s4693608 - Alzheimer's Classifier (Task 8)

[CHAR1VAR1]

This project implements a deep learning classifier to distinguish between Alzheimer’s Disease (AD) and Normal Control (NC) using 2D MRI brain slices from the ADNI dataset. The model is based on ConvNeXt, trained using PyTorch, and makes predictions on the slice-level and then aggregates through these predictions and averages them to make patient-level predictions. The model was trained and tested on UQ’s rangpur, achieving a final patient prediction accuracy of 80.22.

[yexincheng]

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

Recognition Problem : total : 10.5

1. Solves problem: Unsure whether the solution is appropriate for the problem, achieving an accuracy of 80.22% on the testing set.
   Didnt mention how the dataset was split; it seems no validation splitting from the code.
   No loss and metrics plots. (2/5)
2. Implementation functions: Model architecture should be implemented from scratch(1.5/3)
3. Good design: Well-designed (1/1)
4. Commenting: Clear and sufficient comments throughout the code. (1/1)
5. Difficulty: Hard, but imported pre-defined model architecture and used pre-trained checkpoint (5/10)

Note:

• To ensure a reproducible environment, dependency versions should be listed or specified.
• No model description.
• Please add references.

[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
	OK solution to problem.	-1
	Driver Script present.
	File structure present.
	Good Usage & Demo & Visualisation & Data usage.
	Module present.
	Commenting present.
	Data leakage found.	-0.5
	Difficulty : Hard. Hard. ConvNeXt
Commit Log
	Good Meaningful commit messages.
	Good Progressive commits.
Documentation
	Readme :Acceptable.	-1
	Model/technical explanation :Acceptable.	-1
	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		-6.5

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