Deep Learning Approaches Targeting Radiological Images

Artificial Intelligence (AI) algorithms have remarkably improved their performance in the recent years in various domains, thanks to the introduction of deep learning approaches. Indeed they have shown a tremendous potential when solving tasks involving image analysisThe problem of deep learning is its requirement for huge datasets, nonetheless, DL approaches have proved to be helpful in the domain of medical imaging as well. Automated segmentation and classification in different biomedical tasks have proven to be faster and more cost effective. In this thesis we study deep learning approaches used for segmentation and classification of different radiological images mainly CT Scans, MRI Scans and CXR images. In particular, we explored some issues like the multi-modality, and the small dataset problem We first discuss about how the small datasets can be exploited to improve the performance of the deep model in the proposed architectures and then in the next work we train the model with multi modal data consisting of both CT and MRI images together and consider the corresponding opposite modality of CT and MRI as missing data problem. We use Cycle-GAN to generate the synthetic data for the missing data and further train the model with original and synthetic data together. Then we focus on the classification of COVID exploiting the multi-modality data available. We proposed an architecture that is capable of handling multi modal data and extract feature representation from available modalities before concatenation and further use them for final classification. Then we exploit joint learning to train a small dataset from scratch. Finally, this thesis concludes with open questions that may benefit from future work. This thesis demonstrate the potential role of CNNs to address the tasks of segmentation and classification.