Transurethral En Bloc Resection Versus Standard Resection of Bladder Tumour: A Randomised, Multicentre, Phase 3 Trial.

BACKGROUND: Conventionally, standard resection (SR) is performed by resecting the bladder tumour in a piecemeal manner. En bloc resection of the bladder tumour (ERBT) has been proposed as an alternative technique in treating non-muscle-invasive bladder cancer (NMIBC). OBJECTIVE: To investigate whether ERBT could improve the 1-yr recurrence rate of NMIBC, as compared with SR. DESIGN, SETTING, AND PARTICIPANTS: A multicentre, randomised, phase 3 trial was conducted in Hong Kong. Adults with bladder tumour(s) of ≤3 cm were enrolled from April 2017 to December 2020, and followed up until 1 yr after surgery. INTERVENTION: Patients were randomly assigned to receive either ERBT or SR in a 1:1 ratio. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The primary outcome was 1-yr recurrence rate. A modified intention-to-treat analysis on patients with histologically confirmed NMIBC was performed. The main secondary outcomes included detrusor muscle sampling rate, operative time, hospital stay, 30-d complications, any residual or upstaging of disease upon second-look transurethral resection, and 1-yr progression rate. RESULTS AND LIMITATIONS: A total of 350 patients underwent randomisation, and 276 patients were histologically confirmed to have NMIBC. At 1 yr, 31 patients in the ERBT group and 46 in the SR group developed recurrence; the Kaplan-Meier estimate of 1-yr recurrence rates were 29% (95% confidence interval, 18-37) in the ERBT group and 38% (95% confidence interval, 28-46) in the SR group (p = 0.007). Upon a subgroup analysis, patients with 1-3 cm tumour, single tumour, Ta disease, or intermediate-risk NMIBC had a significant benefit from ERBT. None of the patients in the ERBT group and three patients in the SR group developed progression to muscle-invasive bladder cancer; the Kaplan-Meier estimates of 1-yr progression rates were 0% in the ERBT group and 2.6% (95% confidence interval, 0-5.5) in the SR group (p = 0.065). The median operative time was 28 min (interquartile range, 20-45) in the ERBT group and 22 min (interquartile range, 15-30) in the SR group (p < 0.001). All other secondary outcomes were similar in the two groups. CONCLUSIONS: In patients with NMIBC of ≤3 cm, ERBT resulted in a significant reduction in the 1-yr recurrence rate when compared with SR (funded by GRF/ECS, RGC, reference no.: 24116518; ClinicalTrials.gov number, NCT02993211). PATIENT SUMMARY: Conventionally, non-muscle-invasive bladder cancer is treated by resecting the bladder tumour in a piecemeal manner. In this study, we found that en bloc resection, that is, removal of the bladder tumour in one piece, could reduce the 1-yr recurrence rate of non-muscle-invasive bladder cancer.

Prediction of mortality after radical cystectomy for bladder cancer by machine learning techniques.

Bladder cancer is a common cancer in genitourinary malignancy. For muscle invasive bladder cancer, surgical removal of the bladder, i.e. radical cystectomy, is in general the definitive treatment which, unfortunately, carries significant morbidities and mortalities. Accurate prediction of the mortality of radical cystectomy is therefore needed. Statistical methods have conventionally been used for this purpose, despite the complex interactions of high-dimensional medical data. Machine learning has emerged as a promising technique for handling high-dimensional data, with increasing application in clinical decision support, e.g. cancer prediction and prognosis. Its ability to reveal the hidden nonlinear interactions and interpretable rules between dependent and independent variables is favorable for constructing models of effective generalization performance. In this paper, seven machine learning methods are utilized to predict the 5-year mortality of radical cystectomy, including back-propagation neural network (BPN), radial basis function (RBFN), extreme learning machine (ELM), regularized ELM (RELM), support vector machine (SVM), naive Bayes (NB) classifier and k-nearest neighbour (KNN), on a clinicopathological dataset of 117 patients of the urology unit of a hospital in Hong Kong. The experimental results indicate that RELM achieved the highest average prediction accuracy of 0.8 at a fast learning speed. The research findings demonstrate the potential of applying machine learning techniques to support clinical decision making.

Microarray data classification using the spectral-feature-based TLS ensemble algorithm.

The reliable and accurate identification of cancer categories is crucial to a successful diagnosis and a proper treatment of the disease. In most existing work, samples of gene expression data are treated as one-dimensional signals, and are analyzed by means of some statistical signal processing techniques or intelligent computation algorithms. In this paper, from an image-processing viewpoint, a spectral-feature-based Tikhonov-regularized least-squares (TLS) ensemble algorithm is proposed for cancer classification using gene expression data. In the TLS model, a test sample is represented as a linear combination of the atoms of a dictionary. Two types of dictionaries, namely singular value decomposition (SVD)-based eigenassays and independent component analysis (ICA)-based eigenassays, are proposed for the TLS model, and both are extracted via a two-stage approach. The proposed algorithm is inspired by our finding that, among these eigenassays, the categories of some of the testing samples can be assigned correctly by using the TLS models formed from some of the spectral features, but not for those formed from the original samples only. In order to retain the positive characteristics of these spectral features in making correct category assignments, a strategy of classifier committee learning (CCL) is designed to combine the results obtained from the different spectral features. Experimental results on standard databases demonstrate the feasibility and effectiveness of the proposed method.

Using the K-nearest neighbor algorithm for the classification of lymph node metastasis in gastric cancer.

Accurate tumor, node, and metastasis (TNM) staging, especially N staging in gastric cancer or the metastasis on lymph node diagnosis, is a popular issue in clinical medical image analysis in which gemstone spectral imaging (GSI) can provide more information to doctors than conventional computed tomography (CT) does. In this paper, we apply machine learning methods on the GSI analysis of lymph node metastasis in gastric cancer. First, we use some feature selection or metric learning methods to reduce data dimension and feature space. We then employ the K-nearest neighbor classifier to distinguish lymph node metastasis from nonlymph node metastasis. The experiment involved 38 lymph node samples in gastric cancer, showing an overall accuracy of 96.33%. Compared with that of traditional diagnostic methods, such as helical CT (sensitivity 75.2% and specificity 41.8%) and multidetector computed tomography (82.09%), the diagnostic accuracy of lymph node metastasis is high. GSI-CT can then be the optimal choice for the preoperative diagnosis of patients with gastric cancer in the N staging.