Automated tumour budding quantification by machine learning augments TNM staging in muscle-invasive bladder cancer prognosis

The clinical staging and prognosis of muscle-invasive bladder cancer (MIBC) routinely includes the assessment of patient tissue samples by a pathologist. Recent studies corroborate the importance of image analysis in identifying and quantifying immunological markers from tissue samples that can provide further insight into patient prognosis. In this paper, we apply multiplex immunofluorescence to MIBC tissue sections to capture whole-slide images and quantify potential prognostic markers related to lymphocytes, macrophages, tumour buds, and PD-L1. We propose a machine-learning-based approach for the prediction of 5 year prognosis with different combinations of image, clinical, and spatial features. An ensemble model comprising several functionally different models successfully stratifies MIBC patients into two risk groups with high statistical significance (p value < 1×10−5). Critical to improving MIBC survival rates, our method correctly classifies 71.4% of the patients who succumb to MIBC, which is significantly more than the 28.6% of the current clinical gold standard, the TNM staging system.

Download Full-text

Identification of Immunological Features Enables Survival Prediction of Muscle-Invasive Bladder Cancer Patients Using Machine Learning

10.1101/2020.02.24.963181 ◽

2020 ◽

Author(s):

Christos G Gavriel ◽

Neofytos Dimitriou ◽

Nicolas Brieu ◽

Ines P Nearchou ◽

Ognjen Arandjelović ◽

...

Keyword(s):

Machine Learning ◽

Bladder Cancer ◽

Statistical Significance ◽

Tnm Staging ◽

Clinical Staging ◽

Invasive Bladder Cancer ◽

Survival Prediction ◽

Muscle Invasive Bladder Cancer ◽

Tissue Samples ◽

Muscle Invasive

AbstractClinical staging and prognosis of muscle-invasive bladder cancer (MIBC) routinely includes assessment of patient tissue samples by a pathologist. Recent studies corroborate the importance of image analysis in identifying and quantifying immunological markers from tissue samples that can provide further insights into patient prognosis. In this paper, we apply multiplex immunofluorescence on MIBC tissue sections to capture whole slide images and quantify potential prognostic markers related to lymphocytes, macrophages, tumour buds, and PD-L1. We propose a machine learning based approach for the prediction of 5 year prognosis with different combinations of image, clinical, and spatial features. An ensemble model comprising several functionally different models successfully stratifies MIBC patients into two risk groups with high statistical significance (p value < 1e − 05). Critical to improving MIBC survival rates, our method classifies correctly 71.4% of the patients who succumb to MIBC within 5 years, significantly higher than the 28.6% of the current clinical gold standard, the TNM staging system.

Download Full-text

Augmenting TNM staging with machine learning-based immune profiling for improved prognosis prediction in muscle-invasive bladder cancer patients

Annals of Oncology ◽

10.1093/annonc/mdy269.091 ◽

2018 ◽

Vol 29 ◽

pp. viii28-viii29 ◽

Cited By ~ 3

Author(s):

N. Brieu ◽

C.G. Gavriel ◽

D.J. Harrison ◽

G. Schmidt ◽

P.D. Caie

Keyword(s):

Machine Learning ◽

Bladder Cancer ◽

Cancer Patients ◽

Tnm Staging ◽

Invasive Bladder Cancer ◽

Muscle Invasive Bladder Cancer ◽

Prognosis Prediction ◽

Muscle Invasive ◽

Immune Profiling

Download Full-text

The Effect of Tri-Modality Therapy with Bladder Preservation for Selective Muscle-Invasive Bladder Cancer

Technology in Cancer Research & Treatment ◽

10.1177/15330338211062323 ◽

2021 ◽

Vol 20 ◽

pp. 153303382110623

Author(s):

Zhang Zhiyu ◽

Zhou Qi ◽

Song Zhen ◽

Ouyang Jun ◽

Zhang Jianglei

Keyword(s):

