Embedded Files
Worldwide 1.7 billion people suffer from various musculoskeletal conditions and it leads to severe disability and long-term pain. Due to the lack of limited qualified radiologists in various parts of the world, there is a need for an automatic framework that can accurately detect abnormalities in the radiograph images. Deep learning (DL) is very popular due to its capability of extracting useful features automatically with less human intervention, and it is used for solving various research problems in a wide range of fields like biomedical, cybersecurity, autonomous vehicles, etc. The convolutional neural network (CNN) based models are especially used in many biomedical applications because CNN is capable of automatic extraction of the location-invariant features from the input images. In this chapter, we look at the effectiveness of various CNN-based pretrained models for detecting abnormalities in radiographic images and compare their performances using standard statistical measures.
We will also analyze the performance of pretrained CNN architectures with respect to radiographic images on different regions of the body and discuss in detail the challenges of the data set. Standard CNN networks such as Xception, Inception v3, VGG-19, DenseNet, and MobileNet models are trained on radiograph images taken from the musculoskeletal radiographs (MURA) data set, which is given as an open challenge by Stanford machine learning (ML) group. It is the large data set of MURA that contains 40,561 images from 14,863 studies (9045 normal and 5818 abnormal studied) which represents various parts of the body such as the elbow, finger, forearm, hand, humerus, shoulder, and wrist. In this chapter, finger, wrist, and shoulder radiographs are considered for binary classification (normal, abnormal) due to the fact that data from these categories are less biased (less data imbalance) when compared to other categories. There are in total 23,241 and 1683 images given as train and valid set in this data set for the three categories considered in the present work. In the experimental analysis, the performance of the models are measured using statistical measures such as accuracy, precision, recall and F1-score.
Literature survey shows that convolutional neural network (CNN)-based pretrained models have been largely used for CoronaVirus Disease 2019 (COVID-19) classification using chest X-ray (CXR) and computed tomography (CT) datasets. However, most of the methods have used a smaller number of data samples for both CT and CXR datasets for training, validation, and testing. As a result, the model might have shown good performance during testing, but this type of model will not be more effective on unseen COVID-19 data samples. Generalization is an important term to be considered while designing a classifier that can perform well on completely unseen datasets. Here, this work proposes a large-scale learning with stacked ensemble meta-classifier and deep learning-based feature fusion approach for COVID-19 classification. The features from the penultimate layer (global average pooling) of EfficientNet-based pretrained models were extracted and the dimensionality of the extracted features reduced using kernel principal component analysis (PCA). Next, a feature fusion approach was employed to merge the features of various extracted features. Finally, a stacked ensemble meta-classifier-based approach was used for classification. It is a two-stage approach. In the first stage, random forest and support vector machine (SVM) were applied for prediction, then aggregated and fed into the second stage. The second stage includes logistic regression classifier that classifies the data sample of CT and CXR into either COVID-19 or Non-COVID-19. The proposed model was tested using large CT and CXR datasets, which are publicly available. The performance of the proposed model was compared with various existing CNN-based pretrained models. The proposed model outperformed the existing methods and can be used as a tool for point-of-care diagnosis by healthcare professionals.
Tuberculosis (TB) is an infectious disease that remained as a major health threat in the world. The computer-aided diagnosis (CAD) system for TB is one of the automated methods in early diagnosis and treatment, particularly used in developing countries. Literature survey shows that many methods exist based on machine learning for TB classification using X-ray images. Recently, deep learning approaches have been used instead of machine learning in many applications. This is mainly due to the reason that deep learning can learn optimal features from the raw dataset implicitly and obtains better performances. Due to the lack of X-ray image TB datasets, there are a small number of works on deep learning addressing the image-based classification of TB. In addition, the existing works can only classify X-ray images of a patient as TB or Healthy. This work presents a detailed investigation and analysis of 26 pretrained convolutional neural network (CNN) models using a recently released and large public database of TB X-ray. The proposed models have the capability to classify X-ray of a patient as TB, Healthy, or Sick but non-TB. Various visualization methods are adopted to show the optimal features learnt by the pretrained CNN models. Most of the pretrained CNN models achieved above 99% accuracy and less than 0.005 loss with 15 epochs during the training. All 7 different types of EfficientNet (ENet)-based CNN models performed better in comparison to other models in terms of accuracy, average and macro precision, recall, F1 score. Moreover, the proposed ENet-based CNN models performed better than other existing methods such as VGG16 and ResNet-50 for TB classification tasks. These results demonstrate that ENet-based models can be effectively used as a useful tool for TB classification.
