Final project submission - COMP3701 Prostate Segmentation (Project 3)

[rike568]

This pull request contains the complete implementation for the COMP3701 HipMRI Prostate Segmentation project.

Problem

The goal was to segment the prostate gland from 2D HipMRI slices using an Improved 2D U-Net, achieving a minimum Dice score of 0.75 on the test set for the prostate label.

Solution & Key Features

This PR includes the full pipeline to address the problem:

• Model: Implementation of the 2D Improved U-Net [1]
• Training: A complete training script (train.py) that handles data loading, augmentation, training/validation loops, and model saving.
• Inference: A prediction script (predict.py) to run the trained model on new Nifti files and generate segmentation masks.
• Data Handling: Utility scripts for loading, pre-processing (normalization, resizing), and splitting the data on a patient-by-patient basis.
• Documentation: A comprehensive README.md file detailing the project setup, architecture, usage, and results, as required by the project brief.
• Environment: A environment.yml file to ensure full reproducibility of the Conda environment.

Results

The implemented model successfully achieves the project requirement of > 0.75 Dice similarity coefficient on the held-out test set for the prostate label.

This PR represents the final, completed version of the project.

[wangzhaomxy]

<This is an initial inspection, no action is required at this point.>

File Organizing: Well-organized files.

• You have upload two projects. please reserve the improve Unet one and remove the other one.
• Remove the requerement.txt file in the root folder /PatternAnalysis-2025/; otherwise, the merge request will be rejected.

Problem Solving:

• The algorithm solves the problem appropriately.
• Accuracy in testing dataset (Dice): min 0.84, mean 0.93. Meet the requirements.

Model and functions:

• It correctly uses PyTorch to construct the improved UNet 2D models and functions.
• Good data augmentation.
• Properly use the train/validation/test datasets.

Code design: Good.

Code comment and docstring:

• Good code comments
• Good function docstrings
• Good header block

Difficulty: Normal.

Additional Comments:

• Good commits.
• Excellent ReadMe design and comprehensive report content. However, as a report, discussion and conclusion section is expected to properly summarize your project.

[rike568]

<This is an initial inspection, no action is required at this point.>

File Organizing: Well-organized files.

* **You have upload two projects. please reserve the improve Unet one and remove the other one.**

* **Remove the requerement.txt file in the root folder /PatternAnalysis-2025/; otherwise, the merge request will be rejected.**

Problem Solving:

* The algorithm solves the problem appropriately.

* Accuracy in testing dataset (Dice): min 0.84, mean 0.93. Meet the requirements.

Model and functions:

* It correctly uses PyTorch to construct the improved UNet 2D models and functions.

* Good data augmentation.

* Properly use the train/validation/test datasets.

Code design: Good.

Code comment and docstring:

* Good code comments

* Good function docstrings

* Good header block

Difficulty: Normal.

Additional Comments:

* Good commits.

* Excellent ReadMe design and comprehensive report content. **However, as a report, discussion and conclusion section is expected to properly summarize your project.**

Can I still remove the requirements.txt or will I receive 0% since the due date has already passed?

[wangzhaomxy]

<This is an initial inspection, no action is required at this point.>
File Organizing: Well-organized files.

* **You have upload two projects. please reserve the improve Unet one and remove the other one.**

* **Remove the requerement.txt file in the root folder /PatternAnalysis-2025/; otherwise, the merge request will be rejected.**

Problem Solving:

* The algorithm solves the problem appropriately.

* Accuracy in testing dataset (Dice): min 0.84, mean 0.93. Meet the requirements.

Model and functions:

* It correctly uses PyTorch to construct the improved UNet 2D models and functions.

* Good data augmentation.

* Properly use the train/validation/test datasets.

Code design: Good.
Code comment and docstring:

* Good code comments

* Good function docstrings

* Good header block

Difficulty: Normal.
Additional Comments:

* Good commits.

* Excellent ReadMe design and comprehensive report content. **However, as a report, discussion and conclusion section is expected to properly summarize your project.**

Can I still remove the requirements.txt or will I receive 0% since the due date has already passed?

Yes, please do the following two things and you won't lose any marks:

• You have upload two projects. please reserve the improve Unet one and remove the other one.

• Remove the requerement.txt file in the root folder /PatternAnalysis-2025/; otherwise, the merge request will be rejected.
  But you will lose marks if you don't do these two things. :)

[rike568]

<This is an initial inspection, no action is required at this point.>
File Organizing: Well-organized files.

* **You have upload two projects. please reserve the improve Unet one and remove the other one.**

* **Remove the requerement.txt file in the root folder /PatternAnalysis-2025/; otherwise, the merge request will be rejected.**

Problem Solving:

* The algorithm solves the problem appropriately.

* Accuracy in testing dataset (Dice): min 0.84, mean 0.93. Meet the requirements.

Model and functions:

* It correctly uses PyTorch to construct the improved UNet 2D models and functions.

* Good data augmentation.

* Properly use the train/validation/test datasets.

Code design: Good.
Code comment and docstring:

* Good code comments

* Good function docstrings

* Good header block

Difficulty: Normal.
Additional Comments:

* Good commits.

* Excellent ReadMe design and comprehensive report content. **However, as a report, discussion and conclusion section is expected to properly summarize your project.**

Can I still remove the requirements.txt or will I receive 0% since the due date has already passed?

Yes, please do the following two things and you won't lose any marks:

* You have upload two projects. please reserve the improve Unet one and remove the other one.

* Remove the requerement.txt file in the root folder /PatternAnalysis-2025/; otherwise, the merge request will be rejected.
  But you will lose marks if you don't do these two things. :)

Have updated the project by removing the requirements.txt and removing the unnecessary project folder

[wangzhaomxy]

45807321

[gayanku]

Marking

Good/OK/Fair Practice (Design/Commenting, TF/Torch Usage)
	Good design and implementation.
	Spacing and comments.
	Header blocks.
Recognition Problem
	Good solution to problem.
	Driver Script present.
	File structure present.
	Good Usage & Demo & Visualisation & Data usage.
	Module present.
	Commenting present.
	No Data leakage found.
	Difficulty : Normal. Normal. ImprovedUnet2D	-5
Commit Log
	Good Meaningful commit messages.
	Good Progressive commits.
Documentation
	Readme :Good.
	Model/technical explanation :Good.
	Description and Comments :Good.
	Markdown used and PDF submitted.
Pull Request
	Successful Pull Request (Working Algorithm Delivered on Time in Correct Branch).
	No Feedback required.
	Request Description is good.
TOTAL		-5

Marked as per the due date and changes after which aren't necessarily allowed to contribute to grade for fairness.
Subject to approval from Shakes