Improve dataset card: Add task categories, paper link, clarify content, fix title typo

This PR addresses several improvements for the 3DReasonKnee dataset card:

* **Adds `task_categories`**: `image-text-to-text` and `object-detection` are added to the metadata, aligning with the dataset's focus on grounded reasoning, diagnostic questions, and 3D bounding boxes in medical vision language models.
* **Adds `tags`**: The `3d-imaging` tag is added to highlight the dataset's use of 3D MRI volumes for better discoverability.
* **Links to the official Hugging Face paper**: The paper [3DReasonKnee: Advancing Grounded Reasoning in Medical Vision Language Models](https://huggingface.co/papers/2510.20967) is now linked directly in the introductory section, making it easier for users to access the research.
* **Clarifies Content and Fixes Title**: The card's main title typo ("Grouned" -> "Grounded") is corrected. The introduction is also rephrased to clearly state that this repository *is* the 3DReasonKnee dataset and describes its key components, while also noting the presence of code for reproduction and analysis.
* **Adjusts "How to Use"**: This section is updated to emphasize that the processed dataset is readily available in `/generate_data/`, with separate instructions provided for those interested in reproducing it from raw OAI data.

These changes enhance the discoverability, clarity, and overall quality of the dataset card for researchers.

README.md

@@ -1,15 +1,22 @@
 ---
-license: cc-by-4.0
 language:
 - en
-tags:
-- medical
+license: cc-by-4.0
 size_categories:
 - 10K<n<100K
+tags:
+- medical
+- 3d-imaging
+task_categories:
+- image-text-to-text
+- object-detection
 ---
-# 3D ReasonKnee: 3D Grouned Reasoning Dataset
 
-This repository contains code for preprocessing, generating, and analyzing 3D knee MRI data for osteoarthritis assessment.
+# 3D ReasonKnee: 3D Grounded Reasoning Dataset
+
+This repository contains the **3DReasonKnee dataset**, as presented in the paper [3DReasonKnee: Advancing Grounded Reasoning in Medical Vision Language Models](https://huggingface.co/papers/2510.20967). 3DReasonKnee is the first 3D grounded reasoning dataset for medical images, providing 494k high-quality quintuples derived from 7,970 3D knee MRI volumes for osteoarthritis assessment. Each quintuple includes: (1) the 3D MRI volume, (2) a diagnostic question, (3) a 3D bounding box, (4) clinician-generated diagnostic reasoning steps, and (5) structured severity assessments.
+
+The processed data (image paths, prompts, chain-of-thought reasoning, and final diagnoses including bounding boxes of subregions and grade assessments) can be found in the `/generate_data/` folder. This repository also includes code for preprocessing and generating the dataset from raw OAI data, as well as for analyzing it.
 
 ## Repository Structure
 
@@ -35,11 +42,13 @@ This repository contains code for preprocessing, generating, and analyzing 3D kn
   - `/data_preprocessing/` - Scripts for initial data preparation of raw DICOM files
     - `dcm2nifti.py` - Converts DICOM files to NIfTI format and save to `./data/images/`
 
-## How to Use 
+## How to Use the 3DReasonKnee Dataset
+
+The final processed dataset, ready for use, is located in the `/generate_data/` folder.
 
-1. **OAI Download**: Please download the original raw DICOM files from https://nda.nih.gov/oai/query-download
-2. **DICOM to NIfTI Conversion**: Use `/code/data_preprocessing/dcm2nifti.py` to convert DICOM files to NIfTI format 
-3. **Data Example**: data file can be found in `/generate_data/`
+To reproduce the dataset from raw OAI data:
+1.  **OAI Download**: Please download the original raw DICOM files from https://nda.nih.gov/oai/query-download
+2.  **DICOM to NIfTI Conversion**: Use `/code/data_preprocessing/dcm2nifti.py` to convert DICOM files to NIfTI format 
 
