Semi-automated rib cage segmentation in CT images for mesothelioma detection

Brahim, Wael; Mestiri, Makram; Betrouni, Nacim; Hamrouni, Kamel

doi:10.1109/ipas.2016.7880133

Cited by 7 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The minimum HU threshold to identify potentially calcified volumes was predefined at 130 HU. The 3D connected component analysis (26 connectivity) [33] was performed on the threshold image to obtain a set of candidate calcifications. According to Lessmann et al [9], the candidates with a volume of less than 1.5 mm 3 or greater than 1500 mm 3 were considered as noise or metal implants, respectively; hence, they were rejected.…”

Section: Methodsmentioning

confidence: 99%

“…3D Ribcage segmentation: After the VOI determination, we removed the ribcage and the lungs. The ribcage was segmented with a bone threshold ( > 130 HU and greater than 1500 mm 3 ) followed by 3D connected component [33]. The 3D dilatation operation, in which the kernel size was 5 × 5 × 10 and kernel (1 ∶ 3 , ∶ , ∶ ) = 1 , was applied to close the holes between the ribs.…”

Section: Volume Of Interest (Voi) Limitationmentioning

confidence: 99%

“…Then, the 3D connected component tool (3D 26 connectivity) [33] was used to merge the voxels of the threshold image into singular lesions. The candidates with a volume between 1.5 mm 3 and 1500 mm 3 were considered as CAC.…”

Section: Cac Segmentationmentioning

confidence: 99%

See 2 more Smart Citations

Machine learning for coronary artery calcification detection and labeling using only native computer tomography

Zair

Cherfa

et al. 2021

Phys Eng Sci Med

View full text Add to dashboard Cite

In recent decades, the World Health Organization has found an increase in the death rate due to cardiovascular disease. Calcifications of the coronary arteries are the main sign of any cardiovascular event. Each individual's calcium score helps estimate the severity of the disease. However, the score for each artery is more significant. This study aims to research the segmentation, the labeling, and then the complete and partial quantification of calcium using only native coronary computed tomography with the help of machine-learning algorithms. Our semi-automatic system limited the region of interest by applying a defined preprocessing step. We then implemented two random forest classifiers; the first separated true coronary artery calcification (CAC) from the noise, and the second labeled CAC into the right coronary artery, left coronary artery, left anterior descending artery, and left circumflex artery using specific features. Agatston score and volume score of each CAC, each artery, and all of the arteries were calculated. This method gave promising results, comparable to those found in the literature, with the accuracy of 99.98% and 100% for CAC detection and labeling respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Volume Of Interest (Voi) Limitationmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning for coronary artery calcification detection and labeling using only native computer tomography

Zair

Cherfa

et al. 2021

Phys Eng Sci Med

View full text Add to dashboard Cite

show abstract

“…Mesothelioma was also classified using CT images. [16] developed a semi-automated rib cage segmentation method and they achieved to correctly classify 22 samples over 30. [17] selected several machine learning approaches for the purpose.…”

Section: Introductionmentioning

confidence: 99%

A Machine Learning Based Early Diagnosis System for Mesothelioma Disease

Şentürk

Çekiç

2020

Düzce Üniversitesi Bilim Ve Teknoloji Dergisi

View full text Add to dashboard Cite

Mesothelioma is pleura cancer that cause death in about one year after diagnosis. The disease causes pain and shortness of breath. Patients have a CT (Computed Tomography)-scan and lung x-ray traditionally, but the exact method is biopsy. There are also different biopsy methods for its diagnosis. Its prevalence is one or two in a million around the world, but for Turkey it is disastrous. Five hundred people are diagnosed as mesothelioma every year in Turkey. This serious rate makes early diagnosis systems crucial for mesothelioma. In this paper, a machine learning based early detection system has been proposed for this fatal disease. An open database is used for the experiments and different methods have been applied to the problem of diagnosing mesothelioma disease. Accuracy and sensitivity performance metrics were used for the evaluation of the methods. The results show the diagnostic performance of different machine learning methods and present a successful early diagnosis system.

show abstract

“…It includes the application of various methodologies and algorithmic approach to pre-process, cluster, classify and associate the information for useful knowledge retrieval [13].World health organization, World Lung Foundation, and other international health organizations are working together for early detection of malignant mesothelioma. The detection of mesothelioma was done with the help of nomograms [14],CT images [15][16][17] and blood samples [18]. With the rise of computing methods for disease prediction, data mining also played a vital rule to predict malignant mesothelioma.…”

Section: Introductionmentioning

confidence: 99%

Identification of Malignant Mesothelioma Risk Factors through Association Rule Mining

Alam¹

2019

Preprint

View full text Add to dashboard Cite

Malignant mesothelioma is a rare proliferative cancer that develops in the thin layer of tissues surrounding the lungs. Malignant mesothelioma is associated with an extremely poor prognosis and the majority of patients do not show symptoms. The epidemiology of mesothelioma is important for the identification of disease. The primary aim of this study is to explore the risk factors associated with mesothelioma. The dataset consists of healthy and mesothelioma patients but only mesothelioma patients were selected for the identification of symptoms. The raw data set has been pre-processed and then the Apriori method was utilized for association rules with various configurations. The pre-processing task involved the removal of duplicated and irrelevant attributes, balanced the dataset, numerical to the nominal conversion of attributes in the dataset and creating the association rules in the dataset. Strong associations of disease’s factors; asbestos exposure, duration of asbestos exposure, duration of symptoms, erythrocyte sedimentation rate and Pleural to serum LDH ratio determined via Apriori algorithm. The identification of risk factors associated with mesothelioma may prevent patients from going into the high danger of the disease. This will also help to control the comorbidities associated with mesothelioma which are cardiovascular diseases, cancer-related emotional distress, diabetes, anemia, and hypothyroidism.

show abstract

Semi-automated rib cage segmentation in CT images for mesothelioma detection

Cited by 7 publications

References 8 publications

Machine learning for coronary artery calcification detection and labeling using only native computer tomography

Machine learning for coronary artery calcification detection and labeling using only native computer tomography

A Machine Learning Based Early Diagnosis System for Mesothelioma Disease

Identification of Malignant Mesothelioma Risk Factors through Association Rule Mining

Contact Info

Product

Resources

About