Risk Factors ◽

Bladder Cancer ◽

Linear Regression Analysis ◽

Univariate Analysis ◽

Tnm Staging ◽

Invasive Bladder Cancer ◽

Muscle Invasive Bladder Cancer ◽

Bladder Preservation ◽

Significant Difference ◽

Muscle Invasive

Objectives: To compare the efficacy of complete transurethral resection of bladder tumor combined with postoperative chemoradiotherapy and radical cystectomy (RC) in the treatment of muscle-invasive bladder cancer (MIBC). Methods: This is a single-center, retrospective study. Clinical data of 125 patients with MIBC admitted to the First Affiliated Hospital of Soochow University from December 2012 to December 2015 were retrospectively analyzed, in which 79 patients (tri-modality therapy [TMT] group) received TMT bladder-sparing treatment, and 41 patients (RC group) received RC. The differences of probabilities for 1-year, 2-year, 5-year, and comprehensive overall survival (OS), progress-free survival (PFS) between 2 groups were calculated using Kaplan–Meier product limited estimates. Univariate and multivariate analyses were performed to detect potential risk factors for OS and PFS. Results: There was no statistical difference between the TMT group and RC group in the 1-year, 2-year, 5-year, comprehensive OS rate, and PFS rate. And survival analysis found no significant difference in OS and PFS between the 2 groups. Univariate analysis showed that age, TNM staging, and prognostic nutritional index (PNI) were associated with OS, while PNI was connected to tumor recurrence. Multiple linear regression analysis indicated that TNM staging and PNI were independent risk factors for OS. Conclusions: TMT can be used as an alternative to RC for MIBC patients under the premise of strict control of indications, rigorous postoperative follow-up, and timely salvage cystectomy. PNI was negatively correlated with OS and PFS, while TNM staging was positively correlated with OS.

Download Full-text

Prediction of non-muscle invasive bladder cancer recurrence using machine learning of quantitative nuclear features

Modern Pathology ◽

10.1038/s41379-021-00955-y ◽

2021 ◽

Author(s):

Naoto Tokuyama ◽

Akira Saito ◽

Ryu Muraoka ◽

Shuya Matsubara ◽

Takeshi Hashimoto ◽

...

Keyword(s):

Machine Learning ◽

Support Vector Machine ◽

Bladder Cancer ◽

Random Forest ◽

Machine Learning Algorithms ◽

Invasive Bladder Cancer ◽

Support Vector ◽

Muscle Invasive Bladder Cancer ◽

Nuclear Atypia ◽

Muscle Invasive

AbstractNon-muscle invasive bladder cancer (NMIBC) generally has a good prognosis; however, recurrence after transurethral resection (TUR), the standard primary treatment, is a major problem. Clinical management after TUR has been based on risk classification using clinicopathological factors, but these classifications are not complete. In this study, we attempted to predict early recurrence of NMIBC based on machine learning of quantitative morphological features. In general, structural, cellular, and nuclear atypia are evaluated to determine cancer atypia. However, since it is difficult to accurately quantify structural atypia from TUR specimens, in this study, we used only nuclear atypia and analyzed it using feature extraction followed by classification using Support Vector Machine and Random Forest machine learning algorithms. For the analysis, 125 patients diagnosed with NMIBC were used; data from 95 patients were randomly selected for the training set, and data from 30 patients were randomly selected for the test set. The results showed that the support vector machine-based model predicted recurrence within 2 years after TUR with a probability of 90% and the random forest-based model with probability of 86.7%. In the future, the system can be used to objectively predict NMIBC recurrence after TUR.

Download Full-text

MicroRNA Dysregulation and Non-Muscle–Invasive Bladder Cancer Prognosis

Cancer Epidemiology Biomarkers & Prevention ◽

10.1158/1055-9965.epi-18-0884 ◽

2019 ◽

Vol 28 (4) ◽

pp. 782-788 ◽

Cited By ~ 7

Author(s):

Angeline S. Andrew ◽

Margaret R. Karagas ◽

Florian R. Schroeck ◽

Carmen J. Marsit ◽

Alan R. Schned ◽

...

