Connect with us

Google

The promise of using AI to help prostate cancer care

In 2021, nearly 250,000 Americans will be diagnosed with prostate cancer, which remains the second most common cancer among men in the U.S. Even as we make advancements in cancer research and treatment, diagnosing and treating prostate cancer remains difficult. This National Prostate Cancer Awareness Month, we’re sharing how Google researchers are looking at ways…

Published

on

In 2021, nearly 250,000 Americans will be diagnosed with prostate cancer, which remains the second most common cancer among men in the U.S. Even as we make advancements in cancer research and treatment, diagnosing and treating prostate cancer remains difficult. This National Prostate Cancer Awareness Month, we’re sharing how Google researchers are looking at ways artificial intelligence (AI) can improve prostate cancer care and the lessons learned along the way.  

Our AI research to date 

Currently, pathologists rely on a process called the ‘Gleason grading system’ to grade prostate cancer and inform the selection of an effective treatment option. This process involves examining tumor samples under a microscope for tissue growth patterns that indicate the aggressiveness of the cancer. Over the past few years, research teams at Google have developed AI systems that can help pathologists grade prostate cancer with more objectivity and ease. 

These AI systems can help identify the aggressiveness of prostate cancer for tumors at different steps of the clinical timeline — from smaller biopsy samples during initial diagnosis to larger samples from prostate removal surgery. In prior studies published in JAMA Oncology and Nature Partner Journal Digital Medicine, we found our AI system for Gleason grading prostate cancer samples performed at a higher rate of agreement with subspecialists (pathologists who have specialized training in prostate cancer) as compared to general pathologists. These results suggest that AI systems have the potential to support high-quality prostate cancer diagnosis for more patients. 

To understand this system’s potential impact within a clinical workflow, we also studied how general pathologists could use our AI system during their assessments. In a randomized study involving 20 pathologists reviewing 240 retrospective prostate biopsies, we found that the use of an AI system as an assistive tool was associated with an increase in grading agreement between general pathologists and subspecialists. This indicated that AI tools may help general pathologists grade prostate biopsies with greater accuracy. The AI system also improved both pathologists’ efficiency and their self-reported diagnostic confidence. 

In our latest study in Nature Communications Medicine, we directly examined whether the AI’s grading was able to identify high-risk patients by comparing the system’s grading against mortality outcomes. This is important because mortality outcomes are one of the most clinically relevant results for evaluating the value of Gleason grading, ensuring greater confidence in the AI’s grading. We found that the AI’s grades were more strongly associated with patient outcomes than the grades from general pathologists, suggesting that the AI could potentially help inform decision-making on treatment plans. 

Contributing to reducing variability in AI research 

We first began training our AI system using Gleason grades from both general pathologists and subspecialists. As we continued to develop AI systems for assisting prostate cancer grading, we learned that both training the AI and evaluating the model’s performance can be challenging because often the “ground truth” or reference standard is based on expert opinion. Because of this subjectivity, for some cases, two pathologists examining the same sample may arrive at a different Gleason grade.

To improve the quality of the “ground truth”, we developed a set of best practices that we have shared this week in Lancet Digital Health. These recommendations include involving experienced prostate pathology experts, making sure that multiple experts look at each sample, and designing an unbiased disagreement resolution process. By sharing these learnings, we hope to encourage and accelerate further work in this area, particularly in earlier-phase research when it’s impractical to train or validate a model using patient outcomes data.

Our research has shown that AI can be most helpful when it’s built to support clinicians with the right problem, in the right way, at the right time. With that in mind, we plan to further validate the role of AI and other novel technologies in helping improve prostate cancer diagnosis, treatment planning and patient outcomes. 

Source

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published.

Google

Enjoy a warm cup of trends for International Tea Day

From bubble tea to tea ceremonies, tea has deep roots and profound cultural significance across Asia. Just ahead of the United Nations’ International Tea Day on Saturday, May 21, we looked at trends on Google Search around the world and found bags of insights into what the world is searching for when it comes to…

Published

on

By

From bubble tea to tea ceremonies, tea has deep roots and profound cultural significance across Asia. Just ahead of the United Nations’ International Tea Day on Saturday, May 21, we looked at trends on Google Search around the world and found bags of insights into what the world is searching for when it comes to this brew-tea-full beverage.

Worldwide populari-tea

Assam, green or bubble: tea is the world’s most-consumed drink apart from water, so even if Earl Grey isn’t your thing, there’s most likely a brew out there that fits you to a T. But which types of tea are the most popular?

  1. Bubble tea
  2. Green tea
  3. Matcha
  4. Black tea
  5. Milk tea
  6. Kombucha
  7. Masala chai
  8. Iced tea
  9. Hibiscus tea
  10. Ginger tea

Worldwide top-searched types of tea, past 12 months. Source: Google Trends.

Green tea used to be the most popular type of tea on Search — until last year, when bubble tea bubbled up to become the most-searched type of tea around the world. The rise has been remarkable, with search interest for bubble tea more than tripling in the last five years, an increase of +220% worldwide. We’ve seen a similar trend with matcha; the beverage is now the world’s third most popular type of tea after search interest went up by +70% in the last five years.

