Machine learning-based automatic detection of pulmonary trunk

Hong Wu, Kun Deng, Jianming Liang

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    2 Citations (Scopus)

    Abstract

    Pulmonary embolism is a common cardiovascular emergency with about 600,000 cases occurring annually and causing approximately 200,000 deaths in the US. CT pulmonary angiography (CTPA) has become the reference standard for PE diagnosis, but the interpretation of these large image datasets is made complex and time consuming by the intricate branching structure of the pulmonary vessels, a myriad of artifacts that may obscure or mimic PEs, and suboptimal bolus of contrast and inhomogeneities with the pulmonary arterial blood pool. To meet this challenge, several approaches for computer aided diagnosis of PE in CTPA have been proposed. However, none of these approaches is capable of detecting central PEs, distinguishing the pulmonary artery from the vein to effectively remove any false positives from the veins, and dynamically adapting to suboptimal contrast conditions associated the CTPA scans. To overcome these shortcomings, it requires highly efficient and accurate identification of the pulmonary trunk. For this very purpose, in this paper, we present a machine learning based approach for automatically detecting the pulmonary trunk. Our idea is to train a cascaded AdaBoost classifier with a large number of Haar features extracted from CTPA image samples, so that the pulmonary trunk can be automatically identified by sequentially scanning the CTPA images and classifying each encountered sub-image with the trained classifier. Our approach outperforms an existing anatomy-based approach, requiring no explicit representation of anatomical knowledge and achieving a nearly 100% accuracy tested on a large number of cases.

    Original languageEnglish (US)
    Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
    Volume7963
    DOIs
    StatePublished - 2011
    EventMedical Imaging 2011: Computer-Aided Diagnosis - Lake Buena Vista, FL, United States
    Duration: Feb 15 2011Feb 17 2011

    Other

    OtherMedical Imaging 2011: Computer-Aided Diagnosis
    CountryUnited States
    CityLake Buena Vista, FL
    Period2/15/112/17/11

    Fingerprint

    machine learning
    Angiography
    angiography
    Learning systems
    Lung
    classifiers
    veins
    Classifiers
    embolisms
    Computer aided diagnosis
    Adaptive boosting
    anatomy
    emergencies
    arteries
    classifying
    death
    blood
    vessels
    artifacts
    inhomogeneity

    Keywords

    • AdaBoost
    • Automatic machine learning based detection
    • Cascade
    • Haar
    • Pulmonary Embolism
    • Pulmonary Trunk

    ASJC Scopus subject areas

    • Atomic and Molecular Physics, and Optics
    • Electronic, Optical and Magnetic Materials
    • Biomaterials
    • Radiology Nuclear Medicine and imaging

    Cite this

    Wu, H., Deng, K., & Liang, J. (2011). Machine learning-based automatic detection of pulmonary trunk. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 7963). [79630K] https://doi.org/10.1117/12.878397

    Machine learning-based automatic detection of pulmonary trunk. / Wu, Hong; Deng, Kun; Liang, Jianming.

    Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7963 2011. 79630K.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Wu, H, Deng, K & Liang, J 2011, Machine learning-based automatic detection of pulmonary trunk. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 7963, 79630K, Medical Imaging 2011: Computer-Aided Diagnosis, Lake Buena Vista, FL, United States, 2/15/11. https://doi.org/10.1117/12.878397
    Wu H, Deng K, Liang J. Machine learning-based automatic detection of pulmonary trunk. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7963. 2011. 79630K https://doi.org/10.1117/12.878397
    Wu, Hong ; Deng, Kun ; Liang, Jianming. / Machine learning-based automatic detection of pulmonary trunk. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7963 2011.
    @inproceedings{7df7cd19280e4bd49846fb27d4c58f47,
    title = "Machine learning-based automatic detection of pulmonary trunk",
    abstract = "Pulmonary embolism is a common cardiovascular emergency with about 600,000 cases occurring annually and causing approximately 200,000 deaths in the US. CT pulmonary angiography (CTPA) has become the reference standard for PE diagnosis, but the interpretation of these large image datasets is made complex and time consuming by the intricate branching structure of the pulmonary vessels, a myriad of artifacts that may obscure or mimic PEs, and suboptimal bolus of contrast and inhomogeneities with the pulmonary arterial blood pool. To meet this challenge, several approaches for computer aided diagnosis of PE in CTPA have been proposed. However, none of these approaches is capable of detecting central PEs, distinguishing the pulmonary artery from the vein to effectively remove any false positives from the veins, and dynamically adapting to suboptimal contrast conditions associated the CTPA scans. To overcome these shortcomings, it requires highly efficient and accurate identification of the pulmonary trunk. For this very purpose, in this paper, we present a machine learning based approach for automatically detecting the pulmonary trunk. Our idea is to train a cascaded AdaBoost classifier with a large number of Haar features extracted from CTPA image samples, so that the pulmonary trunk can be automatically identified by sequentially scanning the CTPA images and classifying each encountered sub-image with the trained classifier. Our approach outperforms an existing anatomy-based approach, requiring no explicit representation of anatomical knowledge and achieving a nearly 100{\%} accuracy tested on a large number of cases.",
    keywords = "AdaBoost, Automatic machine learning based detection, Cascade, Haar, Pulmonary Embolism, Pulmonary Trunk",
    author = "Hong Wu and Kun Deng and Jianming Liang",
    year = "2011",
    doi = "10.1117/12.878397",
    language = "English (US)",
    isbn = "9780819485052",
    volume = "7963",
    booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

