Quantitative CT Imaging in Chronic Obstructive Pulmonary Disease: Review of Current Status and Future Challenges

Cho, Yong-Hoon; Seo, Joon Beom; Lee, Sang Min; Choe, Jooae; Lee, Dabee; Kim, Namkug

doi:10.3348/jksr.2018.78.1.1

Cited by 11 publications

(15 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many methodologies using quantitative CT features for quantitative assessment of different COPD components have been studied, but few studies have adapted an integrative approach 3 , 34 , 35 . A deep radiomics approach using a CNN to extract many learned features from chest CT images may be helpful in developing clinically useful decision support models.…”

Section: Discussionmentioning

confidence: 99%

“…Medical imaging, which provides multiparametric morphologic and functional information, plays an increasingly significant role in precision medicine. Chest computed tomography (CT) provides in vivo visual information that can be used to investigate structural and underlying pathophysiologic changes in COPD patients, and thus allows analysis of primary features of COPD including morphologic characteristics and the distribution of both emphysema and small airway disease 3 – 6 . However, qualitative CT assessment by radiologists, which has been the mainstream method for acquiring information from CT scans, is prone to inter-reader, and sometimes even intra-reader, variability, limiting its application to broad clinical and experimental settings 7 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep radiomics-based survival prediction in patients with chronic obstructive pulmonary disease

Yun

Cho

Lee

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

Heterogeneous clinical manifestations and progression of chronic obstructive pulmonary disease (COPD) affect patient health risk assessment, stratification, and management. Pulmonary function tests are used to diagnose and classify the severity of COPD, but they cannot fully represent the type or range of pathophysiologic abnormalities of the disease. To evaluate whether deep radiomics from chest computed tomography (CT) images can predict mortality in patients with COPD, we designed a convolutional neural network (CNN) model for extracting representative features from CT images and then performed random survival forest to predict survival in COPD patients. We trained CNN-based binary classifier based on six-minute walk distance results (> 440 m or not) and extracted high-throughput image features (i.e., deep radiomics) directly from the last fully connected layer of it. The various sizes of fully connected layers and combinations of deep features were experimented using a discovery cohort with 344 patients from the Korean Obstructive Lung Disease cohort and an external validation cohort with 102 patients from Penang General Hospital in Malaysia. In the integrative analysis of discovery and external validation cohorts, with combining 256 deep features from the coronal slice of the vertebral body and two sagittal slices of the left/right lung, deep radiomics for survival prediction achieved concordance indices of 0.8008 (95% CI, 0.7642–0.8373) and 0.7156 (95% CI, 0.7024–0.7288), respectively. Deep radiomics from CT images could be used to predict mortality in COPD patients.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep radiomics-based survival prediction in patients with chronic obstructive pulmonary disease

Yun

Cho

Lee

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…With the recent development of CT scan techniques and software, non-invasive quantification of the lung parenchymal and airway changes is possible even with low-dose techniques. 4 Previous studies report an association between bronchial wall thickening on a CT scan and the severity of bronchial asthma 2,5 and airway obstruction. 1 Objective quantification of the CT parameters related to small airway diseases, such as air trapping and emphysema, can also be performed with a CT densitometric analysis.…”

Section: Introductionmentioning

confidence: 99%

“…1 Objective quantification of the CT parameters related to small airway diseases, such as air trapping and emphysema, can also be performed with a CT densitometric analysis. 3,4,6 The purpose of this study was to retrospectively review with quantitative evaluation of airways and lung parenchyma on pretreatment HRCT and to compare CT parameters between patients with well-controlled and those with poorly controlled clinical outcomes in bronchial asthma.…”

Section: Introductionmentioning

confidence: 99%

Quantitative evaluation of computed tomography findings in patients with bronchial asthma: prediction of therapeutic response

