Research
Print page Print page
Switch language
The Capital Region of Denmark - a part of Copenhagen University Hospital
Published

Classification of Volumetric Images Using Multi-Instance Learning and Extreme value Theorem

Research output: Contribution to journalJournal articleResearchpeer-review

DOI

  1. Bag-of-frequencies: a descriptor of pulmonary nodules in computed tomography images

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Geodesic atlas-based labeling of anatomical trees: Application and evaluation on airways extracted from CT

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Attenuation correction for the HRRT PET-scanner using transmission scatter correction and total variation regularization

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. List-mode PET motion correction using markerless head tracking: proof-of-concept with scans of human subject

    Research output: Contribution to journalJournal articleResearchpeer-review

  5. Motion tracking for medical imaging: a nonvisible structured light tracking approach

    Research output: Contribution to journalJournal articleResearchpeer-review

  1. Learning to quantify emphysema extent: What labels do we need?

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Increased respiratory morbidity in individuals with interstitial lung abnormalities

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Observer variability for Lung-RADS categorisation of lung cancer screening CTs: impact on patient management

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. Chest x-ray findings in tuberculosis patients identified by passive and active case finding: A retrospective study

    Research output: Contribution to journalJournal articleResearchpeer-review

View graph of relations

Volumetric imaging is an essential diagnostic tool for medical practitioners. The use of popular techniques such as convolutional neural networks (CNN) for analysis of volumetric images is constrained by the availability of detailed (with local annotations) training data and GPU memory. In this paper, the volumetric image classification problem is posed as a multiinstance classification problem and a novel method is proposed to adaptively select positive instances from positive bags during the training phase. This method uses the extreme value theory to model the feature distribution of the images without a pathology and use it to identify positive instances of an imaged pathology. The experimental results, on three separate image classification tasks (i.e. classify retinal OCT images according to the presence or absence of fluid build-ups, emphysema detection in pulmonary 3D-CT images and detection of cancerous regions in 2D histopathology images) show that the proposed method produces classifiers that have similar performance to fully supervised methods and achieves the state of the art performance in all examined test cases.

Original languageEnglish
JournalIEEE Transactions on Medical Imaging
Volume39
Issue number4
Pages (from-to)854 - 865
ISSN0278-0062
DOIs
Publication statusPublished - 2020

ID: 60299448