Deep Learning Detects Kidney Stones in Ultrasound Images

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 10 Issue: 03 | Mar 2023 www.irjet.net p-ISSN: 2395-0072
© 2023, IRJET | Impact Factor value: 8.226 | ISO 9001:2008 Certified Journal | Page 494
DETECTION OF KIDNEY STONE USING DEEP LEARNING TECHNIQUES
Preethi Nisha N [1], Mrs. Sasikala G.M.E. (Ph.D) [2]
Student [1], Dept of Computer science and engineering, Vivekananda college of Engineering for Women, Namakkal,
Tamil Nadu, India.
Professor [2], Dept of Computer science and engineering, Vivekananda college of Engineering for Women,
Namakkal, Tamil Nadu, India.
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - One of the most serious and potentially fatal
diseases that still exists today is kidney stone disease. A
kidney stone, which is also called a renal calculus, is a
solid piece of material that forms in the kidneys from the
minerals in the urine. A small stone may pass without
causing symptoms, and kidney stones typically leave the
body in the urine. The early stages of the stone diseases
go unnoticed, causing damage to the kidney as they
progress. Using CT images, a comprehensive examination
of image processing techniquesforkidney stonedetection
was conducted. Patients' information was gathered from
the hospital using a CT scannertodiagnosekidney stones.
Image preprocessing with a median filter, segmentation
with deep learning algorithms, and kidney stone
detection were examinedin stages.Kidney stonesarenow
a major issue, and if they are not caught early, they can
lead to complications and sometimes necessitatesurgery
to remove the stones. Therefore, the precise stone
detection paves the way for image processing because
image processing tends to produce precise results and is
an automatic stone detection method. Due to their low
contrast and speckle noise, ultrasound imaging makes it
extremely difficult to identify kidney stones. Utilizing
appropriate image processingstrategiesisthesolutionto
this problem. Using the image restoration procedure, the
ultrasound image is first pre-processed to eliminate
speckle noise. One of the filtering methods is used to
smooth out the restored image. Image segmentation is
used to locate the stone region in thepreprocessedimage.
The segmented image is then processed using CNN
classification and wavelet transformation.
Key Words: image restoration, Image segmentation and
median filter.
I.INTRODUCTION
Kidney stones are the subject of one of the most significant
studies ever conducted. Calcium is the mineral that most
frequently results in kidney stones. Kidney stones are
thought to affect many people. The majority of kidney stone
sufferers are unaware of their condition. Except for extreme
abdominal pain and changes in the color of their urine, the
patients are unaware of the problem duetointernal damage.
It is essential to monitor the issue and carry out tests to
prevent further harm to the body in order to receive the
appropriate medical treatment. Kidney stone disease is still
one of the most serious and potentially fatal diseases.Asolid
piece of material that forms in the kidneysfromtheminerals
in the urine is known as a kidney stone or renal calculus.
Small stones can pass through the body without causing
symptoms, and kidney stones typically leave the body in the
form of urine. The kidney is damaged as the disease
progresses, and the early stages of the disease go unnoticed.
The majority of people experience kidney failure as a result
of a number of conditions, including hypertension,
glomerulonephritis, and diabetes mellitus. Because it canbe
dangerous, early diagnosis of kidney dysfunction is advised.
Ultrasound (US) is one of the non-invasive, low-cost, and
widely used imaging methods currently available for
examiningkidneydiseases. Digital imageprocessinginvolves
using a digital computer to process digital images. We could
also say that it is the use of computer algorithms to get a
better image or to get some useful information out of it. The
manipulation of digital images by means of a digital
computer is the subject of digital image processing. It's a
subfield of signals and systems that focuses on images in
particular. The development of a computer system that can
process images is the primary focus of DIP. A digital image is
the system's input, which it processes using effective
algorithms to produce an image as an output.
II. PROBLEM STATEMENT
Utilizing appropriate image processing methods is the
solution to this problem. To get rid of speckle noise, the
ultrasound image is first pre-processed using image
restoration. One of the filtering methods is used to smooth
out the restored image. Image segmentationisusedtolocate
the stone area in the image that has been pre-processed.The
image is processed using CNN classification and wavelet
transformation following segmentation. The primary
objective of deduplication is to provide security on social
media websites by preventing multiple copies of the same
data so that any issues can be resolved by removingthecopy
of the data. The kidney breaking down can a daily existence
scare. Consequently, early discovery of kidney stone is
fundamental and this should be possible by picture handling
methods. One of the strategies to recognize stones is by
taking ultrasound pictures as an information.The IDofstone

