Alert button
Picture for Dirk Smeets

Dirk Smeets

Alert button

Explainable-by-design Semi-Supervised Representation Learning for COVID-19 Diagnosis from CT Imaging

Dec 02, 2020
Abel Díaz Berenguer, Hichem Sahli, Boris Joukovsky, Maryna Kvasnytsia, Ine Dirks, Mitchel Alioscha-Perez, Nikos Deligiannis, Panagiotis Gonidakis, Sebastián Amador Sánchez, Redona Brahimetaj, Evgenia Papavasileiou, Jonathan Cheung-Wai Chana, Fei Li, Shangzhen Song, Yixin Yang, Sofie Tilborghs, Siri Willems, Tom Eelbode, Jeroen Bertels, Dirk Vandermeulen, Frederik Maes, Paul Suetens, Lucas Fidon, Tom Vercauteren, David Robben, Arne Brys, Dirk Smeets, Bart Ilsen, Nico Buls, Nina Watté, Johan de Mey, Annemiek Snoeckx, Paul M. Parizel, Julien Guiot, Louis Deprez, Paul Meunier, Stefaan Gryspeerdt, Kristof De Smet, Bart Jansen, Jef Vandemeulebroucke

Figure 1 for Explainable-by-design Semi-Supervised Representation Learning for COVID-19 Diagnosis from CT Imaging
Figure 2 for Explainable-by-design Semi-Supervised Representation Learning for COVID-19 Diagnosis from CT Imaging
Figure 3 for Explainable-by-design Semi-Supervised Representation Learning for COVID-19 Diagnosis from CT Imaging
Figure 4 for Explainable-by-design Semi-Supervised Representation Learning for COVID-19 Diagnosis from CT Imaging

Our motivating application is a real-world problem: COVID-19 classification from CT imaging, for which we present an explainable Deep Learning approach based on a semi-supervised classification pipeline that employs variational autoencoders to extract efficient feature embedding. We have optimized the architecture of two different networks for CT images: (i) a novel conditional variational autoencoder (CVAE) with a specific architecture that integrates the class labels inside the encoder layers and uses side information with shared attention layers for the encoder, which make the most of the contextual clues for representation learning, and (ii) a downstream convolutional neural network for supervised classification using the encoder structure of the CVAE. With the explainable classification results, the proposed diagnosis system is very effective for COVID-19 classification. Based on the promising results obtained qualitatively and quantitatively, we envisage a wide deployment of our developed technique in large-scale clinical studies.Code is available at https://git.etrovub.be/AVSP/ct-based-covid-19-diagnostic-tool.git.

Viaarxiv icon

Comparative study of deep learning methods for the automatic segmentation of lung, lesion and lesion type in CT scans of COVID-19 patients

Aug 21, 2020
Sofie Tilborghs, Ine Dirks, Lucas Fidon, Siri Willems, Tom Eelbode, Jeroen Bertels, Bart Ilsen, Arne Brys, Adriana Dubbeldam, Nico Buls, Panagiotis Gonidakis, Sebastián Amador Sánchez, Annemiek Snoeckx, Paul M. Parizel, Johan de Mey, Dirk Vandermeulen, Tom Vercauteren, David Robben, Dirk Smeets, Frederik Maes, Jef Vandemeulebroucke, Paul Suetens

Figure 1 for Comparative study of deep learning methods for the automatic segmentation of lung, lesion and lesion type in CT scans of COVID-19 patients
Figure 2 for Comparative study of deep learning methods for the automatic segmentation of lung, lesion and lesion type in CT scans of COVID-19 patients
Figure 3 for Comparative study of deep learning methods for the automatic segmentation of lung, lesion and lesion type in CT scans of COVID-19 patients
Figure 4 for Comparative study of deep learning methods for the automatic segmentation of lung, lesion and lesion type in CT scans of COVID-19 patients

Recent research on COVID-19 suggests that CT imaging provides useful information to assess disease progression and assist diagnosis, in addition to help understanding the disease. There is an increasing number of studies that propose to use deep learning to provide fast and accurate quantification of COVID-19 using chest CT scans. The main tasks of interest are the automatic segmentation of lung and lung lesions in chest CT scans of confirmed or suspected COVID-19 patients. In this study, we compare twelve deep learning algorithms using a multi-center dataset, including both open-source and in-house developed algorithms. Results show that ensembling different methods can boost the overall test set performance for lung segmentation, binary lesion segmentation and multiclass lesion segmentation, resulting in mean Dice scores of 0.982, 0.724 and 0.469, respectively. The resulting binary lesions were segmented with a mean absolute volume error of 91.3 ml. In general, the task of distinguishing different lesion types was more difficult, with a mean absolute volume difference of 152 ml and mean Dice scores of 0.369 and 0.523 for consolidation and ground glass opacity, respectively. All methods perform binary lesion segmentation with an average volume error that is better than visual assessment by human raters, suggesting these methods are mature enough for a large-scale evaluation for use in clinical practice.

* Updated acknowledgments 
Viaarxiv icon