Scribd
Upload
44 views

Detection of Pneumonia

The document discusses using deep learning techniques to classify chest x-ray images as having pneumonia, tuberculosis, or COVID-19. It proposes using preprocessing like discrete wavelet transform and gray-level co-occurrence matrix to extract features from the images, which would then be used to train a neural network classifier. This approach aims to automatically and accurately diagnose these diseases from medical images while overcoming limitations of prior methods like high development costs or only detecting single diseases.

Uploaded by

TARUN KUMAR
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
44 views

Detection of Pneumonia

The document discusses using deep learning techniques to classify chest x-ray images as having pneumonia, tuberculosis, or COVID-19. It proposes using preprocessing like discrete wavelet transform and gray-level co-occurrence matrix to extract features from the images, which would then be used to train a neural network classifier. This approach aims to automatically and accurately diagnose these diseases from medical images while overcoming limitations of prior methods like high development costs or only detecting single diseases.

Uploaded by

TARUN KUMAR
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 8

detection of pneumonia, Tuberculosis, Covid 19.

disease diagnosis in x-ray image using deep learning.

ABSTRACT:
Chest radiography has become the modality of choice for diagnosing
pneumonia, Tuberculosis,Covid-19. However, analyzing chest X-ray
images may be tedious, time-consuming and requiring expert knowledge
that might not be available in less-developed regions. therefore,
computer-aided diagnosis systems are needed. Recently, many
classification systems based on deep learning have been proposed.
Despite their success, the high development cost for deep networks is still
a hurdle for deployment. Deep Learning has the merit of reducing the
development cost by borrowing architectures from trained models
followed by slight fine-tuning of some layers. Nevertheless, whether deep
learning is effective over training from scratch in the medical setting
remains a research question for many applications. In this work, we
investigate the use of deep learning to classify
pneumonia,Tuberculosis,Covid-19 among chest X-ray images.
Experimental results demonstrated that, with slight fine-tuning, deep
learning brings performance advantage over training from scratch.

Introduction:
COVID-19, Pneumonia and Tuberculosis are a respiratory tract infection
caused by the viruses of influenza, Mycobacterium tuberculosis, corona.
and less commonly by other micro -organisms such as fungi . The
damages caused by the infection and the host’s immune response results
in lung injury and disruption of pulmonary functions. more than one
million adults are hospitalized with pneumonia and Tuberculosis around
50,000 die from the disease every year in the US alone. covid 19 is
currently affect more peoples in all over world . those disease are higher
burden in low-income countries where it is the leading cause of death
where there is limited access to diagnostic and therapeutic facilities.
LITERATURE SURVEY:

EXISTING SYSTEM:
• Construct concentric multilevel partition
• Incorporate intensity, texture, and gradient information
• Image patch feature description
• It classify any one disease only

DRAWBACKS:
• Difficult to get accurate results
• Not applicable for multiple lung disease identification.
• Medical Resonance images contain a noise caused by operator
performance which can lead to serious inaccuracies classification
Proposed system:
• preprocessing
• discrete wavelet transform
• grayscale co-occurrence matrix
• neural network classifier

ADVANTAGE:
• It can segment the infected regions from the image accurately.
• It is useful to classify the pneumonia, Tuberculosis, Covid-19 all three
disease from chest X-ray image.

BLOCK DIAGRAM:

Input Test Preprocessing Features


Image Extraction

Data Base Features Trained all NN Classifier


Images Extraction features

Classified
Disease
PREPROCESSING:
Image Pre-processing is a common name for operations with images at the
lowest level of abstraction. Its input and output are intensity images. The aim of pre-
processing is an improvement of the image data that suppresses unwanted distortions
or enhances some image features important for further processing.
Image restoration is the operation of taking a corrupted/noisy image and
estimating the clean original image. Corruption may come in many forms such as
motion blur, noise, and camera misfocus.  Image restoration is different from image
enhancement in that the latter is designed to emphasize features of the image that
make the image more pleasing to the observer, but not necessarily to produce realistic
data from a scientific point of view. Image enhancement techniques (like contrast
stretching or de-blurring by a nearest neighbor procedure) provided by "Imaging
packages" use no a priori model of the process that created the image.  With image
enhancement noise can be effectively be removed by sacrificing some resolution, but
this is not acceptable in many applications. In a Fluorescence Microscope resolution
in the z-direction is bad as it is. More advanced image processing techniques must be
applied to recover the object.  De-Convolution is an example of image restoration
method. It is capable of: Increasing resolution, especially in the axial direction
removing noise increasing contrast.
Discrete Wavelet Transform (DWT)
The discrete wavelet remodel (DWT) became superior to use the wavelet rework to
the digital international. Filter banks are used to approximate the behavior of the non-
prevent wavelet remodel. The sign is decomposed with a immoderate-skip smooth out
and a low-bypass clear out. The coefficients of these filters are computed using
mathematical evaluation and made to be had to you. See Appendix B for more records
about those computations.