in kidney utilizing ultrasound pictures contain dot clamor
also, are of low difference. Thus, we utilize a channel to
smoothen the picture and CNN calculation is applied for the
exact consequences of kidney stone recognizable proof
III. EXISTING SYSTEM
The fact that level set techniques require a great deal of
thought to construct theappropriatevelocitiesforadvancing
the level set function is one of the disadvantages we
encountered as a result of our use of level set segmentation.
Therefore, there must be a lot of data available to obtain the
accuracy rate, which may not alwaysbethecase.Thecurrent
kidney stone detection system includes level set
segmentation and a smoothing Gabor filter. The fact that
level set techniques require a lot of thought to construct
appropriate velocities is one of the disadvantages we
encountered as a result of using level setsegmentation.After
that, CNN classification and wavelettransformationare used
to process the data. Priortoreappropriation,theinformation
has been scrambled using the merged encryption method.
This framework officially addresses the problem of
authorized information de-duplication to increase the
likelihood of data security. In addition,copycheck document
name characteristic the information itself takes into
consideration distinct filenames based on the distinct
benefits of clients. It also shows some new developments in
de-duplication that support approved copy. Cloud-based
information management features a dynamic and
unpredictable leveled administration chain. In typical
circumstances, this is not the case. Web administrations are
used for solicitation and responses in traditional webdesign
3.1 Disadvantages
 The initial cost can be quite high, depending on the
system used.
 If the system is damaged, the image will vanish. If
the same document name is used again, it mightnot
work.
The Deep Learning Algorithm is utilized to improve the
accuracy and sensitivity of the detection rate, and an image
is used to efficiently identify kidney stone issues.All overthe
world, the problem of kidney stones is becoming more and
more common. The kidneys resemble beans in shape. On
both sides of the spine, they are below the ribs and behind
the belly. Similar in size to the largest fist is the kidney. We
used the clever edge detection method becauseitrevealsthe
presence of a Gaussian filter, which removes noise from an
image. This can be improved in terms of the noise ratio by
using a non-maxima suppression technique that results in
output ridges that are one pixel wide.
4.1 Advantages of Proposed System
 Eliminate noises.
 Accurate contrast and density in the image.
 Facilitates computer storage and retrieval.
 The image can be made available in any desired
format, including negative and black-and-white
versions.
V. RELATED WORK
5.1 Pre-processing of Images
Pre-processing is required because the ultrasound has low
contrast and speckle noise. Image restoration, smoothing
and sharpening, and increasing contrast are all part of pre-
processing. Operations with images at the lowest level of
abstraction, where both the input and the output are
intensity images, are referred to as pre-processing. An
intensity image is typically represented by a matrix ofimage
function values (brightness), and these iconic images are of
the same kind as the original data that was captured by the
sensor. Pre-processing aims to improve the image data by
suppressing unintentional distortions or enhancing some
important image featuresfor subsequentprocessing,despite
image geometric transformations. Pre-handling is required
on the grounds that the ultrasound has low difference and
spot clamor. Picture reclamation,smoothingandhoning, and
expanding contrast are all essential for pre-handling.
Activities with pictures at the least degree of reflection,
where both the info and the result are power pictures, are
alluded to as pre-handling. A force picture is ordinarily
addressed by a lattice of picturecapabilityvalues(splendor),
and these notorious pictures are of the very kind as the first
information that was caught by the sensor. Albeit
mathematical changes of pictures, like revolution, scaling,
and interpretation, are delegated pre-handling strategies
here because of the utilization of comparative techniques,
the objective of pre-handling is an improvement of the
picture information that smothers reluctant mutilations or
upgrades some picture highlights significant for additional
handling. This utilizations Gaussian separating, which is a
technique for improving or changing a picture. You can, for
example, channel a picture to either stress a few highlights
or eliminate others.Smoothing,honing,andimprovingedges
are only a couple of the picture handling tasks that can
performed with channel. The worth of some random pixel in
the result not set in stone by applying a calculation to the
upsides of the pixels nearby the comparing input pixel.
Separating is a local activity.
IV. PROPOSED SYSTEM

