Skip to Main content Skip to Navigation
Theses

Quantitative follow-up of pulmonary diseases using deep learning models

Abstract : Infiltrative lung diseases (ILDs) enclose a large group of irreversible lung disorders which require regular follow-up with computed tomography (CT) imaging. A quantitative assessment is mandatory to establish the (regional) disease progression and/or the therapeutic impact. This implies the development of automated computer-aided diagnosis (CAD) tools for pathological lung tissue segmentation, problem addressed as pixel-based texture classification. Traditionally, such classification relies on a two-dimensional analysis of axial CT images by means of handcrafted features. Recently, the use of deep learning techniques, especially Convolutional Neural Networks (CNNs) for visual tasks, has shown great improvements with respect to handcrafted heuristics-based methods. However, it has been demonstrated the limitations of "classic" CNN architectures when applied to texture-based datasets, due to their inherently higher dimension compared to handwritten digits or other object recognition datasets, implying the need of redesigning the network or enriching the system to learn meaningful textural features from input data. This work addresses an automated quantitative assessment of different disorders based on lung texture classification. The proposed approach exploits a cascade of CNNs (specially redesigned for texture categorization) for a hierarchical classification and a specific preprocessing of input data based on locally connected filtering (applied to the lung images to attenuate the vessel densities while preserving high opacities related to pathologies). The classification targeting the whole lung parenchyma achieves an average of 84% accuracy (75.8% for normal, 90% for emphysema and fibrosis, 81.5% for ground glass)
Complete list of metadatas

https://tel.archives-ouvertes.fr/tel-01892382
Contributor : Abes Star :  Contact
Submitted on : Wednesday, October 10, 2018 - 3:40:08 PM
Last modification on : Monday, August 24, 2020 - 4:16:02 PM
Long-term archiving on: : Friday, January 11, 2019 - 4:39:14 PM

File

these-TARANDO.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01892382, version 1

Citation

Sebastian Roberto Tarando. Quantitative follow-up of pulmonary diseases using deep learning models. Signal and Image processing. Institut National des Télécommunications, 2018. English. ⟨NNT : 2018TELE0008⟩. ⟨tel-01892382⟩

Share

Metrics

Record views

626

Files downloads

230