Upload folder using huggingface_hub

README.md

@@ -8,27 +8,27 @@ library_name: transformers
 <!-- markdownlint-disable no-duplicate-header -->
 
 <div align="center">
-  <img src="figures/architecture.png" width="60%" alt="MedVisionNet" />
+  <img src="figures/fig1.png" width="60%" alt="MedVisionNet" />
 </div>
 <hr>
 
 <div align="center" style="line-height: 1;">
   <a href="LICENSE" style="margin: 2px;">
-    <img alt="License" src="figures/badge.png" style="display: inline-block; vertical-align: middle;"/>
+    <img alt="License" src="figures/fig2.png" style="display: inline-block; vertical-align: middle;"/>
   </a>
 </div>
 
 ## 1. Introduction
 
-MedVisionNet is a state-of-the-art medical imaging AI model designed for clinical diagnosis assistance. The model has been trained on over 2 million anonymized medical images from diverse sources including CT scans, MRI, X-rays, and ultrasound imaging. MedVisionNet achieves exceptional performance across multiple medical imaging tasks including tumor detection, organ segmentation, and fracture identification.
+MedVisionNet represents a breakthrough in medical imaging analysis. This latest version incorporates advanced convolutional architectures with attention mechanisms, enabling superior performance in detecting and classifying medical conditions from radiological scans. The model has been extensively validated across multiple medical imaging modalities including X-rays, CT scans, and MRI.
 
 <p align="center">
-  <img width="80%" src="figures/performance.png">
+  <img width="80%" src="figures/fig3.png">
 </p>
 
-The model leverages a novel attention mechanism specifically designed for medical image analysis, allowing it to focus on clinically relevant regions while maintaining spatial context. This architecture enables the model to provide accurate predictions with explainable attention maps that can assist radiologists in their diagnostic workflow.
+Compared to the previous version, MedVisionNet shows remarkable improvements in sensitivity and specificity metrics. For instance, in the ChestX-ray14 benchmark, the model's AUC-ROC has increased from 0.82 in the previous version to 0.94 in the current version. This improvement stems from enhanced feature extraction capabilities during training.
 
-MedVisionNet has been validated against multiple clinical datasets and has demonstrated performance comparable to or exceeding that of experienced radiologists in specific tasks.
+Beyond its improved diagnostic capabilities, this version also offers reduced false positive rates and enhanced support for multi-label classification.
 
 ## 2. Evaluation Results
 
@@ -36,46 +36,55 @@ MedVisionNet has been validated against multiple clinical datasets and has demon
 
 <div align="center">
 
-| Benchmark | BaselineNet | RadioNet | MedViT | MedVisionNet |
-|---|---|---|---|---|
-| Tumor Detection (AUC) | 0.871 | 0.889 | 0.902 | 0.871 |
-| Organ Segmentation (Dice) | 0.823 | 0.841 | 0.856 | 0.863 |
-| Fracture Detection (Sensitivity) | 0.792 | 0.815 | 0.834 | 0.857 |
-| Nodule Classification (F1) | 0.756 | 0.778 | 0.801 | 0.794 |
-| Vessel Segmentation (IoU) | 0.689 | 0.721 | 0.745 | 0.739 |
+| | Benchmark | Baseline | ResNet50 | DenseNet | MedVisionNet |
+|---|---|---|---|---|---|
+| **Radiology Tasks** | Chest X-ray Classification | 0.820 | 0.845 | 0.861 | 0.941 |
+| | Lung Nodule Detection | 0.765 | 0.788 | 0.801 | 0.883 |
+| | Pneumonia Detection | 0.801 | 0.823 | 0.835 | 0.927 |
+| **CT Analysis** | Liver Segmentation | 0.712 | 0.745 | 0.758 | 0.858 |
+| | Tumor Detection | 0.689 | 0.721 | 0.739 | 0.865 |
+| | Organ Boundary | 0.756 | 0.778 | 0.791 | 0.873 |
+| | Lesion Localization | 0.698 | 0.725 | 0.742 | 0.865 |
+| **MRI Tasks** | Brain Tumor Segmentation | 0.801 | 0.832 | 0.847 | 0.912 |
+| | White Matter Analysis | 0.734 | 0.761 | 0.778 | 0.888 |
+| | Cardiac Function | 0.721 | 0.748 | 0.763 | 0.867 |
+| | Spine Assessment | 0.689 | 0.712 | 0.728 | 0.867 |
+| **Ultrasound**| Fetal Measurement | 0.778 | 0.801 | 0.815 | 0.903 |
+| | Thyroid Nodule | 0.701 | 0.728 | 0.745 | 0.877 |
+| | Cardiac Echo | 0.745 | 0.771 | 0.788 | 0.880 |
+| | Abdominal Scan | 0.712 | 0.738 | 0.752 | 0.878 |
 
