Medical Imaging 2020: Computer-Aided Diagnosis 2020
DOI: 10.1117/12.2549709
|View full text |Cite
|
Sign up to set email alerts
|

Deep learning for pneumothorax detection and localization using networks fine-tuned with multiple institutional datasets

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
3
1
1

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(4 citation statements)
references
References 0 publications
0
4
0
Order By: Relevance
“…Gooßen 101 compared classification and localisation performance of CNNs, multiple‐instance learning, and fully convolutional networks, with AUROCs of 0.96, 0.93 and 0.92, respectively. Crosby 102 increased spatial resolution by reducing the FOV to the lung apices and also using 256x256‐pixel patches for training. Using a pretrained CNN (VGG‐19), the AUROC for the apex‐based network was 0.80 and for the patch‐based network 0.73 in detecting a pneumothorax.…”
Section: Automatic Disease Detection On Cxr Imagesmentioning
confidence: 99%
“…Gooßen 101 compared classification and localisation performance of CNNs, multiple‐instance learning, and fully convolutional networks, with AUROCs of 0.96, 0.93 and 0.92, respectively. Crosby 102 increased spatial resolution by reducing the FOV to the lung apices and also using 256x256‐pixel patches for training. Using a pretrained CNN (VGG‐19), the AUROC for the apex‐based network was 0.80 and for the patch‐based network 0.73 in detecting a pneumothorax.…”
Section: Automatic Disease Detection On Cxr Imagesmentioning
confidence: 99%
“…MIL breaks the input image into smaller parts (instances), makes individual predictions relating to those instances and combines this information to make a prediction for the whole image. Some studies that make use of MIL are (Crosby et al, 2020c;Schwab et al, 2020). Other topics within the literature include model uncertainty (Ul Abideen et al, 2020;Ghesu et al, 2019), quality of the CXR (Moradi et al, 2020;McManigle et al, 2020;Moradi et al, 2019a;Takaki et al, 2020;McManigle et al, 2020) and defence against adversarial attack (Li and Zhu, 2020;Anand et al, 2020;Xue et al, 2019).…”
Section: Image-level Predictionmentioning
confidence: 99%
“…Jennie et al 33 believed that the normal sizes of CXR images used in deep models are not sufficient to classify pneumothorax. They separated the two top thirds of each lung as apex images and extracted patches from them.…”
Section: Introductionmentioning
confidence: 99%
“…Jennie et al 33 . believed that the normal sizes of CXR images used in deep models are not sufficient to classify pneumothorax.…”
Section: Introductionmentioning
confidence: 99%