Objectives:

$1.$ Data Preparation: Download the MRI data from the provided link.

$2.$ Segmentation Task: Implement a segmentation method to segment the brain images. You may choose advanced methods such as machine learning models $($e$.$g$.,$ U$-$Net, or U$-$Net with attention$).$

$3.$ Visualization: Visualize the segmentation results. Provide at least three images showing the original images with their corresponding segmentation maps.

$4.$ Write a conclusion summarizing the findings.

Task $2$: Sequential Sentence Classification with Transformer Models

Objective:

Your primary objective is to develop a Transformer$-$based model that can accurately classify sentences according to their role in the structure of biomedical research paper abstracts $($e$.$g$.,$ objective, methods, results, conclusions$).$

Dataset:

Source: PubMed $20$k RCT dataset

Description: This dataset includes abstracts from randomized controlled trials, with sentences labeled according to their sequential role in the abstract$.$

Access: The dataset can be downloaded from the 'Files' section in a folder named 'Project Files'.

Requirements:

Data Preparation: Load and preprocess the data, ensuring the model can effectively process it$.$ This includes tokenization, handling of special tokens, and batch preparation.

Model Implementation:

Implement a Transformer model for sentence classification. You may use pre$-$existing models like BERT, GPT$,$ or develop your own variant.

Fine$-$tune the model on the dataset, ensuring it is appropriately adjusted to the task of classifying sentences in biomedical abstracts$.$

Evaluation:

Evaluate the model using appropriate metrics such as accuracy, F$1$ score, and confusion matrix.

Analyze the model's performance, highlighting its strengths and weaknesses in different classification categories.

Discussion:

Discuss how the Transformer architecture benefits the task of sequential sentence classification.

Compare its performance against a baseline model, such as a simple RNN or LSTM$.$