Yuxiao Qi1, Jieyu Li2, Huai Chen1, Yujie Guo3, Yong Yin3, Guanzhong Gong4, Lisheng Wang1. 1. Institute of Image Processing and Pattern Recognition, Department of Automation, Shanghai Jiao Tong University, Shanghai, 200240, People's Republic of China. 2. Institute of Image Processing and Pattern Recognition, Department of Automation, Shanghai Jiao Tong University, Shanghai, 200240, People's Republic of China. lijieyu@sjtu.edu.cn. 3. Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, 250117, People's Republic of China. 4. Shandong Cancer Hospital and Institute, Shandong First Medical University and Shandong Academy of Medical Sciences, Jinan, 250117, People's Republic of China. gongguanzhong@163.com.
Abstract
PURPOSE: Nasopharyngeal carcinoma (NPC) is a category of tumors with high incidence in head-and-neck (H&N) body region, and the diagnosis and treatment planning are usually conducted by radiologists manually, which is tedious, time-consuming and unrepeatable. In this paper, we integrated different stages of this process and proposed a computer-aided framework to realize automatic detection, tumor region and sub-region segmentation, and visualization of NPC, which are usually investigated separately in literatures. METHODS: Multi-modality images are utilized in the framework. Firstly, NPC is detected by a convolutional neural network (CNN) on computed tomography (CT) scans. Then, NPC area is segmented from magnetic resonance imaging (MRI) images by using a multi-modality MRI fusion network. Thirdly, NPC sub-regions with different metabolic activities are divided on CT images of the same patient via an adaptive threshold algorithm. Finally, 3D surface model of NPC is generated for observing its shape, size, and location in the head region. The proposed method is compared with other algorithms by evaluation on the volumes and shapes of detected NPCs. RESULTS: Experiments are conducted on CT images of 130 NPC patients and 102 subjects without NPC and MRI images of 149 NPC patients, among which 52 subjects are overlapped with both CT and MRI images. The reference for evaluation is generated by three experienced radiologists. The results demonstrated that our utilized models outperform other strategies with detection accuracy 0.882 and Dice similarity coefficient 0.719 for NPC segmentation. Sub-region division and the 3D visualized models show great acceptability in clinical usage. CONCLUSION: The remarkable performance indicated the potential of our framework in alleviating workload of radiologist. Furthermore, the combined usage of multi-modality images is able to generate reliable segmentations of NPC area and sub-regions, which provide evidence to judge the heterogeneity among patients and guide the dose painting for radiation therapy.
PURPOSE: Nasopharyngeal carcinoma (NPC) is a category of tumors with high incidence in head-and-neck (H&N) body region, and the diagnosis and treatment planning are usually conducted by radiologists manually, which is tedious, time-consuming and unrepeatable. In this paper, we integrated different stages of this process and proposed a computer-aided framework to realize automatic detection, tumor region and sub-region segmentation, and visualization of NPC, which are usually investigated separately in literatures. METHODS: Multi-modality images are utilized in the framework. Firstly, NPC is detected by a convolutional neural network (CNN) on computed tomography (CT) scans. Then, NPC area is segmented from magnetic resonance imaging (MRI) images by using a multi-modality MRI fusion network. Thirdly, NPC sub-regions with different metabolic activities are divided on CT images of the same patient via an adaptive threshold algorithm. Finally, 3D surface model of NPC is generated for observing its shape, size, and location in the head region. The proposed method is compared with other algorithms by evaluation on the volumes and shapes of detected NPCs. RESULTS: Experiments are conducted on CT images of 130 NPC patients and 102 subjects without NPC and MRI images of 149 NPC patients, among which 52 subjects are overlapped with both CT and MRI images. The reference for evaluation is generated by three experienced radiologists. The results demonstrated that our utilized models outperform other strategies with detection accuracy 0.882 and Dice similarity coefficient 0.719 for NPC segmentation. Sub-region division and the 3D visualized models show great acceptability in clinical usage. CONCLUSION: The remarkable performance indicated the potential of our framework in alleviating workload of radiologist. Furthermore, the combined usage of multi-modality images is able to generate reliable segmentations of NPC area and sub-regions, which provide evidence to judge the heterogeneity among patients and guide the dose painting for radiation therapy.
Entities:
Keywords:
3D model visualization; Computer-aided diagnosis; Multi-modality medical images; Nasopharyngeal carcinoma; Segmentation
Authors: Jose Dolz; Karthik Gopinath; Jing Yuan; Herve Lombaert; Christian Desrosiers; Ismail Ben Ayed Journal: IEEE Trans Med Imaging Date: 2018-10-30 Impact factor: 10.048
Authors: I Fitton; S A P Cornelissen; J C Duppen; R J H M Steenbakkers; S T H Peeters; F J P Hoebers; J H A M Kaanders; P J C M Nowak; C R N Rasch; M van Herk Journal: Med Phys Date: 2011-08 Impact factor: 4.071
Authors: C Rasch; R Keus; F A Pameijer; W Koops; V de Ru; S Muller; A Touw; H Bartelink; M van Herk; J V Lebesque Journal: Int J Radiat Oncol Biol Phys Date: 1997-11-01 Impact factor: 7.038
Authors: Inna Serganova; Michael Doubrovin; Jelena Vider; Vladimir Ponomarev; Suren Soghomonyan; Tatiana Beresten; Ludmila Ageyeva; Alexander Serganov; Shangde Cai; Julius Balatoni; Ronald Blasberg; Juri Gelovani Journal: Cancer Res Date: 2004-09-01 Impact factor: 12.701
Authors: Jan Kubicek; Alice Varysova; Martin Cerny; Kristyna Hancarova; David Oczka; Martin Augustynek; Marek Penhaker; Ondrej Prokop; Radomir Scurek Journal: Sensors (Basel) Date: 2022-08-23 Impact factor: 3.847