 ## Example Data Format
 
@@ -47,8 +56,12 @@ Below is an example of the data format in our generated data files:
 ```json
   {
     "image": "/data/images/9021195/48M/20090518_12801512_1.nii.gz",
-    "prompt": "### Question:\nIn this DESS MRI, can you diagnose cartilage lesions in the femur medial central subregion? Cartilage lesions are scored using two MOAKS components: Size (Grade 0: None, Grade 1: <10% of surface area, Grade 2: 10-75% of surface area, Grade 3: >75% of surface area) and Percent of full-thickness loss (Grade 0: No full-thickness loss, Grade 1: <10% of cartilage defect shows full-thickness loss, Grade 2: 10-75% of cartilage defect shows full-thickness loss, Grade 3: >75% of cartilage defect shows full-thickness loss). Provide your reasoning, the bounding box of the femur medial central subregion, and the MOAKS scores for size and depth. The output format should be a JSON object with the bounding box coordinates and the MOAKS scores: {\"bounding_box\": [start_slice, end_slice, x_min, x_max, y_min, y_max], \"final_diagnosis\": {\"femur medial central cartilage lesion\": {\"Size of lesion\": (grade from 0-3), \"Depth of lesion\": (grade from 0-3)}}}\n### Answer (think step by step):\n",
-    "answer": "The cartilage looks gray in the DESS image. It covers the articular surfaces of the bones. I need to see whether the patient's cartilage has a smooth surface, evenly distributed thickness. If there is an abrupt thinning of cartilage, disruption of contour, it implies a cartilage lesion. There is no abrupt change in cartilage contour or any absence of cartilage in this subregion.\n Final diagnosis: {\"bounding_box\": [83, 141, 117, 261, 154, 258], \"final_diagnosis\": {\"femur medial central cartilage lesion\": {\"size\": 0, \"depth\": 0}}}",
+    "prompt": "### Question:\
+In this DESS MRI, can you diagnose cartilage lesions in the femur medial central subregion? Cartilage lesions are scored using two MOAKS components: Size (Grade 0: None, Grade 1: <10% of surface area, Grade 2: 10-75% of surface area, Grade 3: >75% of surface area) and Percent of full-thickness loss (Grade 0: No full-thickness loss, Grade 1: <10% of cartilage defect shows full-thickness loss, Grade 2: 10-75% of cartilage defect shows full-thickness loss, Grade 3: >75% of cartilage defect shows full-thickness loss). Provide your reasoning, the bounding box of the femur medial central subregion, and the MOAKS scores for size and depth. The output format should be a JSON object with the bounding box coordinates and the MOAKS scores: {\\\"bounding_box\\\": [start_slice, end_slice, x_min, x_max, y_min, y_max], \\\"final_diagnosis\\\": {\\\"femur medial central cartilage lesion\\\": {\\\"Size of lesion\\\": (grade from 0-3), \\\"Depth of lesion\\\": (grade from 0-3)}}}\
+### Answer (think step by step):\
+",
+    "answer": "The cartilage looks gray in the DESS image. It covers the articular surfaces of the bones. I need to see whether the patient's cartilage has a smooth surface, evenly distributed thickness. If there is an abrupt thinning of cartilage, disruption of contour, it implies a cartilage lesion. There is no abrupt change in cartilage contour or any absence of cartilage in this subregion.\
+ Final diagnosis: {\\\"bounding_box\\\": [83, 141, 117, 261, 154, 258], \\\"final_diagnosis\\\": {\\\"femur medial central cartilage lesion\\\": {\\\"size\\\": 0, \\\"depth\\\": 0}}}\",
     "cot": "The cartilage looks gray in the DESS image. It covers the articular surfaces of the bones. I need to see whether the patient's cartilage has a smooth surface, evenly distributed thickness. If there is an abrupt thinning of cartilage, disruption of contour, it implies a cartilage lesion. There is no abrupt change in cartilage contour or any absence of cartilage in this subregion.",
     "final_diagnosis": {
       "bounding_box": [