RESUMEN
Rationale: Shared symptoms and genetic architecture between coronavirus disease (COVID-19) and lung fibrosis suggest severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection may lead to progressive lung damage. Objectives: The UK Interstitial Lung Disease Consortium (UKILD) post-COVID-19 study interim analysis was planned to estimate the prevalence of residual lung abnormalities in people hospitalized with COVID-19 on the basis of risk strata. Methods: The PHOSP-COVID-19 (Post-Hospitalization COVID-19) study was used to capture routine and research follow-up within 240 days from discharge. Thoracic computed tomography linked by PHOSP-COVID-19 identifiers was scored for the percentage of residual lung abnormalities (ground-glass opacities and reticulations). Risk factors in linked computed tomography were estimated with Bayesian binomial regression, and risk strata were generated. Numbers within strata were used to estimate posthospitalization prevalence using Bayesian binomial distributions. Sensitivity analysis was restricted to participants with protocol-driven research follow-up. Measurements and Main Results: The interim cohort comprised 3,700 people. Of 209 subjects with linked computed tomography (median, 119 d; interquartile range, 83-155), 166 people (79.4%) had more than 10% involvement of residual lung abnormalities. Risk factors included abnormal chest X-ray (risk ratio [RR], 1.21; 95% credible interval [CrI], 1.05-1.40), percent predicted DlCO less than 80% (RR, 1.25; 95% CrI, 1.00-1.56), and severe admission requiring ventilation support (RR, 1.27; 95% CrI, 1.07-1.55). In the remaining 3,491 people, moderate to very high risk of residual lung abnormalities was classified at 7.8%, and posthospitalization prevalence was estimated at 8.5% (95% CrI, 7.6-9.5), rising to 11.7% (95% CrI, 10.3-13.1) in the sensitivity analysis. Conclusions: Residual lung abnormalities were estimated in up to 11% of people discharged after COVID-19-related hospitalization. Health services should monitor at-risk individuals to elucidate long-term functional implications.
Asunto(s)
COVID-19 , Enfermedades Pulmonares Intersticiales , Humanos , SARS-CoV-2 , COVID-19/epidemiología , Teorema de Bayes , Pulmón/diagnóstico por imagen , HospitalizaciónRESUMEN
In this paper, we present an automated approach for segmenting multiple sclerosis (MS) lesions from multi-modal brain magnetic resonance images. Our method is based on a deep end-to-end 2D convolutional neural network (CNN) for slice-based segmentation of 3D volumetric data. The proposed CNN includes a multi-branch downsampling path, which enables the network to encode information from multiple modalities separately. Multi-scale feature fusion blocks are proposed to combine feature maps from different modalities at different stages of the network. Then, multi-scale feature upsampling blocks are introduced to upsize combined feature maps to leverage information from lesion shape and location. We trained and tested the proposed model using orthogonal plane orientations of each 3D modality to exploit the contextual information in all directions. The proposed pipeline is evaluated on two different datasets: a private dataset including 37 MS patients and a publicly available dataset known as the ISBI 2015 longitudinal MS lesion segmentation challenge dataset, consisting of 14 MS patients. Considering the ISBI challenge, at the time of submission, our method was amongst the top performing solutions. On the private dataset, using the same array of performance metrics as in the ISBI challenge, the proposed approach shows high improvements in MS lesion segmentation compared with other publicly available tools.
Asunto(s)
Encéfalo/diagnóstico por imagen , Encéfalo/patología , Imagenología Tridimensional/métodos , Imagen por Resonancia Magnética , Esclerosis Múltiple/diagnóstico por imagen , Esclerosis Múltiple/patología , Adulto , Femenino , Humanos , Masculino , Persona de Mediana Edad , Redes Neurales de la ComputaciónRESUMEN
Background: The COVID-19 can cause long-term symptoms in the patients after they overcome the disease. Given that this disease mainly damages the respiratory system, these symptoms are often related with breathing problems that can be caused by an affected diaphragm. The diaphragmatic function can be assessed with imaging modalities like computerized tomography or chest X-ray. However, this process must be performed by expert clinicians with manual visual inspection. Moreover, during the pandemic, the clinicians were asked to prioritize the use of portable devices, preventing the risk of cross-contamination. Nevertheless, the captures of these devices are of a lower quality. Objectives: The automatic quantification of the diaphragmatic function can determine the damage of COVID-19 on each patient and assess their evolution during the recovery period, a task that could also be complemented with the lung segmentation. Methods: We propose a novel multi-task fully automatic methodology to simultaneously localize the position of the hemidiaphragms and to segment the lung boundaries with a convolutional architecture using portable chest X-ray images of COVID-19 patients. For that aim, the hemidiaphragms' landmarks are located adapting the paradigm of heatmap regression. Results: The methodology is exhaustively validated with four analyses, achieving an 82.31% ± 2.78% of accuracy when localizing the hemidiaphragms' landmarks and a Dice score of 0.9688 ± 0.0012 in lung segmentation. Conclusions: The results demonstrate that the model is able to perform both tasks simultaneously, being a helpful tool for clinicians despite the lower quality of the portable chest X-ray images.
