Scribd
Upload
4 views2 pages

Ganesh

The project focuses on automatic kidney stone detection using a Deep Convolutional Neural Network (CNN) and MATLAB, emphasizing the importance of early diagnosis and treatment of renal disorders. The methodology includes pre-processing, segmentation using Fuzzy C-Means clustering, feature extraction with Gray-Level Co-occurrence Matrix, and classification via a trained CNN model. The proposed approach demonstrates superior performance in sensitivity, specificity, and overall accuracy compared to traditional detection methods.

Uploaded by

divyasri.kcp
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4 views2 pages

Ganesh

The project focuses on automatic kidney stone detection using a Deep Convolutional Neural Network (CNN) and MATLAB, emphasizing the importance of early diagnosis and treatment of renal disorders. The methodology includes pre-processing, segmentation using Fuzzy C-Means clustering, feature extraction with Gray-Level Co-occurrence Matrix, and classification via a trained CNN model. The proposed approach demonstrates superior performance in sensitivity, specificity, and overall accuracy compared to traditional detection methods.

Uploaded by

divyasri.kcp
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Project Title:Automatic Kidney Stone

Detection Using DIP and Artificial Neural


Network
Course: B.Tech Year: IV Sem: II Section:B

Project ID:24ECEBPB4

Abstract:
Kidney stone detection plays a crucial role in early diagnosis and treatment of renal disorders. In
this study, we propose a comprehensive approach for kidney stone detection utilizing a Deep
Convolutional Neural Network (CNN) in MATLAB. The workflow encompasses pre-processing,
segmentation, feature extraction, and classification stages. Firstly, the input image undergoes pre-
processing using a median filter to reduce noise and enhance clarity. Subsequently, a segmentation
technique based on Fuzzy C-Means (FCM) clustering is employed to delineate the kidney stone
regions accurately. Next, texture features are extracted using Gray-Level Co-occurrence Matrix
(GLCM), providing valuable information regarding the spatial distribution of pixel intensities
within the segmented regions. These features serve as discriminative attributes for distinguishing
between kidney stone and non-stone regions. The core of our methodology lies in the application
of a Deep CNN for classification. The network is trained on a large dataset of ultrasound labeled
images, learning intricate patterns and representations that differentiate between kidney stone and
non-stone regions effectively. The trained CNN model is then utilized to classify unseen
ultrasound images with high accuracy. The deep CNN architecture exhibits superior performance
in terms of sensitivity, specificity, and overall accuracy compared to traditional methods.
Keywords:
Kidney Stone Detection
Deep CNN-Convolution Neural Network
FCM-Fuzzy C-Means Clustering
GLCM-Gray-Level Co-Occurrence Matrix

Academic Year 2023- 2024


Name of the students:

Signature of the
S.No Name of the Student Roll Number
student
1 K.DIVYA SRI 20751A0465
2 K.GANESH 20751A0471
3 K.RAMANJINEYULU 20751A0478
4 K.SRAVANTH 20751A0468

Signature of the Guide Project Coordinator HOD/ECE

Academic Year 2023- 2024

You might also like