagnostic tool in upper urinary tract tumor. Minerva Urol Nephrol 2024; 76:195-202. [PMID: 38498297 DOI: 10.23736/s2724-6051.23.05488-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/20/2024]
Abstract
BACKGROUND Upper-tract-urothelial-carcinoma (UTUC) represents 5-10% of all urothelial-neoplasms with increasing incidence in the last decades. Current standard tools for diagnosis of UTUC include cytology, computed tomography (CT) urography and ureterorenoscopy (URS). The aim of this study was to evaluate the impact of Bladder Epicheck® Test as diagnostic tool for UTUC diagnosis and recurrence. METHODS Overall, 136 urine samples, selective collected from upper-urinary-tract before URS for suspicion of UTUC were analyzed with cytology and Bladder Epicheck® Test. Sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of both markers were calculated and compared to URS and/or histology as reference. RESULTS UTUC was detected in 40 cases (33.3%), among them 30 were classified as low-grade (LG) and 10 as high-grade (HG). Overall sensitivity of Bladder Epicheck® for UTUC detection was 65% compared to 42.5% for cytology, increasing to 100% for Bladder Epicheck® and 90% for cytology if considering only HG tumors. Overall specificity of Bladder Epicheck® was 81.2% and of cytology 93.7%. PPV and NPV were 63.4% and 82.2% for Bladder Epicheck® and 77.2% and 76.5% for cytology. Considering an EpiScore cut-off >75, instead of 60, specificity of Bladder Epicheck® improves to 89% and PPV to 74.2%. Limitations include the use of a marker validated only for bladder-cancer and the relatively small number of cases. CONCLUSIONS Due to its high sensitivity for HG tumors, the Bladder Epicheck® Test can be used in diagnosis and treatment decision-making of UTUC. Furthermore, it could be very useful in follow-up of UTUC, after endoscopic treatment to postpone or avoid unnecessary endoscopic exploration. Even if further studies are needed to validate these findings, Bladder Epicheck® could be a promising clinical tool for detection of UTUC.
Collapse
Affiliation(s)
| | - Carolina D'Elia
- Department of Urology, Central Hospital of Bolzano, Bolzano, Italy
| | - Emanuela Trenti
- Department of Urology, Central Hospital of Bolzano, Bolzano, Italy -
| | - Evi Comploj
- Department of Urology, Central Hospital of Bolzano, Bolzano, Italy
| | - Christine Mian
- Department of Pathology, Central Hospital of Bolzano, Bolzano, Italy
| | | | - Isabel Heidegger
- Department of Urology, Medical University of Innsbruck, Innsbruck, Austria
| | - Silvia Clauser
- Department of Urology, Central Hospital of Bolzano, Bolzano, Italy
| | - Armin Pycha
- Department of Urology, Central Hospital of Bolzano, Bolzano, Italy
- Medical School, Sigmund Freud Private University, Vienna, Austria
| | - Egils Vjaters
- Department of Urology, Riga Stradins University Hospital, Riga, Latvia
| |
Collapse
|
3
|
Carmona O, Kleinmann N, Zilberman DE, Dotan ZA, Shvero A. Do Urine Cytology and FISH Analysis Have a Role in the Follow-Up Protocol of Upper Tract Urothelial Carcinoma? Clin Genitourin Cancer 2024; 22:98-105. [PMID: 37996271 DOI: 10.1016/j.clgc.2023.10.010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/08/2023] [Revised: 10/24/2023] [Accepted: 10/29/2023] [Indexed: 11/25/2023]
Abstract
BACKGROUND Current guidelines recommend a stringent follow-up regimen that includes interval cystoureteronephscopy, CT urography, and selective urine cytology sampling for upper tract urothelial carcinoma (UTUC) patients undergoing endoscopic treatment and management. There are no recommendations regarding FISH analysis. Our purpose was to assess the efficacy of cytology and FISH as part of the follow-up protocol and its significance to clinical decision-making in this scenario. METHODS The medical records of all patients who managed endoscopically for UTUC at our institute between 2014 and 2022 were retrospectively analyzed. Demographic and clinical data, histology, cytology, and FISH results were collected. FISH analysis was considered malignant according to Paris criteria. RESULTS During the study period, 62 patients underwent 561 ureteroscopies as part of the treatment and follow-up regimen of low-grade UTUC. Urine from the affected upper tract was sampled for cytology in 377 procedures, and FISH analyses were performed in 273. In 75.4% of FISH analyses, the result was different from the cytology results: FISH found malignant aberrations in 15.5% of cases where cytology was benign. Furthermore, FISH classified all the cells defined as atypical via cytology as either benign or malignant. In only one case (0.17%), the urinary cytology report changed the follow-up regimen. CONCLUSION Cytology may be omitted from the follow-up protocol of low-grade UTUC. In the handful of cases cytology does assist the diagnosis of UTUC, there is an additional benefit to performing FISH analysis, particularly when cellular atypia is reported in the cytology results.
