Topology optimization search of deep convolution neural networks for CT and X-ray image classification
Abstract Covid-19 is a disease that can lead to pneumonia, respiratory syndrome, septic shock, multiple organ failure, and death. This pandemic is viewed as a critical component of the fight against an enormous threat to the human population. Deep convolutional neural networks have recently proved t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-07-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-022-00847-w |
| _version_ | 1818519176079212544 |
|---|---|
| author | Hassen Louati Ali Louati Slim Bechikh Fatma Masmoudi Abdulaziz Aldaej Elham Kariri |
| author_facet | Hassen Louati Ali Louati Slim Bechikh Fatma Masmoudi Abdulaziz Aldaej Elham Kariri |
| author_sort | Hassen Louati |
| collection | DOAJ |
| description | Abstract Covid-19 is a disease that can lead to pneumonia, respiratory syndrome, septic shock, multiple organ failure, and death. This pandemic is viewed as a critical component of the fight against an enormous threat to the human population. Deep convolutional neural networks have recently proved their ability to perform well in classification and dimension reduction tasks. Selecting hyper-parameters is critical for these networks. This is because the search space expands exponentially in size as the number of layers increases. All existing approaches utilize a pre-trained or designed architecture as an input. None of them takes design and pruning into account throughout the process. In fact, there exists a convolutional topology for any architecture, and each block of a CNN corresponds to an optimization problem with a large search space. However, there are no guidelines for designing a specific architecture for a specific purpose; thus, such design is highly subjective and heavily reliant on data scientists’ knowledge and expertise. Motivated by this observation, we propose a topology optimization method for designing a convolutional neural network capable of classifying radiography images and detecting probable chest anomalies and infections, including COVID-19. Our method has been validated in a number of comparative studies against relevant state-of-the-art architectures. |
| first_indexed | 2024-12-11T01:20:39Z |
| format | Article |
| id | doaj.art-2e560ac66ac1490e9b9108e60f108bf2 |
| institution | Directory Open Access Journal |
| issn | 1471-2342 |
| language | English |
| last_indexed | 2024-12-11T01:20:39Z |
| publishDate | 2022-07-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj.art-2e560ac66ac1490e9b9108e60f108bf22022-12-22T01:25:43ZengBMCBMC Medical Imaging1471-23422022-07-0122111110.1186/s12880-022-00847-wTopology optimization search of deep convolution neural networks for CT and X-ray image classificationHassen Louati0Ali Louati1Slim Bechikh2Fatma Masmoudi3Abdulaziz Aldaej4Elham Kariri5SMART Lab, University of Tunis, ISGSMART Lab, University of Tunis, ISGSMART Lab, University of Tunis, ISGDepartment of Information Systems, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz UniversityDepartment of Information Systems, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz UniversityDepartment of Information Systems, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz UniversityAbstract Covid-19 is a disease that can lead to pneumonia, respiratory syndrome, septic shock, multiple organ failure, and death. This pandemic is viewed as a critical component of the fight against an enormous threat to the human population. Deep convolutional neural networks have recently proved their ability to perform well in classification and dimension reduction tasks. Selecting hyper-parameters is critical for these networks. This is because the search space expands exponentially in size as the number of layers increases. All existing approaches utilize a pre-trained or designed architecture as an input. None of them takes design and pruning into account throughout the process. In fact, there exists a convolutional topology for any architecture, and each block of a CNN corresponds to an optimization problem with a large search space. However, there are no guidelines for designing a specific architecture for a specific purpose; thus, such design is highly subjective and heavily reliant on data scientists’ knowledge and expertise. Motivated by this observation, we propose a topology optimization method for designing a convolutional neural network capable of classifying radiography images and detecting probable chest anomalies and infections, including COVID-19. Our method has been validated in a number of comparative studies against relevant state-of-the-art architectures.https://doi.org/10.1186/s12880-022-00847-wDCNNOptimizationTopologiesPruningCT imagesXRAY images |
| spellingShingle | Hassen Louati Ali Louati Slim Bechikh Fatma Masmoudi Abdulaziz Aldaej Elham Kariri Topology optimization search of deep convolution neural networks for CT and X-ray image classification BMC Medical Imaging DCNN Optimization Topologies Pruning CT images XRAY images |
| title | Topology optimization search of deep convolution neural networks for CT and X-ray image classification |
| title_full | Topology optimization search of deep convolution neural networks for CT and X-ray image classification |
| title_fullStr | Topology optimization search of deep convolution neural networks for CT and X-ray image classification |
| title_full_unstemmed | Topology optimization search of deep convolution neural networks for CT and X-ray image classification |
| title_short | Topology optimization search of deep convolution neural networks for CT and X-ray image classification |
| title_sort | topology optimization search of deep convolution neural networks for ct and x ray image classification |
| topic | DCNN Optimization Topologies Pruning CT images XRAY images |
| url | https://doi.org/10.1186/s12880-022-00847-w |
| work_keys_str_mv | AT hassenlouati topologyoptimizationsearchofdeepconvolutionneuralnetworksforctandxrayimageclassification AT alilouati topologyoptimizationsearchofdeepconvolutionneuralnetworksforctandxrayimageclassification AT slimbechikh topologyoptimizationsearchofdeepconvolutionneuralnetworksforctandxrayimageclassification AT fatmamasmoudi topologyoptimizationsearchofdeepconvolutionneuralnetworksforctandxrayimageclassification AT abdulazizaldaej topologyoptimizationsearchofdeepconvolutionneuralnetworksforctandxrayimageclassification AT elhamkariri topologyoptimizationsearchofdeepconvolutionneuralnetworksforctandxrayimageclassification |