Automatic Lung Segmentation in Computed Tomography Images Using Active Shape Model

Shariaty, Faridoddin; Orooji, Mahdi; Mousavi, Mojtaba; Baranov, Maksim; Velichko, Elena

doi:10.1109/eexpolytech50912.2020.9243982

Cited by 13 publications

(5 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Сегментация легочных узелков на КТ-изображениях является сложной и основной задачей CAD. Фактически многие методы количественной оценки легочных заболеваний автоматически требуют сегментации легочной паренхимы и узелков на этапе первичной обработки [6]. Методы сегментации можно разделить на несколько классов [7]: полностью основанные на изображении [8][9][10], основанные на модели [11] и гибридные методы [12].…”

Section: применение модели внешнего вида текстуры для сегментации лег...unclassified

Application of a Texture Appearance Model for Segmentation of Lung Nodules on Computed Tomography of the Chest

Shariaty

Pavlov

Zavjalov

et al. 2022

Izv. vysš. učebn. zaved. Ross., Radioèlektron.

View full text Add to dashboard Cite

Introduction. Lung cancer is one of the most critical diseases globally, with more than 1.6 million new cases registered every year. Early detection of lung cancer is essential; therefore, particular attention should be paid to the development of effective diagnostic and therapeutic procedures. Computer processing of CT scans in the course of lung cancer diagnostics involves the following stages: medical image acquisition, pre-processing of medical images, segmentation, and false-positive reduction. Since segmentation is an essential stage in the process of medical image analysis, the development of novel segmentation approaches is attracting much research interest. Model-based segmentation approaches have recently gained in popularity, largely due to their potential to restore lost information.Aim. To apply a texture appearance model for the segmentation of pulmonary nodules on computed tomography of the chest.Materials and methods. A novel model-based Texture Appearance Model (TAM) is proposed for precise and effective segmentation of all sorts of nodule regions. We taught the TAM for segmentation of a lung nodule in lung CT images using a combination of extracted texture characteristics from CT scans and Texture Representation of Image (TRI).Results. The results of applying the described TAM method to normal and noisy CT images are presented and compared to those obtained using the Region Growing and Active Contour algorithms, as well as the combination of Active Contour and Watershed algorithms. The TAM was tested in 85 nodules from a dataset, yielding an average dice similarity coefficient (DSC) of 84.75 percent.Conclusion. A novel method for segmenting nodules in the lung, which is capable of segmenting all forms of nodules with excellent accuracy, is proposed. This model-based technique, when used with the active loop algorithm, can enhance accuracy and decrease false positives by selecting the initial mask. The precision, dice, accuracy, and specificity of lung nodule segmentation on a normal CT scan are 85.5, 85, 96, and 98, which levels are superior to those produced by the Active Contour, Region Growing and the combination of Active Contour and Watershed algorithms.

show abstract

Section: применение модели внешнего вида текстуры для сегментации лег...unclassified

Application of a Texture Appearance Model for Segmentation of Lung Nodules on Computed Tomography of the Chest

Shariaty

Pavlov

Zavjalov

et al. 2022

Izv. vysš. učebn. zaved. Ross., Radioèlektron.

View full text Add to dashboard Cite

show abstract

“…Given the rapid spread of COVID-19, using Machine Learning (ML) algorithms for processing chest CT scans might help to identify the defining clinical characteristics and severity of the disease [31]. Although CT provides rich pathological information, only a qualitative assessment was made in the radiological reports, as there are no computer-aided tools for quantifying the infection regions and their longitudinal changes [32]. Developing computer vision systems aids in medical applications such as image quality enhancement, organ segmentation, and organ texture classification [21,33].…”

Section: Covid-19 Detection From Similar Diseasesmentioning

confidence: 99%

“…For example, in a person with COVID-19 disease, the progression of lung infections is significant and vital. By isolating these infections in the lungs (by segmentation algorithms), the progression of the disease can be measured and monitored quickly and automatically [19,30,32,40,41]. Assessing the disease's progression is very important in medicine, which helps analyze the disease type.…”

