Lorenzo Aliboni1, Francesca Pennati1, Alice Gelmini2,3, Alessandra Colombo2,3, Andrea Ciuni4, Gianluca Milanese4, Nicola Sverzellati4, Sandro Magnani5, Valentina Vespro6, Francesco Blasi2,3, Andrea Aliverti1, Stefano Aliberti2,3. 1. Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano. 2. Respiratory Unit and Cystic Fibrosis Adult Center, Fondazione IRCCS Ca'Granda Ospedale Maggiore Policlinico. 3. Department of Pathophysiology and Transplantation, Università degli Studi di Milano. 4. Department of Clinical Sciences, Section of Radiology, University of Parma, Parma. 5. Department of Radiology, ASST Lodi, Ospedale Maggiore di Lodi, Lodi, Italy. 6. Department of Radiology, Fondazione IRCCS Ca'Granda Ospedale Maggiore Policlinico Milan, University of Milan, Milan.
Abstract
PURPOSE: Bronchiectasis is a chronic disease characterized by an irreversible dilatation of bronchi leading to chronic infection, airway inflammation, and progressive lung damage. Three specific patterns of bronchiectasis are distinguished in clinical practice: cylindrical, varicose, and cystic. The predominance and the extension of the type of bronchiectasis provide important clinical information. However, characterization is often challenging and is subject to high interobserver variability. The aim of this study is to provide an automatic tool for the detection and classification of bronchiectasis through convolutional neural networks. MATERIALS AND METHODS: Two distinct approaches were adopted: (i) direct network performing a multilabel classification of 32×32 regions of interest (ROIs) into 4 classes: healthy, cylindrical, cystic, and varicose and (ii) a 2-network serial approach, where the first network performed a binary classification between normal tissue and bronchiectasis and the second one classified the ROIs containing abnormal bronchi into one of the 3 bronchiectasis typologies. Performances of the networks were compared with other architectures presented in the literature. RESULTS: Computed tomography from healthy individuals (n=9, age=47±6, FEV1%pred=109±17, FVC%pred=116±17) and bronchiectasis patients (n=21, age=59±15, FEV1%pred=74±25, FVC%pred=91±22) were collected. A total of 19,059 manually selected ROIs were used for training and testing. The serial approach provided the best results with an accuracy and F1 score average of 0.84, respectively. Slightly lower performances were observed for the direct network (accuracy=0.81 and F1 score average=0.82). On the test set, cylindrical bronchiectasis was the subtype classified with highest accuracy, while most of the misclassifications were related to the varicose pattern, mainly to the cylindrical class. CONCLUSION: The developed networks accurately detect and classify bronchiectasis disease, allowing to collect quantitative information regarding the radiologic severity and the topographical distribution of bronchiectasis subtype.
PURPOSE: Bronchiectasis is a chronic disease characterized by an irreversible dilatation of bronchi leading to chronic infection, airway inflammation, and progressive lung damage. Three specific patterns of bronchiectasis are distinguished in clinical practice: cylindrical, varicose, and cystic. The predominance and the extension of the type of bronchiectasis provide important clinical information. However, characterization is often challenging and is subject to high interobserver variability. The aim of this study is to provide an automatic tool for the detection and classification of bronchiectasis through convolutional neural networks. MATERIALS AND METHODS: Two distinct approaches were adopted: (i) direct network performing a multilabel classification of 32×32 regions of interest (ROIs) into 4 classes: healthy, cylindrical, cystic, and varicose and (ii) a 2-network serial approach, where the first network performed a binary classification between normal tissue and bronchiectasis and the second one classified the ROIs containing abnormal bronchi into one of the 3 bronchiectasis typologies. Performances of the networks were compared with other architectures presented in the literature. RESULTS: Computed tomography from healthy individuals (n=9, age=47±6, FEV1%pred=109±17, FVC%pred=116±17) and bronchiectasis patients (n=21, age=59±15, FEV1%pred=74±25, FVC%pred=91±22) were collected. A total of 19,059 manually selected ROIs were used for training and testing. The serial approach provided the best results with an accuracy and F1 score average of 0.84, respectively. Slightly lower performances were observed for the direct network (accuracy=0.81 and F1 score average=0.82). On the test set, cylindrical bronchiectasis was the subtype classified with highest accuracy, while most of the misclassifications were related to the varicose pattern, mainly to the cylindrical class. CONCLUSION: The developed networks accurately detect and classify bronchiectasis disease, allowing to collect quantitative information regarding the radiologic severity and the topographical distribution of bronchiectasis subtype.