Deep learning for multisource medical information processing

The application of deep learning algorithms is rapidly expanding, Deep learning algorithms show great potential to revolutionize healthcare towards the development of smart clinical decision support systems. The development of computer-aided diagnostics systems is crucial to support clinicians with second diagnostic opinions, overcoming the subjectivity of manual diagnosis and handcrafted features. While significant progress has been made in multimodal image data fusion, the application of deep learning for processing of healthcare image and acoustic information has not yet been fully explored. It is through multisource information fusion and computational modeling that outcomes of interest such as treatment targets and drug development ultimately facilitate improved patient-level decision making in care facilities and homes. Such a phenomenon has attracted interest in healthcare multisource data fusion studies. The application of machine learning and deep learning algorithms provides insight into various outcomes of healthcare such as drug discovery, clinical trials, phenotyping, and surgical techniques. This is crucial in providing support to practitioners and health centers to provide the most precise and efficient evidence-based medicine possible. Moreover, unimodal deep learning models are often less robust and face misclassification challenges. In this chapter we focus on multisource medical information processing for disease classification and prediction tasks. Specifically, we propose a framework and algorithms for multimodal deep learning models for classifying acoustic and image type multimodal datasets for lung cancer. First, the data fusion techniques are reported. Second, a deep learning-based multimodal data fusion framework is proposed for multisource image and acoustic data processing. Further, the existing challenges in multisource information processing systems based on deep learning are identified and a prospective opinion is given. This will pave the way for future research.