Hey everyone!
\nI wanted to start a papers thread and build on it, and hope others share as well, papers to gain domain knowledge. I have no domain knowledge in this area so I have downloaded papers that appeared to be relevant after reading their abstracts. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!
\nResearch Papers:
\nCovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection - in this research, we present a method to generate synthetic chest X-ray (CXR) images by developing an Auxiliary Classifier Generative Adversarial Network (ACGAN) based model called CovidGAN. In addition, we demonstrate that the synthetic images produced from CovidGAN can be utilized to enhance the performance of CNN for COVID-19 detection. Classification using CNN alone yielded 85% accuracy. By adding synthetic images produced by CovidGAN, the accuracy increased to 95%. We hope this method will speed up COVID-19 detection and lead to more robust systems of radiology.
Iteratively Pruned Deep Learning Ensembles for COVID-19 Detection in Chest X-rays - The best performing models are iteratively pruned to reduce complexity and improve memory efficiency. The predictions of the best-performing pruned models are combined through different ensemble strategies to improve classification performance. Empirical evaluations demonstrate that the weighted average of the best-performing pruned models significantly improves performance resulting in an accuracy of 99.01% and area under the curve of 0.9972 in detecting COVID-19 findings on CXRs. The combined use of modality-specific knowledge transfer, iterative model pruning, and ensemble learning resulted in improved predictions. We expect that this model can be quickly adopted for COVID-19 screening using chest radiographs.
COVID-ResNet: A Deep Learning Framework for Screening of COVID19 from Radiographs - Using these techniques, we showed the state of the art results on the open-access COVID-19 dataset. This work presents a 3-step technique to fine-tune a pre-trained ResNet-50 architecture to improve model performance and reduce training time. We call it COVIDResNet. This is achieved through progressively re-sizing of input images to 128x128x3, 224x224x3, and 229x229x3 pixels and fine-tuning the network at each stage. This approach along with the automatic learning rate selection enabled us to achieve the state of the art accuracy of 96.23% (on all the classes) on the COVIDx dataset with only 41 epochs. This work presented a computationally efficient and highly accurate model for multi-class classification of three different infection types from along with Normal individuals. This model can help in the early screening of COVID19 cases and help reduce the burden on healthcare systems.
Hey everyone!
\nI wanted to start a papers thread and build on it, and hope others share as well, papers to gain domain knowledge. I have no domain knowledge in this area so I have downloaded papers that appeared to be relevant after reading their abstracts. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!
\nResearch Papers:
\nCovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection - in this research, we present a method to generate synthetic chest X-ray (CXR) images by developing an Auxiliary Classifier Generative Adversarial Network (ACGAN) based model called CovidGAN. In addition, we demonstrate that the synthetic images produced from CovidGAN can be utilized to enhance the performance of CNN for COVID-19 detection. Classification using CNN alone yielded 85% accuracy. By adding synthetic images produced by CovidGAN, the accuracy increased to 95%. We hope this method will speed up COVID-19 detection and lead to more robust systems of radiology.
Iteratively Pruned Deep Learning Ensembles for COVID-19 Detection in Chest X-rays - The best performing models are iteratively pruned to reduce complexity and improve memory efficiency. The predictions of the best-performing pruned models are combined through different ensemble strategies to improve classification performance. Empirical evaluations demonstrate that the weighted average of the best-performing pruned models significantly improves performance resulting in an accuracy of 99.01% and area under the curve of 0.9972 in detecting COVID-19 findings on CXRs. The combined use of modality-specific knowledge transfer, iterative model pruning, and ensemble learning resulted in improved predictions. We expect that this model can be quickly adopted for COVID-19 screening using chest radiographs.
COVID-ResNet: A Deep Learning Framework for Screening of COVID19 from Radiographs - Using these techniques, we showed the state of the art results on the open-access COVID-19 dataset. This work presents a 3-step technique to fine-tune a pre-trained ResNet-50 architecture to improve model performance and reduce training time. We call it COVIDResNet. This is achieved through progressively re-sizing of input images to 128x128x3, 224x224x3, and 229x229x3 pixels and fine-tuning the network at each stage. This approach along with the automatic learning rate selection enabled us to achieve the state of the art accuracy of 96.23% (on all the classes) on the COVIDx dataset with only 41 epochs. This work presented a computationally efficient and highly accurate model for multi-class classification of three different infection types from along with Normal individuals. This model can help in the early screening of COVID19 cases and help reduce the burden on healthcare systems.
Thank you so much for sharing these ! It is really helpful !
", "rawMarkdown": "Thank you so much for sharing these ! It is really helpful !", "votes": null }, { "id": "1315066", "postDate": "05/19/2021 14:32:46", "content": "@crained , I'm amazed by the quality of your post. Great resource again!
