Deep Learning and Semi-Supervised and Transfer Learning Algorithms for Medical Imaging

AbstractDeep learning has provided numerous breakthroughs in natural imaging tasks. However, its successful application to medical images is severely handicapped with the limited amount of annotated training data. Transfer learning is commonly adopted for the medical imaging tasks. However, a large covariant shift between the source domain of natural images and target domain of medical images results in poor transfer learning. Moreover, scarcity of annotated data for the medical imaging tasks causes further problems for effective transfer learning. To address these problems, we develop an augmented ensemble transfer learning technique that leads to significant performance gain over the conventional transfer learning. Our technique uses an ensemble of deep learning models, where the architecture of each network is modified with extra layers to account for dimensionality change between the images of source and target data domains. Moreover, the model is hierarchically tuned to the target domain with augmented training data. Along with the network ensemble, we also utilize an ensemble of dictionaries that are based on features extracted from the augmented models. The dictionary ensemble provides an additional performance boost to our method. We first establish the effectiveness of our technique with the challenging ChestXray-14 radiography data set. Our experimental results show more than 50% reduction in the error rate with our method as compared to the baseline transfer learning technique. We then apply our technique to a recent COVID-19 data set for binary and multi-class classification tasks. Our technique achieves 99.49% accuracy for the binary classification, and 99.24% for multi-class classification.

Download Full-text

Novel Transfer Learning Approach for Medical Imaging with Limited Labeled Data

Cancers ◽

10.3390/cancers13071590 ◽

2021 ◽

Vol 13 (7) ◽

pp. 1590

Author(s):

Laith Alzubaidi ◽

Muthana Al-Amidie ◽

Ahmed Al-Asadi ◽

Amjad J. Humaidi ◽

Omran Al-Shamma ◽

...

Keyword(s):

Deep Learning ◽

Medical Imaging ◽

Transfer Learning ◽

Medical Image ◽

Medical Images ◽

Image Data ◽

Learning Approach ◽

Learning Models ◽

Annotation Process ◽

Deep Learning Model

Deep learning requires a large amount of data to perform well. However, the field of medical image analysis suffers from a lack of sufficient data for training deep learning models. Moreover, medical images require manual labeling, usually provided by human annotators coming from various backgrounds. More importantly, the annotation process is time-consuming, expensive, and prone to errors. Transfer learning was introduced to reduce the need for the annotation process by transferring the deep learning models with knowledge from a previous task and then by fine-tuning them on a relatively small dataset of the current task. Most of the methods of medical image classification employ transfer learning from pretrained models, e.g., ImageNet, which has been proven to be ineffective. This is due to the mismatch in learned features between the natural image, e.g., ImageNet, and medical images. Additionally, it results in the utilization of deeply elaborated models. In this paper, we propose a novel transfer learning approach to overcome the previous drawbacks by means of training the deep learning model on large unlabeled medical image datasets and by next transferring the knowledge to train the deep learning model on the small amount of labeled medical images. Additionally, we propose a new deep convolutional neural network (DCNN) model that combines recent advancements in the field. We conducted several experiments on two challenging medical imaging scenarios dealing with skin and breast cancer classification tasks. According to the reported results, it has been empirically proven that the proposed approach can significantly improve the performance of both classification scenarios. In terms of skin cancer, the proposed model achieved an F1-score value of 89.09% when trained from scratch and 98.53% with the proposed approach. Secondly, it achieved an accuracy value of 85.29% and 97.51%, respectively, when trained from scratch and using the proposed approach in the case of the breast cancer scenario. Finally, we concluded that our method can possibly be applied to many medical imaging problems in which a substantial amount of unlabeled image data is available and the labeled image data is limited. Moreover, it can be utilized to improve the performance of medical imaging tasks in the same domain. To do so, we used the pretrained skin cancer model to train on feet skin to classify them into two classes—either normal or abnormal (diabetic foot ulcer (DFU)). It achieved an F1-score value of 86.0% when trained from scratch, 96.25% using transfer learning, and 99.25% using double-transfer learning.

Download Full-text

Impact of Deep Learning in Medical Imaging: a Systematic New Proposed Model

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.c1019.1083s219 ◽

2019 ◽

Vol 8 (3S2) ◽

pp. 112-118

Keyword(s):

Deep Learning ◽

Medical Imaging ◽

Learning Algorithms ◽

Brain Lesion ◽

Research Area ◽

Magnetic Resonance Images ◽

Machine Learning Algorithms ◽

Proposed Model ◽

Active Research ◽

Active Research Area

For years’ radiologist and clinician continues to employs various approaches, machine learning algorithms included to detect, diagnose, and prevent diseases using medical imaging. Recent advances in deep learning made medical imaging analysis and processing an active research area, various algorithms for segmentation, detection, and classification have been proposed. In this survey, we describe the trends of deep learning algorithms use in medical imaging, their architecture, hardware, and software used are all discussed. We concluded with the proposed model for brain lesion segmentation and classification using Magnetic Resonance Images (MRI).

