{
  "site": {
    "title": "Andrew L.Z.",
    "description": "Andrew Zhou — researcher and incoming Stanford student. World models, neuroimaging, robotics, and startups.",
    "favicon": "Assests/fatcatsoosh.gif",
    "ogImage": "/Assests/fatcatsoosh.gif",
    "author": {
      "name": "Andrew Zhou",
      "nameDisplay": "Andrew L. Zhou"
    },
    "email": "andrewlz [at] stanford [dot] edu",
    "copyright": "© 2026 Andrew Zhou. All rights reserved.",
    "sameAs": [
      "https://www.linkedin.com/in/andrewzhou105/",
      "https://github.com/sooshysoosh"
    ]
  },

  "navigation": {
    "main": [
      { "text": "LinkedIn", "url": "https://www.linkedin.com/in/andrewzhou105/", "external": true },
      { "text": "GitHub", "url": "https://github.com/sooshysoosh", "external": true },
      { "text": "Commentary/Thoughts", "url": "/blog", "external": false }
    ],
    "blog": [
      { "text": "Back Home", "url": "/", "external": false },
      { "text": "LinkedIn", "url": "https://www.linkedin.com/in/andrewzhou105/", "external": true },
      { "text": "GitHub", "url": "https://github.com/sooshysoosh", "external": true }
    ]
  },

  "bio": {
    "text": "I am a researcher and incoming student at Stanford, where I plan on majoring in Computer Science & Electrical Engineering. I'm interested in understanding and developing the capabilities of {worldModels}. Specifically, I am exploring world models that replicate the processes underlying human cognition, such as simulated sensory input and social reasoning. My earlier research focused on developing self-assessing deep learning models for brain lesion segmentation. Previously, I founded {svRobotics}, a 501c3 that organized national robotics competitions for 300+ teams, and co-founded {vog}, a geospatial analytics startup backed by Motiv Space Systems & NASA. Before that, I won several national robotics championships, international science fairs, and was a 2025 Conrad Finalist.",
    "links": {
      "worldModels": {
        "text": "world models",
        "url": "https://amilabs.xyz/",
        "class": "link-underline"
      },
      "svRobotics": {
        "text": "SVRobotics",
        "url": "https://siliconvalleyroboticsacademy.org/",
        "class": "link-underline"
      },
      "vog": {
        "text": "Vision of Grove",
        "url": "https://www.vision-of-grove.com/",
        "class": "link-underline"
      }
    }
  },

  "research": [
    {
      "title": "Enhancing Neuro-Oncology Through Self-Assessing Deep Learning Models for Brain Tumor and Whole Brain Segmentation",
      "authors": [
        { "name": "Andrew L. Zhou", "isPrimary": true }
      ],
      "description": "This study introduces an uncertainty-aware brain tumor segmentation framework that augments the nnUNet model with an additional prediction channel for voxel-wise uncertainty estimation. The proposed method predicts uncertainty directly from the deep learning model and therefore does not require multiple networks or multiple inference passes. To further aid physicians in reviewing tumors in whole brain context, we build upon our previously published unified segmentation model that jointly segments tumor and whole brain structures.",
      "context": "Arxiv Preprint · Nov 16, 2025",
      "links": [],
      "isSelected": true
    },
    {
      "title": "Novel Unified 3D nnU-Net Deep-Learning Model for Brain Tumor & Whole Brain Segmentation",
      "authors": [
        { "name": "Andrew L. Zhou", "isPrimary": true }
      ],
      "description": "Due to the distortions in the brain caused by tumors, whole-brain segmentation models trained on healthy brains do not perform accurately on diseased ones. To address this issue, this paper proposes a novel unified 3D nnU-Net model for the segmentation of both brain tumor and whole-brain structures for the first time. This paper introduces a novel method to augment data from OASIS-1 and BraTS2023 to train the baseline model. The model successfully achieves a Dice Similarity Coefficient (DSC) of 0.814 for whole brain structures and 0.874 for tumor segmentation.",
      "publicationUrl": "https://ieeexplore.ieee.org/document/11141202",
      "context": "IEEE 4th International Conference on Computing and Machine Learning · Apr 5, 2025",
      "links": [],
      "isSelected": true
    },
    {
      "title": "A Unique Block-Based 3D U-Net Deep Learning Model for Brain Metastasis MRI Image Segmentation and Classification",
      "authors": [
        { "name": "Andrew L. Zhou", "isPrimary": true }
      ],
      "description": "Scarcity of data has limited the progression of deep learning studies to automate the classification and segmentation of brain metastasis. Furthermore, due to the nature of BM's, the available data is highly unbalanced with relatively diminutive cancer regions. This paper presents a novel 3D U-net deep learning model on the first public BM database. Two models are presented, the aggressive model which is tailored towards precise segmentation that reached a DSC of 0.88; and the Passive model which is suited towards detecting blocks that contain cancer with fewer false positives. Combining both models can detect 85% of all cancer cases.",
      "publicationUrl": "https://ieeexplore.ieee.org/document/10586196",
      "context": "IEEE 3rd International Conference on Computing and Machine Learning · Apr 14, 2024",
      "links": [],
      "isSelected": false
    }
  ],

  "projects": [
    {
      "title": "Surgical View: Deep Learning Pipeline for Brain Tumor Imaging",
      "description": "Brain tumor diagnosis is time-sensitive, but current workflows are slow, fragmented, and dependent on manual segmentation. Through insights from neurosurgeons and radiologists, we built a preprocessing deep-learning pipeline that helps radiologists and neurosurgeons locate, segment, and visualize brain tumors with greater accuracy and speed. The pipeline processes raw MRI images into segmented masks to reconstruct a 3D projection. Tunable suggestions and resection paths are then displayed along with the brain model on Microsoft HoloLens (VR).",
      "links": [],
      "isSelected": true
    }
  ],

  "pages": {
    "blog": {
      "indexTitle": "Writings",
      "description": "Notes and commentary by Andrew Zhou.",
      "copyright": "© 2026 Andrew L. Zhou. All rights reserved.",
      "posts": [
        {
          "slug": "Placeholder Post",
          "title": "Placeholder Post",
          "date": "April 2, 2026",
          "excerpt": "N/A Coming Soon!",
          "body": "Coming Soon! Currently, this is a placeholder for the blog section."
        }
      ]
    }
  }
}