Update README.md

README.md

@@ -266,9 +266,17 @@ NORMALIZATION="-1000 500 0 1"   # HU window and output range
 
 ## Validation & Quality Assurance
 
+**Evaluation Criteria:** In the absence of voxel-level ground truth, we adopted a bounding box–supervised evaluation strategy to assess segmentation performance. Each CT volume was accompanied by annotations specifying the nodule center in world coordinates and its dimensions in millimeters, which were converted into voxel indices using the image spacing and clipped to the volume boundaries. A binary mask representing the bounding box was then constructed and used as a weak surrogate for ground truth. we extracted a patch centered on the bounding box, extending it by a fixed margin (64 voxels) to define the volume of interest (VOI). Predicted segmentation masks were cropped to the same VOI-constrained region of interest, and performance was quantified in terms of Dice similarity coefficient. Metrics were computed per lesion. This evaluation strategy enables consistent comparison of segmentation algorithms under weak supervision while acknowledging the limitations of not having voxel-level annotations.
 
+Segmentation performance of **KNN (ours PiNS)**, **VISTA3D auto**, and **VISTA3D points** ([He et al. 2024](https://github.com/Project-MONAI/VISTA/tree/main/vista3d)) across different nodule size buckets. (top) Bar plots display the mean Dice similarity coefficient for each model and size category. (buttom) Boxplots show the distribution of Dice scores, with boxes representing the interquartile range, horizontal lines indicating the median, whiskers extending to 1.5× the interquartile range, and circles denoting outliers.
 
+<p align="center">
+  <img src="assets/Segmentation_Evaluation_KNNVista3Dauto_DLCS24_HIST.png" alt="(a)" width="700">
+</p>
 
+<p align="center">
+  <img src="assets/Segmentation_Evaluation_KNNVista3Dauto_DLCS24_BOX.png" alt="(b)" width="700">
+</p>
 ## Limitations & Considerations
 
 ### Current Limitations
@@ -288,8 +296,6 @@ We welcome collaborations from:
 - **Medical AI Companies**
 - **Open Source Contributors**
 
-
-
 ## Citation & References
 
 ### Primary Citation
@@ -308,9 +314,10 @@ We welcome collaborations from:
 1. **AI in Lung Health: Benchmarking** : [Tushar et al. arxiv (2024)](https://arxiv.org/abs/2405.04605)
 2. **AI in Lung Health: Benchmarking** : [https://github.com/fitushar/AI-in-Lung-Health-Benchmarking](https://github.com/fitushar/AI-in-Lung-Health-Benchmarking-Detection-and-Diagnostic-Models-Across-Multiple-CT-Scan-Datasets)
 4. **DLCS Dataset**: [Wang et al. Radiology AI 2024](https://doi.org/10.1148/ryai.240248);[Zenedo](https://zenodo.org/records/13799069)
-5. **Refining Focus in AI for Lung Cancer:** Comparing Lesion-Centric and Chest-Region Models with Performance Insights from Internal and External Validation. [![arXiv](https://img.shields.io/badge/arXiv-2411.16823-<color>.svg)](https://arxiv.org/abs/2411.16823)
-6. **Peritumoral Expansion Radiomics** for Improved Lung Cancer Classification. [![arXiv](https://img.shields.io/badge/arXiv-2411.16008-<color>.svg)](https://arxiv.org/abs/2411.16008)
-7. **PyRadiomics Framework**: [van Griethuysen et al., Cancer Research 2017](https://pubmed.ncbi.nlm.nih.gov/29092951/)
+5. **SYN-LUNGS**: [Tushar et al., arxiv 2025](https://arxiv.org/abs/2502.21187)
+6. **Refining Focus in AI for Lung Cancer:** Comparing Lesion-Centric and Chest-Region Models with Performance Insights from Internal and External Validation. [![arXiv](https://img.shields.io/badge/arXiv-2411.16823-<color>.svg)](https://arxiv.org/abs/2411.16823)
+7. **Peritumoral Expansion Radiomics** for Improved Lung Cancer Classification. [![arXiv](https://img.shields.io/badge/arXiv-2411.16008-<color>.svg)](https://arxiv.org/abs/2411.16008)
+8. **PyRadiomics Framework**: [van Griethuysen et al., Cancer Research 2017](https://pubmed.ncbi.nlm.nih.gov/29092951/)
 
 
 
@@ -325,8 +332,6 @@ You are free to use, modify, and distribute this code under the following condit
 For commercial licensing inquiries, please contact: tushar.ece@duke.edu
 
 
-
-
 ## Support & Community
 
 ### Getting Help
@@ -336,24 +341,9 @@ For commercial licensing inquiries, please contact: tushar.ece@duke.edu
 - **📧 Email**: tushar.ece@Duke.edu ; fitushar.mi@gmail.com
 
 ### Community Stats
-- **Users**: 
 - **Publications**: 5+ research papers
-- **Downloads**: 
 - **Contributors**: Active open-source community
 
 ---
 
-<div align="center">
-
-### 🌟 **Star this project on [GitHub](https://github.com/fitushar/PiNS) if it helps your research!** 🌟
-
-**Made with ❤️ for the medical imaging community**
-
-[🚀 Get Started](#quick-start) • [📖 Full Documentation](https://github.com/ft42/PiNS) • [💻 Source Code](https://github.com/ft42/PiNS) • [🐳 Docker Image](https://hub.docker.com/r/ft42/nodule-segmentation)
 
-</div>
-
-
----
-license: mit
----