AI Startup Opseyes Revolutionizes Wastewater Analysis

What do radiology and wastewater have in common? Hopefully, not much. But at startup Opseyes, founder Bryan Arndt and data scientist Robin Schlenga are putting the AI that’s revolutionizing medical imaging to work on analyzing wastewater samples.

Arndt and Schlenga spoke with NVIDIA AI Podcast host Noah Kravitz about the inspiration for Opseyes, which began with Arndt’s career at wastewater industry leader Ramboll. Effluent has typically been analyzed by sending tightly sealed samples through the mail to experts.

The AI Podcast · Waste Not, Want Not: AI Startup Opseyes Revolutionizes Wastewater Analysis – Ep. 145

While speaking with his brother, a radiologist using deep learning, Arndt realized that AI could do something similar for wastewater samples.

Schlenga then led the creation of Opseyes’ convolutional neural network, which allows customers to upload a photo of a sample taken through a microscope. With Opseyes already in use at several wastewater plants, Arndt and Schlenga anticipate much more bacterial analysis in their future.

Key Points From This Episode:

Opseyes’ approach has dramatically improved efficiency. Whereas previous methods took a week through the postal system, with AI models accelerated on GPUs, a wastewater sample can be identified in three to four minutes.
The startup’s AI models hold the potential to expand beyond wastewater analysis — Arndt and Schlenga predict that it could aid in identifying hazardous algae blooms, which contain cancer-causing toxins.

Tweetables:

“Wastewater is any water we’ve dirtied up somehow — it’s everything from the runoff in a farmer’s field to sewage.” — Bryan Arndt [2:31]

“It’s a digital dream come true, where you can use the nerdy data stuff to actually do something that helps people … and maybe even the environment.” — Robin Schlenga [22:21]

You Might Also Like:

Miracle Qure: Founder Pooja Rao Talks Medical Technology at Qure.ai

Pooja Rao, a doctor, data scientist and entrepreneur, wants to make cutting-edge medical care available to communities around the world, regardless of their resources. Her startup, Qure.ai, is doing exactly that, with technology that’s used in 150+ healthcare facilities in 27 countries.

Exploring the AI Startup Ecosystem with NVIDIA Inception’s Jeff Herbst

Jeff Herbst is the vice president of business development at NVIDIA and head of NVIDIA Inception, an accelerator program that currently has over 7,000 members across a wide range of industries. He talks about how Inception is accelerating startups in every industry.

Finding Trash in Sensitive Waterways with AI

Cleaning up our oceans, rivers and waterways has become a major environmental issue. San Francisco Estuary Institute’s Lorenzo Flores speaks on using machine learning to find trash in waterways.