Collapse
Affiliation(s)
- Orel Carmona
- The Department of Urology, Sheba Medical Center, Ramat Gan, Israel; The School of Medicine, Tel Aviv University, Tel Aviv, Israel.
| | - Nir Kleinmann
- The Department of Urology, Sheba Medical Center, Ramat Gan, Israel; The School of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Dorit E Zilberman
- The Department of Urology, Sheba Medical Center, Ramat Gan, Israel; The School of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Zohar A Dotan
- The Department of Urology, Sheba Medical Center, Ramat Gan, Israel; The School of Medicine, Tel Aviv University, Tel Aviv, Israel
| | - Asaf Shvero
- The Department of Urology, Sheba Medical Center, Ramat Gan, Israel; The School of Medicine, Tel Aviv University, Tel Aviv, Israel
| |
Collapse
|
4
|
Xu B, Zhang JE, Ye L, Yuan CW. Evaluation of the diagnostic efficiency of voided urine fluorescence in situ hybridization for predicting the pathology of preoperative "low-risk" upper tract urothelial carcinoma. Front Oncol 2023; 13:1225428. [PMID: 37576882 PMCID: PMC10412927 DOI: 10.3389/fonc.2023.1225428] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2023] [Accepted: 07/03/2023] [Indexed: 08/15/2023] Open
Abstract
Objectives To evaluate the clinical utility of voided urine fluorescence in situ hybridization (FISH) for predicting the pathology of preoperative "low-risk" upper tract urothelial carcinoma (UTUC). Methods Information of patients preoperatively diagnosed with "low-risk" UTUC receiving radical nephroureterectomy (RNU) between May 2014 and October 2019 were retrospectively collected. All of the patients accepted the FISH test and then were divided into two groups according to the results of FISH. The diagnostic value of FISH was assessed through the receiver operating characteristics (ROC) curve and area under the curve. Logistic regression analysis was applied to examine FISH as a predictive factor of tumor final stage and grade of preoperative "low-risk" UTUC. Results In total, 129 patients were included. Of them, 70 (54.2%) were marked with positive FISH result. The difference at final pathology in tumor stage and tumor grade between these two groups of FISH (-) and FISH (+) had significantly statistical significance (p<0.001). Regarding to the tumor stage at final pathology, the sensitivity, specificity, positive predictive value and negative predictive value of FISH were 70.7 (58.9-80.3)68.5 (54.3-80.1)75.7 (63.7-84.8) and 62.7 (49.1-74.7), respectively. Regarding to the tumor grade at final pathology, the sensitivity, specificity, positive predictive value and negative predictive value of FISH were 64.7 (53.5-74.6), 65.9 (50.0-79.1), 78.6 (66.8-87.1) and 49.1 (36.5-62.3), respectively. The results of logistic regression analysis indicated that FISH could predict the pathologic characteristics of preoperative "low-risk" UTUC independently. Conclusions FISH was qualified with relatively high diagnostic estimates for predicting tumor stage and grade of preoperative "low-risk" UTUC, and could be an independent predictive factor in clinical practice. For preoperative "low-risk" UTUC patients but with positive FISH result, choosing nephron-sparing surgery may require special caution.
