Update README.md

Author: gourav3017

README.md

@@ -79,7 +79,7 @@ The easiest way to start is through the PorPy following Jupiter Notebook example
 
 This figure illustrates the inspiration behind developing PortPy, drawing from successful open-source practices in the AI and computer science communities. Tools like PyTorch and TensorFlow, along with benchmark datasets such as ImageNet and algorithms like AlexNet, have revolutionized AI and data science. Our goal is to replicate this successful model in the field of radiotherapy by equipping researchers with PortPy toolkit, benchmark algorithms, and datasets, as outlined below:
 1. **PortPy Toolkit**. PortPy allows researchers to develop, test, and validate novel treatment planning optimization algorithms.
-2. **Benchmark Datasets**. We have curated and made publicly available a dataset of 50 lung cancer patients, which includes all the necessary data for treatment plan optimization (e.g., beamlets, voxels, dose influence matrix). These data are extracted from the commercial FDA-approved Eclipse treatment planning system using its API. For more info about data, see [Data](#Data).
+2. **Benchmark Datasets**. We have curated and made publicly available a dataset of 100 lung and 129 prostate cancer patients, which includes all the necessary data for treatment plan optimization (e.g., beamlets, voxels, dose influence matrix). These data are extracted from the commercial FDA-approved Eclipse treatment planning system using its API. For more info about data, see [Data](#Data).
 3. **Benchmark Algorithms**. Many optimization problems in radiotherapy treatment planning suffer from “non-convexity”, a mathematical property that can cause optimization algorithms to become trapped in “local optima” rather than finding the global optimum. Several of these problems (e.g., VMAT planning) can be formulated using advanced optimization techniques like Mixed Integer Programming (MIP). Although MIP is computationally intensive, often taking days to solve for each patient, it can provide global optimal solutions that can serve as "ground truth" benchmarks, enabling researchers to develop and evaluate more computationally efficient algorithms. For more info, see our Jupyter Notebooks ([vmat_global_optimal.ipynb](https://github.com/PortPy-Project/PortPy/blob/master/examples/vmat_global_optimal.ipynb), [beam_orientation_global_optimal.ipynb](https://github.com/PortPy-Project/PortPy/blob/master/examples/beam_orientation_global_optimal.ipynb), [dvh_constraint_global_optimal.ipynb](https://github.com/PortPy-Project/PortPy/blob/master/examples/dvh_constraint_global_optimal.ipynb)).