xai_framework / app.py
hodorfi's picture
Update app.py
3b1a029
raw
history blame
3.82 kB
""" Resources:
1- https://streamlit-emoji-shortcodes-streamlit-app-gwckff.streamlit.app/
2- https://github.com/giswqs/streamlit-geospatial
"""
import streamlit as st
USER_GROUPS = ["Developer", "Manager", "Practitioner"]
st.set_page_config(layout="wide")
if 'user_group' not in st.session_state:
index_tmp = 0
else:
index_tmp = USER_GROUPS.index(st.session_state['user_group'])
#Sidebar for USER GROUPS
st.sidebar.title("USER GROUPS")
backend = st.sidebar.selectbox(
"Select User-Group ", USER_GROUPS, index=index_tmp
)
st.session_state['user_group'] = backend
st.sidebar.title("About")
st.sidebar.info(
"""
Web App URL: <https://google.com>
GitHub repository: <https://github.com/kaplansinan/streamlit-airamework>
"""
)
st.sidebar.title("Contact")
st.sidebar.info(
"""
Sinan Kaplan: <https://www.linkedin.com/in/kaplansinan>
[GitHub](https://github.com/kaplansinan) | [LinkedIn](https://www.linkedin.com/in/kaplansinan)
"""
)
# Customize page title
st.title("XAI Framework Application-OCT Image Analysis by Deep Learning")
markdown1 = """
The framework is created to briefly illustrate how to use the poposed framework in our paper. Hence, we demonstrate a case study,which aims to detect certain anomalies from Retinal OCT images.
This system is developed to classifiy certain anamolies from OCT of retina images. Those anamolies are:
1. Choroidal Neovascularization (CNV): neovascular membrane and associated subretinal fluid (Choroidal Neovascularization (CNV) is a retinal disease,which is associated with the growth of
abnormal blood vessels in the choroid layer, which lies between two other layers of tissue that make up the wall of the eye.
These new blood vessels can cause fluid to accumulate beneath and within these layers, leading to vision loss.)
2. Diabetic Macular Edema (DME) : A retinal disease that appears as a result of diabetes in the retina. retinal-thickening-associated intraretinal fluid (arrows).Diabetic Macular Edema (DME) is a common complication of diabetes that affects the retina,
which is responsible for central vision. DME occurs when fluid accumulates in and around the macula, causing retinal thickening and swelling.
This can lead to impaired vision or even blindness if left untreated.)
3. Drusen is a condition accosiated with early AMD Age-Related Macular Degeneration (AMD) in the retina.
4. NORMAL(HEALTHY): A healthy retina,
"""
st.markdown(markdown1)
# st.markdown(
# """
# This system is developed to classifiy certain anamolies from OCT images. Those anamolies are and [leafmap](https://leafmap.org). It is an open-source project and you are very welcome to contribute to the [GitHub repository](https://github.com/giswqs/streamlit-multipage-template).
# """
# )
st.header("Framework Sections")
markdown = """
A different users can beenfit from this framework. The framework is divided into 4 different sections and each of them sheds a light at a different part of this AI application.
1. DATA PANEL:This section presents information regarding thedata in details.
2. MODEL PANEL: This section presents details regarding AI model.
3. PERFORMANCE EVALUATION PANEL: This panel hihglights the performance of the AI model over test set.
4. DECISION EXPLORATION: This section is decisgned to explore global and instance level explanations.
"""
st.markdown(markdown)
st.header("How to Use the Framework")
markdown = """
To effectively use the framwork, please follow steps as instrcuted below:
1. On left sidebar under'USER GROUPS' choose user group
2. Start exploring any panel by clicking on them on the upper left corner. We suggest to follow the order as data-> model-> performance-> decision exploration.
"""
st.markdown(markdown)