Computational Analysis and Deep Learning for Medical Care (eBook)

Principles, Methods, and Applications

Amit Kumar Tyagi (Herausgeber)

eBook Download: EPUB

2021
John Wiley & Sons (Verlag)
978-1-119-78573-6 (ISBN)

Infos

This book discuss how deep learning can help healthcare images or text data in making useful decisions'. For that, the need of reliable deep learning models like Neural networks, Convolutional neural network, Backpropagation, Recurrent neural network is increasing in medical image processing, i.e., in Colorization of Black and white images of X-Ray, automatic machine translation, object classification in photographs / images (CT-SCAN), character or useful generation (ECG), image caption generation, etc. Hence, Reliable Deep Learning methods for perception or producing belter results are highly effective for e-healthcare applications, which is the challenge of today. For that, this book provides some reliable deep leaning or deep neural networks models for healthcare applications via receiving chapters from around the world. In summary, this book will cover introduction, requirement, importance, issues and challenges, etc., faced in available current deep learning models (also include innovative deep learning algorithms/ models for curing disease in Medicare) and provide opportunities for several research communities with including several research gaps in deep learning models (for healthcare applications).

---

The book details deep learning models like ANN, RNN, LSTM, in many industrial sectors such as transportation, healthcare, military, agriculture, with valid and effective results, which will help researchers find solutions to their deep learning research problems. We have entered the era of smart world devices, where robots or machines are being used in most applications to solve real-world problems. These smart machines/devices reduce the burden on doctors, which in turn make their lives easier and the lives of their patients better, thereby increasing patient longevity, which is the ultimate goal of computer vision. Therefore, the goal in writing this book is to attempt to provide complete information on reliable deep learning models required for e-healthcare applications. Ways in which deep learning can enhance healthcare images or text data for making useful decisions are discussed. Also presented are reliable deep learning models, such as neural networks, convolutional neural networks, backpropagation, and recurrent neural networks, which are increasingly being used in medical image processing, including for colorization of black and white X-ray images, automatic machine translation images, object classification in photographs/images (CT scans), character or useful generation (ECG), image caption generation, etc. Hence, reliable deep learning methods for the perception or production of better results are a necessity for highly effective e-healthcare applications. Currently, the most difficult data-related problem that needs to be solved concerns the rapid increase of data occurring each day via billions of smart devices. To address the growing amount of data in healthcare applications, challenges such as not having standard tools, efficient algorithms, and a sufficient number of skilled data scientists need to be overcome. Hence, there is growing interest in investigating deep learning models and their use in e-healthcare applications. Audience Researchers in artificial intelligence, big data, computer science, and electronic engineering, as well as industry engineers in transportation, healthcare, biomedicine, military, agriculture.

Autor

Amit Kumar Tyagi is an assistant professor and senior researcher at Vellore Institute of Technology (VIT), Chennai Campus, India. He received his PhD in 2018 from Pondicherry Central University, India. He has published more than 8 patents in the area of deep learning, Internet of Things, cyber physical systems and computer vision.

Textauszug

1
CNN: A Review of Models, Application of IVD Segmentation

Leena Silvoster M.1* and R. Mathusoothana S. Kumar2

1Department of Computer Science Engg, College of Engg, Attingal, Thiruvananthapuram, Kerala, India

2Department of Information Technology, Noorul Islam University, Tamilnadu, India

Abstract

The widespread publicity of Convolutional Neural Network (CNN) in various domains such as image classification, object recognition, and scene classification has revolutionized the research in machine learning, especially in medical images. Magnetic Resonance Images (MRIs) are suffering from severe noise, weak edges, low contrast, and intensity inhomogeneity. Recent advances in deep learning with fewer connections and parameters made their training easier. This chapter presents an in-depth review of the various deep architectures as well as its application for segmenting the Intervertebral disc (IVD) from the 3D spine image and its evaluation. The first section deals with the study of various traditional architectures of deep CNN such as LeNet, AlexNet, ZFNet, GoogleNet, VGGNet, ResNet, Inception model, ResNeXt, SENet, MobileNet V1/V2, and DenseNet. It also deals with the study of the parameters and components associated with the models in detail. The second section discusses the application of these models to segment IVD from the spine image. Finally, theoretically performance and experimental results of the state-of-art of the literature shows that 2.5D multi-scale FCN performs the best with the Dice Similarity Index (DSC) of 90.64%.

Keywords: CNN, deep learning, intervertebral disc degeneration, MRI segmentation

1.1 Introduction

The concept of Convolutional Neural Network (CNN) was introduced by Fukushima. The principle in CNN is that the visual mechanism of human is hierarchical in structure. CNN has been successfully applied in various image domain such as image classification, object recognition, and scene classification. CNN is defined as a series of convolution layer and pooling layer. In the convolution layer, the image is convolved with a filter, i.e., slide over the image spatially and computing dot products. Pooling layer provides a smaller feature set.

One major cause of low back pain is disc degeneration. Automated detection of lumbar abnormalities from the clinical scan is a burden for radiologist. Researchers focus on the automation task of the segmentation of large set of MRI data due to the huge size of such images. The success of the application of CNN in various field of object detection enables the researchers to apply various models for the detection of Intervertebral Disc (IVD) and, in turn, helps in the diagnosis of diseases.

