A Study on Diagnostic Assist Systems of Chronic Obstructive Pulmonary Disease from Medical Images by Deep Learning

Kimura, Tōru; Kawakami, Takashi; Kikuchi, Akihiro; Ooev, Ryosuke; Akiyama, Masaki; Horikoshi, Hiroyuki

doi:10.4236/jcc.2018.61003

Cited by 4 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, emphysema grading on CR and DE were correlated with the CT-derived The Goddard score is a semi-quantitative assessment score functioning as a surrogate marker for the presence of emphysema based on the evaluation of low attenuation areas in a number of representative lung fields. The total score is defined as the sum of the single scores [22]. The Goddard score was used for overall emphysema grading as well as for defining the most affected lung quadrant.…”

Section: Discussionmentioning

confidence: 99%

Diagnostic Performance of Dual-Energy Subtraction Radiography for the Detection of Pulmonary Emphysema: An Intra-Individual Comparison

et al. 2021

View full text Add to dashboard Cite

Purpose/Objectives: To compare the diagnostic performance of dual-energy subtraction (DE) and conventional radiography (CR) for detecting pulmonary emphysema using computed tomography (CT) as a reference standard. Methods and Materials: Sixty-six patients (24 female, median age 73) were retrospectively included after obtaining lateral and posteroanterior chest X-rays with a dual-shot DE technique and chest CT within ±3 months. Two experienced radiologists first evaluated the standard CR images and, second, the bone-/soft tissue weighted DE images for the presence (yes/no), degree (1–4), and quadrant-based distribution of emphysema. CT was used as a reference standard. Inter-reader agreement was calculated. Sensitivity and specificity for the correct detection and localization of emphysema was calculated. Further degree of emphysema on CR and DE was correlated with results from CT. A p-value < 0.05 was considered as statistically significant. Results: The mean interreader agreement was substantial for CR and moderate for DE (kCR = 0.611 vs. kDE = 0.433; respectively). Sensitivity, as well as specificity for the detection of emphysema, was comparable between CR and DE (sensitivityCR 96% and specificityCR 75% vs. sensitivityDE 91% and specificityDE 83%; p = 0.157). Similarly, there was no significant difference in the sensitivity or specificity for emphysema localization between CR and DE (sensitivityCR 50% and specificityCR 100% vs. sensitivityDE 57% and specificityDE 100%; p = 0.157). There was a slightly better correlation with CT of emphysema grading in DE compared to CR (rDE = 0.75 vs. rCR = 0.68; p = 0.108); these differences were not statistically significant, however. Conclusion: Diagnostic accuracy for the detection, quantification, and localization of emphysema between CR and DE is comparable. Interreader agreement, however, is better with CR compared to DE

show abstract

Section: Discussionmentioning

confidence: 99%

Diagnostic Performance of Dual-Energy Subtraction Radiography for the Detection of Pulmonary Emphysema: An Intra-Individual Comparison

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Deep learning methods using deep Convolutional Neural Networks (DCNN) for deep recognition and also image recognition tasks have been resolved with the same structures. DCNN learn region classification and organ extraction from accurate CT scan images taken from the entire body [78]. Cystic fibrosis is a genital illness that is likely to occur early in life, along with physical abnormalities in the lungs' tissues.…”

Section: Respiratory Systemmentioning

confidence: 99%

Healthcare Techniques Through Deep Learning: Issues, Challenges and Opportunities

et al. 2021

View full text Add to dashboard Cite

In artificial intelligence, deep learning (DL) is a process that replicates the working mechanism of the human brain in data processing, and it also creates patterns for decision making. Deep learning or neural networks have been deployed in several fields, such as computer vision, natural language processing, and speech recognition. It has been used in many healthcare applications for the diagnosis and treatment of many chronic diseases. These algorithms have the power to avoid outbreaks of illness, recognize and diagnose illnesses, minimize running expenses for hospital management and patients. This paper discusses the deep learning methods used in different healthcare fields, i.e., identifying depression, heart diseases, physiological signals, lymph node metastases from breast cancer, etc. These diseases are categorized into the central nervous system, cardiovascular system, and respiratory system. For each category, after summarizing the studies, comparison tables are laid down using some important factors. Different applications, tools, methods, and data sets used for DL models are leveraged. Finally, research opportunities and challenges being faced for deep learning models are discussed.

show abstract

“…Parametric Response Mapping, 3D PRM Das et al, [12] Machine learning has been magnificently used in automated interpretation of pulmonary function tests for differential diagnosis of obstructive lung diseases. Deep learning models such as convolutional neural network are state-of-the art for obstructive pattern recognition in CT Convolutional Neural Network Kanwade, Archana, and V. K. Bairagi [13] Support Vector Machine based approach is explained for the classification of COPD disease Support Vector Machine Kimura, Toru, et al, [14] Deep learning algorithm is utilized Deep Learning algorithms Fernandez-Graneroet al, [15] In this study, 16 patients were telemonitored at home during six months. Respiratory sounds were recorded daily with an electronic sensor ad-hoc designed.…”

Section: Topological Data Analysismentioning

confidence: 99%

A Novel Hybrid Framework for the Detection and Risk Severity of Chronic Obstructive Pulmonary Disease

Karthikeyan,

Sathiamoorthy

2018

AJES

View full text Add to dashboard Cite

The COPD is a limitation in airflow and is not completely reversible, and affects up to one quarter of adults with 40 or more years. The risk factors of COPD typically include tobacco smoke, masculine gender, exposure to chemicals and dusts, asthma, air pollution and genetic reasons as rare hereditary deficiency of α1-antitrypsin. The COPD leads to death if it is treated properly. So if it recognized earlier and more correctly, the life span of affected people will increase. Thus, in this paper, new framework based on block variation of local correlation coefficients (BVLC) and support vector machine (SVM) is suggested to identify chronic obstructive pulmonary disease in CT images. The experiments on benchmark database clearly proven that recommended approach is suggestively good in terms of accuracy and time.

show abstract

A Study on Diagnostic Assist Systems of Chronic Obstructive Pulmonary Disease from Medical Images by Deep Learning

Cited by 4 publications

References 10 publications

Diagnostic Performance of Dual-Energy Subtraction Radiography for the Detection of Pulmonary Emphysema: An Intra-Individual Comparison

Diagnostic Performance of Dual-Energy Subtraction Radiography for the Detection of Pulmonary Emphysema: An Intra-Individual Comparison

Healthcare Techniques Through Deep Learning: Issues, Challenges and Opportunities

A Novel Hybrid Framework for the Detection and Risk Severity of Chronic Obstructive Pulmonary Disease

Contact Info

Product

Resources

About