    }

    TY - GEN

    T1 - Machine learning-based automatic detection of pulmonary trunk

    AU - Wu, Hong

    AU - Deng, Kun

    AU - Liang, Jianming

    PY - 2011

    Y1 - 2011

    N2 - Pulmonary embolism is a common cardiovascular emergency with about 600,000 cases occurring annually and causing approximately 200,000 deaths in the US. CT pulmonary angiography (CTPA) has become the reference standard for PE diagnosis, but the interpretation of these large image datasets is made complex and time consuming by the intricate branching structure of the pulmonary vessels, a myriad of artifacts that may obscure or mimic PEs, and suboptimal bolus of contrast and inhomogeneities with the pulmonary arterial blood pool. To meet this challenge, several approaches for computer aided diagnosis of PE in CTPA have been proposed. However, none of these approaches is capable of detecting central PEs, distinguishing the pulmonary artery from the vein to effectively remove any false positives from the veins, and dynamically adapting to suboptimal contrast conditions associated the CTPA scans. To overcome these shortcomings, it requires highly efficient and accurate identification of the pulmonary trunk. For this very purpose, in this paper, we present a machine learning based approach for automatically detecting the pulmonary trunk. Our idea is to train a cascaded AdaBoost classifier with a large number of Haar features extracted from CTPA image samples, so that the pulmonary trunk can be automatically identified by sequentially scanning the CTPA images and classifying each encountered sub-image with the trained classifier. Our approach outperforms an existing anatomy-based approach, requiring no explicit representation of anatomical knowledge and achieving a nearly 100% accuracy tested on a large number of cases.

    AB - Pulmonary embolism is a common cardiovascular emergency with about 600,000 cases occurring annually and causing approximately 200,000 deaths in the US. CT pulmonary angiography (CTPA) has become the reference standard for PE diagnosis, but the interpretation of these large image datasets is made complex and time consuming by the intricate branching structure of the pulmonary vessels, a myriad of artifacts that may obscure or mimic PEs, and suboptimal bolus of contrast and inhomogeneities with the pulmonary arterial blood pool. To meet this challenge, several approaches for computer aided diagnosis of PE in CTPA have been proposed. However, none of these approaches is capable of detecting central PEs, distinguishing the pulmonary artery from the vein to effectively remove any false positives from the veins, and dynamically adapting to suboptimal contrast conditions associated the CTPA scans. To overcome these shortcomings, it requires highly efficient and accurate identification of the pulmonary trunk. For this very purpose, in this paper, we present a machine learning based approach for automatically detecting the pulmonary trunk. Our idea is to train a cascaded AdaBoost classifier with a large number of Haar features extracted from CTPA image samples, so that the pulmonary trunk can be automatically identified by sequentially scanning the CTPA images and classifying each encountered sub-image with the trained classifier. Our approach outperforms an existing anatomy-based approach, requiring no explicit representation of anatomical knowledge and achieving a nearly 100% accuracy tested on a large number of cases.

    KW - AdaBoost

    KW - Automatic machine learning based detection

    KW - Cascade

    KW - Haar

    KW - Pulmonary Embolism

    KW - Pulmonary Trunk

    UR - http://www.scopus.com/inward/record.url?scp=79955750552&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=79955750552&partnerID=8YFLogxK

    U2 - 10.1117/12.878397

    DO - 10.1117/12.878397

    M3 - Conference contribution

    AN - SCOPUS:79955750552

    SN - 9780819485052

    VL - 7963

    BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

    ER -