2.2 Discrete Wavelet Transform

Where,

LP d: Low Pass Decomposition Filter


HP d: High Pass Decomposition Filter
LP r: Low Pass Reconstruction Filter
HP r: High Pass Reconstruction Filter 
The wavelet literature offers the filter coefficients to you in tables. An example
is the Daubechies filters for wavelets. These filters rely upon a parameter p called the
vanishing 2nd.
Wavelets Image Processing
         Wavelets have located a massive type of programs within the photo
processing discipline. The JPEG 2000 famous uses wavelets for photo compression.
Other photo processing programs which incorporates noise reduction, issue detection,
and finger print evaluation have additionally been investigated inside the literature.
 Wavelet Decomposition of Images
          In wavelet decomposing of an photo, the decomposition is achieved row
thru row after which column through column. For example, proper here is the
technique for an N x M photograph. You filter out every row after which down-
sample to acquire  N x (M/2) pictures. Then clear out each column and subsample the
filter output to attain four (N/2) x (M/2) pictures of the four sub snap shots obtained as
visible in Figure 12, the most effective acquired through the use of low-pass filtering
the rows and columns is referred to as the LL image.

Gray-Level Co-Occurrence Matrix:

To create a GLCM, use the graycomatrix function. The graycomatrix function


creates a gray-level co-occurrence matrix (GLCM) by calculating how often a pixel
with the intensity (gray-level) value i occurs in a specific spatial relationship to a pixel
with the value j. By default, the spatial relationship is defined as the pixel of interest
and the pixel to its immediate right (horizontally adjacent), but you can specify other
spatial relationships between the two pixels. Each element (i,j) in the resultant GLCM
is simply the sum of the number of times that the pixel with value i occurred in the
specified spatial relationship to a pixel with value j in the input image. Because the
processing required to calculate a GLCM for the full dynamic range of an image is
prohibitive, graycomatrix scales the input image. By default, graycomatrix uses
scaling to reduce the number of intensity values in gray scale image from 256 to eight.
The number of gray levels determines the size of the GLCM. To control the number of
gray levels in the GLCM and the scaling of intensity values, using the Num
Levels and the Gray Limits parameters of the graycomatrix function. 

The gray-level co-occurrence matrix can reveal certain properties about the
spatial distribution of the gray levels in the texture image. For example, if most of the
entries in the GLCM are concentrated along the diagonal, the texture is coarse with
respect to the specified offset. To illustrate, the following figure shows
how graycomatrix calculates the first three values in a GLCM. In the output GLCM,
element (1,1) contains the value 1 because there is only one instance in the input
image where two horizontally adjacent pixels have the values 1 and 1, respectively.

 GLCM(1,2)contains the value 2 because there are two instances where two


horizontally adjacent pixels have the values 1 and 2. Element (1,3) in the GLCM has
the value 0 because there are no instances of two horizontally adjacent pixels with the
values 1 and 3. graycomatrix continues processing the input image, scanning the
image for other pixel pairs (i,j) and recording the sums in the corresponding elements
of the GLCM.
                    To create multiple GLCMs, specify an array of offsets to
the graycomatrix function. These offsets define pixel relationships of varying
direction and distance. For example, you can define an array of offsets that specify
four directions (horizontal, vertical, and two diagonals) and four distances. In this
case, the input image is represented by 16 GLCMs. When you calculate statistics from
these GLCMs, you can take the average.
REFERENCE:
• 1. M. M. Hasan, M. Md. Jahangir Kabir, M. R. Haque and M. Ahmed, "A Combined
Approach Using Image Processing and Deep Learning to Detect Pneumonia from
Chest X-Ray Image," 2019 3rd International Conference on Electrical, Computer &
Telecommunication Engineering (ICECTE), 2019, pp. 89-92, doi:
10.1109/ICECTE48615.2019.9303543.
• 2. V. Kaul, S. Enslin, S.A. Gross, “The history of a O. Gozes and H. Greenspan,
"Deep Feature Learning from a Hospital-Scale Chest X-ray Dataset with Application
to TB Detection on a Small-Scale Dataset," 2019 41st Annual International
Conference of the IEEE Engineering in Medicine and Biology Society (EMBC),
2019, pp. 4076-4079, doi: 10.1109/EMBC.2019.8856729.
• 3. D. Haritha, N. Swaroop and M. Mounika, "Prediction of COVID-19 Cases Using
CNN with X-rays," 2020 5th International Conference on Computing,
Communication and Security (ICCCS), 2020, pp. 1-6, doi:
10.1109/ICCCS49678.2020.9276753.
• 4. AM. Foysal and A. B. M. Aowlad Hossain, "COVID-19 Detection from Chest CT
Images using Ensemble Deep Convolutional Neural Network," 2021 2nd International
Conference for Emerging Technology (INCET), 2021, pp. 1-6, doi:
10.1109/INCET51464.2021.9456387.
• 5. D. -P. Fan et al., "Inf-Net: Automatic COVID-19 Lung Infection Segmentation
From CT Images," in IEEE Transactions on Medical Imaging, vol. 39, no. 8, pp.
2626-2637, Aug. 2020, doi: 10.1109/TMI.2020.2996645.

You might also like