Search

Item does not contain fulltext

Lung cancer is the leading cause of cancer-related mortality worldwide. Lung cancer screening (LCS) using annual low-dose computed tomography (CT) scanning has been proven to significantly reduce lung cancer mortality by detecting cancerous lung nodules at an earlier stage. Improving risk stratification of malignancy risk in lung nodules can be enhanced using machine/deep learning algorithms. However most existing algorithms: a) have primarily assessed single time-point CT data alone thereby failing to utilize the inherent advantages contained within longitudinal imaging datasets; b) have not integrated into computer models pertinent clinical data that might inform risk prediction; c) have not assessed algorithm performance on the spectrum of nodules that are most challenging for radiologists to interpret and where assistance from analytic tools would be most beneficial. Here we show the performance of our time-series deep learning model (DeepCAD-NLM-L) which integrates multi-model information across three longitudinal data domains: nodule-specific, lung-specific, and clinical demographic data. We compared our time-series deep learning model to a) radiologist performance on CTs from the National Lung Screening Trial enriched with the most challenging nodules for diagnosis; b) a nodule management algorithm from a North London LCS study (SUMMIT). Our model demonstrated comparable and complementary performance to radiologists when interpreting challenging lung nodules and showed improved performance (AUC=88\%) against models utilizing single time-point data only. The results emphasise the importance of time-series, multi-modal analysis when interpreting malignancy risk in LCS.

MC Dropout is a mainstream "free lunch" method in medical imaging for approximate Bayesian computations (ABC). Its appeal is to solve out-of-the-box the daunting task of ABC and uncertainty quantification in Neural Networks (NNs); to fall within the variational inference (VI) framework; and to propose a highly multimodal, faithful predictive posterior. We question the properties of MC Dropout for approximate inference, as in fact MC Dropout changes the Bayesian model; its predictive posterior assigns $0$ probability to the true model on closed-form benchmarks; the multimodality of its predictive posterior is not a property of the true predictive posterior but a design artefact. To address the need for VI on arbitrary models, we share a generic VI engine within the pytorch framework. The code includes a carefully designed implementation of structured (diagonal plus low-rank) multivariate normal variational families, and mixtures thereof. It is intended as a go-to no-free-lunch approach, addressing shortcomings of mean-field VI with an adjustable trade-off between expressivity and computational complexity.

The primary analysis of the INBUILD trial showed that in subjects with progressive fibrosing interstitial lung diseases (ILDs), nintedanib slowed the decline in forced vital capacity (FVC) over 52 weeks. We report the effects of nintedanib on ILD progression over the whole trial.Subjects with fibrosing ILDs other than idiopathic pulmonary fibrosis, who had ILD progression within the 24 months before screening despite management deemed appropriate in clinical practice, were randomised to receive nintedanib or placebo. Subjects continued on blinded randomised treatment until all subjects had completed the trial. Over the whole trial, mean (sd) exposure to trial medication was 15.6 (7.2) and 16.8 (5.8) months in the nintedanib and placebo groups, respectively.In the nintedanib (n=332) and placebo (n=331) groups, respectively, the proportions of subjects who had ILD progression (absolute decline in FVC ≥10% predicted) or died were 40.4% and 54.7% in the overall population (HR 0.66 [95% CI: 0.53, 0.83]; p=0.0003), and 43.7% and 55.8% among subjects with a usual interstitial pneumonia (UIP)-like fibrotic pattern on high-resolution computed tomography (HRCT) (HR 0.69 [0.53, 0.91]; p=0.009). In the nintedanib and placebo groups, respectively, the proportions who had an acute exacerbation of ILD or died were 13.9% and 19.6% in the overall population (HR 0.67 [95% CI: 0.46, 0.98]; p=0.04), and 15.0% and 22.8% among subjects with a UIP-like fibrotic pattern on HRCT (HR 0.62 [0.39, 0.97]; p=0.03).Based on data from the whole INBUILD trial, nintedanib reduced the risk of events indicating ILD progression.

Datasets are rarely a realistic approximation of the target population. Say, prevalence is misrepresented, image quality is above clinical standards, etc. This mismatch is known as sampling bias. Sampling biases are a major hindrance for machine learning models. They cause significant gaps between model performance in the lab and in the real world. Our work is a solution to prevalence bias. Prevalence bias is the discrepancy between the prevalence of a pathology and its sampling rate in the training dataset, introduced upon collecting data or due to the practioner rebalancing the training batches. This paper lays the theoretical and computational framework for training models, and for prediction, in the presence of prevalence bias. Concretely a bias-corrected loss function, as well as bias-corrected predictive rules, are derived under the principles of Bayesian risk minimization. The loss exhibits a direct connection to the information gain. It offers a principled alternative to heuristic training losses and complements test-time procedures based on selecting an operating point from summary curves. It integrates seamlessly in the current paradigm of (deep) learning using stochastic backpropagation and naturally with Bayesian models.

