Connect with us

News

Researchers develop artificial intelligence that can identify cancer cells

Published

on

Scientists from Osaka University in Japan have developed artificial intelligence (AI) that can identify different types of cancers based on microscopy images of their cells. The AI was also able to determine whether the cancer cells were resistant to radiation, and further learned the differences between human and animal cancers. Since the accuracy and timeliness of traditional methods of identifying cancer cells are prone to delays and errors, an accurate and automated system for accomplishing this would be beneficial to cancer research and treatment overall. The results of the scientists’ research were published in the December 2018 issue of Cancer Research.

The type of AI developed for the cell identification is called a convolutional neural network (CNN); it’s loosely based on the connectivity patterns used by neurons in the brain and primarily used for classifying images. As described in their publication, the scientists used a training set of 10,000 images each of human cervical cancer cells (ME-180) and mouse squamous cancer cells (NR-S1), e.g., the thin, flat types of cells found on the surface of the skin and thin linings around various organs throughout the body. They also included images of radioresistant clones with the set, and ultimately obtained a 96% accuracy in a 2,000 image test.

Because the types of cells in a single cancerous tumor can vary widely, identifying the specific cells present is important for determining the best treatment. Thus, having a tool to provide this information quickly and accurately could have a significant impact. The Osaka team hopes to expand the types of cancers their AI can identify and ultimately establish a universal system that can identify all cancer cell types.

Microscopic image of skin cancer cells (squamous) in a mouse (blue). | Credit: Catherine and James Galbraith, Oregon Health and Science University, Knight Cancer Institute/NIH, CC BY-NC 2.0.

Using artificial intelligence in the battle against cancer is being explored throughout the world as the number of uses devised expands. In one notable instance, a team of scientists from The Institute of Cancer Research in London and the University of Edinburgh has developed an AI technique called REVOLVER (repeated evolution of cancer) which identifies DNA mutation patterns in cancers to predict the ways they will change in response to treatment. Similar to how bacteria become resistant to antibiotics, so too can cancers become resistant to the drugs used against them. By removing the unpredictability variable in cancer behavior, scientists would be able to stay ahead of the disease’s progress and tailor treatments accordingly.

The collaboration between AI and healthcare overall is growing, not just in cancer research – even Google is making contributions to the field. Fortunately, the agencies regulating developments are also attuned to the changes. Earlier this year at the AcademyHealth 2018 Health Datapalooza, the U.S. Food and Drug Administration (FDA) Commissioner Scott Gottlieb, MD signaled the agency’s positive position towards the field. “AI holds enormous promise for the future of medicine, and we’re actively developing a new regulatory framework to promote innovation in this space and support the use of AI-based technologies,” he stated at the event. He also referred to the agency’s plans to streamline their regulations and tools to be sufficiently flexible to handle the rapid pace of advancements and “focus on the ways in which real-world data flows.”

Accidental computer geek, fascinated by most history and the multiplanetary future on its way. Quite keen on the democratization of space. | It's pronounced day-sha, but I answer to almost any variation thereof.

Advertisement
Comments

Elon Musk

Elon Musk’s Boring Company opens Vegas Loop’s newest station

The Fontainebleau is the latest resort on the Las Vegas Strip to embrace the tunneling startup’s underground transportation system.

Published

on

Credit: The Boring Company/X

Elon Musk’s tunneling startup, The Boring Company, has welcomed its newest Vegas Loop station at the Fontainebleau Las Vegas.

The Fontainebleau is the latest resort on the Las Vegas Strip to embrace the tunneling startup’s underground transportation system.

Fontainebleau Loop station

The new Vegas Loop station is located on level V-1 of the Fontainebleau’s south valet area, as noted in a report from the Las Vegas Review-Journal. According to the resort, guests will be able to travel free of charge to the stations serving the Las Vegas Convention Center, as well as to Loop stations in Encore and Westgate.

The Fontainebleau station connects to the Riviera Station, which is located in the northwest parking lot of the convention center’s West Hall. From there, passengers will be able to access the greater Vegas Loop.

Vegas Loop expansion

In December, The Boring Company began offering Vegas Loop rides to and from Harry Reid International Airport. Those trips include a limited above-ground segment, following approval from the Nevada Transportation Authority to allow surface street travel tied to Loop operations.

Under the approval, airport rides are limited to no more than four miles of surface street travel, and each trip must include a tunnel segment. The Vegas Loop currently includes more than 10 miles of tunnels. From this number, about four miles of tunnels are operational.

