Lung nodule malignancy classification with weakly supervised explanation generation

2021 ◽  
Vol 8 (04) ◽  
Author(s):  
Aniket Joshi ◽  
Jayanthi Sivaswamy ◽  
Gopal Datt Joshi
Keyword(s):  
Lung Nodule ◽  
Weakly Supervised ◽  
Explanation Generation

LUNGRADS AND UPDATE OF LUNG NODULES SCREENING BY LOW DOSE COMPUTED TOMOGRAPHY

2015 ◽  
pp. 12-19
Author(s):  
Thi Ngoc Ha Hoang ◽  
Trong Khoan Le
Keyword(s):  
Lung Cancer ◽  
Low Dose ◽  
False Negative ◽  
Lung Nodule ◽  
Lung Cancer Mortality ◽  
Smoking History ◽  
Low Dose Ct ◽  
History Of ◽  
Chest X Ray ◽  
Low Dose Computed Tomography

Background: A pulmonary nodule is defined as a rounded or irregular opacity, well or poorly defined, measuring up to 3 cm in diameter. Early detection the malignancy of nodules has a significant role in decreasing the mortality, increasing the survival time and consider as early diagnosis lung cancer. The main risk factors are those of current or former smokers, aged 55 to 74 years with a smoking history of at least 1 pack-day. Low dose CT: screening individuals with high risk of lung cancer by low dose CT scans could reduce lung cancer mortality by 20 percent compared to chest X-ray. Radiation dose has to maximum reduced but respect the rule of ALARA (As Low as Resonably Archivable). LungRADS 2014: Classification of American College of Radiology, LungRADS, is a newly application but showed many advantages in comparison with others classification such as increasing positive predict value (PPV), no result of false negative and cost effectiveness. Key words: LungRADS, screening lung nodule, low dose CT, lung cancer

Coordinating Text and Graphics in Explanation Generation

1989 ◽  
Author(s):  
Steven K. Feiner ◽  
Kathleen R. McKeown
Keyword(s):  
Explanation Generation

Multi-level 3D Densenets for False-positive Reduction in Lung Nodule Detection Based on Chest Computed Tomography

2020 ◽  
Vol 16 (8) ◽  
pp. 1004-1021
Author(s):  
Xiaoqi Lu ◽  
Yu Gu ◽  
Lidong Yang ◽  
Baohua Zhang ◽  
Ying Zhao ◽  
...  
Keyword(s):  
False Positive ◽  
Contextual Information ◽  
Lung Nodule ◽  
Positive Sample ◽  
Lung Nodules ◽  
Lung Nodule Detection ◽  
Nodule Detection ◽  
Level Information ◽  
Multi Level ◽  
Cade System

Objective: False-positive nodule reduction is a crucial part of a computer-aided detection (CADe) system, which assists radiologists in accurate lung nodule detection. In this research, a novel scheme using multi-level 3D DenseNet framework is proposed to implement false-positive nodule reduction task. Methods: Multi-level 3D DenseNet models were extended to differentiate lung nodules from falsepositive nodules. First, different models were fed with 3D cubes with different sizes for encoding multi-level contextual information to meet the challenges of the large variations of lung nodules. In addition, image rotation and flipping were utilized to upsample positive samples which consisted of a positive sample set. Furthermore, the 3D DenseNets were designed to keep low-level information of nodules, as densely connected structures in DenseNet can reuse features of lung nodules and then boost feature propagation. Finally, the optimal weighted linear combination of all model scores obtained the best classification result in this research. Results: The proposed method was evaluated with LUNA16 dataset which contained 888 thin-slice CT scans. The performance was validated via 10-fold cross-validation. Both the Free-response Receiver Operating Characteristic (FROC) curve and the Competition Performance Metric (CPM) score show that the proposed scheme can achieve a satisfactory detection performance in the falsepositive reduction track of the LUNA16 challenge. Conclusion: The result shows that the proposed scheme can be significant for false-positive nodule reduction task.

Sign in / Sign up

Export Citation Format

Share Document