Holistic classification of CT attenuation patterns for interstitial lung diseases via deep convolutional neural networks
Proceedings of the 1st Workshop on Deep Learning in Medical Image Analysis (DLMIA 2015), held in conjunction with the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015), pp. 41–48
Abstract
Interstitial lung diseases (ILD) involve several abnormal imaging patterns observed in computed tomography (CT) images. Accurate classification of these patterns plays a significant role in precise clinical decision making of the extent and nature of the diseases. Therefore, it is important for developing automated pulmonary computer-aided detection systems. Conventionally, this task relies on experts' manual identification of regions of interest (ROIs) as a prerequisite to diagnose potential diseases. This protocol is time consuming and inhibits fully automatic assessment. In this paper, we present a new method to classify ILD imaging patterns on CT images. The main difference is that the proposed algorithm uses the entire image as a holistic input. By circumventing the prerequisite of manual input ROIs, our problem set-up is significantly more difficult than previous work but can better address the clinical workflow. Qualitative and quantitative results using a publicly available ILD database demonstrate state-of-the-art classification accuracy under the patch-based classification and shows the potential of predicting the ILD type using holistic image.
Abstract sourceThis 2015 workshop paper examines classifying interstitial lung disease patterns from whole CT slices, without requiring manually selected regions of interest. The authors compare this holistic approach with patch-based classification using a publicly available dataset.
Summary
Gao and colleagues describe a convolutional neural network for classifying interstitial lung disease (ILD) patterns in computed tomography (CT) images. Rather than requiring manually marked regions of interest, the method uses whole CT slices as inputs. The authors evaluate it on a publicly available ILD dataset and report results for both patch-based classification and the more challenging whole-slice setting. The paper presents preliminary research findings, not prospective clinical validation.
Cite this work
Mingchen Gao, Ulas Bagci, Le Lu, Aaron Wu, Mario Buty, Hoo-Chang Shin, Holger Roth, Georgios Z. Papadakis, Adrien Depeursinge, Ronald M. Summers, Ziyue Xu, Daniel J. Mollura (2015). Holistic classification of CT attenuation patterns for interstitial lung diseases via deep convolutional neural networks. Proceedings of the 1st Workshop on Deep Learning in Medical Image Analysis (DLMIA 2015), held in conjunction with the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015), pp. 41–48 https://cse.buffalo.edu/~mgao8/files/MingchenGao_MICCAIworkshop2015.pdf
BibTeX