Accurate automatic Identification and localization of spine vertebrae points in CT scan images is crucial in medical diagnosis. This paper presents an automatic feature extraction network, based on transfer learned CNN, in order to handle the availability of limited samples. The 3D vertebrae centroids are identified and localized by an LSTM network, which is trained on CNN features extracted from 242 CT spine sequences. The model is further trained to estimate age and gender from LSTM features. Thus, we present a framework that serves as a multi-task data driven model for identifying and localizing spine vertebrae points, age estimation and gender classification. The proposed approach is compared with benchmark results obtained by testing 60 scans. The advantage of the multi-task framework is that it does not need any additional information other than the annotations on the spine images indicating the presence of vertebrae points.
The novelty proposed in this article are as follows. • Pretrained CNN-based feature extraction from pediatric pneumonia CXRs.
A cost-sensitive approach to handle disadvantages caused by an imbalance in the pediatric pneumonia CXR Images dataset.
Meta-classifiers for reduced false predictions and to achieve generalization. • Feature fusion for merging CNN-based pretrained models such as CS_Xception, CS_InceptionResNetV2, CS_DenseNet201, and CS_ NASNetMobile.
KPCA was employed for dimensionality reduction of pediatric pneumonia CXR images database features of CS_Xception, CS_ InceptionResNetV2, CS_DenseNet201, and CS_NASNetMobile models.
t-Distributed Stochastic Neighbour Embedding (t-SNE) approach was employed for penultimate layer feature visualization of the proposed model.
State-of-the-art performance among the existing techniques on the same dataset
The major contributions of the proposed work are as follows:
Autoencoder approach is employed for learning optimal features to differentiate between normal data and attacks in a CAN bus.
GMM is employed to cluster the CAN network packet data into normal and attacks.
Detailed investigation and analysis of the proposed method are shown on a CAN IDS dataset.
To develop a robust CAN IDS system and achieve generalization, the performance analysis is shown for two computer network intrusion datasets and a wireless sensor network intrusion dataset.
The existing unsupervised approach i.e. Improved Deep Embedded Clustering (IDEC) [9] is evaluated on a CAN IDS dataset and compared with the proposed approach.
Tuberculosis (TB) is an infectious disease that remained as a major health threat in the world. The computer-aided diagnosis (CAD) system for TB is one of the automated methods in early diagnosis and treatment, particularly used in developing countries. Literature survey shows that many methods exist based on machine learning for TB classification using X-ray images. Recently, deep learning approaches have been used instead of machine learning in many applications. This is mainly due to the reason that deep learning can learn optimal features from the raw dataset implicitly and obtains better performances. Due to the lack of X-ray image TB datasets, there are a small number of works on deep learning addressing the image-based classification of TB. In addition, the existing works can only classify X-ray images of a patient as TB or Healthy. This work presents a detailed investigation and analysis of 26 pretrained convolutional neural network (CNN) models using a recently released and large public database of TB X-ray. The proposed models have the capability to classify X-ray of a patient as TB, Healthy, or Sick but non-TB. Various visualization methods are adopted to show the optimal features learnt by the pretrained CNN models. Most of the pretrained CNN models achieved above 99% accuracy and less than 0.005 loss with 15 epochs during the training. All 7 different types of EfficientNet (ENet)-based CNN models performed better in comparison to other models in terms of accuracy, average and macro precision, recall, F1 score. Moreover, the proposed ENet-based CNN models performed better than other existing methods such as VGG16 and ResNet-50 for TB classification tasks. These results demonstrate that ENet-based models can be effectively used as a useful tool for TB classification.
Page updated
Google Sites
Report abuse