", "rawMarkdown": "crained , I'm amazed by the quality of your post. Great resource again!", "votes": null }, { "id": "1315270", "postDate": "05/19/2021 17:11:50", "content": "Thanks, @joseguzman hope it is helpful!
", "rawMarkdown": "Thanks, @joseguzman hope it is helpful!", "votes": null }, { "id": "1315271", "postDate": "05/19/2021 17:12:13", "content": "Awesome @amartyabhattacharya hope it helps with the competition!
", "rawMarkdown": "Awesome @amartyabhattacharya hope it helps with the competition!", "votes": null }, { "id": "1327651", "postDate": "05/29/2021 13:52:10", "content": "Great resources!
", "rawMarkdown": "Great resources!", "votes": null } ], "comments": [ { "id": 1314757, "author_name": "amartyabhattacharya", "author_url": "", "post_date": "05/19/2021 11:16:57", "content": "Thank you so much for sharing these ! It is really helpful !
", "votes": null, "replies": [ { "id": 1315271, "author_name": "crained", "author_url": "", "post_date": "05/19/2021 17:12:13", "content": "Awesome @amartyabhattacharya hope it helps with the competition!
", "votes": null, "replies": [] } ] }, { "id": 1315066, "author_name": "joseguzman", "author_url": "", "post_date": "05/19/2021 14:32:46", "content": "@crained , I'm amazed by the quality of your post. Great resource again!
", "votes": null, "replies": [ { "id": 1315270, "author_name": "crained", "author_url": "", "post_date": "05/19/2021 17:11:50", "content": "Thanks, @joseguzman hope it is helpful!
", "votes": null, "replies": [] } ] }, { "id": 1327651, "author_name": "asmirm", "author_url": "", "post_date": "05/29/2021 13:52:10", "content": "Great resources!
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "1313570": "Hey everyone!\n\nI wanted to start a papers thread and build on it, and hope others share as well, papers to gain domain knowledge. I have no domain knowledge in this area so I have downloaded papers that appeared to be relevant after reading their abstracts. I'll be reading these over the coming days and commenting more as I go through all of them. Hope this helps!\n\n**Research Papers:**\n\n- [CovidGAN: Data Augmentation Using Auxiliary Classifier GAN for Improved Covid-19 Detection](https://arxiv.org/abs/2103.05094) - in this research, we present a method to generate synthetic chest X-ray (CXR) images by developing an Auxiliary Classifier Generative Adversarial Network (ACGAN) based model called CovidGAN. In addition, we demonstrate that the synthetic images produced from CovidGAN can be utilized to enhance the performance of CNN for COVID-19 detection. Classification using CNN alone yielded 85% accuracy. By adding synthetic images produced by CovidGAN, the accuracy increased to 95%. We hope this method will speed up COVID-19 detection and lead to more robust systems of radiology.\n\n- [Iteratively Pruned Deep Learning Ensembles for COVID-19 Detection in Chest X-rays](https://arxiv.org/abs/2004.08379) - The best performing models are iteratively pruned to reduce complexity and improve memory efficiency. The predictions of the best-performing pruned models are combined through different ensemble strategies to improve classification performance. Empirical evaluations demonstrate that the weighted average of the best-performing pruned models significantly improves performance resulting in an accuracy of 99.01% and area under the curve of 0.9972 in detecting COVID-19 findings on CXRs. The combined use of modality-specific knowledge transfer, iterative model pruning, and ensemble learning resulted in improved predictions. We expect that this model can be quickly adopted for COVID-19 screening using chest radiographs.\n\n- [COVID-ResNet: A Deep Learning Framework for Screening of COVID19 from Radiographs](https://arxiv.org/abs/2003.14395) - Using these techniques, we showed the state of the art results on the open-access COVID-19 dataset. This work presents a 3-step technique to fine-tune a pre-trained ResNet-50 architecture to improve model performance and reduce training time. We call it COVIDResNet. This is achieved through progressively re-sizing of input images to 128x128x3, 224x224x3, and 229x229x3 pixels and fine-tuning the network at each stage. This approach along with the automatic learning rate selection enabled us to achieve the state of the art accuracy of 96.23% (on all the classes) on the COVIDx dataset with only 41 epochs. This work presented a computationally efficient and highly accurate model for multi-class classification of three different infection types from along with Normal individuals. This model can help in the early screening of COVID19 cases and help reduce the burden on healthcare systems.", "1314757": "Thank you so much for sharing these ! It is really helpful !", "1315066": "crained , I'm amazed by the quality of your post. Great resource again!", "1315270": "Thanks, @joseguzman hope it is helpful!", "1315271": "Awesome @amartyabhattacharya hope it helps with the competition!", "1327651": "Great resources!" }, "source": "meta" }