The other day, a simple request from my daughter to help her craft a kids' wind chime turned into an unexpected journey of self-discovery and reflection. What began as a fun little project quickly unfolded into a task demanding serious concentration and dishing out a healthy dose of frustration.

In a fascinating development in medical imaging technology, Jingya Liu and colleagues have introduced an innovative method that could revolutionize how contrast-enhanced CT scans are performed. Published in the notable journal 'Computational Medicine and Imaging Graphics', their research unveils a generative adversarial network (GAN) framework capable of creating virtual contrast-enhanced CT images directly from non-contrast scans.

I read a lot, and most of the time, there's a specific reason behind my choice of books—be it seeking knowledge or inspiration. However, on rare occasions, I indulge in reading purely as a hobby. One such occasion recently led me to a treasure trove of inspiration and admiration.

We are in the eye of the hurricane, but in recent months this knowledge has become more and more unconscious. While the world was initially fascinated or shocked by the first release of ChatGPT, it soon kind of forgot about its steady presence and the continuous development of various AI technologies around us. This isn't just a technological revolution; it's a societal one, and it brings with it many questions about our values and moral integrity as a community.

As a scientist, there are different audiences for whom you might write. Audience number one is your scientific community niche—colleagues who are as expert as you are. For them, you don't need to simplify terms or assume a lack of knowledge. Then there's a newer audience for many scientists: the general public.

The number of radiology AI solutions released in recent years seems virtually uncountable. There is an overwhelming array of tools capable of detecting findings in CT and MRI scans, alongside an ever-increasing number of tools designed to enhance workflow efficiency.

Critics argue that our unrelenting desire for safety and certainty drives us toward new, better, and inevitably more expensive medical diagnostics to determine if we're genuinely healthy or if some form of cancer lurks within us. Supporters contend that it's another significant step toward a personal mindset that values preventive medicine and is willing to invest in health and longevity.

Healthcare services have improved globally over the last few centuries. Of course, this improvement has occurred at varying paces and levels across different regions, but generally, we are all moving in the same direction: toward longer and healthier lives than ever before.

My focus on AI is primarily in radiology, given my background, so I acknowledge a certain bias in my perception of how extensively AI is utilized in clinical settings (though "extensively" might be an overstatement considering the current minimal routine use of AI in radiology). This is why the survey conducted by Giannitto and his team from Italy particularly caught my attention.

Do you remember the days when patients typed their symptoms into Google and were directed to various websites offering a mix of advice, both good and bad? Then, they would visit their doctors, hoping to confirm what they had learned online. Those days are nearly over - TikTok is quickly becoming the go-to platform for healthcare advice.

The vast potential of interpretative AIs is often celebrated in conference talks and research papers. However, a closer look at the actual numbers can be quite sobering: the use of AI in radiology is still struggling to take off. The primary reason? It simply does not deliver enough value to offset the costs and time invested in acquiring the AI.

Imagine this scenario: you’re on a plane, buckling up due to turbulence, when suddenly, you decide to ignore the flight attendants. Instead, you stroll up to the cockpit and suggest to the pilot—based on your grand aunt’s recent advice—that flying backwards might just be the superior strategy during turbulence.

ermanent loud noises in an enclosed space and coils wrapped around your body - this sums up the discomfort each patient faces in an MRI, and for some, it's an actual nightmare. Understanding not only the needs and fears of our patients but also discovering if there's a pattern or structure behind this fear is crucial. A deeper understanding will enable tailored interventions to alleviate the fear associated with this diagnostic gold standard.

We're living in fascinating times for entrepreneurship in healthcare. There's a boom of startups sprouting up everywhere, much like mushrooms in the forest during autumn. However, just like those mushrooms, a staggering 98% of these startups tend to disappear or fail [1]. But why is this the case? What are the hurdles stopping so many brilliant ideas from succeeding?

If you're a radiologist, you definitely know the feeling of absolutely loathing your phone. That little device just keeps interrupting your flow with its same old annoying ring, and after a while, it gets to the point where it makes you jump every time it rings. But beyond being super annoying and bossy, this piece of tech actually causes real issues by seriously affecting the error rate in many imaging departments.

The rise of patient portals and the ubiquity of 'Dr. Google' have brought many benefits but also some notable challenges. Patients now have easier access to their medical records, which empowers them to take ownership of their health journey. However, the complexity of medical terminology often poses a barrier to those without a medical background. What happens then is that patients try to figure it out themselves using the resources available: Dr. Google and some friend of a friend who has heard something about this topic.

Medical imaging is a significant consumer of energy, a fact that becomes startlingly clear when you learn it accounts for about 1% of greenhouse gas (GHG) emissions. The primary culprits have been the production and operation of MRI, CT, and other similar equipment. Now, AI's rapidly increasing energy demand is joining the ranks. We're at a crossroads of innovation and climate change, a classic double-edged sword.

It has been almost 3 months now since Open AI launched their GPT store where you can get customized GPTs that are tailored to a specific task. If you are on the premium subscription this feature is available for you.

I just finished the really great book “Steal like an Artist” by Austin Kleon. It’s full of many great and very inspiring thoughts, but what really stuck in my mind was this one particular figure. Funnily enough, he obviously based it on a strong inspiration from a friend. So, in a way, he basically stole it.

In my personal opinion MRI is one of the greatest technological achievements of all time and definitely one of the methodologies in radiology that most fascinate me. We can really look into bodies and analyze the consistency of tissue! We can even tell if there is inflammation or not or if there are areas in your brain that lack oxygen (or to be more exact and really nerd it out: have lacked oxygen for too long time). So basically from a physicians point of view this machine is just perfect.