In the last two decades, Computer Aided Detection (CAD) systems were developed to help radiologists analyse screening mammograms, however benefits of current CAD technologies appear to be ...contradictory, therefore they should be improved to be ultimately considered useful. Since 2012, deep convolutional neural networks (CNN) have been a tremendous success in image recognition, reaching human performance. These methods have greatly surpassed the traditional approaches, which are similar to currently used CAD solutions. Deep CNN-s have the potential to revolutionize medical image analysis. We propose a CAD system based on one of the most successful object detection frameworks, Faster R-CNN. The system detects and classifies malignant or benign lesions on a mammogram without any human intervention. The proposed method sets the state of the art classification performance on the public INbreast database, AUC = 0.95. The approach described here has achieved 2nd place in the Digital Mammography DREAM Challenge with AUC = 0.85. When used as a detector, the system reaches high sensitivity with very few false positive marks per image on the INbreast dataset. Source code, the trained model and an OsiriX plugin are published online at https://github.com/riblidezso/frcnn_cad .
This article summarizes great efforts that Chinese scholars had made in fighting against cervical cancer from aspects of the epidemiology, etiology, population-based screening studies, novel ...screening technology development, guideline, strategy and policy making and population delivery. After decades of continuous efforts, Chinese scientists successfully translated their scientific discovery to appropriate screening product development and eventually, delivered it to the whole population. We hope our experience could serve as a 'case-story' for cancer prevention in other low- and middle-income countries. Moreover, challenges confronted in the prevention and control of cervical cancer in China are reviewed as well to appeal for future multi-collaborations and potential solutions to acquire the final success of the campaign.
Cancer patients have a higher risk of cardiovascular disease (CVD) mortality than the general population. Low dose computed tomography (LDCT) for lung cancer screening offers an opportunity for ...simultaneous CVD risk estimation in at-risk patients. Our deep learning CVD risk prediction model, trained with 30,286 LDCTs from the National Lung Cancer Screening Trial, achieves an area under the curve (AUC) of 0.871 on a separate test set of 2,085 subjects and identifies patients with high CVD mortality risks (AUC of 0.768). We validate our model against ECG-gated cardiac CT based markers, including coronary artery calcification (CAC) score, CAD-RADS score, and MESA 10-year risk score from an independent dataset of 335 subjects. Our work shows that, in high-risk patients, deep learning can convert LDCT for lung cancer screening into a dual-screening quantitative tool for CVD risk estimation.
Tuberculosis (TB), caused by Mycobacterium tuberculosis (MTB) (Zopf 1883) Lehmann and Neumann 1896, is a major cause of morbidity and mortality. Nearly one-third of the world's population is infected ...with MTB; TB has an annual incidence of 9 million new cases and each year causes 2 million deaths worldwide.
To investigate the clinical effectiveness and cost-effectiveness of screening tests interferon-gamma release assays (IGRAs) and tuberculin skin tests (TSTs) in latent tuberculosis infection (LTBI) diagnosis to support National Institute for Health and Care Excellence (NICE) guideline development for three population groups: children, immunocompromised people and those who have recently arrived in the UK from high-incidence countries. All of these groups are at higher risk of progression from LTBI to active TB.
Electronic databases including MEDLINE, EMBASE, The Cochrane Library and Current Controlled Trials were searched from December 2009 up to December 2014.
English-language studies evaluating the comparative effectiveness of commercially available tests used for identifying LTBI in children, immunocompromised people and recent arrivals to the UK were eligible. Interventions were IGRAs QuantiFERON(®)-TB Gold (QFT-G), QuantiFERON(®)-TB Gold-In-Tube (QFT-GIT) (Cellestis/Qiagen, Carnegie, VA, Australia) and T-SPOT.TB (Oxford Immunotec, Abingdon, UK). The comparator was TST 5 mm or 10 mm alone or with an IGRA. Two independent reviewers screened all identified records and undertook a quality assessment and data synthesis. A de novo model, structured in two stages, was developed to compare the cost-effectiveness of diagnostic strategies.
In total, 6687 records were screened, of which 53 unique studies were included (a further 37 studies were identified from a previous NICE guideline). The majority of the included studies compared the strength of association for the QFT-GIT/G IGRA with the TST (5 mm or 10 mm) in relation to the incidence of active TB or previous TB exposure. Ten studies reported evidence on decision-analytic models to determine the cost-effectiveness of IGRAs compared with the TST for LTBI diagnosis. In children, TST (≥ 5 mm) negative followed by QFT-GIT was the most cost-effective strategy, with an incremental cost-effectiveness ratio (ICER) of £18,900 per quality-adjusted life-year (QALY) gained. In immunocompromised people, QFT-GIT negative followed by the TST (≥ 5 mm) was the most cost-effective strategy, with an ICER of approximately £18,700 per QALY gained. In those recently arrived from high TB incidence countries, the TST (≥ 5 mm) alone was less costly and more effective than TST (≥ 5 mm) positive followed by QFT-GIT or T-SPOT.TB or QFT-GIT alone.
