Scribd
Upload
3 views8 pages

PCOS Presentation

The document discusses the use of deep learning to detect Polycystic Ovary Syndrome (PCOS) from ultrasound images, highlighting its prevalence among reproductive-aged women and its impact on fertility. A dataset was created with labeled images of healthy and cystic ovaries, and a Keras-based MobileNetModel was developed, achieving 100% accuracy in classifying the images. The study emphasizes the effectiveness of deep learning techniques in diagnosing PCOS through image analysis.

Uploaded by

dhruviejoshi
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
3 views8 pages

PCOS Presentation

The document discusses the use of deep learning to detect Polycystic Ovary Syndrome (PCOS) from ultrasound images, highlighting its prevalence among reproductive-aged women and its impact on fertility. A dataset was created with labeled images of healthy and cystic ovaries, and a Keras-based MobileNetModel was developed, achieving 100% accuracy in classifying the images. The study emphasizes the effectiveness of deep learning techniques in diagnosing PCOS through image analysis.

Uploaded by

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

Polycystic Ovary Syndrome

Detection from Images


using
Deep Learning

By
GANESHKUMAR KARUNANIDHI
Abstract

Polycystic Ovary Syndrome (PCOS) is an


endocrinological dysfunction prevalent among
women of reproductive age. PCOS is a
combination of syndromes caused by an
excess of androgens — a group of sex
hormones — in women, Syndromes including
acne, alopecia, hirsutism, hyperandrogenemia,
oligoovulation, etc. are caused by PCOS

It is also a major cause of female infertility. An


estimated 15% of reproductive-aged women
are affected by PCOS globally.
Dataset Description

Tools
A Datasets included ultrasound pictures of healthy and Technologies used
ovaries as well as cystic ovaries .The ultrasound
photos that showed infected cysts on the ovary were  Tensorflow
given the label ‘infected’ while the ultrasound  Keras
images that showed a healthy ovary were given the  NumPy
label ‘not infected’.

In the Kaggle ,the Dataset have 2 different folder ,


I have take only train folder and then used for
As a Train data, test data and validation data.
Sample Image

Infected Not Infected


Image Preprocessing

our models with images of uniform


dimensions, we have rescaled all the photos
of both the datasets to 224×224 pixels.

ImagedataGenerator:
Generate batches of
We have used ImageDataGenerator from tensor image data
Keras to normalize our image data. with real-time data
augmentation.
Model Description

We have use a Keras image classification


model, optionally loaded with weights pre-
trained on ImageNet.

After the we have to pass model output as a


Input of the Dence and Flatten layers
Class Indices of train, test
and validation data
Result

we have developed MobileNetModel - a CNN


model to classify polycystic ovarian ultrasound
images
we get the 100 % accuracy, our model really
perform well in a datasets

THANK YOU

You might also like