Source

Continue Reading

Google

Protecting Android users from 0-Day attacks

To protect our users, Google’s Threat Analysis Group (TAG) routinely hunts for 0-day vulnerabilities exploited in-the-wild. In 2021, we reported nine 0-days affecting Chrome, Android, Apple and Microsoft, leading to patches to protect users from these attacks.This blog is a follow up to our July 2021 post on four 0-day vulnerabilities we discovered in 2021,…

Published

on

By

To protect our users, Google’s Threat Analysis Group (TAG) routinely hunts for 0-day vulnerabilities exploited in-the-wild. In 2021, we reported nine 0-days affecting Chrome, Android, Apple and Microsoft, leading to patches to protect users from these attacks.

This blog is a follow up to our July 2021 post on four 0-day vulnerabilities we discovered in 2021, and details campaigns targeting Android users with five distinct 0-day vulnerabilities:

We assess with high confidence that these exploits were packaged by a single commercial surveillance company, Cytrox, and sold to different government-backed actors who used them in at least the three campaigns discussed below. Consistent with findings from CitizenLab, we assess government-backed actors purchasing these exploits are located (at least) in Egypt, Armenia, Greece, Madagascar, Côte d’Ivoire, Serbia, Spain and Indonesia.

The 0-day exploits were used alongside n-day exploits as the developers took advantage of the time difference between when some critical bugs were patched but not flagged as security issues and when these patches were fully deployed across the Android ecosystem. Our findings underscore the extent to which commercial surveillance vendors have proliferated capabilities historically only used by governments with the technical expertise to develop and operationalize exploits.

Seven of the nine 0-days TAG discovered in 2021 fall into this category: developed by commercial providers and sold to and used by government-backed actors. TAG is actively tracking more than 30 vendors with varying levels of sophistication and public exposure selling exploits or surveillance capabilities to government-backed actors.

Source

Continue Reading

Google

Why this Pixel engineer chose Google Taiwan

Welcome to the latest edition of “My Path to Google,” where we talk to Googlers, interns, apprentices and alumni about how they got to Google, what their roles are like and even some tips on how to prepare for interviews.Today’s post is all about Gordon Kuo, a Taiwan-based engineer on the Pixel Mobile Wireless Team.…

Published

on

By

Welcome to the latest edition of “My Path to Google,” where we talk to Googlers, interns, apprentices and alumni about how they got to Google, what their roles are like and even some tips on how to prepare for interviews.

Today’s post is all about Gordon Kuo, a Taiwan-based engineer on the Pixel Mobile Wireless Team. He shares what makes Google Taiwan a unique place for engineers to work and advice for anyone interested in applying to Google.

What’s your role at Google?

I’m an engineering lead on the Pixel Mobile Wireless team. Our goal is to help connect people across the world with Google Pixel phones. We solve hardware and software challenges and work with different teams to improve functionality and performance. We talk about everything from design and bug fixes to performance optimization, which makes every day feel different. I love that no matter what we’re working on, it’s always interesting and helpful.

How did you land in your current role?

After completing my PhD in Computer Networking, I started my career at a Taiwanese integrated circuit (IC) design company. After that, I worked on modems at a technology company in China for several years. During that time, I had a few friends and former colleagues at Google, and when we spoke about their jobs and the company culture, everyone shared really positive experiences. Getting the chance to build a career around work that I enjoy was one of the biggest draws. So I applied and interviewed — and now, two years in, I’m leading a team.

What was your application and interview experience like?

Above everything, my recruiter was really supportive, which helped make the process feel much more straightforward. I actually applied and interviewed for another engineering position at first, but I didn’t end up getting it. I was disappointed at the time, but it wasn’t long before my recruiter shared another position that was even more aligned with my skills and career goals. Finding the right fit doesn’t always happen right away, and I appreciated that my recruiter was so committed to setting me up for success.

What have you learned about leadership since joining Google?

Google is a place where people truly listen and communicate openly. Because of this, I’ve learned to never assume anything. Instead, I put in the time to better understand my team and others we work with. It’s important to stay on the same page when you’re leading a team or project, and that requires respect and regular communication.

What makes Google Taiwan such a special place to work?

Taiwan is home to world-class integrated circuit design companies and is known for its thriving manufacturing industry. There’s a lot of exciting product development work happening here too, and it’s one of our largest sites in Asia. In fact, Taiwan is our largest hardware hub outside of the U.S. — with an engineering team that is uniquely skilled in both software and hardware integration. We collaborate with other functions and teams worldwide, and have opportunities to lead important projects from start to finish. From working on widely used products to building and leading a team, I’ve had growth opportunities here that I couldn’t have imagined just a few years ago. I’m continually inspired by the work we do.

On a more personal note, Taiwan is a relatively small island, easy to get around and nestled between the beach and the mountains — it’s a pretty nice place to work!

You recently participated in a live-streamed event about career opportunities at Google Taiwan. Can you tell us more about that?

The event was aimed at helping potential candidates learn more about technical career opportunities at Google Taiwan and what it’s like to work with us. I really enjoyed the conversation! If anyone is interested, they can watch the recording.

What advice do you have for aspiring Googlers?

Work closely with your recruiter! My recruiter guided me through Google’s interview process, shared tips about how to answer leadership-based questions and gave me insight into what the technical interview would be like. I hadn’t experienced this kind of interview support and care before, and it went a long way in helping me prepare. If you’re applying for an engineering role, I recommend doing programming exercises to practice your coding abilities. I also revisited my textbooks to review material, brushed up on my skills and searched for tips online from previous interviewees. Going through an interview process can be nerve-wracking, but the best thing you can do is just go for it.

Source

Continue Reading

Trending

Copyright © 2021 Today's Digital.