The Boring Company President Steve Davis previously told the Review-Journal that the University Center Loop segment, which is currently under construction, is expected to open in the first quarter of 2026. That extension would allow Loop vehicles to travel beneath Paradise Road between the convention center and the airport, with a planned station located just north of Tropicana Avenue.

Continue Reading

News

Tesla leases new 108k-sq ft R&D facility near Fremont Factory

The lease adds to Tesla’s presence near its primary California manufacturing hub as the company continues investing in autonomy and artificial intelligence.

Published

on

Credit: Tesla

Tesla has expanded its footprint near its Fremont Factory by leasing a 108,000-square-foot R&D facility in the East Bay. 

The lease adds to Tesla’s presence near its primary California manufacturing hub as the company continues investing in autonomy and artificial intelligence.

A new Fremont lease

Tesla will occupy the entire building at 45401 Research Ave. in Fremont, as per real estate services firm Colliers. The transaction stands as the second-largest R&D lease of the fourth quarter, trailing only a roughly 115,000-square-foot transaction by Figure AI in San Jose.

As noted in a Silicon Valley Business Journal report, Tesla’s new Fremont lease was completed with landlord Lincoln Property Co., which owns the facility. Colliers stated that Tesla’s Fremont expansion reflects continued demand from established technology companies that are seeking space for engineering, testing, and specialized manufacturing.

Tesla has not disclosed which of its business units will be occupying the building, though Colliers has described the property as suitable for office and R&D functions. Tesla has not issued a comment about its new Fremont lease as of writing.

AI investments

Silicon Valley remains a key region for automakers as vehicles increasingly rely on software, artificial intelligence, and advanced electronics. Erin Keating, senior director of economics and industry insights at Cox Automotive, has stated that Tesla is among the most aggressive auto companies when it comes to software-driven vehicle development.

Other automakers have also expanded their presence in the area. Rivian operates an autonomy and core technology hub in Palo Alto, while GM maintains an AI center of excellence in Mountain View. Toyota is also relocating its software and autonomy unit to a newly upgraded property in Santa Clara.

Despite these expansions, Colliers has noted that Silicon Valley posted nearly 444,000 square feet of net occupancy losses in Q4 2025, pushing overall vacancy to 11.2%.

Advertisement
Continue Reading

News

Tesla winter weather test: How long does it take to melt 8 inches of snow?

Published

on

Credit: Teslarati

In Pennsylvania, we got between 10 and 12 inches of snow over the weekend as a nasty Winter storm ripped through a large portion of the country, bringing snow to some areas and nasty ice storms to others.

I have had a Model Y Performance for the week courtesy of Tesla, which got the car to me last Monday. Today was my last full day with it before I take it back to my local showroom, and with all the accumulation on it, I decided to run a cool little experiment: How long would it take for Tesla’s Defrost feature to melt 8 inches of snow?

Tesla Model Y Performance set for new market entrance in Q1

Tesla’s Defrost feature is one of the best and most underrated that the car has in its arsenal. While every car out there has a defrost setting, Tesla’s can be activated through the Smartphone App and is one of the better-performing systems in my opinion.

It has come in handy a lot through the Fall and Winter, helping clear up my windshield more efficiently while also clearing up more of the front glass than other cars I’ve owned.

The test was simple: don’t touch any of the ice or snow with my ice scraper, and let the car do all the work, no matter how long it took. Of course, it would be quicker to just clear the ice off manually, but I really wanted to see how long it would take.

Tesla Model Y heat pump takes on Model S resistive heating in defrosting showdown

Observations

I started this test at around 10:30 a.m. It was still pretty cloudy and cold out, and I knew the latter portion of the test would get some help from the Sun as it was expected to come out around noon, maybe a little bit after.

I cranked it up and set my iPhone up on a tripod, and activated the Time Lapse feature in the Camera settings.

The rest of the test was sitting and waiting.

It didn’t take long to see some difference. In fact, by the 20-minute mark, there was some notable melting of snow and ice along the sides of the windshield near the A Pillar.

However, this test was not one that was “efficient” in any manner; it took about three hours and 40 minutes to get the snow to a point where I would feel comfortable driving out in public. In no way would I do this normally; I simply wanted to see how it would do with a massive accumulation of snow.

It did well, but in the future, I’ll stick to clearing it off manually and using the Defrost setting for clearing up some ice before the gym in the morning.

Check out the video of the test below:

Continue Reading