5.2 IMAGE SEGMENTATION
Segmentation is an important part of medical imaging. It
makes it easier to diagnose diseases and see medical data.
The kidney stone and one level set segmentation technique
known as "canny edge detection" are used to identify and
sharpen the kidney's edge. Image segmentation is the
process of dividing a digital image into multiple segments
(sets of pixels, also known as image objects). In medical
imaging, segmentation is an essential component. It
facilitates disease diagnostics and visualization of medical
data. One level set segmentation technique called "canny
edge detection" is used to identify and sharpen the kidney's
edge as well as the kidney stone. The process of dividing a
digital image into multiple segments (sets of pixels, also
known as image objects) is called image segmentation.
Segmentation aims to simplify or transform an image's
representation into somethingmoremeaningful andsimpler
to analyse. Typically, image segmentation is used to locate
boundaries (lines, curves, etc.) and objects.inpictures.To be
more specific, image segmentation is the process of giving
each pixel in an image a label so that pixels with the same
label have the same characteristics. A collection of segments
that collectively cover the entire image, or a collection of
contours extracted from the image, is the outcome of image
segmentation (see edge detection). In terms of a
characteristic or computed property, such as colour,
intensity, or texture, each of the pixelsina regionisidentical.
5.3 Wavelet Processing
When the frequency of a signal changes over time, wavelet
transforms are a mathematical method for analyzing it.
Wavelet analysis outperforms other signal analysis methods
in providing more precise information about signal data for
particular classes of images and signals. Due to their high
contrast of neighboring pixel intensity values, wavelets are
frequently utilized in image processing for the purpose of
detecting and filtering white Gaussian noise. The two-
dimensional image undergoes a wavelet transformation
thanks to these wavelets. In order to obtain a compressed
image, this project applies the wavelet transform to the
segmented input image. Theimagecanbe"cleanedup"inthis
way without muddle or blurring the details.
VI. SYSTEM ARCHITECTURE
VII CONVOLUTIONAL NEURAL NETWORK
Convolutional neural network is produced by performing
convolution on artificial neural networks (ANNs). A CNN is
made up of neuronal weights and biases that can be learned.
The architecture of convolutional neural networks is made
up of three main layers: the convolutional layer, the pooling
layer, and the fully connected layer. Because it has one or
more convolutional layers, a convolutional neural network
(CNN) gets its name from them. Convolutional layers are
used to identify certain local features in the input images.
Every single node in a convolutional layer is connected to a
subset of spatially connected neurons. This aids in the
detection of local forms (structures) in the input image's
channels. In order to look for a similar local trait in the input
channels, the convolutional layer's nodes share the weights
on the connections. A kernel (convolution kernel) is the
name given to each shared weight set. Convolutional layer
kernels learn the local features to be detected across the
input images, whose strength can beseeninthefeature map.
In CNN, the pooling layer is the layer that comes after the
convolution layer and whose primary goal is to reduce the
size of the representation. Deep learning neural networks
fall under the convolutional neural network (CNN)category.
CNNs are a significant advance in image recognition. They
are frequently employed in the background of image
classification and are most frequently used to analyze visual
imagery. They are at the heart of everything, from self-
driving cars to Facebook's photo tagging system. They are
putting in a lot of effort behind the scenes to improve
security and healthcare. The process of assigning a class to
an input (such as a picture) or a probability that the input
belongs to a particular class (such as "there's a 90%
probability that this input is a picture") is known as image
classification. CNNs can be thought of as automatic image
feature extractors. It effectively down-samples the image by
making use of information from adjacentpixels.Convolution
units can be found in one or more layers on a CNN. A
proximity is created when multiple units fromthepreceding
layer provide input to a convolution unit. As a result, the
weights of the input units, which make up a small
neighborhood, are shared.
VIII CONCLUSION
The survey of various algorithms and classifications is
examined in this project, followed by the detection of kidney
stones. As a result of this implementation, the limitations of
the current system are deduced, and a new design is
suggested to overcome them. For instance, level set
techniques necessitate a lot of thought in order to construct
velocities in order to produce an ideal advanced level set
function. This implies that a lot of data should be available to
determine the accuracy rate, which may not always be the
case.

REFERENCES
[1] Viswanath, R.Gunasundari, “Design and Analysis
Performance of Kidney Stone Detection from Ultrasound
Image by Level Set Segmentation and ANN
Classification.”,2014.
[2] Koushalkumar, Abhishek “Artificial Neural Networks for
Diagnosis of Kidney Stones Disease”,2012.
[3 ] K. Divya Krishna, V. Akkala, R. Bharath, P. Rajalakshmi,
A.M. Mohammed, S.N. Merchant,U.B. Desai “Computer Aided
Abnormality Detection for Kidney on FPGA Based IoT
Enabled Portable Ultrasound Imaging System”,2016.
[4] Nur Farhana Rosli,Musab Sahrim1,Wan Zakian Wan
Ismail1,Irneza Ismail,JulizaJamaludin,Sharma Rao
Balakrishnan, ”Automated Feature Description of Renal Size
Using Image processing”,2018.
[5] Bomana raja “ Analysis of Ultrasound kidney Image using
content description multiple features for disorder
identification”,2007.

Deep Learning Detects Kidney Stones in Ultrasound Images

Recommended

Recommended

More Related Content

Similar to Deep Learning Detects Kidney Stones in Ultrasound Images

Similar to Deep Learning Detects Kidney Stones in Ultrasound Images (20)

More from IRJET Journal

More from IRJET Journal (20)

Recently uploaded

Recently uploaded (20)

Deep Learning Detects Kidney Stones in Ultrasound Images