RESUMEN
Lung cancer screening (LCS) using annual computed tomography (CT) scanning significantly reduces mortality by detecting cancerous lung nodules at an earlier stage. Deep learning algorithms can improve nodule malignancy risk stratification. However, they have typically been used to analyse single time point CT data when detecting malignant nodules on either baseline or incident CT LCS rounds. Deep learning algorithms have the greatest value in two aspects. These approaches have great potential in assessing nodule change across time-series CT scans where subtle changes may be challenging to identify using the human eye alone. Moreover, they could be targeted to detect nodules developing on incident screening rounds, where cancers are generally smaller and more challenging to detect confidently. Here, we show the performance of our Deep learning-based Computer-Aided Diagnosis model integrating Nodule and Lung imaging data with clinical Metadata Longitudinally (DeepCAD-NLM-L) for malignancy prediction. DeepCAD-NLM-L showed improved performance (AUC = 88%) against models utilizing single time-point data alone. DeepCAD-NLM-L also demonstrated comparable and complementary performance to radiologists when interpreting the most challenging nodules typically found in LCS programs. It also demonstrated similar performance to radiologists when assessed on out-of-distribution imaging dataset. The results emphasize the advantages of using time-series and multimodal analyses when interpreting malignancy risk in LCS.
Asunto(s)
Aprendizaje Profundo , Detección Precoz del Cáncer , Neoplasias Pulmonares , Tomografía Computarizada por Rayos X , Humanos , Neoplasias Pulmonares/diagnóstico por imagen , Tomografía Computarizada por Rayos X/métodos , Detección Precoz del Cáncer/métodos , Interpretación de Imagen Radiográfica Asistida por Computador/métodos , Diagnóstico por Computador/métodos , AlgoritmosRESUMEN
Efficient algorithms are needed to segment vasculature in new three-dimensional (3D) medical imaging datasets at scale for a wide range of research and clinical applications. Manual segmentation of vessels in images is time-consuming and expensive. Computational approaches are more scalable but have limitations in accuracy. We organized a global machine learning competition, engaging 1,401 participants, to help develop new deep learning methods for 3D blood vessel segmentation. This paper presents a detailed analysis of the top-performing solutions using manually curated 3D Hierarchical Phase-Contrast Tomography datasets of the human kidney, focusing on the segmentation accuracy and morphological analysis, thereby establishing a benchmark for future studies in blood vessel segmentation within phase-contrast tomography imaging.
RESUMEN
Automated blood vessel segmentation is critical for biomedical image analysis, as vessel morphology changes are associated with numerous pathologies. Still, precise segmentation is difficult due to the complexity of vascular structures, anatomical variations across patients, the scarcity of annotated public datasets, and the quality of images. Our goal is to provide a foundation on the topic and identify a robust baseline model for application to vascular segmentation using a new imaging modality, Hierarchical Phase-Contrast Tomography (HiP-CT). We begin with an extensive review of current machine learning approaches for vascular segmentation across various organs. Our work introduces a meticulously curated training dataset, verified by double annotators, consisting of vascular data from three kidneys imaged using Hierarchical Phase-Contrast Tomography (HiP-CT) as part of the Human Organ Atlas Project. HiP-CT, pioneered at the European Synchrotron Radiation Facility in 2020, revolutionizes 3D organ imaging by offering resolution around 20µm/voxel, and enabling highly detailed localized zooms up to 1µm/voxel without physical sectioning. We leverage the nnU-Net framework to evaluate model performance on this high-resolution dataset, using both known and novel samples, and implementing metrics tailored for vascular structures. Our comprehensive review and empirical analysis on HiP-CT data sets a new standard for evaluating machine learning models in high-resolution organ imaging. Our three experiments yielded Dice scores of 0.9523 and 0.9410, and 0.8585, respectively. Nevertheless, DSC primarily assesses voxel-to-voxel concordance, overlooking several crucial characteristics of the vessels and should not be the sole metric for deciding the performance of vascular segmentation. Our results show that while segmentations yielded reasonably high scores-such as centerline Dice values ranging from 0.82 to 0.88, certain errors persisted. Specifically, large vessels that collapsed due to the lack of hydro-static pressure (HiP-CT is an ex vivo technique) were segmented poorly. Moreover, decreased connectivity in finer vessels and higher segmentation errors at vessel boundaries were observed. Such errors, particularly in significant vessels, obstruct the understanding of the structures by interrupting vascular tree connectivity. Through our review and outputs, we aim to set a benchmark for subsequent model evaluations using various modalities, especially with the HiP-CT imaging database.