Section: Disease Progressionmentioning

confidence: 99%

Application of Artificial Intelligence for Rapid Prevention of Epidemic Diseases (COVID-19)

2022

IJHPP

View full text Add to dashboard Cite

Background: Epidemic diseases are hazardous in terms of a rapid outbreak. Rapid control of these diseases by finding patients and quarantine and treatment can be the only tool to reduce the number of cases and mortality at the beginning of the outbreak, in the absence of therapy and vaccines. COVID-19 (coronavirus) is a deadly viral disease that causes severe respiratory illness and spreads through the air. Artificial intelligence (AI) technologies have played an essential role in solving complex problems. The use of these technologies in response to the challenges posed by the COVID-19 epidemic can reduce the effects of epidemics in various contexts. Objective: The purpose of this article is to review the applications of artificial intelligence in cases of contagious disease. In this work, COVID-19 disease has been used as an example of dangerous infectious diseases (while the studied methods can be used for all contagious diseases), and a systematic review of the literature on the role of artificial intelligence as COVID-19 has become a comprehensive and critical technology for combating epidemiology, diagnosis, and disease progression. Methods: A complete search of the literature has been done using the databases of PubMed, Scopus, Web of Science, and Google Scholar, and other sources. In this work, the aim is to review articles that the authors believe can be helpful in the prevention of infectious diseases in the event of an outbreak of artificial intelligence in the prevention of more casualties. The first steps needed in a flurry of a disease (including coronavirus) include identifying the primary sufferers and isolating them from the public and examining the illness and how the disease has progressed. In these stages, artificial intelligence can very effectively help the medical community and even the government prevent an epidemic. In this study, the keywords COVID-19, artificial intelligence, and infectious diseases have been used. Results: During our literature search, we came across 73 papers. Researchers analyzed studies examining the diagnostic roles and imaging features of patients with COVID-19. The latter were scanned using CT or ultrasound scans, chest radiographs, or positron emission tomography/computed tomography (PET/CT) scans. Chest x-ray and CT scan are the imaging modalities that are most widely utilized for the diagnosis and management of COVID-19 patients, with chest CT scan being more accurate and sensitive in diagnosing COVID-19 at an early stage. Only a handful of studies have looked into the roles of ultrasonography and PET/CT scans in diagnosing COVID-19 infection. Conclusions: We gathered research from the existing COVID-19 literature that employed artificial intelligence-based methodologies to give insights into various domains of COVID-19 in this systematic review. Our findings indicate critical variables, data formats, and COVID-19 sources to help with clinical research and translation. Findings from this study may also assist in reducing the harm caused by the pandemic in the case of such epidemic diseases in the future.

show abstract

“…In the last ten years, several publications have become available on diagnosis based on ML, most notably for cancer. Examples of cancers that are subject to computer-assisted diagnosis include lung cancer [ 2 ], gastric cancer [ 3 ], prostate cancer [ 4 , 5 ], pancreatic cancer [ 6 , 7 ], and breast cancer [ [8] , [9] , [10] , [11] ].…”

Section: Introductionmentioning

confidence: 99%

CerviLearnNet: Advancing cervical cancer diagnosis with reinforcement learning-enhanced convolutional networks

Muksimova,

Umirzakova,

Kang

et al. 2024

Heliyon

View full text Add to dashboard Cite

Automatic Lung Segmentation in Computed Tomography Images Using Active Shape Model

Cited by 13 publications

References 38 publications

Application of a Texture Appearance Model for Segmentation of Lung Nodules on Computed Tomography of the Chest

Application of a Texture Appearance Model for Segmentation of Lung Nodules on Computed Tomography of the Chest

Application of Artificial Intelligence for Rapid Prevention of Epidemic Diseases (COVID-19)

CerviLearnNet: Advancing cervical cancer diagnosis with reinforcement learning-enhanced convolutional networks

Contact Info

Product

Resources

About