Label Propagation Algorithm for the Slices Detection of a Ground-Glass Opacity Nodule

2019 ◽  
Vol 7 (1) ◽  
pp. 104-118 ◽  
Author(s):  
Weiwei Du ◽  
Dandan Yuan ◽  
Jianming Wang ◽  
Xiaojie Duan ◽  
Yanhe Ma ◽  
...  

A radiologist must read hundreds of slices to recognize a malignant or benign lung tumor in computed tomography (CT) volume data. To reduce the burden of the radiologist, some proposals have been applied with the ground-glass opacity (GGO) nodules. However, the GGO nodules need be detected and labeled by a radiologist manually. Some slices with the GGO nodule can be missed because there are many slices in several volume data. Although some papers have proposed a semi-supervised learning method to find the slices with GGO nodules, the was no discussion on the impact of parameters in the proposed semi-supervised learning. This article also explains and analyzes the label propagation algorithm which is one of the semi-supervised learning methods to detect the slices including the GGO nodules based on the parameters. Experimental results show that the proposal can detect the slices including the GGO nodules effectively.

2018 ◽  
Vol 10 (9) ◽  
pp. 5428-5434 ◽  
Author(s):  
Kai Obayashi ◽  
Kimihiro Shimizu ◽  
Seshiru Nakazawa ◽  
Toshiteru Nagashima ◽  
Toshiki Yajima ◽  
...  

2020 ◽  
Vol 61 (3) ◽  
pp. 426-430
Author(s):  
Hiroshi Onishi ◽  
Yoshiyuki Shioyama ◽  
Yasuo Matsumoto ◽  
Yuta Shibamoto ◽  
Akifumi Miyakawa ◽  
...  

Abstract We retrospectively reviewed the effect of stereotactic body radiation therapy (SBRT) in patients with stage I lung cancer whose lung tumor showed a nodular appearance of ground glass opacity, so-called ground glass nodule (GGN). A total of 84 patients (42 men, 42 women; mean age, 75 years) with stage I lung cancer with GGN accompanying a solid component <50% in diameter of the tumor and no metastases were studied. Concerning histology, 32 tumors were adenocarcinoma, 1 was squamous cell carcinoma, 2 were unclassified carcinoma and 49 cases were histology-unproven but increased in size or had a positive finding in 18F-FDG positron emission tomography (PET) examination. The median tumor size was 20 mm (range, 10–41 mm). All of the patients were treated with SBRT, and the total prescribed dose at the isocenter ranged between 48 Gy in four fractions and 84 Gy in ten fractions. Median follow-up duration was 33 months. No patient had local failure nor regional lymph node failure. The 3-year rate of distant failure was 2.6%. Two patients who experienced distant metastases had a past surgical history of initial lung cancer before SBRT. The rates of cause-specific and overall survival at 3 years were 98.2 and 94.6%, respectively. Treatment-related adverse events of ≥grade 4 were not reported. Although more cases and longer follow-ups are mandatory, SBRT may be one of the radical treatment options for patients with GGN.


2013 ◽  
Vol 32 (2) ◽  
pp. 403-406
Author(s):  
Pei-qi LIU ◽  
Jie-han SUN

Sign in / Sign up

Export Citation Format

Share Document