Medical imaging is no exception whenwe consider technological advances of deep learning algorithms in computer vision. Considering diverse data, the objective of the book is to advocate "no to feature engineering" since handcrafted features require prior domain knowledge. However, even though we have a rich set of state-of-the-art algorithms, no generic deep learning model can be applied when expert-based decisions are required to be considered (medical imaging, for instance). The book aims to provide a thorough concept of deep learning, its importance in medical imaging and/or healthcare with two different case studies: a) cytology image analysis and b) coronavirus (COVID-19) prediction, screening, and decision-making. Both of them use publicly available datasets in their experiments. Of many deep learning models, custom Convolutional NeuralNetwork (CNN), ResNet, InceptionNet, and DenseNet are considered in our experiments. Our results follow 'with' and 'without' transfer learning (including different optimization solutions), in addition to the use of data augmentation and ensemble networks. The book covers a wide range of readers starting from early career research scholars, professors/scientists to industrialists.
- ISBN13 9780128235041
- Publish Date 1 October 2021
- Publish Status Forthcoming
- Publish Country US
- Publisher Elsevier Science Publishing Co Inc
- Imprint Academic Press Inc
- Format Paperback
- Pages 170
- Language English