The limitations and scarcity of the evidence, variation in the exposure-based definitions of LTBI and heterogeneity in IGRA performance relative to TST limit the applicability of the review findings.
Given the current evidence, TST (≥ 5 mm) negative followed by QFT-GIT for children, QFT-GIT negative followed by TST (≥ 5 mm) for the immunocompromised population and TST (≥ 5 mm) for recent arrivals were the most cost-effective strategies for diagnosing LTBI that progresses to active TB. These results should be interpreted with caution given the limitations identified. The evidence available is limited and more high-quality research in this area is needed including studies on the inconsistent performance of tests in high-compared with low-incidence TB settings; the prospective assessment of progression to active TB for those at high risk; the relative benefits of two-compared with one-step testing with different tests; and improved classification of people at high and low risk for LTBI.
This study is registered as PROSPERO CRD42014009033.
The National Institute for Health Research Health Technology Assessment programme.
The manufacturer has developed a new ECG screening tool to determine eligibility for the subcutaneous ICD (S-ICD), the “automatic screening tool” (AST), which may render manual ECG-screening ...unnecessary. The aim of the study was to determine the eligibility for the S-ICD using two methods (manual ECG-screening versus AST) in different patient categories including patients with cardiomyopathy, congenital heart disease and inherited primary arrhythmia syndrome.
We prospectively evaluated the ECG suitability for an S-ICD in consecutive patients at our outpatient clinic between February and June 2017. The primary endpoint of the study was ECG eligibility defined as at least 1 successful vector in both supine and sitting postures.
A total of 254 patients (167 men; mean age 45 ± 16 years) were screened using both methods. Overall, there was a high ECG eligibility using either method (93% versus 92%, P = 0.45). Overall agreement between both methods was 94%. Patients with hypertrophic cardiomyopathy (HCM) more often had a failed screening test using either test in comparison to the patients without HCM (manual: odds ratio OR 3.3, 95% confidence interval CI 1.2–9.3, P = 0.02; AST: OR 3.0, 95% CI 1.2–7.6, P = 0.02).
AST showed a high agreement with manual ECG-screening for S-ICD. Overall there was a high ECG eligibility for S-ICD, although patients with HCM had a lower passing rate irrespective of the screening method.
•The automatic screening tool has a high agreement with manual ECG-screening to determine eligibility for a subcutaneous ICD.•The automatic screening tool is an appropriate alternative to manual ECG-screening•Failed ECG-screening is more often in patients with hypertrophic cardiomyopathy irrespective of the screening method.•The eligibility rate for a subcutaneous ICD is not different between patients with and without an ICD indication.
Summary
The long-term impact of hormone therapy for breast cancer on risk of osteoporosis and the extent to which bone screening recommendations are implemented in daily practice remain unknown. We ...found that the aromatase inhibitor-induced risk of osteoporosis did not continue in the off-treatment follow-up. Adherence to screening recommendations was suboptimal.
Introduction
A case-cohort study was undertaken to better understand the impact of hormone therapy on breast cancer patients’ risk of osteoporosis, and to estimate the extent to which current bone mineral density screening recommendations are implemented in real-life daily practice.
Methods
This study is based on 1692 female breast cancer survivors recruited from “Leumit” healthcare fund, who were diagnosed with primary nonmetastatic invasive breast cancer between 2002 and 2012. A 20% random subcohort was sampled at baseline, and all osteoporosis cases were identified. Adjusted hazard ratios (HR) with 95% confidence intervals (CI) were estimated by weighted Cox proportional hazards models.
Results
Of 1692 breast cancer survivors, 312 developed osteoporosis during a median follow-up of 5 years. The crude cumulative incidence of osteoporosis accounting for death as a competing risk was 25.7% (95% CI, 21.9–29.5%). In multivariable analyses, osteoporosis was positively associated with the aromatase inhibitor (AI) sequential treatment after tamoxifen (HR, 3.14; 95% CI, 1.44–6.88;
P =
.004) but was more pronounced with AI use as upfront monotherapy (HR, 5.53; 95% CI, 1.46–20.88;
P =
.012). This effect did not continue in the off-treatment follow-up. In subgroup analysis by menopausal status, tamoxifen did not seem to confer a protective effect on bone health in postmenopausal patients. Adherence to screening recommendations in AI-treated postmenopausal women was suboptimal, particularly at baseline and after 48 months of continuous AI use.
