Colposcopy is widely used to detect cervical cancers, but experienced physicians who are needed for an accurate diagnosis are lacking in developing countries. Artificial intelligence (AI) has been recently used in computer-aided diagnosis showing remarkable promise. In this study, we developed and validated deep learning models to automatically classify cervical neoplasms on colposcopic photographs. Pre-trained convolutional neural networks were fine-tuned for two grading systems: the cervical intraepithelial neoplasia (CIN) system and the lower anogenital squamous terminology (LAST) system. The multi-class classification accuracies of the networks for the CIN system in the test dataset were 48.6 ± 1.3% by Inception-Resnet-v2 and 51.7 ± 5.2% by Resnet-152. The accuracies for the LAST system were 71.8 ± 1.8% and 74.7 ± 1.8%, respectively. The area under the curve (AUC) for discriminating high-risk lesions from low-risk lesions by Resnet-152 was 0.781 ± 0.020 for the CIN system and 0.708 ± 0.024 for the LAST system. The lesions requiring biopsy were also detected efficiently (AUC, 0.947 ± 0.030 by Resnet-152), and presented meaningfully on attention maps. These results may indicate the potential of the application of AI for automated reading of colposcopic photographs. Cervical cancer is the fourth most common cancer in women worldwide, and the second most common cancer among females in developing countries 1. Screening is the principal prevention method aimed at reducing mortality rates. Screening includes certain steps, including population-based Papanicolaou (Pap) testing, colposcopydirected biopsy of suspicious lesions, and the treatment of confirmed pre-cancer lesions 2,3. In women with low-grade intraepithelial lesions (LSIL) or high-grade intraepithelial lesions (HSIL), the risk of pre-cancer is medium to high, and immediate referral for colposcopy is necessary. However, referring all women with atypical squamous cells of undetermined significance (ASC-US) is considered inefficient, as the risk of such cases being pre-cancerous is lower 4. Screening programs have been successful in the developed countries, leading to an approximately 80% decrease in the cervical cancer incidence over the past 4 decades. In contrast, the increase in cervical cancer incidence reported in developing countries 5 has been attributed to the unsuccessful implementation of screening programs. This, has been attributed to logistics in health systems, infrastructural inadequacies, and the lack of expert physicians capable of introducing screening programs and follow-up 6 .
ObjectiveThe impact of beta blockers (BBs) on survival outcomes in ovarian cancer was investigated.MethodsBy using Korean National Health Insurance Service Data, Cox proportional hazards regression was performed to analyze hazard ratios (HRs) with 95% confidence intervals (CIs) adjusting for confounding factors.ResultsAmong 866 eligible patients, 206 (23.8%) were BB users and 660 (76.2%) were non-users. Among the 206 BB users, 151 (73.3%) were non-selective beta blocker (NSBB) users and 105 (51.0%) were selective beta blocker (SBB) users. BB use in patients aged ≥60 years, longer duration use (≥1 year), in patients with Charlson Comorbidity Index (CCI) ≥3, and in cardiovascular disease including hypertension was associated with better survival outcome. These findings were observed in both NSBB and SBB. When duration of medication was analyzed based on number of days, NSBB (≥180 days) was associated with improved overall survival (OS) with a relatively shorter period of use compared to SBB (≥720 days). In multivariate Cox proportional hazards model, longer duration of BB medication (≥1 year) was an independent favorable prognostic factor for both OS and disease-specific survival in ovarian cancer patients.ConclusionIn our nationwide population-based cohort study, BB use was associated with better survival outcomes in ovarian cancer in cases of long term duration of use, in older patients, and in cardiovascular and/or other underlying disease (CCI ≥3).
Abstract. The aim of the present study was to investigate the prognostic role of a number of clinical factors in advanced cervical cancer patients. Patients (n=157) with stage IIA-IIB cervical cancer treated at four Hallym Medical Centers in South Korea (Hallym University Sacred Heart Hospital; Kangnam Sacred Heart Hospital; Chuncheon Sacred Heart Hospital; and Kangdong Sacred Heart Hospital) between 2006 and 2010 were retrospectively enrolled. Univariate analysis identified significant predictive values in the following eight factors: i) Cancer stage (P<0.0001); ii) tumor size (≤4 vs. 4-6 cm, P=0.0147; and ≤4 vs. >6 cm, P<0.0001); iii) serum squamous cell carcinoma antigen level (≤2 vs. >15 ng/ml; P=0.0291); iv) lower third vaginal involvement (P<0.0001); v) hydronephrosis (P=0.0003); vi) bladder/rectum involvement (P=0.0015); vii) pelvic (P=0.0017) or para-aortic (P=0.0019) lymph node (LN) metastasis detected by imaging vs. no metastasis; and viii) pelvic LN metastasis identified by pathological analysis (P=0.0289). Furthermore, multivariate analysis determined that tumor size (≤4 vs. 4-6 cm, P= 0.0371; and ≤4 vs. >6 cm, P=0.0024) and pelvic LN metastasis determined by imaging vs. no metastasis (P=0.0499) were independent predictive variables. Therefore, tumor size and pelvic LN metastasis measured by imaging were independent predictive factors for the prognosis of advanced cervical cancer. These factors may provide more clinically significant prognostic information compared with the currently used International Federation of Gynecology and Obstetrics staging system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.