s48027522-Topic22DUNet

[anhadh676842]

This project implements a 2D UNet CNN architecture for segmenting prostates from MRI scans using a 2D U-Net architecture. The workflow is designed to handle pre-processed 2D slices of prostate MRIs, enabling efficient training and evaluation of segmentation models. Preprocessing was already handled by the 2d segments taken as inputs to this CNN, but some augmentation (flipping and rotation) and normalisation was still done.

The goal is to accurately delineate the prostate from surrounding tissues, which is critical for clinical applications such as radiotherapy planning, disease diagnosis, and progression monitoring.

[24msingh24]

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

2D UNet – Prostate MRI Segmentation → Easy

Category		Marks	Comments
Algorithm solves the problem	5	3.5	Implemented 2D UNet with Dice Loss and early stopping. Sample output images not included on GitHub, and test metrics are not explicitly reported.
Implementation functions as intended	3	2	Code is functional and modular. Some minor inconsistencies in transforms and unclear validation metrics; model checkpoints not included.
Good design	1	1	-Well-structured scripts with correct encoder-decoder and skip connections.
Commenting	1	0.5	Some docstrings and comments present, but more explanation and avoidance of hardcoded paths would improve clarity.
Algorithm above Normal Difficulty	5	0
Algorithm is Hard difficulty	5	0	Easy
Section IV : Max mark 10 from 20		7

• Discussion: None provided. This is needed.

Suggestions/Notes:

• No plots., no outputs images are shown. Readme file seems to be too brief.

[gayanku]

Marking

Good/OK/Fair Practice (Design/Commenting, TF/Torch Usage)
	No design and implementation.	-2
	Spacing and comments.
	No Header blocks.	-1
Recognition Problem
	Implemented 2D UNet with Dice Loss and early stopping. Sample output images not included on GitHub, and test metrics are not explicitly reported.
	Driver Script present.
	File structure present.
	Good Usage & Demo & Visualisation & Data usage.
	Module present.
	Commenting missing.	-1
	No Data leakage found.
	Difficulty : Easy. Easy. Unet 2D	-10
Commit Log
	Good Meaningful commit messages.
	Some/Adequate Progressive commits. 2 Days	-1
Documentation
	Readme :Acceptable.	-4
	Model/technical explanation :Missing.	-3
	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		-22

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