Su Huang1, Xiaowei Han2, Jingfan Fan1, Jing Chen1, Lei Du3, Wenwen Gao3, Bing Liu3, Yue Chen3, Xiuxiu Liu3, Yige Wang3, Danni Ai1, Guolin Ma3, Jian Yang1. 1. Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of Technology, Beijing, China. 2. Department of Radiology, The Affiliated Drum Tower Hospital of Nanjing University Medical School, Nanjing, China. 3. Department of Radiology, China-Japan Friendship Hospital, Beijing, China.
Abstract
OBJECTIVES: Anterior mediastinal disease is a common disease in the chest. Computed tomography (CT), as an important imaging technology, is widely used in the diagnosis of mediastinal diseases. Doctors find it difficult to distinguish lesions in CT images because of image artifact, intensity inhomogeneity, and their similarity with other tissues. Direct segmentation of lesions can provide doctors a method to better subtract the features of the lesions, thereby improving the accuracy of diagnosis. METHOD: As the trend of image processing technology, deep learning is more accurate in image segmentation than traditional methods. We employ a two-stage 3D ResUNet network combined with lung segmentation to segment CT images. Given that the mediastinum is between the two lungs, the original image is clipped through the lung mask to remove some noises that may affect the segmentation of the lesion. To capture the feature of the lesions, we design a two-stage network structure. In the first stage, the features of the lesion are learned from the low-resolution downsampled image, and the segmentation results under a rough scale are obtained. The results are concatenated with the original image and encoded into the second stage to capture more accurate segmentation information from the image. In addition, attention gates are introduced in the upsampling of the network, and these gates can focus on the lesion and play a role in filtering the features. The proposed method has achieved good results in the segmentation of the anterior mediastinal. RESULTS: The proposed method was verified on 230 patients, and the anterior mediastinal lesions were well segmented. The average Dice coefficient reached 87.73%. Compared with the model without lung segmentation, the model with lung segmentation greatly improved the accuracy of lesion segmentation by approximately 9%. The addition of attention gates slightly improved the segmentation accuracy. CONCLUSION: The proposed automatic segmentation method has achieved good results in clinical data. In clinical application, automatic segmentation of lesions can assist doctors in the diagnosis of diseases and may facilitate the automated diagnosis of illnesses in the future.
OBJECTIVES: Anterior mediastinal disease is a common disease in the chest. Computed tomography (CT), as an important imaging technology, is widely used in the diagnosis of mediastinal diseases. Doctors find it difficult to distinguish lesions in CT images because of image artifact, intensity inhomogeneity, and their similarity with other tissues. Direct segmentation of lesions can provide doctors a method to better subtract the features of the lesions, thereby improving the accuracy of diagnosis. METHOD: As the trend of image processing technology, deep learning is more accurate in image segmentation than traditional methods. We employ a two-stage 3D ResUNet network combined with lung segmentation to segment CT images. Given that the mediastinum is between the two lungs, the original image is clipped through the lung mask to remove some noises that may affect the segmentation of the lesion. To capture the feature of the lesions, we design a two-stage network structure. In the first stage, the features of the lesion are learned from the low-resolution downsampled image, and the segmentation results under a rough scale are obtained. The results are concatenated with the original image and encoded into the second stage to capture more accurate segmentation information from the image. In addition, attention gates are introduced in the upsampling of the network, and these gates can focus on the lesion and play a role in filtering the features. The proposed method has achieved good results in the segmentation of the anterior mediastinal. RESULTS: The proposed method was verified on 230 patients, and the anterior mediastinal lesions were well segmented. The average Dice coefficient reached 87.73%. Compared with the model without lung segmentation, the model with lung segmentation greatly improved the accuracy of lesion segmentation by approximately 9%. The addition of attention gates slightly improved the segmentation accuracy. CONCLUSION: The proposed automatic segmentation method has achieved good results in clinical data. In clinical application, automatic segmentation of lesions can assist doctors in the diagnosis of diseases and may facilitate the automated diagnosis of illnesses in the future.
Authors: Luis Garcia Ugarriza; Eli Saber; Sreenath Rao Vantaram; Vincent Amuso; Mark Shaw; Ranjit Bhaskar Journal: IEEE Trans Image Process Date: 2009-06-16 Impact factor: 10.856
Authors: Philipp Ströbel; Andrea Bauer; Bernhard Puppe; Til Kraushaar; Axel Krein; Klaus Toyka; Ralf Gold; Michael Semik; Reinhard Kiefer; Wilfred Nix; Berthold Schalke; Hans Konrad Müller-Hermelink; Alexander Marx Journal: J Clin Oncol Date: 2004-04-15 Impact factor: 44.544
Authors: Eli Gibson; Francesco Giganti; Yipeng Hu; Ester Bonmati; Steve Bandula; Kurinchi Gurusamy; Brian Davidson; Stephen P Pereira; Matthew J Clarkson; Dean C Barratt Journal: IEEE Trans Med Imaging Date: 2018-02-14 Impact factor: 10.048