Tanay Kothari

San Francisco, California, United States Contact Info
8K followers 500+ connections

Join to view profile

About

Building personal computing systems for the AI revolution. DM me for more info…

Activity

Join now to see all activity

Experience & Education

  • Wispr AI

View Tanay’s full experience

See their title, tenure and more.

or

By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.

Licenses & Certifications

Volunteer Experience

  • Pratham Education Foundation Graphic

    Associate Technical Developer, Pratham Books

    Pratham Education Foundation

    - 2 years 2 months

    Education

    Developed a framework to convert physical books to interactive games using Unity3D. Reached students in over 2000 rural schools in India.
    Field tested and interacted with children in rural schools near Delhi and managed a team of 10.

    More about this: https://prathambooks.org/blog/more-apps-to-play-with-from-studio-of/

Publications

  • PENet—a scalable deep-learning model for automated diagnosis of pulmonary embolism using volumetric CT imaging

    Nature Digital Medicine

    Pulmonary embolism (PE) is a life-threatening clinical problem and computed tomography pulmonary angiography (CTPA) is the gold standard for diagnosis. Prompt diagnosis and immediate treatment are critical to avoid high morbidity and mortality rates, yet PE remains among the diagnoses most frequently missed or delayed. In this study, we developed a deep learning model—PENet, to automatically detect PE on volumetric CTPA scans as an end-to-end solution for this purpose. The PENet is a 77-layer…

    Pulmonary embolism (PE) is a life-threatening clinical problem and computed tomography pulmonary angiography (CTPA) is the gold standard for diagnosis. Prompt diagnosis and immediate treatment are critical to avoid high morbidity and mortality rates, yet PE remains among the diagnoses most frequently missed or delayed. In this study, we developed a deep learning model—PENet, to automatically detect PE on volumetric CTPA scans as an end-to-end solution for this purpose. The PENet is a 77-layer 3D convolutional neural network (CNN) pretrained on the Kinetics-600 dataset and fine-tuned on a retrospective CTPA dataset collected from a single academic institution. The PENet model performance was evaluated in detecting PE on data from two different institutions: one as a hold-out dataset from the same institution as the training data and a second collected from an external institution to evaluate model generalizability to an unrelated population dataset. PENet achieved an AUROC of 0.84 [0.82–0.87] on detecting PE on the hold out internal test set and 0.85 [0.81–0.88] on external dataset. PENet also outperformed current state-of-the-art 3D CNN models. The results represent successful application of an end-to-end 3D CNN model for the complex task of PE diagnosis without requiring computationally intensive and time consuming preprocessing and demonstrates sustained performance on data from an external institution. Our model could be applied as a triage tool to automatically identify clinically important PEs allowing for prioritization for diagnostic radiology interpretation and improved care pathways via more efficient diagnosis.

    See publication

Projects

  • Canteen: Decentralizing container orchestration

    Winner at ETH Denver.

    Canteen is an extremely scalable container orchestrator that is fault-tolerant, easy to install, easy to distribute, and most importantly decentralized through the utility of an Ethereum smart contract.

    Canteen efficiently schedules and orchestrates designated Docker containers to a set of servers based on speculated/provisioned container resource limits.

    Other creators
    See project

  • Dream.it: Synthesizing fashion with Generative Adversarial Networks

    Developed a product with Generative Adversarial Networks trained on datasets of various fashion products to synthesize new products based on rough sketches and color schemes. The output from this was then passed on to a Single Image Super Resolution algorithm for more detailing.

    This image is then labelled, and the image along with the associated tags is used to run a web search to find similar products.

    This won the Microsoft and IBM Sponsor Prizes at Treehacks 2017, Stanford…

    Developed a product with Generative Adversarial Networks trained on datasets of various fashion products to synthesize new products based on rough sketches and color schemes. The output from this was then passed on to a Single Image Super Resolution algorithm for more detailing.

    This image is then labelled, and the image along with the associated tags is used to run a web search to find similar products.

    This won the Microsoft and IBM Sponsor Prizes at Treehacks 2017, Stanford University.
    We are currently working on researching on this to make a better model and developing this into a better product.

    https://github.com/Tanay1998/Dream-It

    Other creators
    See project

Honors & Awards

  • Forbes 30 under 30

    Forbes Inc.

    Consumer Technology - 30 under 30

  • Finalist, ACM ICPC Regionals

    ACM ICPC

    Representing Stanford University at the ACM ICPC North America Regionals

  • Winner, ETH Denver

    ETH Denver

    Finalist at the biggest Ethereum Hackathon.

    Worked on two projects:
    1. Canteen: Decentralized Container Orchestration
    2. Ethmoji: The first customizable NFTs, in collaboration with OpenSea

  • Bronze Medalist, International Olympiad in Informatics (IOI '15)

    IOI Committee

  • Silver Medalist, Asia-Pacific Informatics Olympiad (APIO '15)

    APIO

  • 2nd in Indian Linguistics Olympiad

    PLO

    Finished 2nd in India and represented India at IOL 2015 (International Olympiad in Linguistics) in Bulgaria

Languages

  • English

    Native or bilingual proficiency

  • Hindi

    Native or bilingual proficiency

  • Spanish

    Limited working proficiency

Recommendations received

2 people have recommended Tanay

Join now to view

More activity by Tanay

View Tanay’s full profile

  • See who you know in common
  • Get introduced
  • Contact Tanay directly
Join to view full profile

People also viewed

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Others named Tanay Kothari in United States

5 others named Tanay Kothari in United States are on LinkedIn

See others named Tanay Kothari

Add new skills with these courses

See all courses