Computer-aided Diagnosis in Lungs Radiography

Lis, Aleksandra; Śniatała, Pawel; Konkol, Marek

doi:10.23919/mixdes.2018.8436863

Cited by 1 publication

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the fact that pre-trained weights of the Unet [10] for lung segmentations were obtained by training and evaluating from the data in the standard Hounsfield scale. [17] We projected the image intensity back to the Hounsfield scale that allows us to produce consistent lung segmentation masks using the pre-trained weights. To further improve the image loading efficiency in the training, a sequence of slides in a case is converted to a 3D CT volume saved in NIfTI format.…”

Section: Data Preprocessingmentioning

confidence: 99%

A transformer-based framework for automatic COVID19 diagnosis in chest CTs

Zhang

Wen

2021

2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)

View full text Add to dashboard Cite

Automated diagnosis of covid19 in chest CTs is becoming a clinically important technique to support precision and efficient diagnosis and treatment planning. A few efforts have been made to automatically diagnose the COVID-19 in CTs using CNNs, and the task still remains a challenge. In this paper, we present a transformer-based framework for COVID19 classification. We attempt to expand the adaption of vision transformer as a robust feature learner to the 3D CTs to diagnose the COVID-19. The framework consists of two main stages: lung segmentation using UNet followed by the classification, in which the features extracted from each CT slice using Swin transformer in a CT scan are aggregated into 3D volume level feature. We also investigated the performance of using the robust CNNs (BiT and Effi-cientNetV2) as backbones in the framework. The dataset from the ICCV workshop: MIA-COV19D, is used in our experiments. The evaluation results show that the method with the backbone of Swin transformer gain the best F1 score of 0.935 on the validation dataset, while the CNN based backbone of EfficientNetV2 has the competitive classification performance with the best precision of 93.7%. The final prediction model with Swin transformer achieves the F1 score of 0.84 on the test dataset, which doesn't require an additional post-processing stage.

show abstract

Section: Data Preprocessingmentioning

confidence: 99%