Collapse
Affiliation(s)
- Ben Xu
- Department of Urology, Peking University First Hospital, Beijing, China
| | | | | | | |
Collapse
|
5
|
Krajewski W, Łaszkiewicz J, Nowak Ł, Szydełko T. Current methods facilitating diagnosis of upper tract urothelial carcinoma: a comprehensive literature review. Curr Opin Urol 2023; 33:230-238. [PMID: 36727755 DOI: 10.1097/mou.0000000000001078] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/03/2023]
Abstract
PURPOSE OF REVIEW Currently, kidney-sparing surgeries are considered the preferred approach in low-risk tumours and in selected high-risk patients. Therefore, accurate diagnosis of UTUC is crucial for further management. The purpose of this review is to summarize available methods facilitating the diagnosis of upper tract urothelial carcinoma (UTUC). RECENT FINDINGS Recent articles propose numerous techniques of UTUC diagnosis. In this review, imaging, as well as, urine-based and endoscopic methods have been described and assessed. SUMMARY Regarding imaging, computed tomography urography remains a gold standard, while PET is superior in search for small lesions and nodal metastases. However, contrast-enhanced ultrasonography also shows promise. On the contrary, available urine tests, such as urinary cytology, fluorescent in-situ hybridization, Xpert, DNA methylation analysis, urine-based liquid biopsy, p16/Ki-67 dual immunolabelling, ImmunoCyt and NMP22 are either poorly researched, or not accurate enough to use solely. Finally, during ureterorenoscopy, photodynamic diagnosis and narrow-band imaging can facilitate proper visualization of the tumor. Endoluminal ultrasonography and confocal laser endomicroscopy can potentially improve staging and grading of UTUC. Also, the 'form tackle' biopsy should be performed using a basket in papillary lesions and cold-cup biopsy of flat or sessile lesions. Even though cryobiopsy shows promise in UTUC diagnosis, in-vivo studies are necessary before it is introduced into clinical practice.
Collapse
Affiliation(s)
- Wojciech Krajewski
- Department of Minimally Invasive and Robotic Urology, University Center of Excellence in Urology, Wroclaw Medical University, Wroclaw, Poland
| | | | | | | |
Collapse
|
6
|
Pycha S, Trenti E, Mian C, Schwienbacher C, Hanspeter E, Palermo M, Pycha A, Danuser H, D'Elia C. Diagnostic value of Xpert® BC Detection, Bladder Epicheck®, Urovysion® FISH and cytology in the detection of upper urinary tract urothelial carcinoma. World J Urol 2023; 41:1323-1328. [PMID: 36929411 DOI: 10.1007/s00345-023-04350-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/15/2022] [Accepted: 02/26/2023] [Indexed: 03/18/2023] Open
Abstract
PURPOSE Following the current guidelines, diagnosis and staging for upper urinary tract tumours (UTUC) can be performed with Computed Tomography, urography, ureterorenoscopy (URS) and selective cytology. The aim of the study was to evaluate the performance of the Xpert®-BC-Detection and the Bladder-Epicheck®-test in the detection of UTUC and compare it with cytology and the Urovysion®-FISH test using histology and URS as gold standard. METHODS A total of 97 analyses were collected through selective catheterization of the ureter before URS to test for cytology, Xpert®-BC-Detection, Bladder-Epicheck® and Urovysion®-FISH. Sensitivity, specificity, and predictive values were calculated using histology results/URS as reference. RESULTS Overall sensitivity was 100% for Xpert®-BC-Detection, 41.9% for cytology, 64.5% for Bladder-Epicheck® and 87.1% for Urovysion®-FISH. The sensitivity of Xpert®-BC-Detection was 100% in both, LG and HG tumours, sensitivity of cytology increased from 30.8% in LG to 100% in HG, for Bladder-Epicheck® from 57.7% in LG to 100% in HG and of Urovysion®-FISH from 84.6% in LG to 100% in HG tumours. Specificity was 4.5% for Xpert®-BC-Detection, 93.9% for cytology, 78.8% for Bladder-Epicheck® and 81.8% for Urovysion®-FISH. PPV was 33% for Xpert®-BC-Detection, 76.5% for cytology, 58.8% for Bladder-Epicheck® and 69.2% for Urovysion®FISH. NPV was 100% for Xpert®-BC-Detection, 77.5% for cytology, 82.5% for Bladder-Epicheck® and 93.1% for Urovysion®FISH. CONCLUSION Bladder-Epicheck® and Urovysion®FISH along with cytology could be a helpful ancillary method in the diagnosis and follow-up of UTUC while due to its low specificity Xpert®-BC Detection seems to be of limited usefulness.
