News
Researchers develop artificial intelligence that can identify cancer cells
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.
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.”
Tesla has rolled out a new Supercharging safety feature in the United States, one that will answer concerns that some owners may have if they need to leave in a pinch.
It is also a suitable alternative for non-Tesla chargers, like third-party options that feature J1772 or CCS to NACS adapters.
The feature has been available in Europe for some time, but it is now rolling out to Model 3 and Model Y owners in the U.S.
With Software Update 2026.2.3, Tesla is launching the Unlatching Charge Cable function, which will now utilize the left rear door handle to release the charging cable from the port. The release notes state:
“Charging can now be stopped and the charge cable released by pulling and holding the rear left door handle for three seconds, provided the vehicle is unlocked, and a recognized key is nearby. This is especially useful when the charge cable doesn’t have an unlatch button. You can still release the cable using the vehicle touchscreen or the Tesla app.”
The feature was first spotted by Not a Tesla App.
This is an especially nice feature for those who commonly charge at third-party locations that utilize plugs that are not NACS, which is the Tesla standard.
For example, after plugging into a J1772 charger, you will still be required to unlock the port through the touchscreen, which is a minor inconvenience, but an inconvenience nonetheless.
Additionally, it could be viewed as a safety feature, especially if you’re in need of unlocking the charger from your car in a pinch. Simply holding open the handle on the rear driver’s door will now unhatch the port from the car, allowing you to pull it out and place it back in its housing.
This feature is currently only available on the Model 3 and Model Y, so Model S, Model X, and Cybertruck owners will have to wait for a different solution to this particular feature.
News
LG Energy Solution pursuing battery deal for Tesla Optimus, other humanoid robots: report
Optimus is expected to be one of Tesla’s most ambitious projects, with Elon Musk estimating that the humanoid robot could be the company’s most important product.
A recent report has suggested that LG Energy Solution is in discussions to supply batteries for Tesla’s Optimus humanoid robot.
Optimus is expected to be one of Tesla’s most ambitious projects, with Elon Musk estimating that the humanoid robot could be the company’s most important product.
Humanoid robot battery deals
LG Energy Solution shares jumped more than 11% on the 28th after a report from the Korea Economic Daily claimed that the company is pursuing battery supply and joint development agreements with several humanoid robot makers. These reportedly include Tesla, which is developing Optimus, as well as multiple Chinese robotics companies.
China is already home to several leading battery manufacturers, such as CATL and BYD, making the robot makers’ reported interest in LG Energy Solution quite interesting. Market participants interpreted the reported outreach as a signal that performance requirements for humanoid robots may favor battery chemistries developed by companies like LG.
LF Energy Solution vs rivals
According to the report, energy density is believed to be the primary reason humanoid robot developers are evaluating LG Energy Solution’s batteries. Unlike electric vehicles, humanoid robots have significantly less space available for battery packs while requiring substantial power to operate dozens of joint motors and onboard artificial intelligence processors.
LG Energy Solution’s ternary lithium batteries offer higher energy density compared with rivals’ lithium iron phosphate (LFP) batteries, which are widely used by Chinese EV manufacturers. That advantage could prove critical for humanoid robots, where runtime, weight, and compact packaging are key design constraints.
News
Tesla receives approval for FSD Supervised tests in Sweden
Tesla confirmed that it has been granted permission to test FSD Supervised vehicles across Sweden in a press release.
Tesla has received regulatory approval to begin tests of its Full Self-Driving Supervised system on public roads in Sweden, a notable step in the company’s efforts to secure FSD approval for the wider European market.
FSD Supervised testing in Sweden
Tesla confirmed that it has been granted permission to test FSD Supervised vehicles across Sweden following cooperation with national authorities and local municipalities. The approval covers the Swedish Transport Administration’s entire road network, as well as urban and highways in the Municipality of Nacka.
Tesla shared some insights into its recent FSD approvals in a press release. “The approval shows that cooperation between authorities, municipalities and businesses enables technological leaps and Nacka Municipality is the first to become part of the transport system of the future. The fact that the driving of the future is also being tested on Swedish roads is an important step in the development towards autonomy in real everyday traffic,” the company noted.
With approval secured for FSD tests, Tesla can now evaluate the system’s performance in diverse environments, including dense urban areas and high-speed roadways across Sweden, as noted in a report from Allt Om Elbil. Tesla highlighted that the continued development of advanced driver assistance systems is expected to pave the way for improved traffic safety, increased accessibility, and lower emissions, particularly in populated city centers.
Tesla FSD Supervised Europe rollout
FSD Supervised is already available to drivers in several global markets, including Australia, Canada, China, Mexico, New Zealand, and the United States. The system is capable of handling city and highway driving tasks such as steering, acceleration, braking, and lane changes, though it still requires drivers to supervise the vehicle’s operations.
Tesla has stated that FSD Supervised has accumulated extensive driving data from its existing markets. In Europe, however, deployment remains subject to regulatory approval, with Tesla currently awaiting clearance from relevant authorities.
The company reiterated that it expects to start rolling out FSD Supervised to European customers in early 2026, pending approvals. It would then be unsurprising if the company secures approvals for FSD tests in other European territories in the coming months.
Tesla rolls out new Supercharging safety feature in the U.S.
LG Energy Solution pursuing battery deal for Tesla Optimus, other humanoid robots: report
