Investigating Beta-Variational Convolutional Autoencoders for the Unsupervised Classification of Chest Pneumonia.

The world's population is increasing and so is the challenge on existing healthcare infrastructure to cope with the growing demand in medical diagnosis and evaluation. Although human experts are primarily tasked with the diagnosis of different medical conditions, artificial intelligence (AI)-assisted diagnoses have become considerably useful in recent times. One of the critical lung infections, which requires early diagnosis and subsequent treatment to reduce the mortality rate, is pneumonia. There are different methods for obtaining a pneumonia diagnosis; however, the adoption of chest X-rays is popular since it is non-invasive. The AI systems for a pneumonia diagnosis using chest X-rays are often built on supervised machine-learning (ML) models, which require labeled datasets for development. However, collecting labeled datasets is sometimes infeasible due to constraints such as human resources, cost, and time. As such, the problem that we address in this paper is the unsupervised classification of pneumonia using unsupervised ML models including the beta-variational convolutional autoencoder (ß-VCAE) and other variants, such as convolutional autoencoders (CAE), denoising convolutional autoencoders (DCAE), and sparse convolutional autoencoders (SCAE). Namely, the pneumonia classification problem is cast into an anomaly detection to develop the aforementioned ML models. The experimental results show that pneumonia can be diagnosed with high recall, precision, f1-score, and f2-score using the proposed unsupervised models. In addition, we observe that the proposed models are competitive with the state-of-the-art models, which are trained on a labeled dataset.

The incidence of urethral stricture and bladder neck contracture with transurethral resection vs. holmium laser enucleation of prostate: A matched, dual-center study.

INTRODUCTION: Urethral strictures (US) and bladder neck contracture (BNC) are common, long-term complications of transurethral prostate surgery. We aimed to compare transurethral resection of the prostate (TURP) and holmium laser enucleation of the prostate (HoLEP) regarding incidence of US or BNC and identify possible risk factors. METHODS: A retrospective review of patients who underwent TURP and HoLEP with followup data of at least one year in two separate institutions was performed. The incidence of postoperative US or BNC in both groups was compared. Bivariate and multivariate analysis of risk factors in both cohorts with US or BNC were performed. RESULTS: The study included 208 patients: 101 and 107 patients in the TURP and HoLEP arms, respectively. The two groups were matched for age and prostate size. Eight (7.92%) and five (4.72%) patients in the TURP and HoLEP arms, respectively, developed US (p=0.3423), while two (1.87%) patients in the HoLEP arm had BNC (p=0.2634). Of the eight patients with the US in the TURP arm, six (9.8%) had bipolar TURP, while two (5%) had monopolar TURP. Multivariate analysis showed that larger prostate volume (hazard ratio [HR] 1.22, 95% confidence interval [CI] 1.05, 1.41, p=0.0066) and longer operative time (HR 1.84, 95% CI 1.76, 1.93, p=0.0015) were associated with risk of US/BNC. CONCLUSIONS: There is no significant difference between TURP and HoLEP regarding incidence of US or BNC, although there is a tendency towards a higher rate of US associated with bipolar TURP. Increased prostate volume and operative time are possible risk factors.