Transfer Learning for Cell Nuclei Classification in Histopathology Images
In histopathological image assessment, there is a high demand to obtain fast and precise quantification automatically. Such automation could be beneficial to find clinical assessment clues to produce correct diagnoses, to reduce observer variability, and
- PDF / 365,773 Bytes
- 8 Pages / 439.37 x 666.142 pts Page_size
- 94 Downloads / 196 Views
Abstract. In histopathological image assessment, there is a high demand to obtain fast and precise quantification automatically. Such automation could be beneficial to find clinical assessment clues to produce correct diagnoses, to reduce observer variability, and to increase objectivity. Due to its success in other areas, deep learning could be the key method to obtain clinical acceptance. However, the major bottleneck is how to train a deep CNN model with a limited amount of training data. There is one important question of critical importance: Could it be possible to use transfer learning and fine-tuning in biomedical image analysis to reduce the effort of manual data labeling and still obtain a full deep representation for the target task? In this study, we address this question quantitatively by comparing the performances of transfer learning and learning from scratch for cell nuclei classification. We evaluate four different CNN architectures trained on natural images and facial images.
1
Introduction
There are two key concepts that makes neural networks powerful in various applications. First, unlike conventional machine learning techniques, deep convolutional neural networks (CNNs) extract features automatically only by using the training data. Second, deep learning methods discover image features at multiple levels (layers) which is called “feature hierarchies”. Features at each layer are computed from the previous layer representations and it was shown that features are learned gradually from low-level to high-level. Multi-level abstraction enables deep learning networks to handle very complex functions and high dimensional data. While deep learning algorithms achieves state-of-the-art results in different machine learning applications, there are several challenges in their application in biomedical domain. First, training deep CNN requires large amount of annotated images to learn millions of parameters. Although large-scale annotated databases are available for generic object recognition task (e.g. ImageNet), it is currently lacking in biomedical domain. Annotating biomedical data requires expertise therefore it is expensive, time consuming, and subject to observer variability. Second, limited amount of training data leads “overfitting” and features can not generalize well on data. Overfitting becomes more serious when the data contain c Springer International Publishing Switzerland 2016 G. Hua and H. J´ egou (Eds.): ECCV 2016 Workshops, Part III, LNCS 9915, pp. 532–539, 2016. DOI: 10.1007/978-3-319-49409-8 46
Transfer Learning for Cell Nuclei Classification in Histopathology Images
533
high variability in the image appearance which is usually the case in biomedical domain. Third, training deep CNNs from scratch requires high computational power, extensive memory resources, and time. Such approaches have practical limitations in biomedical field. In generic object recognition tasks, “transfer learning” and “fine-tuning” methods are proposed to overcome these challenges [13]. Transfer learning and fine-tuning
Data Loading...
