Automated estimation of total lung volume using chest radiographs and deep learning

Sogancioglu, Ecem; Scholten, Ernst Th.; Boulogne, Luuk; Prokop, Mathias; Ginneken, Bram van

doi:10.1002/mp.15655

Cited by 9 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Earlier work has shown promising results for producing PFT results at a patient level using convolutional neural networks. For example, total lung volume has been estimated from chest radiographs 16 and CT scans have been used for estimating spirometry test results 17 . These methods did not produce lobe level estimates.…”

Section: Related Workmentioning

confidence: 99%

Estimating lung function from computed tomography at the patient and lobe level using machine learning

Boulogne,

Charbonnier,

Jacobs

et al. 2024

Medical Physics

View full text Add to dashboard Cite

BackgroundAutomated estimation of Pulmonary function test (PFT) results from Computed Tomography (CT) could advance the use of CT in screening, diagnosis, and staging of restrictive pulmonary diseases. Estimating lung function per lobe, which cannot be done with PFTs, would be helpful for risk assessment for pulmonary resection surgery and bronchoscopic lung volume reduction.PurposeTo automatically estimate PFT results from CT and furthermore disentangle the individual contribution of pulmonary lobes to a patient's lung function.MethodsWe propose I3Dr, a deep learning architecture for estimating global measures from an image that can also estimate the contributions of individual parts of the image to this global measure. We apply it to estimate the separate contributions of each pulmonary lobe to a patient's total lung function from CT, while requiring only CT scans and patient level lung function measurements for training. I3Dr consists of a lobe‐level and a patient‐level model. The lobe‐level model extracts all anatomical pulmonary lobes from a CT scan and processes them in parallel to produce lobe level lung function estimates that sum up to a patient level estimate. The patient‐level model directly estimates patient level lung function from a CT scan and is used to re‐scale the output of the lobe‐level model to increase performance. After demonstrating the viability of the proposed approach, the I3Dr model is trained and evaluated for PFT result estimation using a large data set of 8 433 CT volumes for training, 1 775 CT volumes for validation, and 1 873 CT volumes for testing.ResultsFirst, we demonstrate the viability of our approach by showing that a model trained with a collection of digit images to estimate their sum implicitly learns to assign correct values to individual digits. Next, we show that our models can estimate lobe‐level quantities, such as COVID‐19 severity scores, pulmonary volume (PV), and functional pulmonary volume (FPV) from CT while only provided with patient‐level quantities during training. Lastly, we train and evaluate models for producing spirometry and diffusion capacity of carbon mono‐oxide (DLCO) estimates at the patient and lobe level. For producing Forced Expiratory Volume in one second (FEV1), Forced Vital Capacity (FVC), and DLCO estimates, I3Dr obtains mean absolute errors (MAE) of 0.377 L, 0.297 L, and 2.800 mL/min/mm Hg respectively. We release the resulting algorithms for lung function estimation to the research community at https://grand‐challenge.org/algorithms/lobe‐wise‐lung‐function‐estimation/ConclusionsI3Dr can estimate global measures from an image, as well as the contributions of individual parts of the image to this global measure. It offers a promising approach for estimating PFT results from CT scans and disentangling the individual contribution of pulmonary lobes to a patient's lung function. The findings presented in this work may advance the use of CT in screening, diagnosis, and staging of restrictive pulmonary diseases as well as in risk assessment for pulmonary resection surgery and bronchoscopic lung volume reduction.

show abstract

Section: Related Workmentioning

confidence: 99%

Estimating lung function from computed tomography at the patient and lobe level using machine learning

Boulogne,

Charbonnier,

Jacobs

et al. 2024

Medical Physics

View full text Add to dashboard Cite

show abstract

“…Moreover, some deep learning techniques are used for calculating lung volume capacity. Ecem Sogancioglu et al [22] proposed an automated method for estimating total lung volume using CXR and deep learning. They used posteroanterior and lateral view CXR with five different deep learning architectures: DenseNet121, ResNet34, ResNet50, VGG-Net19, and six layers CNN.…”

