Deep Learning for Diagnosis and Segmentation of Pneumothorax: The Results on The Kaggle Competition and Validation Against Radiologists
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Deep Learning for Diagnosis and Segmentation of Pneumothorax : The Results on The Kaggle Competition and Validation Against Radiologists. / Tolkachev, Alexey; Sirazitdinov, Ilyas; Kholiavchenko, Maksym; Mustafaev, Tamerlan; Ibragimov, Bulat.
In: IEEE Journal of Biomedical and Health Informatics, Vol. 25, No. 5, 2021, p. 1660-1672 .Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Deep Learning for Diagnosis and Segmentation of Pneumothorax
T2 - The Results on The Kaggle Competition and Validation Against Radiologists
AU - Tolkachev, Alexey
AU - Sirazitdinov, Ilyas
AU - Kholiavchenko, Maksym
AU - Mustafaev, Tamerlan
AU - Ibragimov, Bulat
PY - 2021
Y1 - 2021
N2 - Pneumothorax is potentially a life-threatening disease that requires urgent diagnosis and treatment. The chest X-ray is the diagnostic modality of choice when pneumothorax is suspected. The computer-aided diagnosis of pneumothorax has received a dramatic boost in the last few years due to deep learning advances and the first public pneumothorax diagnosis competition with 15257 chest X-rays manually annotated by a team of 19 radiologists. This paper describes one of the top frameworks that participated in the competition. The framework investigates the benefits of combining the Unet convolutional neural network with various backbones, namely ResNet34, SE-ResNext50, SE-ResNext101, and DenseNet121. The paper presents a step-by-step instruction for the framework application, including data augmentation, and different pre- and post-processing steps. The performance of the framework was of 0.8574 measured in terms of the Dice coefficient. The second contribution of the paper is the comparison of the deep learning framework against three experienced radiologists on the pneumothorax detection and segmentation on challenging X-rays. We also evaluated how diagnostic confidence of radiologists affects the accuracy of the diagnosis and observed that the deep learning framework and radiologists find the same X-rays to be easy/difficult to analyze (p-value <1e4). Finally, the methodology of all top-performing teams from the competition leaderboard was analyzed to find the consistent methodological patterns of accurate pneumothorax detection and segmentation.
AB - Pneumothorax is potentially a life-threatening disease that requires urgent diagnosis and treatment. The chest X-ray is the diagnostic modality of choice when pneumothorax is suspected. The computer-aided diagnosis of pneumothorax has received a dramatic boost in the last few years due to deep learning advances and the first public pneumothorax diagnosis competition with 15257 chest X-rays manually annotated by a team of 19 radiologists. This paper describes one of the top frameworks that participated in the competition. The framework investigates the benefits of combining the Unet convolutional neural network with various backbones, namely ResNet34, SE-ResNext50, SE-ResNext101, and DenseNet121. The paper presents a step-by-step instruction for the framework application, including data augmentation, and different pre- and post-processing steps. The performance of the framework was of 0.8574 measured in terms of the Dice coefficient. The second contribution of the paper is the comparison of the deep learning framework against three experienced radiologists on the pneumothorax detection and segmentation on challenging X-rays. We also evaluated how diagnostic confidence of radiologists affects the accuracy of the diagnosis and observed that the deep learning framework and radiologists find the same X-rays to be easy/difficult to analyze (p-value <1e4). Finally, the methodology of all top-performing teams from the competition leaderboard was analyzed to find the consistent methodological patterns of accurate pneumothorax detection and segmentation.
U2 - 10.1109/JBHI.2020.3023476
DO - 10.1109/JBHI.2020.3023476
M3 - Journal article
C2 - 32956067
VL - 25
SP - 1660
EP - 1672
JO - IEEE Journal of Biomedical and Health Informatics
JF - IEEE Journal of Biomedical and Health Informatics
SN - 2168-2194
IS - 5
ER -
ID: 255114059