Technology evolves in rather unique ways and for rather unusual reasons, and nothing embodies this principle in medical imaging more than how an early AI-driven cancer detector originated as a way to tell pastries apart.

To explain why, it is important to understand the need for an AI scanner for bakeries in the first place.

Starting in the mid-2000s, artisan bakeries and patisseries were becoming very popular in Japan but quickly became a victim of their own success when people queued up around the block to pick up cakes, sandwiches and pastries, leaving the staff overwhelmed.

Automation could help here, but fresh pastries could not have a barcode applied to them, and wrapping them up could make it appear as though they are not actually fresh baked goods.

The solution, therefore, was BakeryScan, an AI scanner that can detect the type and quantity of baked goods on a tray, identifying often variable products by common key characteristics.

Once sufficiently trained, BakeryScan was remarkably accurate, even compared to other machine learning algorithms, and this led a doctor working for the Louis Pasteur Center for Medical Research in Kyoto to have a moment of inspiration.

Cancer cells viewed on a slide via a biopsy do not look entirely dissimilar to baked goods, so if the underlying technology could detect different types of bread, perhaps it could identify different types of cancer.

This led to the development of AI-Scan, a more variable form of the technology that could learn very quickly the different types of cells that could be cancerous from training data and provide at least a starting point if not an outright confirmation for a doctor by scanning an entire slide at once.

The system did not work the same way as modern deep learning and machine learning algorithms, but it highlighted that the biggest benefit of AI-powered medical imaging equipment was not just accuracy but speed.

Artificial intelligence (AI) has been playing an increasingly significant role in the healthcare sector in recent years, particularly when it comes to machine learning (ML). 

ML involves analysing a substantial quantity of data to make informed decisions, or in the case of the medical sector, coming up with a diagnostic formula. The more the software is used, the more precise the outcomes are, as ML is exposed to increasing numbers of statistics. 

The good thing about using ML is that it can look at huge amounts of data, such as tens of thousands of patients and millions of molecular biomarkers, to create an accurate analysis.

Being able to digest this information, including structured and unstructured data, as well as variations or inefficiencies in the result, it can identify patterns using complex datasets. 

This means it can identify what combination of genetic and epigenetic biomarkers are associated with particular diseases.

This helps when it comes to diagnostics, as it can draw conclusions from this data or probabilities of developing health conditions in the future. Therefore, doctors can take immediate action in treating patients or using preventative interventions to reduce their risk of falling ill. 

This also means patients who are deemed high risk can be seen quickly, and hospitals have a better understanding of how to prioritise their resources. 

ML, therefore, can make conclusions much more quickly than a human can, which means it can help with earlier detection, boosting the success rate of treatments. 

It is also able to create care plans and tailor them to individual patients so they receive the most appropriate medical intervention. By using the patient’s biomarkers and risk factors, it can estimate drug responses and assign the most effective course of treatment.

To find out more about cloud medical image storage for use in machine learning, get in touch with us today.

Whilst many radical revolutions in medical imaging are focused on new approaches to designing imaging machines and taking advantage of machine learning to allow for accurate results with less expensive and intensive machines, there are other, even more fascinating use cases being explored.

One of the most fascinating implementations of accurate three-dimensional medical imaging technologies such as computed tomography and magnetic resonance imaging is found in the Mayo Clinic’s 3D anatomic modelling laboratory.

This laboratory converts accurate medical images into personalised, detailed models using three-dimensional printing, allowing for tactile visual aids to help patients understand potential procedures. However, researchers at Mayo Clinic are exploring the potential to go even further than accurate impressions.

The research team is exploring the potential of using a 3D bioprinter, which uses biocompatible cell structures to “print” tissue structures that could be used for research and potentially even therapeutic purposes.

Because these models would effectively be alive, they could be used to help in the study of the progression of diseases and screen for a range of conditions such as the final stages of organ failure, defects in bone and cartilage density and inflammation.

Its use in disease models would allow for more focused laboratory testing of treatments and medication in close to real-world conditions, but it could go beyond this and potentially lead to treatments in and of itself.

The end goal for the research team is to check the technology’s feasibility for bioprinting tissue and potentially even functioning organs.

The implications of this technology if it were to successfully bioprint organs is almost impossible to comprehend but the complex nature of organ structures has currently made such an ambition extremely challenging.

Networks of blood vessels need to be printed at scale, something that the current bioprinted structures have struggled with.

As well as this, there is the issue of potential organ rejection, which is a problem with transplantation in general, but were it to be overcome, it could potentially change the world.

Although there is lots of innovative technology available these days, it can often take a long time before it is implemented in the NHS. This is why NICE, together with NHS England, have launched proposals to fast-track funding for these innovations, which could provide a big boost to the service. 

Patients, clinicians, and academics are being invited to leave feedback on the proposals as part of a consultation, which will run for 12 weeks. 

Mark Chapman, director of the Health Technologies Programme at NICE, said medical technology, such as online radiology reporting, is developing so quickly that products need to be adopted at a faster rate by the NHS to be able to provide the best care. 

“This new pathway aims to ensure that patients in every area of the country can benefit from the best products, devices, digital technologies, or a diagnostic innovation,” he stated.

Automated funding means there would be routine commissioning for products as long as they meet certain criteria, which will provide MedTech developers with certainty they will receive NHS funding for their innovations. 

The consultation is expected to close at midnight on Thursday August 15th, with Dr Vin Diwakar, interim medical director for transformation at NHS England, saying it is hoped both the public and those in the industry will provide feedback to develop the MedTech pathway. 

This, he comments, will ensure the outcome will benefit patients in the best way possible.

NHS England recently announced an investment of £1 million to improve access to patient data across seven trusts. 

The Wireless Trials programme is intended to provide a secure and fast solution to network accessibility and connectivity. This will mean clinicians can see data much more quickly and they will not have to do as many administrative tasks that take away time with their patients.

Medical imaging has been a critical part of diagnosing unseen illnesses and injuries for over a century, and yet despite this, the evolution of imaging technologies has only intensified over the years.

The most recent developments involve the use of artificial intelligence to help streamline and speed up the process of creating medical images and detecting samples which have the potential to display markers of diseases.

However, even as early as the first X-ray, there have been myths and misconceptions about the technology, as well as common beliefs that are not quite true.

Here are some of the most common and the truth behind them.

MRIs Do Not Generate Radiation

Given that the first diagnostic imaging technology was the X-ray, and systems such as CT scans rely heavily on radiography to function, there is an assumption that any diagnostic equipment also involves radiation.

However, that is not the case when it comes to MRI. Short for magnetic resonance imaging, MRI scans do not use radiation but instead use a strong magnetic field and radio waves to create images of the body.

As well as this, ultrasound scanners use sound waves rather than radiation to generate images.

Ultrasounds Are Highly Versatile

There is a perception that ultrasounds are only used for scans on pregnant women, but they are also a fast, effective baseline scan used to check abdominal organs, blood vessels, the heart and even the joints and muscles.

X-Rays Are Still Evolving

The first X-ray was generated by accident in 1895, but do not confuse this century of history with an antiquated approach, as X-rays are not only a widely used technology but one that is rapidly developing and at the cutting edge of diagnostic technology.

The technology is still used to provide quick, affordable imaging results when a basic scan of the body is all that is needed, with digital X-rays providing even more efficient results.

Beyond this, X-rays are a core component of computer tomography (CT) scans, which work by essentially taking X-ray scans at multiple angles and splicing the results using highly advanced computers.