Mehdi Astaraki1, Yousuf Zakko2, Iuliana Toma Dasu3, Örjan Smedby4, Chunliang Wang4. 1. KTH Royal Institute of Technology, Department of Biomedical Engineering and Health Systems, SE-14157 Huddinge, Sweden; Karolinska Institutet, Department of Oncology-Pathology, Karolinska Universitetssjukhuset, Solna, SE-17176 Stockholm, Sweden. Electronic address: mehast@kth.se. 2. Karolinska University Hospital, Imaging and Function, Radiology Department, Solna, SE-17176 Stockholm, Sweden. 3. Karolinska Institutet, Department of Oncology-Pathology, Karolinska Universitetssjukhuset, Solna, SE-17176 Stockholm, Sweden; Stockholm University, Department of Physics, SE-106 91 Stockholm, Sweden. 4. KTH Royal Institute of Technology, Department of Biomedical Engineering and Health Systems, SE-14157 Huddinge, Sweden.
Abstract
PURPOSE: Low-Dose Computed Tomography (LDCT) is the most common imaging modality for lung cancer diagnosis. The presence of nodules in the scans does not necessarily portend lung cancer, as there is an intricate relationship between nodule characteristics and lung cancer. Therefore, benign-malignant pulmonary nodule classification at early detection is a crucial step to improve diagnosis and prolong patient survival. The aim of this study is to propose a method for predicting nodule malignancy based on deep abstract features. METHODS: To efficiently capture both intra-nodule heterogeneities and contextual information of the pulmonary nodules, a dual pathway model was developed to integrate the intra-nodule characteristics with contextual attributes. The proposed approach was implemented with both supervised and unsupervised learning schemes. A random forest model was added as a second component on top of the networks to generate the classification results. The discrimination power of the model was evaluated by calculating the Area Under the Receiver Operating Characteristic Curve (AUROC) metric. RESULTS: Experiments on 1297 manually segmented nodules show that the integration of context and target supervised deep features have a great potential for accurate prediction, resulting in a discrimination power of 0.936 in terms of AUROC, which outperformed the classification performance of the Kaggle 2017 challenge winner. CONCLUSION: Empirical results demonstrate that integrating nodule target and context images into a unified network improves the discrimination power, outperforming the conventional single pathway convolutional neural networks.
PURPOSE: Low-Dose Computed Tomography (LDCT) is the most common imaging modality for lung cancer diagnosis. The presence of nodules in the scans does not necessarily portend lung cancer, as there is an intricate relationship between nodule characteristics and lung cancer. Therefore, benign-malignant pulmonary nodule classification at early detection is a crucial step to improve diagnosis and prolong patient survival. The aim of this study is to propose a method for predicting nodule malignancy based on deep abstract features. METHODS: To efficiently capture both intra-nodule heterogeneities and contextual information of the pulmonary nodules, a dual pathway model was developed to integrate the intra-nodule characteristics with contextual attributes. The proposed approach was implemented with both supervised and unsupervised learning schemes. A random forest model was added as a second component on top of the networks to generate the classification results. The discrimination power of the model was evaluated by calculating the Area Under the Receiver Operating Characteristic Curve (AUROC) metric. RESULTS: Experiments on 1297 manually segmented nodules show that the integration of context and target supervised deep features have a great potential for accurate prediction, resulting in a discrimination power of 0.936 in terms of AUROC, which outperformed the classification performance of the Kaggle 2017 challenge winner. CONCLUSION: Empirical results demonstrate that integrating nodule target and context images into a unified network improves the discrimination power, outperforming the conventional single pathway convolutional neural networks.