Wenhao Wu1, Lei Gao1, Huihong Duan1, Gang Huang2, Xiaodan Ye3, Shengdong Nie1. 1. School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai, 200093, People's Republic of China. 2. Shanghai University of Medicine & Health Science, Shanghai, 201318, People's Republic of China. 3. Shanghai Chest Hospital, Shanghai Jiao Tong University, Shanghai, 200030, People's Republic of China.
Abstract
PURPOSE: Pulmonary nodules are a potential manifestation of lung cancer. In computer-aided diagnosis (CAD) of lung cancer, it is of great significance to extract the complete boundary of the pulmonary nodules in the computed tomography (CT) scans accurately. It can provide doctors with important information such as tumor size and density, which assist doctors in subsequent diagnosis and treatment. In addition to this, in the molecular subtype and radiomics of lung cancer, segmentation of lung nodules also plays a pivotal role. Existing methods are difficult to use only one model to simultaneously treat the boundaries of multiple types of lung nodules in CT images. METHOD: In order to solve the problem, this paper proposed a three-dimensional (3D)-UNET network model optimized by a 3D conditional random field (3D-CRF) to segment pulmonary nodules. On the basis of 3D-UNET, the 3D-CRF is used to optimize the sample output of the training set, so as to update the network weights in training process, reduce the model training time, and reduce the loss rate of the model. We selected 936 sets of pulmonary nodule data for the lung image database consortium and image database resource initiative (LIDC-IDRI)1 database to train and test the model. What's more, we used clinical data from partner hospitals for additional validation. RESULTS AND CONCLUSIONS: The results show that our method is accurate and effective. Particularly, it shows more significance for the optimization of the segmentation of adhesive pulmonary nodules (the juxta-pleural and juxta-vascular nodules) and ground glass pulmonary nodules (GGNs).
PURPOSE: Pulmonary nodules are a potential manifestation of lung cancer. In computer-aided diagnosis (CAD) of lung cancer, it is of great significance to extract the complete boundary of the pulmonary nodules in the computed tomography (CT) scans accurately. It can provide doctors with important information such as tumor size and density, which assist doctors in subsequent diagnosis and treatment. In addition to this, in the molecular subtype and radiomics of lung cancer, segmentation of lung nodules also plays a pivotal role. Existing methods are difficult to use only one model to simultaneously treat the boundaries of multiple types of lung nodules in CT images. METHOD: In order to solve the problem, this paper proposed a three-dimensional (3D)-UNET network model optimized by a 3D conditional random field (3D-CRF) to segment pulmonary nodules. On the basis of 3D-UNET, the 3D-CRF is used to optimize the sample output of the training set, so as to update the network weights in training process, reduce the model training time, and reduce the loss rate of the model. We selected 936 sets of pulmonary nodule data for the lung image database consortium and image database resource initiative (LIDC-IDRI)1 database to train and test the model. What's more, we used clinical data from partner hospitals for additional validation. RESULTS AND CONCLUSIONS: The results show that our method is accurate and effective. Particularly, it shows more significance for the optimization of the segmentation of adhesive pulmonary nodules (the juxta-pleural and juxta-vascular nodules) and ground glass pulmonary nodules (GGNs).
Authors: Sergey P Primakov; Abdalla Ibrahim; Janita E van Timmeren; Guangyao Wu; Simon A Keek; Manon Beuque; Renée W Y Granzier; Elizaveta Lavrova; Madeleine Scrivener; Sebastian Sanduleanu; Esma Kayan; Iva Halilaj; Anouk Lenaers; Jianlin Wu; René Monshouwer; Xavier Geets; Hester A Gietema; Lizza E L Hendriks; Olivier Morin; Arthur Jochems; Henry C Woodruff; Philippe Lambin Journal: Nat Commun Date: 2022-06-14 Impact factor: 17.694
Authors: Gabriele C Forte; Stephan Altmayer; Ricardo F Silva; Mariana T Stefani; Lucas L Libermann; Cesar C Cavion; Ali Youssef; Reza Forghani; Jeremy King; Tan-Lucien Mohamed; Rubens G F Andrade; Bruno Hochhegger Journal: Cancers (Basel) Date: 2022-08-09 Impact factor: 6.575
Authors: Hedvig Hricak; May Abdel-Wahab; Rifat Atun; Miriam Mikhail Lette; Diana Paez; James A Brink; Lluís Donoso-Bach; Guy Frija; Monika Hierath; Ola Holmberg; Pek-Lan Khong; Jason S Lewis; Geraldine McGinty; Wim J G Oyen; Lawrence N Shulman; Zachary J Ward; Andrew M Scott Journal: Lancet Oncol Date: 2021-03-04 Impact factor: 41.316