Category "notizie dai blog"

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 arandomized 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. 

It’s important for businesses to have the insights they need to drive more conversions on their websites. But rising expectations and regulations around user privacy can make it hard to meet both performance and privacy needs. We’re continuing to invest in solutions to help you find that balance.

Server-Side Tagging in Google Tag Manager allows you to move measurement and advertising tags off your website and into a secure server container. This helps protect your customers by restricting access to their information, and helps increase conversion rates on your site by reducing page load times.

To ensure all businesses can use this feature, Server-Side Tagging now works with any cloud or server provider that supports Docker — an open source platform for developing and running applications. We’ve also integrated Server-Side Tagging into more Google products and services to help you move more tags off your website and achieve better site performance. With these improvements, we’re moving Server-Side Tagging out of beta and making it generally available to all customers in Tag Manager and Tag Manager 360.

Support for more Google advertising products

Server-Side Tagging now supports Google Ads and Google Marketing Platform products, including Campaign Manager 360, Display & Video 360 and Search Ads 360. Previously, you had to continue using a client-side tag for each marketing product you use, and keep them all running directly on your site.

Now, when customers interact with your site, a single client-side tag can activate multiple tags for these products directly in your server container. This means you’ll have fewer tags on your site, which can help improve your site’s page load time.

Integration with other privacy solutions

Marketers often ask us how to use Server-Side Tagging with other privacy solutions like Consent Mode and enhanced conversions. Consent Mode helps you customize how Google tags behave before and after users make their consent decisions; and enhanced conversions help you use consented, first-party, user-provided data to better understand how users convert after engaging with your ads.

We’re now making it simpler to use these products together. Advertisers with Google Analytics 4 on their sites will soon be able to use enhanced conversions in Google Ads without needing to add additional tags to their site. And once you’ve set up Consent Mode, any Google tags implemented in your server container will automatically respect consent choices that users have made on your website.

We’re also making it easier for you to ensure that user data is handled according to your security preferences. Server-Side Tagging automatically anonymizes your users’ IP addresses before the information is shared with Google’s reporting tools. And in cases where you need more control, you have the option to eliminate users’ IP addresses from your data completely before they’re shared.

Success with Server-Side Tagging

Since launching Server-Side Tagging last year, we’ve seen businesses around the world use this feature to uphold higher expectations around user privacy and drive better marketing performance.

Nemlig, Denmark’s leading online grocer, saw a large rise in visitors to its site as people turned to online shopping and home delivery for their daily essentials last year. This resulted in longer page load times, which negatively impacted conversion rates on Nemlig’s site. After adopting Server-Side Tagging, the company was able to move tags from the browser into its secure server container, improving its page load time by 7%. Read the full story here.

Square has also found success with Server-Side Tagging. The San Francisco-based company helps businesses of all sizes reach buyers online and in person, manage their business and access financing. Since implementing Server-Side Tagging, Square has seen a 46% increase in reported conversions.

With Server-Side Tagging, you can improve both user trust and website performance. As we continue to work on new features and updates, our goal is to help you achieve your privacy and performance goals across all of your measurement needs.

More than half of the world’s spices originated from Indonesia. These spices not only flavor one of the world’s most diverse cuisines — they also influenced the culinary world as we know it, changing tastes around the globe.

Spice Up The World, a new destination on Google Arts & Culture, is a collaboration with the Indonesian Ministry of Tourism & Creative Economy and Indonesia Gastronomy Network. It features 45 immersive digital stories that dive into Indonesia’s 1,000-year history of spices and give you a taste of the delicious dishes that make up Indonesian gastronomy.  

Here’s a quick taste of 5 things you should know about Indonesian spices: 

1. Half the world’s spices originated from Indonesia

For over two decades of Search, we’ve been at the forefront of innovation in language understanding to help deliver on our mission of making the world’s information more accessible and useful for everyone. We’ve seen how critical these advancements are to making information more helpful, and being able to better connect people to creators, publishers and businesses on the web. It’s this constant improvement in understanding human language that’s enabled us to send more traffic to the web every year since Google was created.