Collapse
Affiliation(s)
- Stefan Pycha
- University of Bern, Faculty of Medicine, Bern, Switzerland
| | - Emanuela Trenti
- Department of Urology, Provincial Hospital of Bolzano, Lorenz Böhler St 5, 39100, Bolzano, Italy.
| | - Christine Mian
- Department of Pathology, Provincial Hospital of Bolzano, Bolzano, Italy
| | | | - Esther Hanspeter
- Department of Pathology, Provincial Hospital of Bolzano, Bolzano, Italy
| | | | - Armin Pycha
- Department of Urology, Provincial Hospital of Bolzano, Lorenz Böhler St 5, 39100, Bolzano, Italy.,Sigmund Freud Private University, Vienna, Austria
| | | | - Carolina D'Elia
- Department of Urology, Provincial Hospital of Bolzano, Lorenz Böhler St 5, 39100, Bolzano, Italy
| |
Collapse
|
7
|
Aalami AH, Abdeahad H, Aalami F, Amirabadi A. Can microRNAs be utilized as tumor markers for recurrence following nephrectomy in renal cell carcinoma patients? A meta-analysis provides the answer. Urol Oncol 2023; 41:52.e1-52.e10. [PMID: 36280530 DOI: 10.1016/j.urolonc.2022.09.022] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2022] [Revised: 09/07/2022] [Accepted: 09/22/2022] [Indexed: 11/24/2022]
Abstract
INTRODUCTION Renal cell carcinoma (RCC) is an aggressive tumor. Many studies investigated microRNAs (miRs) as RCC prognostic biomarkers, often reporting inconsistent findings. We present a meta-analysis to identify if tissue-derived miRs can be used as a prognostic factor in patients after nephrectomy. METHODS Data were obtained from PubMed, Embase, and Web of Science. The hazard ratio with 95% confidence intervals assessed the prognostic value of microRNAs. Outcomes of interest included the prognosis role of microRNAs in overall survival (OS), recurrence-free survival (RFS), and cancer-specific survival (CSS) in nephrectomy patients. RESULTS Nine retrospective studies that evaluated microRNAs in 1,541 nephrectomy patients were collected. There were heterogeneities across studies for microRNAs in the 15 studies examining OS, RFS, and CSS (I2 = 84.51%; P < 0.01); the random-effect model was calculated (HR = 1.371; (95% CI: 0.831-2.260); P = 0.216). CONCLUSION Our study indicated that miRNAs cannot be used as a marker for recurrence in RCC patients after nephrectomy, and researchers shouldn't make the mistake that if miRs can be used as a biomarker in RCC, they cannot be used as a marker after nephrectomy in RCC. As all of these findings were from retrospective studies, further studies are needed to verify the role of microRNAs in clinical trials.
Collapse
Affiliation(s)
- Amir Hossein Aalami
- Department of Biology, Mashhad Branch, Islamic Azad University, Mashhad, Iran.
| | - Hossein Abdeahad
- Department of Nutrition and Integrative Physiology, University of Utah, Salt Lake City, UT, USA
| | - Farnoosh Aalami
- Student Research Committee, Faculty of Medicine, North Khorasan University of Medical Sciences, Bojnurd, Iran
| | - Amir Amirabadi
- Department of Internal Medicine, Mashhad Medical Sciences Branch, Islamic Azad University, Mashhad, Iran
| |
Collapse
|