The details of the structure of the remaining section of the paper are as follows. The next section deals with the study of the various CNN models. Section 1.3, presents applications of CNN for the detection of the IVD. In Section 1.4, comparison with state-of-the-art segmentation approaches for spine T2W images is carried out, and conclusion is in Section 1.5.

1.2 Various CNN Models

1.2.1 LeNet-5

The LeNet architecture was proposed by LeCun et al. [1], and it successfully classified the images in the MNIST dataset. LeNet uses grayscale image of 32×32 pixel as input image. As a pre-processing step the input pixel values are normalized so that white (background) pixel represents a value of 1 and the black (foreground) represents a value of 1.175, which, in turn, speedup the learning task. The LeNet-5 architecture consists of succession of input layer, two sets of convolutional and average pooling layers, followed by a flattening convolutional layer, then two fully connected layers, and finally a softmax classifier.

The first convolutional layer filters the 32×32 input image with six filters. All filter kernels are of size 5×5 (receptive field) with a stride of 1 pixel (this is the distance between the receptive field centers of neighboring neurons in a kernel map) and uses “same” padding. Given the input image of size 28×28, apply six convolutional kernels each of size 5×5 with stride 1 in C1, the feature maps obtained is of size 14×14. Figure 1.1 shows the architecture of LeNet-5, and Table 1.1 shows the various parameter details of LeNet-5. Let Wc is the number of weights in the layer; Bc is the number of biases in the layer; Pc is the number of parameters in the layer; K is the size (width) of kernels in the layer; N is the number of kernels; C is the number of channels in the input image.

(1.1)

(1.2)

In the first convolutional layer, number of learning parameters is (5×5 + 1) × 6 = 156 parameters; where 6 is the number of filters, 5 × 5 is the filter size, and bias is 1, and there are 28×28×156 = 122,304 connections. The number of feature map calculation is as follows:

(1.3)

(1.4)

W = 32; H = 32; Fw = Fh = 5; P = 0, and the number of feature map is 28 × 28.

First pooling layer: W = 28; H = 28; P = 0; S = 2

(1.5)

Figure 1.1 Architecture of LeNet-5.

Table 1.1 Various parameters of the layers of LeNet.

Sl no.

Layer

Feature map

Feature map size

Kernel size

Stride

Activation

Trainable parameters

# Connections

1

Image

1

32 × 32

-

-

-

-

-

2

C1

6

28 × 28

5 × 5

1

tanh

156

122,304

3

S1

6

14 × 14

2 × 2

2

tanh

12

5,880

4

C2

16

10 × 10

5 × 5

1

tanh

1516

151,600

5

S2

16

5 × 5

2 × 2

2

tanh

32

2,000

6

Dense

120

1 × 1

5 × 5

1

tanh

48,120

48,120

7

Dense

-

84

-

-

tanh

10,164

10,164

8

Dense

-

10

-

-

softmax

-

-

60,000 (Total)

(1.6)

The number of feature map is 14×14 and the number of learning parameters is (coefficient + bias) × no. filters = (1+1) × 6 = 12 parameters and the number of connections = 30×14×14 = 5,880.

Layer 3: In this layer, only 10 out of 16 feature maps are connected to six feature maps of the previous layer as shown in Table 1.2. Each unit in C3 is connected to several 5 × 5 receptive fields at identical locations in S2. Total number of trainable parameters = (3×5×5+1)×6+(4×5×5+1)×9+(6×5×5+1) = 1516. Total number of connections = (3×5×5+1)×6×10×10+(4×5×5+1) ×9×10×10 +(6×5×5+1)×10×10 = 151,600. Total number of parameters is 60K.

1.2.2 AlexNet

Alex Krizhevsky et al. [2] presented a new architecture “AlexNet” to train the ImageNet dataset, which consists of 1.2 million high-resolution images, into 1,000 different classes. In the original implementation, layers are divided into two and to train them on separate GPUs (GTX 580 3GB GPUs) takes around 5–6 days. The network contains five convolutional layers, maximum pooling layers and it is followed by three fully connected layers, and finally a 1,000-way softmax classifier. The network uses ReLU activation function, data augmentation, dropout and smart optimizer layers, local response normalization, and overlapping pooling. The AlexNet has 60M parameters. Figure 1.2 shows the architecture of AlexNet and Table 1.3 shows the various parameters of AlexNet.

Table 1.2 Every column indicates which feature map in S2 are combined by the units in a particular feature map of C3...

Produkt-Details

• Erscheint lt. Verlag: 10.8.2021
• Sprache: englisch
• Themenwelt: Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
• Themenwelt: Technik ► Elektrotechnik / Energietechnik
• Schlagworte: Artificial Intelligence • biomedical engineering • Biomedizintechnik • Computer Science • Electrical & Electronics Engineering • Elektrotechnik u. Elektronik • Informatik • Künstliche Intelligenz • Medical Informatics & Biomedical Information Technology • Medizininformatik u. biomedizinische Informationstechnologie • Medizinische Informatik • Systems Engineering & Management • Systemtechnik • Systemtechnik u. -management
• ISBN-10: 1-119-78573-1 / 1119785731
• ISBN-13: 978-1-119-78573-6 / 9781119785736