Conclusions
The natural, age-related reduction in bone density is exacerbated by breast cancer active AI treatment. Future research should focus on investigating screening adherence-related barriers/facilitators and effective strategies to bring practice in line with agreed standards.
IMPORTANCE: Unrealistic patient expectations of the benefits and harms of interventions can influence decision making and may be contributing to increasing intervention uptake and health care costs. ...OBJECTIVE: To systematically review all studies that have quantitatively assessed patients’ expectations of the benefits and/or harms of any treatment, test, or screening test. EVIDENCE REVIEW: A comprehensive search strategy was used in 4 databases (MEDLINE, Embase, Cumulative Index to Nursing and Allied Health Literature, PsycINFO) up to June 2013, with no language or study type restriction. We also ran cited reference searches of included studies and contacted experts and study authors. Two researchers independently evaluated methodological quality and extracted participants’ estimates of benefit and harms and authors’ contemporaneous estimates. FINDINGS: Of the 15 343 records screened, 36 articles (from 35 studies) involving a total of 27 323 patients were eligible. Fourteen studies focused on a screen, 15 on treatment, 3 a test, and 3 on treatment and screening. More studies assessed only benefit expectations (22 63%) than benefit and harm expectations (10 29%) or only harm (3 8%). Fifty-four outcomes (across 32 studies) assessed benefit expectations: of the 34 outcomes with overestimation data available, the majority of participants overestimated benefit for 22 (65%) of them. For 17 benefit expectation outcomes, we could not calculate the proportion of participants who overestimated or underestimated, although for 15 (88%) of these, study authors concluded that participants overestimated benefits. Expectations of harm were assessed by 27 outcomes (across 13 studies): underestimation data were available for 15 outcomes and the majority of participants underestimated harm for 10 (67%) of these. A correct estimation by at least 50% of participants only occurred for 2 outcomes about benefit expectations and 2 outcomes about harm expectations. CONCLUSIONS AND RELEVANCE: The majority of participants overestimated intervention benefit and underestimated harm. Clinicians should discuss accurate and balanced information about intervention benefits and harms with patients, providing the opportunity to develop realistic expectations and make informed decisions.
The foreign-born population make up an increasing and large proportion of tuberculosis (TB) cases in European Union/European Economic Area (EU/EEA) low-incidence countries and challenge TB ...elimination efforts.
: We conducted a systematic review to determine effectiveness (yield and performance of chest radiography (CXR) to detect active TB, treatment outcomes and acceptance of screening) and a second systematic review on cost-effectiveness of screening for active TB among migrants living in the EU/EEA.
: We identified six systematic reviews, one report and three individual studies that addressed our aims. CXR was highly sensitive (98%) but only moderately specific (75%). The yield of detecting active TB with CXR screening among migrants was 350 per 100,000 population overall but ranged widely by host country (110-2,340), migrant type (170-1,192), TB incidence in source country (19-336) and screening setting (220-1,720). The CXR yield was lower (19.6 vs 336/100,000) and the numbers needed to screen were higher (5,076 vs 298) among migrants from source countries with lower TB incidence (≤ 50 compared with ≥ 350/100,000). Cost-effectiveness was highest among migrants originating from high (> 120/100,000) TB incidence countries. The foreign-born had similar or better TB treatment outcomes than those born in the EU/EEA. Acceptance of CXR screening was high (85%) among migrants.
: Screening programmes for active TB are most efficient when targeting migrants from higher TB incidence countries. The limited number of studies identified and the heterogeneous evidence highlight the need for further data to inform screening programmes for migrants in the EU/EEA.
Women require information about the impact of regularly attending screening mammography on breast cancer mortality and overdiagnosis to make informed decisions. To provide this information we aimed ...to meta-analyse randomised controlled trials adjusted for adherence to the trial protocol.
Nine screening mammography trials used in the Independent UK Breast Screening Report were selected. Extending an existing approach to adjust intention-to-treat (ITT) estimates for less than 100% adherence rates, we conducted a random-effects meta-analysis. This produced a combined deattenuated prevented fraction and a combined deattenuated percentage risk of overdiagnosis.
In women aged 39-75 years invited to screen, the prevented fraction of breast cancer mortality at 13-year follow-up was 0.22 (95% CI 0.15-0.28) and it increased to 0.30 (95% CI 0.18-0.42) with deattenuation. In women aged 40-69 years invited to screen, the ITT percentage risk of overdiagnosis during the screening period was 19.0% (95% CI 15.2-22.7%), deattenuation increased this to 29.7% (95% CI 17.8-41.5%).
Adjustment for nonadherence increased the size of the mortality benefit and risk of overdiagnosis by up to 50%. These estimates are more appropriate when developing quantitative information to support individual decisions about attending screening mammography.