Transfer representation learning for medical image analysis

Abstract

There are two major challenges to overcome when developing a classifier to perform automatic disease diagnosis. First, the amount of labeled medical data is typically very limited, and a classifier cannot be effectively trained to attain high disease-detection accuracy. Second, medical domain knowledge is required to identify representative features in data for detecting a target disease. Most computer scientists and statisticians do not have such domain knowledge. In this work, we show that employing transfer learning can remedy both problems. We use Otitis Media (OM) to conduct our case study. Instead of using domain knowledge to extract features from labeled OM images, we construct features based on a dataset entirely OM-irrelevant. More specifically, we first learn a codebook in an unsupervised way from 15 million images collected from ImageNet. The codebook gives us what the encoders consider being the fundamental elements of those 15 million images. We then encode OM images using the codebook and obtain a weighting vector for each OM image. Using the resulting weighting vectors as the feature vectors of the OM images, we employ a traditional supervised learning algorithm to train an OM classifier. The achieved detection accuracy is 88.5% (89.63% in sensitivity and 86.9% in specificity), markedly higher than all previous attempts, which relied on domain experts to help extract features.

Bearing Fault Diagnosis under Variable Rotational Speeds Using Stockwell Transform-Based Vibration Imaging and Transfer Learning

“…In this study, transfer learning is employed to reduce the overhead of the training network. In practice, TL creates a robust fault diagnosis process [38]. Figure 4 illustrates the TL concept.…”

“…One more reason for considering CNN as the deep neural network for this study is that a large-scale CNN has the potential to be the most effective of the deep learning and classical methods. Moreover, using the transferred knowledge obtained from TL, with only a small set of training data, the large-scale CNN can achieve excellent performance in the considered scenarios [33,34,38].…”

Deep learning for cardiac computer-aided diagnosis: benefits, issues & solutions

“…Despite its benefits, deep learning and CNN models face certain complications during training. A large amount of training data is required to avoid the over-fitting problem (73,74). In the medical field, this is a challenging requirement as expert annotation is costly and disease specific datasets are rare (70,75).…”

“…Medical images that are acquired at fixed viewpoints or infrequently experience variations of angles may encounter reduced performance due to added noise created from augmented data. A further step to handling limited training data is by performing transfer learning which applies knowledge learned from a previous task to a new task (74). The availability of big data repositories, though dissimilar, has made transfer learning a suitable choice for pretraining and adapting CNNs for the medical imaging domain (75,81).…”

Medical Image Classification Algorithm Based on Weight Initialization‐Sliding Window Fusion Convolutional Neural Network

“…Kallenberg et al [33] used convolutional SAEs to extract features from unlabeled breast cancer X-ray images. e main difference between convolutional SAEs and convolutional neural networks (CNNs) is the use of SAEs for pretraining [34][35][36][37]. For such tasks, it is often necessary to combine local information about the appearance of the lesion with global context information about the location of the lesion to determine a more precise classification [37,38].…”