Scribd
Upload
16 views9 pages

RETINAL

detection of Retinal

Uploaded by

Rishi
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
16 views9 pages

RETINAL

detection of Retinal

Uploaded by

Rishi
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/ 9

Detection of Retinal pigmentosa

in paediatric age patients using


CNN with Tkinter Framework
The project Detection of retinal pigmentosa in paediatric age
patients involves a combination of deep learning and MySQL in
the process of registering the user who wants to use the
application. The project consists of a Tkinter GUI where the user
can register himself/herself and login to evaluate and test the
model. The model predicts by taking image as an input an
predicts whether a person is affected with retinal pigmentosa
or not, the model which we use to train and test the data is
Convolutional neural network model.

Base Paper
1. https://www.researchgate.net/publication/
342285658_Deep_Learning-
Based_Detection_of_Pigment_Signs_for_Analysis_and_Diag
nosis_of_Retinitis_Pigmentosa
2. https://www.researchgate.net/publication/
327294998_Machine_Learning_and_Deep_Learning_appro
aches_for_Retinal_Disease_Diagnosis

Algorithm Description
Convolutional Neural Network: As we all are aware of the
fact, how deep learning and transfer learning is revolutionizing
the world with its immense capability of handling any kind of
data and learning so efficiently. So, similarly we have applied
the same concept by picking a deep learning model i.e.,
Convolutional neural network which basically work son the
principle of having filters. Each convolutional layer has some
specific filters to identify and extract the features from the
input image and learn it and transfer it to other layers for
further processing. We can have as many filters as possible in
the convolutional layer depending on the data we are dealing
on. Filter are nothing but feature detectors in the input data.
Along with the convolutional layer we also have other layers
which does further pre-processing such as Maxpooling,
Activation function, Batch Normalization and dropout layer.
These all contribute to the CNN model creation and along with
the flatten and output layer. The reason we do flattening is to
feed the output of the CNN model to the dense layer which
gives us the probability of the predicted value.

Installing SQLITE Database


Ok, so as this project is integrated with database login support,
we might need to install SQLite database in our system to make
the code running. Trust me this will not take more than 5 min of
your precious time, hang on.
1. Visit the given link and download the SQLITE standard
installer.
https://sqlitebrowser.org/dl/
2. After the download has ended, click on the .msi file and
follow the all the necessary installation procedures.
3. Click on next and make sure to check the boxes for
making the shortcuts.
4. Click on next and the installation procedures begins.
5. At last, click on finish to complete the setup procedure.

Steps to Execute the Code!


Note: Make sure you have added path while installing the
software’s.

https://techieyantechnologies.com/2022/07/how-to-install-
anaconda/

https://techieyantechnologies.com/2022/06/get-started-with-
creating-new-environment-in-anaconda-configuring-jupyter-
notebook-and-installing-libraries-using-requirements-txt-2/

1. Install the prerequisites/software’s required to execute the


code from reading the above blog which is provided in the
link above.
2. Press windows key and type in anaconda prompt a
terminal opens up.
3. Go to the directory where your requirement.txt file is
present, not just requirement.txt, if you want to execute
any .py or .ipynb files, you need to go to that specific
folder or path, where they are saved.

4. <<directory of your file:>>. E.g., If my file is in d drive,


then
5. Type d:

6. cd d:\License-Plate-Recognition-main #CHANGE PATH AS


PER YOUR PROJECT, THIS IS JUST AN EXAMPLE
7. If your project is in c drive, you can ignore step 4 and go
with step 5.
E.g., cd C:\Users\Hi\License-Plate-Recognition-main
CHANGE PATH AS PER YOUR PROJECT, THIS IS JUST
AN EXAMPLE
8. Run pip install -r requirements.txt or conda install
requirements.txt (Requirements.txt is a text file consisting
of all the necessary libraries required for executing this
python file. If it gives any error while installing libraries,
you might need to install them individually.), example: pip
install “module_name” i.e., pip install pandas

9. Run main.py in your anaconda terminal and make sure to


change the path where your executable files are located in
the anaconda terminal.
(Please refer to the output images to understand how to
login, On the right we have registration box and on the left
we have Login Box)
10. If you would like to run .ipynb file, Please follow the
link to setup and open jupyter notebook, You will be
redirected to the local server there you can select which
ever .ipynb file you’d like to run and click on it and
execute each cell one by one by pressing shift+enter.

Dataset Description
The dataset was downloaded from a private data repository
which might not be available now. The dataset is divided into
train and test sets, where each folder is again divided into
negative and positive folders, where thee training_negative
consists of 386 images and training_positive consists of 134
images, similarly test_negative consists of 96 images and
test_positive consists of 34 images. Shape of all the images is
equally scaled about 3072 x 2048.
Negative

Positive
Issues Faced
1. We might face an issue while installing specific libraries, in
this case, you might need to install the libraires manually.
Example: pip install “module_name/library” i.e., pip install
pandas
2. Make sure you have the latest or specific version of python,
since sometimes it might cause version mismatch.
3. Adding path to environment variables in order to run python
files and anaconda environment in code editor, specifically in
any code editor.
4. Make sure to change the paths in the code accordingly
where your dataset/model is saved.

Refer to the Below links to get more details on installing


python and anaconda and how to configure it.

https://techieyantechnologies.com/2022/07/how-to-install-
anaconda/

https://techieyantechnologies.com/2022/06/get-started-with-
creating-new-environment-in-anaconda-configuring-jupyter-
notebook-and-installing-libraries-using-requirements-txt-2/

Note:
All the required data has been provided over here.
Please feel free to contact me for model weights and if
you face any issues.
https://www.linkedin.com/in/abhinay-lingala-5a3ab7205/

Yes, you now have more knowledge than


yesterday, Keep Going.

Evaluation Metrics
Evaluation metrics are considered as one of the most important
steps in any machine learning and deep learning projects,
where it will allow us to evaluate how good our model is
performing on the new data or on unseen data. There are a lot
of evaluation metrics which can be used in order to assess how
good our model is performing, in our case, since we are dealing
with binary classification and neural network, we are going to
sue binary_cross_entropy/log_loss, which basically compares
the actual class with the predicted probabilities and then it
calculates a corrected probability by subtracting it with the
probability of a datapoint belonging to class1 with the predicted
probability, i.e. for the case of ID8 it is actually class 0, but the
probability is of class 1 is 0.56, so we subtract (1 – 0.56), we
get 0.44 that is our corrected probability. Then Log_loss is
calculated by applying log transformation on each of the
calculated_probablities. The the average of the negative
corrected_probablities are taken which will gives us the
log_loss/binary_cross_entropy, the lower the value the better
our model is performing.

Log_loss calculation for corrected_probablities


Log_Loss formula without calculating
corrected_probablities

Reference:
https://www.analyticsvidhya.com/blog/2021/03/binary-cross-
entropy-log-loss-for-binary-classification/

Results

You might also like