Lung cancer screening (LCS) with low-dose computed tomography (LDCT) was demonstrated in the National Lung Screening Trial (NLST) to reduce mortality from the disease. European mortality data has recently become available from the Nelson randomised controlled trial, which confirmed lung cancer mortality reductions by 26% in men and 39-61% in women. Recent studies in Europe and the USA also showed positive results in screening workers exposed to asbestos. All European experts attending the "Initiative for European Lung Screening (IELS)"-a large international group of physicians and other experts concerned with lung cancer-agreed that LDCT-LCS should be implemented in Europe. However, the economic impact of LDCT-LCS and guidelines for its effective and safe implementation still need to be formulated. To this purpose, the IELS was asked to prepare recommendations to implement LCS and examine outstanding issues. A subgroup carried out a comprehensive literature review on LDCT-LCS and presented findings at a meeting held in Milan in November 2018. The present recommendations reflect that consensus was reached.

Lung cancer screening (LCS) with low-dose computed tomography (LDCT) was demonstrated in the National Lung Screening Trial (NLST) to reduce mortality from the disease. European mortality data has recently become available from the Nelson randomised controlled trial, which confirmed lung cancer mortality reductions by 26% in men and 39-61% in women. Recent studies in Europe and the USA also showed positive results in screening workers exposed to asbestos. All European experts attending the "Initiative for European Lung Screening (IELS)"-a large international group of physicians and other experts concerned with lung cancer-agreed that LDCT-LCS should be implemented in Europe. However, the economic impact of LDCT-LCS and guidelines for its effective and safe implementation still need to be formulated. To this purpose, the IELS was asked to prepare recommendations to implement LCS and examine outstanding issues. A subgroup carried out a comprehensive literature review on LDCT-LCS and presented findings at a meeting held in Milan in November 2018. The present recommendations reflect that consensus was reached.

The INBUILD trial investigated the efficacy and safety of nintedanib versus placebo in patients with progressive fibrosing interstitial lung diseases (ILDs) other than idiopathic pulmonary fibrosis (IPF). We aimed to establish the effects of nintedanib in subgroups based on ILD diagnosis., info:eu-repo/semantics/published

info:eu-repo/semantics/published

Contains fulltext : 195130.pdf (Publisher’s version ) (Open Access)

Contains fulltext : 195130.pdf (Publisher’s version ) (Open Access)

Contains fulltext : 195130.pdf (Publisher’s version ) (Open Access)

600 patients aged ≥18 years will be randomised in a 1:1 ratio to nintedanib or placebo. Patients with diagnosis of IPF will be excluded. The study population will be enriched with two-thirds having a usual interstitial pneumonia-like pattern on HRCT. The primary endpoint is the annual rate of decline in forced vital capacity over 52 weeks. The main secondary endpoints are the absolute change from baseline in King's Brief Interstitial Lung Disease Questionnaire total score, time to first acute interstitial lung disease exacerbation or death and time to all-cause mortality over 52 weeks.Ethics and disseminationThe trial is conducted in accordance with the Declaration of Helsinki, the International Conference on Harmonisation Tripartite Guideline for Good Clinical Practice (GCP) and Japanese GCP regulations.Trial registration numberNCT02999178.

Lung cancer screening with low-dose CT can save lives. This European Union (EU) position statement presents the available evidence and the major issues that need to be addressed to ensure the successful implementation of low-dose CT lung cancer screening in Europe. This statement identified specific actions required by the European lung cancer screening community to adopt before the implementation of low-dose CT lung cancer screening. This position statement recommends the following actions: a risk stratification approach should be used for future lung cancer low-dose CT programmes; that individuals who enter screening programmes should be provided with information on the benefits and harms of screening, and smoking cessation should be offered to all current smokers; that management of detected solid nodules should use semi-automatically measured volume and volume-doubling time; that national quality assurance boards should be set up to oversee technical standards; that a lung nodule management pathway should be established and incorporated into clinical practice with a tailored screening approach; that non-calcified baseline lung nodules greater than 300 mm3, and new lung nodules greater than 200 mm3, should be managed in multidisciplinary teams according to this EU position statement recommendations to ensure that patients receive the most appropriate treatment; and planning for implementation of low-dose CT screening should start throughout Europe as soon as possible. European countries need to set a timeline for implementing lung cancer screening.