As a subclass of interstitial lung diseases, fibrosing idiopathic interstitial pneumonia (IIP), whose cause is mostly unknown, is a continuous and irreversible process, manifesting as progressive worsening of lung function. Quantifying the evolution of the patient status imposes the development of automated CAD tools to depict the pathology occurrence in the lung but also an associated severity degree. In this paper we propose several biomarkers for IIP quantification, associating spatial localization of the disease using lung texture classification, and severity measures in relation with vascular and bronchial remodeling which correlate with clinical parameters. We follow-up our work on lung texture analysis based on convolutional neural networks (reporting an increased performance in sensitivity, specificity and accuracy) on an enlarged training/testing database (110/20 patients respectively). The area under the curve (AUC:2-6) for vessel calibers distribution between 2-6 mm radii (evaluated in 70 patients) showed up as a promising biomarker of the severity of the disease, independently of the extent of lesions, correlating with the composite physiologic index. In the same way, normalized airway lobe length, normalized airway lobe volume and the score of distal airway caliber deviation from the physiologically power decrease law correlated with radiologic severity score, manifesting as potential biomarkers of traction bronchiectasis (assessment in 18 patients).
Infiltrative lung diseases describe a large group of irreversible lung disorders requiring regular follow-up with CT
imaging. Quantifying the evolution of the patient status imposes the development of automated classification tools for
lung texture. This paper presents an original image pre-processing framework based on locally connected filtering
applied in multiresolution, which helps improving the learning process and boost the performance of CNN for lung
texture classification. By removing the dense vascular network from images used by the CNN for lung classification,
locally connected filters provide a better discrimination between different lung patterns and help regularizing the
classification output. The approach was tested in a preliminary evaluation on a 10 patient database of various lung
pathologies, showing an increase of 10% in true positive rate (on average for all the cases) with respect to the state of the
art cascade of CNNs for this task.
The infiltrative lung diseases are a class of irreversible, non-neoplastic lung pathologies requiring regular follow-up with CT imaging. Quantifying the evolution of the patient status imposes the development of automated classification tools for lung texture. Traditionally, such classification relies on a two-dimensional analysis of axial CT images. This paper proposes a cascade of the existing CNN based CAD system, specifically tuned-up. The advantage of using a deep learning approach is a better regularization of the classification output. In a preliminary evaluation, the combined approach was tested on a 13 patient database of various lung pathologies, showing an increase of 10% in True Positive Rate (TPR) with respect to the best suited state of the art CNN for this task.
Correct segmentation and labeling of lungs in thorax MSCT is a requirement in pulmonary/respiratory disease analysis as a basis for further processing or direct quantitative measures: lung texture classification, respiratory functional simulations, intrapulmonary vascular remodeling evaluation, detection of pleural effusion or subpleural opacities, are only few clinical applications related to this requirement. Whereas lung segmentation appears trivial for normal anatomo-pathological conditions, the presence of disease may complicate this task for fully-automated algorithms. The challenges come either from regional changes of lung texture opacity or from complex anatomic configurations (e.g., thin septum between lungs making difficult proper lung separation). They make difficult or even impossible the use of classic algorithms based on adaptive thresholding, 3-D connected component analysis and shape regularization. The objective of this work is to provide a robust segmentation approach of the pulmonary field, with individualized labeling of the lungs, able to overcome the mentioned limitations. The proposed approach relies on 3-D mathematical morphology and exploits the concept of controlled relief flooding (to identify contrasted lung areas) together with patient-specific shape properties for peripheral dense tissue detection. Tested on a database of 40 MSCT of pathological lungs, the proposed approach showed correct identification of lung areas with high sensitivity and specificity in locating peripheral dense opacities.
The infiltrative lung diseases are a class of irreversible, non-neoplastic lung pathologies requiring regular follow-up with CT imaging. Quantifying the evolution of the patient status imposes the development of automated classification tools for lung texture. For the large majority of CAD systems, such classification relies on a two-dimensional analysis of axial CT images. In a previously developed CAD system, we proposed a fully-3D approach exploiting a multi-scale morphological analysis which showed good performance in detecting diseased areas, but with a major drawback consisting of sometimes overestimating the pathological areas and mixing different type of lung patterns. This paper proposes a combination of the existing CAD system with the classification outcome provided by a convolutional network, specifically tuned-up, in order to increase the specificity of the classification and the confidence to diagnosis. The advantage of using a deep learning approach is a better regularization of the classification output (because of a deeper insight into a given pathological class over a large series of samples) where the previous system is extra-sensitive due to the multi-scale response on patient-specific, localized patterns. In a preliminary evaluation, the combined approach was tested on a 10 patient database of various lung pathologies, showing a sharp increase of true detections.
The increasing need of remote medical investigation services in the framework of collaborative multidisciplinary meetings (e.g. cancer follow-up) raises the challenge of on-line remote access of (large amount of) radiologic data in a limited period of time. This paper proposes a scalable compression framework of DICOM images providing low-latency display through low speed networks. The developed approach relies on useless information removal from images (i.e. not related with the patient body) and the exploitation of the JPEG2000 standard to achieve progressive quality encoding and access of the data. This mechanism also allows the efficient exploitation of any idle times (corresponding to on-line visual image analysis) to download the remaining data at lossless quality in a way transparent to the user, thus minimizing the perceived latency. The experiments performed in comparison with exchanging uncompressed or JPEGlossless compressed DICOM data, showed the benefit of the proposed approach for collaborative on-line remote diagnosis and follow-up services.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.