Download Full-text

A Broad Transfer Learning Algorithm for Classification of Bearing Faults

Volume 2: Manufacturing Processes; Manufacturing Systems; Nano/Micro/Meso Manufacturing; Quality and Reliability ◽

10.1115/msec2020-8312 ◽

2020 ◽

Author(s):

Guokai Liu ◽

Liang Gao ◽

Weiming Shen ◽

Andrew Kusiak

Keyword(s):

Deep Learning ◽

Transfer Learning ◽

Manufacturing Industry ◽

Domain Adaptation ◽

Learning Algorithm ◽

Learning Algorithms ◽

Training Data ◽

Training Time ◽

Bearing Faults

Abstract Condition monitoring and fault diagnosis are of great interest to the manufacturing industry. Deep learning algorithms have shown promising results in equipment prognostics and health management. However, their success has been hindered by excessive training time. In addition, deep learning algorithms face the domain adaptation dilemma encountered in dynamic application environments. The emerging concept of broad learning addresses the training time and the domain adaptation issue. In this paper, a broad transfer learning algorithm is proposed for the classification of bearing faults. Data of the same frequency is used to construct one- and two-dimensional training data sets to analyze performance of the broad transfer and deep learning algorithms. A broad learning algorithm contains two main layers, an augmented feature layer and a classification layer. The broad learning algorithm with a sparse auto-encoder is employed to extract features. The optimal solution of a redefined cost function with a limited sample size to ten per class in the target domain offers the classifier of broad learning domain adaptation capability. The effectiveness of the proposed algorithm has been demonstrated on a benchmark dataset. Computational experiments have demonstrated superior efficiency and accuracy of the proposed algorithm over the deep learning algorithms tested.

Download Full-text

Study on transfer learning ability for classifying marsh vegetation with multi-sensor images using DeepLabV3+ and HRNet deep learning algorithms

International Journal of Applied Earth Observation and Geoinformation ◽

10.1016/j.jag.2021.102531 ◽

2021 ◽

Vol 103 ◽

pp. 102531

Author(s):

Man Liu ◽

Bolin Fu ◽

Donglin Fan ◽

Pingping Zuo ◽

Shuyu Xie ◽

...

Keyword(s):

Deep Learning ◽

Transfer Learning ◽

Learning Algorithms ◽

Learning Ability ◽

Marsh Vegetation

Download Full-text

Demystification of Deep Learning-Driven Medical Image Processing and Its Impact on Future Biomedical Applications

Deep Neural Networks for Multimodal Imaging and Biomedical Applications - Advances in Bioinformatics and Biomedical Engineering ◽

10.4018/978-1-7998-3591-2.ch010 ◽

2020 ◽

pp. 155-171

Author(s):

R. Udendhran ◽

Balamurugan M.

Keyword(s):

Image Analysis ◽

Deep Learning ◽

Medical Imaging ◽

Medical Image ◽

Biomedical Applications ◽

Medical Image Analysis ◽

Learning Algorithms ◽

New Era ◽

Fast Development ◽

Computational Technology

The recent growth of big data has ushered in a new era of deep learning algorithms in every sphere of technological advance, including medicine, as well as in medical imaging, particularly radiology. However, the recent achievements of deep learning, in particular biomedical applications, have, to some extent, masked decades-long developments in computational technology for medical image analysis. The methods of multi-modality medical imaging have been implemented in clinical as well as research studies. Due to the reason that multi-modal image analysis and deep learning algorithms have seen fast development and provide certain benefits to biomedical applications, this chapter presents the importance of deep learning-driven medical imaging applications, future advancements, and techniques to enhance biomedical applications by employing deep learning.

Download Full-text

Review on anomalous gait behavior detection using machine learning algorithms

Bulletin of Electrical Engineering and Informatics ◽

10.11591/eei.v9i5.2255 ◽

2020 ◽

Vol 9 (5) ◽

pp. 2090-2096

Author(s):

Hana’ Abd Razak ◽

M. Ahmed M. Saleh ◽

Nooritawati Md Tahir

Keyword(s):

Machine Learning ◽

Feature Extraction ◽

Deep Learning ◽

Transfer Learning ◽

Gait Recognition ◽

Learning Algorithms ◽

Anomalous Behavior ◽

Machine Learning Algorithms ◽

Behavior Detection ◽

Detection And Recognition

A review on anomalous behavior in crime by other researchers is discussed in this study that focused specifically on the linkage between anomalous behaviors. Next, comprehensive reviews related to gait recognition in utilizing machine learning algorithms for detection and recognition of anomalous behavior is elaborated too. The review begins with the conventional approach of gait recognition that includes feature extraction and classification using PCA, OLS, ANN, and SVM. Further, the review focused on utilization of deep learning namely CNN for anomalous gait behavior detection and transfer learning using pre-trained CNNs such as AlexNet, VGG, and a few more. To the extent of our knowledge, very few studies investigated and explored crime related anomalous behavior based on their gaits, hence this will be the next study that we will explore.

Download Full-text