Section: Literature Reviewmentioning

confidence: 99%

Estimating Lung Volume Capacity from X-ray Images Using Deep Learning

Ghimire,

Subedi

2024

QuBS

View full text Add to dashboard Cite

Estimating lung volume capacity is crucial in clinical medicine, especially in disease diagnostics. However, the existing estimation methods are complex and expensive, which require experts to handle and consequently are more error-prone and time-consuming. Thus, developing an automatic measurement system without a human operator that is less prone to human error and, thus, more accurate has always been a prerequisite. The limitation of radiation dose and various medical conditions in technologies like computed tomography was also the primary concern in the past. Although qualitative prediction of lung volume may be a trivial task, designing clinically relevant and automated methods that effectively incorporate imaging data is a challenging problem. This paper proposes a novel multi-tasking-based automatic lung volume estimation method using deep learning that jointly learns segmentation and regression of volume estimation. The two networks, namely, segmentation and regression networks, are sequentially operated with some shared layers. The segmentation network segments the X-ray images, whose output is regressed by the regression network to determine the final lung volume. Besides, the dataset used in the proposed method is collected from three different secondary sources. The experimental results show that the proposed multi-tasking approach performs better than the individual networks. Further analysis of the multi-tasking approach with two different networks, namely, UNet and HRNet, shows that the network with HRNet performs better than the network with UNet with less volume estimation mean square error of 0.0010.

show abstract

“…Machine learning has resulted in breakthroughs in medical image analysis in recent years, and several studies have used general image recognition models in medical image analysis and the estimation of functional parameters and other information from images ( 19 ). Sogancioglu et al ( 20 ) reported the use of artificial intelligence (AI) for the estimation of the lung volume from pseudo-CXRs calculated from CT images. However, the estimated lung volumes were calculated from CT image data and not pulmonary function values.…”

Section: Introductionmentioning

confidence: 99%

Spirometry test values can be estimated from a single chest radiograph

Yoshida,

Kai,

Futamura

et al. 2024

Front. Med.

View full text Add to dashboard Cite

IntroductionPhysical measurements of expiratory flow volume and speed can be obtained using spirometry. These measurements have been used for the diagnosis and risk assessment of chronic obstructive pulmonary disease and play a crucial role in delivering early care. However, spirometry is not performed frequently in routine clinical practice, thereby hindering the early detection of pulmonary function impairment. Chest radiographs (CXRs), though acquired frequently, are not used to measure pulmonary functional information. This study aimed to evaluate whether spirometry parameters can be estimated accurately from single frontal CXR without image findings using deep learning.MethodsForced vital capacity (FVC), forced expiratory volume in 1 s (FEV1), and FEV1/FVC as spirometry measurements as well as the corresponding chest radiographs of 11,837 participants were used in this study. The data were randomly allocated to the training, validation, and evaluation datasets at an 8:1:1 ratio. A deep learning network was pretrained using ImageNet. The input and output information were CXRs and spirometry test values, respectively. The training and evaluation of the deep learning network were performed separately for each parameter. The mean absolute error rate (MAPE) and Pearson’s correlation coefficient (r) were used as the evaluation indices.ResultsThe MAPEs between the spirometry measurements and AI estimates for FVC, FEV1 and FEV1/FVC were 7.59% (r = 0.910), 9.06% (r = 0.879) and 5.21% (r = 0.522), respectively. A strong positive correlation was observed between the measured and predicted indices of FVC and FEV1. The average accuracy of >90% was obtained in each estimation of spirometry indices. Bland–Altman analysis revealed good agreement between the estimated and measured values for FVC and FEV1.DiscussionFrontal CXRs contain information related to pulmonary function, and AI estimation performed using frontal CXRs without image findings could accurately estimate spirometry values. The network proposed for estimating pulmonary function in this study could serve as a recommendation for performing spirometry or as an alternative method, suggesting its utility.

show abstract

Automated estimation of total lung volume using chest radiographs and deep learning

Cited by 9 publications

References 37 publications

Estimating lung function from computed tomography at the patient and lobe level using machine learning

Estimating lung function from computed tomography at the patient and lobe level using machine learning

Estimating Lung Volume Capacity from X-ray Images Using Deep Learning

Spirometry test values can be estimated from a single chest radiograph

Contact Info

Product

Resources

About