2021
DOI: 10.1109/tpami.2021.3065086
|View full text |Cite
|
Sign up to set email alerts
|

SANet: A Slice-Aware Network for Pulmonary Nodule Detection

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
74
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 68 publications
(74 citation statements)
references
References 66 publications
0
74
0
Order By: Relevance
“…Newer studies have been proposed with relevant results. For example, Zhu et al [28] treated the quality of the images, and Peng et al [35] and Mei et al [36] proposed new DCNN architectures. However, they do not surpass all our results in the different steps (NCD and FPR) with the evaluation metrics average sensitivity at FPs/Scan or CPM.…”
Section: Experiments and Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…Newer studies have been proposed with relevant results. For example, Zhu et al [28] treated the quality of the images, and Peng et al [35] and Mei et al [36] proposed new DCNN architectures. However, they do not surpass all our results in the different steps (NCD and FPR) with the evaluation metrics average sensitivity at FPs/Scan or CPM.…”
Section: Experiments and Resultsmentioning
confidence: 99%
“…The CPM score of their scheme is 92.30% on the LUNA16 dataset. In another approach, Mei et al [36] proposed a CADe system based on DCNN named SANet. Initially, they used a 3D RPN to generate pulmonary nodule candidates.…”
Section: Related Workmentioning
confidence: 99%
“…Liao et al [14] utilized a 3D Faster RCNN with a U-net structure, supplementing it with a location crop to aid in determining whether the object is a nodule. Mei et al [10] proposed a slice grouped non-local (SGNL) module for capturing longrange dependencies between any positions in the feature maps. However, these methods treat every pixel in the feature maps the same, which is contrary to how experienced doctors assess the lung areas.…”
Section: A Spatial Context and Attention Mechanismmentioning
confidence: 99%
“…Moreover, we find that commonly used public datasets, such as LIDC-IDRI [12], LUNA 16 [13] and PN9 [10] contain many small nodules, ranging in size from 3mm to 10mm, and are composed of an imbalanced proportion of different sized lung nodules. However, nodules less than 5 mm in diameter, in need of long-term follow-ups, are not a primary focus of therapeutic applications.…”
Section: Introductionmentioning
confidence: 96%
See 1 more Smart Citation