RESUMEN
In this study, we present a hybrid CNN-RNN approach to investigate long-term survival of subjects in a lung cancer screening study. Subjects who died of cardiovascular and respiratory causes were identified whereby the CNN model was used to capture imaging features in the CT scans and the RNN model was used to investigate time series and thus global information. To account for heterogeneity in patients' follow-up times, two different variants of LSTM models were evaluated, each incorporating different strategies to address irregularities in follow-up time. The models were trained on subjects who underwent cardiovascular and respiratory deaths and a control cohort matched to participant age, gender, and smoking history. The combined model can achieve an AUC of 0.76 which outperforms humans at cardiovascular mortality prediction. The corresponding F1 and Matthews Correlation Coefficient are 0.63 and 0.42 respectively. The generalisability of the model is further validated on an 'external' cohort. The same models were applied to survival analysis with the Cox Proportional Hazard model. It was demonstrated that incorporating the follow-up history can lead to improvement in survival prediction. The Cox neural network can achieve an IPCW C-index of 0.75 on the internal dataset and 0.69 on an external dataset. Delineating subjects at increased risk of cardiorespiratory mortality can alert clinicians to request further more detailed functional or imaging studies to improve the assessment of cardiorespiratory disease burden. Such strategies may uncover unsuspected and under-recognised pathologies thereby potentially reducing patient morbidity.
RESUMEN
The COVID-19 pandemic has been a great challenge to healthcare systems worldwide. It highlighted the need for robust predictive models which can be readily deployed to uncover heterogeneities in disease course, aid decision-making and prioritise treatment. We adapted an unsupervised data-driven model-SuStaIn, to be utilised for short-term infectious disease like COVID-19, based on 11 commonly recorded clinical measures. We used 1344 patients from the National COVID-19 Chest Imaging Database (NCCID), hospitalised for RT-PCR confirmed COVID-19 disease, splitting them equally into a training and an independent validation cohort. We discovered three COVID-19 subtypes (General Haemodynamic, Renal and Immunological) and introduced disease severity stages, both of which were predictive of distinct risks of in-hospital mortality or escalation of treatment, when analysed using Cox Proportional Hazards models. A low-risk Normal-appearing subtype was also discovered. The model and our full pipeline are available online and can be adapted for future outbreaks of COVID-19 or other infectious disease.
Asunto(s)
COVID-19 , Humanos , COVID-19/epidemiología , SARS-CoV-2 , Pandemias , Hospitales , PredicciónRESUMEN
In this study, the long-term mortality in the National Lung Screening Trial (NLST) was investigated using a deep learning-based method. Binary classification of the non-lung-cancer mortality (i.e. cardiovascular and respiratory mortality) was performed using neural network models centered around a 3D-ResNet. The models were trained on a participant age, gender, and smoking history matched cohort. Utilising both the 3D CT scan and clinical information, the models can achieve an AUC of 0.73 which outperforms humans at cardiovascular mortality prediction. The corresponding F1 and Matthews Correlation Coefficient are 0.60 and 0.38 respectively. By interpreting the trained models with 3D saliency maps, we examined the features on the CT scans that correspond to the mortality signal. By extracting information from 3D CT volumes, we can highlight regions in the thorax region that contribute to mortality that might be overlooked by the clinicians. Therefore, this can help focus preventative interventions appropriately, particularly for under-recognised pathologies and thereby reducing patient morbidity.