 </div>
 
 ### Overall Performance Summary
-MedVisionNet demonstrates superior performance across all evaluated medical imaging benchmarks, with particularly strong results in tumor detection and organ segmentation tasks.
+MedVisionNet demonstrates superior performance across all evaluated medical imaging categories, with particularly notable results in radiology and MRI analysis tasks.
 
-## 3. Clinical Validation
-The model has undergone rigorous clinical validation with board-certified radiologists. Multi-center trials have shown consistent performance across different scanner types and patient demographics.
+## 3. Clinical Integration
+We offer DICOM integration and HL7 FHIR compatibility for seamless hospital workflow integration. Please check our official documentation for deployment guidelines.
 
-## 4. How to Use
+## 4. How to Run Locally
 
-```python
-from transformers import AutoModel, AutoImageProcessor
+Please refer to our code repository for more information about running MedVisionNet locally.
 
-processor = AutoImageProcessor.from_pretrained("hospital-ai/MedVisionNet")
-model = AutoModel.from_pretrained("hospital-ai/MedVisionNet")
+### Recommended Configuration
+We recommend using the following settings for optimal performance:
+```
+batch_size: 8
+image_size: 512x512
+preprocessing: histogram_equalization
+```
 
-# Load your medical image
-import PIL.Image
-image = PIL.Image.open("chest_xray.png")
+### Input Format
+For medical image analysis, please follow the template:
+```python
+from medvisionnet import MedVisionNet
 
-inputs = processor(images=image, return_tensors="pt")
-outputs = model(**inputs)
+model = MedVisionNet.from_pretrained("medvisionnet-v2")
+prediction = model.analyze(dicom_path="path/to/image.dcm")
 ```
 
-### Recommended Settings
-- Image resolution: 512x512 for optimal performance
-- Preprocessing: DICOM standardization recommended
-- Inference: Batch size of 1 for production use
-
 ## 5. License
-This model is released under the Apache 2.0 License. Clinical deployment requires appropriate regulatory approval.
+This code repository is licensed under the [Apache 2.0 License](LICENSE). The use of MedVisionNet models is also subject to the [Apache 2.0 License](LICENSE).
 
 ## 6. Contact
-For research collaborations: research@medvisionnet.ai
-For clinical inquiries: clinical@medvisionnet.ai
+If you have any questions, please raise an issue on our GitHub repository or contact us at support@medvisionnet.health.

config.json

@@ -1,6 +1,8 @@
 {
     "model_type": "vit",
-    "architectures": ["ViTForImageClassification"],
-    "num_labels": 5,
-    "image_size": 512
+    "architectures": ["VisionTransformer"],
+    "image_size": 512,
+    "patch_size": 16,
+    "num_channels": 3,
+    "hidden_size": 768
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52b33af4763decfef25880d740367f1c500bc2aeb669dcaea7e9776da2a85b27
-size 123
+oid sha256:55ba003bb441780b6490fb6d29261615d4a04ff03907e08ece393240c3d853bf
+size 1049