We’ve also seen how AI models have significantly improved language innovation. Each successive milestone, from neural nets, to BERT, to MUM, has blown us away with the step changes in information understanding they’ve offered. But with each step forward, we look closely at the limitations and risks new technologies can present.

Across Google, we have been examining the risks and challenges associated with more powerful language models, and we’re committed to responsibly applying AI in Search. Here are some of the ways we do that.

Training on high quality data

We pretrain our models on high-quality data to reduce their potential to perpetuate undesirable biases that may exist in web content. In the case of MUM, we ensured that training data from the web was designated as high-quality based on our search quality metrics, which are informed by our Search Quality Rater Guidelines and driven by our quality rating and evaluation system. This substantially reduces the risk of training on misinformation or explicit content, for example, and is key to our approach.

And as part of our efforts to build a Search experience that works for everyone, MUM was trained on over 75 languages from around the world.

Rigorous Evaluation

Every improvement to Google Search undergoes a rigorous evaluation process to ensure we’re providing more relevant, helpful results. Our Search Quality Rater Guidelines are our north star for how we evaluate great search results. Human raters follow these guidelines and help us understand if our improvements are better fulfilling people’s information needs.

This evaluation process is central to the responsible application of any improvement to Search, whether we’re introducing powerful new systems like BERT or MUM, or simply adding a new feature.

Some changes are bigger than others, so we have to adjust our process accordingly. At the time of its introduction to Search, BERT impacted 1 in 10 English-language queries, so we scaled our evaluation process to be even more rigorous than usual. We subjected our systems to an unprecedented amount of scrutiny, increasing both the scale and granularity of quality testing, to help ensure they weren’t introducing concerning patterns into our systems.

While our standard evaluation process helps us judge launches across a representative query stream, for some improvements, we also more closely examine whether changes provide quality gains or losses across specific slices of queries, or topic areas. This allows us to identify if concerning patterns exist and pursue mitigations before launching an improvement to Search.

Search is not perfect, and any application of AI will not be perfect — this is why any change to Search involves extensive and constant evaluation and testing.

Responsible application design

In addition to working with responsibly designed and trained models, the thoughtful design of products and applications is key to addressing some of the challenges of language models. In Search, many of these critical mitigations take place at the application level, where we can focus on the end-user experience and more effectively manage risk in smaller models designed for specific tasks.

When we adopt new AI technologies such as BERT or MUM, they’re able to help improve individual systems to perform tasks more efficiently and effectively. This approach allows us to focus the scope of our evaluation and understand if an application is introducing concerning patterns. In the event that we do find concerning behavior, we’re able to design much more targeted solutions.

Minding our footprint

Training and running advanced AI models can be energy consumptive. Another benefit of training smaller, application-specific models is that the energy costs of the larger base model, such as MUM, are amortized over the many different applications.

The Google Research team recently published research detailing the energy costs of training state-of-the art language models, and their findings show that combining efficient models, processors, and data centers with clean energy sources can reduce the carbon footprint of a model by as much as one thousand-fold — and we follow this approach to train our models in Search.

Language models in practice

New language models like MUM have enormous potential to transform our ability to understand language and information about the world. And while they may be powerful, they do not make our existing systems obsolete. Today, Google Search employs hundreds of algorithms and machine learning models, none of which are wholly reliant on any singular, large model.

Amongst these hundreds of applications are systems and protections designed specifically to ensure you have a safe, high quality experience. For example, we design our ranking systems to surface relevant and reliable information. Even if a model were to present issues around low quality content, our systems are built to counteract this.

As we’re able to introduce new technologies like MUM into Search, they’ll help us greatly improve our systems and introduce entirely new product experiences. And they can also help us tackle other challenges we face. Improved AI systems can help bolster our spam fighting capabilities and even help us combat known loss patterns. In fact, we recently introduced a BERT-based system to better identify queries seeking explicit content, so we can better avoid shocking or offending users not looking for that information, and ultimately make our Search experience safer for everyone.

We look forward to making Search a better, more helpful product with improved information understanding from these advanced language models, and bringing these new capabilities to Search in a responsible way.