Glioma MRI Human Brain Tumor Detection

[abhisheks008]

Deep Learning Simplified Repository (Proposing new issue)

:red_circle: Project Title : Glioma MRI Human Brain Tumor Detection
:red_circle: Aim : The aim is to identify the brain tumors from the given images of the dataset using different deep learning methods.
:red_circle: Dataset : https://www.kaggle.com/datasets/kuljeetshan/glioma-mri-human-brain-tumor
:red_circle: Approach : Try to use 3-4 algorithms to implement the models and compare all the algorithms to find out the best fitted algorithm for the model by checking the accuracy scores. Also do not forget to do a exploratory data analysis before creating any model.

---

📍 Follow the Guidelines to Contribute in the Project :

• You need to create a separate folder named as the Project Title.
• Inside that folder, there will be four main components.
  • Images - To store the required images.
  • Dataset - To store the dataset or, information/source about the dataset.
  • Model - To store the machine learning model you've created using the dataset.
  • requirements.txt - This file will contain the required packages/libraries to run the project in other machines.
• Inside the Model folder, the README.md file must be filled up properly, with proper visualizations and conclusions.

---

:red_circle::yellow_circle: Points to Note :

• The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
• "Issue Title" and "PR Title should be the same. Include issue number along with it.
• Follow Contributing Guidelines & Code of Conduct before start Contributing.

---

:white_check_mark: To be Mentioned while taking the issue :

• Full name :
• GitHub Profile Link :
• Email ID :
• Participant ID (if applicable):
• Approach for this Project :
• What is your participant role? (Mention the Open Source program)

---

Happy Contributing 🚀

All the best. Enjoy your open source journey ahead. 😎

[Arihant-Bhandari]

Hi @abhisheks008 I would like to work on this, I will be implementing prebuilt models as well as a custom CNN on this , if the results end up satisfactory, I will start a PR for this.

I hope you can assign this to me. Thank you for you time regardless.

I am a GSSoC 2024 contributor under the discord ID : eternal_insight.

[abhisheks008]

I guess you have already commented in an issue, it's better to go with one issue at a time.

[Arihant-Bhandari]

No issues @abhisheks008 if I can't solve the other and this one remains unclaimed , pls assign this to me at a later date 😅

[akv2011]

Hi @abhisheks008 I would like to work on this issue My steps would be :

1.Exploration of the dataset , image dimensions, and class distributions. 2.Visualizing the sample images and corresponding labels to gain insights.

Comparing Difeerent models and their F1 score for most accurate model . 3.Comparing CNN, VGG, ResNet, and a custom CNN

4.Validatiing the Evaluated models on the validation set using metrics like accuracy, precision, recall, and F1-score. 5.Including visualizations (e.g., training curves, confusion matrices) to better illustration of the model performance.

[abhisheks008]

Looks good to me! Issue assigned to you @akv2011

[akv2011]

Thanks will work on this pronto ...and raise pull for review.

[Harihara04sudhan]

Hi @abhisheks008 , I'm really interested in contributing to this issue! While it's already assigned, I believe I can bring a unique perspective to the table. Here's how I plan to complement the existing work:

1 .Enhanced Data Exploration: I'll dive deep into the dataset, exploring not only its structure and class distributions but also conducting additional analysis to uncover any hidden patterns or anomalies.

2. Advanced Visualizations: Building upon the sample image visualization, I'll create more advanced visualizations, utilizing techniques like t-SNE or PCA to gain deeper insights into the data distribution and relationships between classes.

3. Model Optimization: While the assigned contributor is comparing different models, I can focus on optimizing hyperparameters for the selected models, leveraging techniques like Bayesian optimization or random search to fine-tune performance.

4. Ensemble Learning: As a supplementary approach, I'll explore ensemble learning methods to combine the strengths of multiple models, potentially boosting overall performance and robustness.

5. Interactive Dashboards: To enhance project deliverables, I'll develop interactive dashboards using tools like Plotly or Streamlit, allowing for easy exploration and interpretation of model results by project stakeholders.

[abhisheks008]

Sorry @Harihara04sudhan this issue is already assigned.

[diptarup794]

Hello @abhisheks008 I want to work on this issue .If possible kindly assign it to me

[abhisheks008]

Hello @abhisheks008 I want to work on this issue .If possible kindly assign it to me

Already assigned to someone.

[akv2011]

Hi @abhisheks008 sorry kindly reassign if possible would not be able to work on tis due to unforeseen circumstances.

Sorry again

[diptarup794]

Hi @abhisheks008 . If possible can you assign it to me . I want to work on this issue .

[abhisheks008]

Hi @abhisheks008 sorry kindly reassign if possible would not be able to work on tis due to unforeseen circumstances.

Sorry again

Unassigned @akv2011

[abhisheks008]

Hi @abhisheks008 . If possible can you assign it to me . I want to work on this issue .

Please share your detailed approach for solving this issue @diptarup794

[diptarup794]

@abhisheks008 I plan to use image segmentation on dataset of MRI scans to identify tumours. For that I plan to use U-NET or ResUnet.

[diptarup794]

I have previously worked on medical image segmentation and detection . Please consider assigning it to me @abhisheks008

[abhisheks008]

@abhisheks008 I plan to use image segmentation on dataset of MRI scans to identify tumours. For that I plan to use U-NET or ResUnet.

You need to implement 2-3 deep learning architectures for this project, that's why I am asking for a detailed approach.

[diptarup794]

@abhisheks008 I can work on multiple models . There are many models that can be use : UNET,Res-UNET,SegNET ,X-NET ,Multires-NET ( for sharper edge detection).

[abhisheks008]

@abhisheks008 sorry the above message was wrongly pinned to someone else .

You can edit your reply.

Assigned to you @diptarup794. You can start working on it.