Keyword(s):

Bladder Cancer ◽

Cancer Prognosis ◽

Invasive Bladder Cancer ◽

Muscle Invasive Bladder Cancer ◽

Muscle Invasive ◽

Microrna Dysregulation

Download Full-text

Inflammatory-Related Genetic Variants in Non–Muscle-Invasive Bladder Cancer Prognosis: A Multimarker Bayesian Assessment

Cancer Epidemiology Biomarkers & Prevention ◽

10.1158/1055-9965.epi-15-0894 ◽

2016 ◽

Vol 25 (7) ◽

pp. 1144-1150 ◽

Cited By ~ 5

Author(s):

Alexandra Masson-Lecomte ◽

Evangelina López de Maturana ◽

Michael E. Goddard ◽

Antoni Picornell ◽

Marta Rava ◽

...

Keyword(s):

Bladder Cancer ◽

Genetic Variants ◽

Cancer Prognosis ◽

Invasive Bladder Cancer ◽

Muscle Invasive Bladder Cancer ◽

Muscle Invasive

Download Full-text

1042 Association between PDL1 variants and muscle invasive bladder cancer prognosis

European Urology Supplements ◽

10.1016/s1569-9056(16)61043-6 ◽

2016 ◽

Vol 15 (3) ◽

pp. e1042

Author(s):

A.J.A.M. Masson-Lecomte ◽

S. Pineda ◽

M. Rava ◽

A. Carrato ◽

A. Tàrdon ◽

...

Keyword(s):

Bladder Cancer ◽

Cancer Prognosis ◽

Invasive Bladder Cancer ◽

Muscle Invasive Bladder Cancer ◽

Muscle Invasive

Download Full-text

Intravesical Prostatic Protrusion and Prognosis of Non-Muscle Invasive Bladder Cancer: Analysis of Long-Term Data over 5 Years with Machine-Learning Algorithms

Journal of Clinical Medicine ◽

10.3390/jcm10184263 ◽

2021 ◽

Vol 10 (18) ◽

pp. 4263

Author(s):

Junghoon Lee ◽

Min Soo Choo ◽

Sangjun Yoo ◽

Min Chul Cho ◽

Hwancheol Son ◽

...

Keyword(s):

Machine Learning ◽

Bladder Cancer ◽

Machine Learning Algorithms ◽

Invasive Bladder Cancer ◽

Support Vector ◽

Recurrence Free Survival ◽

Bladder Tumors ◽

Muscle Invasive Bladder Cancer ◽

Free Survival ◽

Muscle Invasive

We aim to investigate the significance of intravesical prostate protrusion (IPP) on the prognosis of non-muscle invasive bladder cancer (NMIBC) after the transurethral resection of bladder tumors (TURBT). For newly diagnosed NMIBC, we retrospectively analyzed the association between prognosis and IPP for at least a 5-year follow-up. A degree of IPP over 5 mm in a preoperative CT scan was classified as severe. The primary endpoint was recurrence-free survival, and the secondary endpoint was progression-free survival. The machine learning (ML) algorithm of a support vector machine was used for predictive model development. Of a total of 122 patients, ultimately, severe IPP was observed in 33 patients (27.0%). IPP correlated positively with age, BPH, recurrence, and prognosis. Severe IPP was significantly higher in the recurrence group and reduced in the recurrence-free survival group (p = 0.038, p =0.032). Severe IPP independently increased the risk of intravesical recurrence by 2.6 times. The addition of IPP to the known oncological risk factors in the prediction model using the ML algorithm improved the predictability of cancer recurrence by approximately 6%, to 0.803. IPP was analyzed as a potential independent risk factor for NMIBC recurrence and progression after TURBT. This anatomical feature of the prostate could affect the recurrence of bladder tumors.

Download Full-text