Nam

Hwang

2021

J Med Imag Rad Onc

View full text Add to dashboard Cite

Introduction: To compare pretreatment quantitative CT parameters between patients with well-controlled and those with poorly controlled bronchial asthma after treatment. Methods: We retrospectively reviewed 785 patients with clinical diagnosis of bronchial asthma from January 2009 to April 2015. Of these, 43 patients underwent high-resolution CT and pulmonary function tests at initial diagnosis. According to the Global Initiative for Asthma (GINA) 2015 guidelines, the patients were classified into two groups (well-controlled (GINA1), n = 18; poorly controlled (GINA2 and GINA3), n = 25). Quantitative measurements for airways (total cross-sectional area (TA), lumen area (LA), wall area (WA) and wall area percentage (WA%)), air trapping and emphysema were performed on initial pretreatment CT scans. We compared CT measurements for airways between well-controlled and poorly controlled groups and also compared those between ever-smokers and never-smokers. The significant quantitative CT parameters were evaluated with multiple regression analysis. Results: The TA and the WA demonstrated significantly higher values in the poorly controlled than in the well-controlled patient group (TA in RB1 and LB1, each P < 0.05; WA in RB1 and RB8, each P < 0.05). Quantitative parameters for air trapping and emphysema did not show significant differences between the two patient groups. On multiple regression analysis, the TA and the WA were statistically significant in comparison of two patient groups with an adjustment for age, sex, body mass index and smoking history (each P < 0.05). Significantly higher values of the WA and the WA% were revealed in the asthmatics with smoking history comparing to non-smokers (P < 0.05). Conclusion: Most of the quantitative CT measurements did not correlate significantly with clinical outcomes in patients with bronchial asthma. And, further research that supplements the limitations of this study is needed to support and validate the association between CT parameters and therapeutic response. This can be justified by the fact that a trend of higher values in airway measurements on initial pretreatment HRCT scan in the poorly controlled than in the well-controlled patient group.

show abstract

“…The diagnosis of COPD through CT helps to evaluate the extent and distribution of COPD [16], estimated by visual quantification or by analyzing the distribution of lung density [17], providing a more accurate and objective assessment of the disease [18]. Unlike COPD, stroke is considered a medical emergency and needs to be diagnosed and treated promptly to minimize the implications that may occur [19].…”

mentioning

confidence: 99%

Internet of Medical Things—Based on Deep Learning Techniques for Segmentation of Lung and Stroke Regions in CT Scans

et al. 2020

View full text Add to dashboard Cite

The classification and segmentation of pathologies through intelligent systems is a significant challenge for medical image analysis and computer vision systems. Diseases, such as lung problems and strokes, have a serious effect on human health worldwide. Lung diseases are among the leading causes of death worldwide, lagging behind strokes that in 2016 became the second leading cause of death from illnesses. Computed tomography (CT) is one of the main clinical diagnostic exams, linked to Computerized Diagnostic Assistance Systems (CAD), which are becoming solutions for health technologies. In this work, we propose a method based on the health of things for the classification and segmentation of CT images of the lung and hemorrhagic stroke. The system called HTSCS -Medical Images: Health-of-Things System for the Classification and Segmentation of Medical Images, uses transfer learning between models based on deep learning combined with classical methods for fine-tuning. The proposed method obtained excellent results for the classification of hemorrhagic stroke and pulmonary regions, with values of up to 100% accuracy. The models also achieved outstanding performances for segmentation, with Accuracy above 99 % and Dice coefficient above 97% in the best cases with an average segmentation time between 0.095 and 1.7 seconds. To validate our approach, we compared our best models for the segmentation of lung and hemorrhagic stroke in CTs, with related works found in state of the art. Our method brings an innovative approach to classification and segmentation through the use of the Health of Things for different types of medical images with promising results for medical image analysis and computer vision fields.INDEX TERMS Health of things, classification and segmentation, CTs lung and stroke, transfer learning, fine-tuning. I. INTRODUCTIONVarious pathologies have a serious effect on human health worldwide, and the main ones are related to the lungs, brain, and heart. Chronic Obstructive Pulmonary Disease (COPD) is the main causes of respiratory mortality worldwide [1], andThe associate editor coordinating the review of this manuscript and approving it for publication was Victor H. Albuquerque . it was the third leading cause of death globally, according to the World Health Organization (WHO), in 2016 [2]. Also, according to the WHO, about 3.2 million deaths were caused by COPD in 2015, a total of one-twentieth of all deaths globally in that year, and over 90% of these deaths were in low and middle-income countries. Now, in 2020, 200 million people worldwide have been diagnosed with COPD, and many more are living with undiagnosed diseases [3].

show abstract

Quantitative CT Imaging in Chronic Obstructive Pulmonary Disease: Review of Current Status and Future Challenges

Cited by 11 publications

References 59 publications

Deep radiomics-based survival prediction in patients with chronic obstructive pulmonary disease

Deep radiomics-based survival prediction in patients with chronic obstructive pulmonary disease

Quantitative evaluation of computed tomography findings in patients with bronchial asthma: prediction of therapeutic response

Internet of Medical Things—Based on Deep Learning Techniques for Segmentation of Lung and Stroke Regions in CT Scans

Contact Info

Product

Resources

About