Shamie Kumar describes how AI fits into a radiology clinical workflow and her perspective on how clinical radiographers could use this to learn from and enhance their skills.

AI in radiology and workflow 

We all know that AI is already here, actively being implemented and used in many trusts in seeing its real world value supporting radiology departments to solve current challenges.Often this is focused on benefits to radiologist, clinicians, reporting radiographers, patients, and cost savings, but what about clinical non-reporting radiographers undertaking the X-ray or scans – can AI benefit them too?Let’s think about how AI is implemented and where are the AI outputs displayed?

If the AI findings are seen in PACS, how many radiographers actually log into PACS after taking a scan or X-ray? Good practice is seen to have PACS open to cross-check images that have been sent from the modality. Often this doesn’t happen for various reasons but maybe it should be a part of the radiographers’ routine practice, just like post-documentation is.

Can Radiographers Up-Skill?

Given the view it does happen, radiographers will have the opportunity to look at the AI outputs and potentially take away learnings on whether the AI found something that they didn’t see initially or whether there was a very subtle finding. We all know people learn through experience, exposure, and repetition, so if the AI is consistently picking up true findings, then the radiographer can learn from it too.

But what about when AI is incorrect – could it fool a radiographer, or will it empower them to research and understand the error in more detail?

As with many things in life, nothing is 100% and this includes AI in terms of false positive and false negatives. The radiographers have the opportunity to research erroneous findings in more detail to enhance their learning, but do they actually have time to undertake additional learning and steps to interpret AI?

CPD, self-reflection, learning through clinical practice are all key aspects of maintaining your registration, and self-motivation is often key to furthering yourself and your career. The question remains: are radiographers engaged and self-motivated to be part of the AI revolution and use it to their professional benefit with potential learnings at their fingertips?

There have been a few recent publications that share insight on how AI is perceived by radiographers, what is their understanding, training and educational needs.

Many Universities like City University London and AI companies like Qure.ai are taking the initial steps in understanding this better and taking active efforts in filling the knowledge gap, training and understanding of AI in radiology.

Radiographers who are key part of any radiology pathway, are yet to see the real-world evidence on whether AI can upskill radiographers, but there is no doubt this will unfold with time.

About Shamie Kumar

Shamie Kumar is a practicing HCPC Diagnostic Radiographer; graduated from City University London with a BSc Honors in Diagnostic Radiography in 2009 and is a part of Society of Radiographers with over 12 years of clinical knowledge and skills within all aspects of radiography. She studied further in leadership, management, and counselling with a keen interest in artificial intelligence in radiology.

Shamie Kumar describes her perspective on how radiography has evolved over time, the impact radiographers can have in detecting abnormal X-rays and reflects how she views fast approaching AI in advancing current skills.

 The red dot system 

Often one of the first courses a newly qualified radiographer attends is the red dot course. This course demonstrates pathologies and abnormalities often seen in x-rays some obvious, others not, giving radiographers the confidence to alert the referring clinician and/or radiologist that there is something abnormal they have seen. 

The red dot system is a human alert system, often 2 pairs of eyes are better than one and assist with near misses. How this is done in practice can vary between hospitals, in the era of films the radiographer would place a red dot sticker on the film itself before returning it to clinician or radiologist. In the world of digital imaging this is often done during ‘post documentation’ a term used once the x-ray is finished, the radiographer will complete the rest of the patient documentation to suggest the x-ray is complete, ready to be viewed and reported. As part of this process the radiographer can change the status of the patient to urgent along with a note for what has been observed. From this the radiologist knows the radiographer has seen something urgent on the image and the patient appears at the top of their worklist for reporting and, so the radiologist can view the radiographer’s notes. 

 The Role of AI in Radiology 

Artificial Intelligence (AI) is moving at a pace within healthcare and fast approaching radiology departments, with algorithms showing significant image recognition in detecting, characterisation and monitoring of various diseases within radiology. AI excels in automatically recognising complex patterns in imaging data providing quantitative assessments of radiological characteristics. With the numbers for diagnostic imaging requests forever increasing, many AI companies are focusing on how to ease this burden and supporting healthcare professionals. 

AI triage is done by the algorithm based on abnormal and normal finding’s this is used to create an alert for the referring clinician/radiologist. It can be customised to the radiologist, for example colour-coded flags, red for abnormal, green for normal, patients with a red flag would appear at the top of the radiologist worklist. For the referring clinicians who don’t have access to the reporting worklist, the triage would be viewed on the image itself with an additional text note suggesting abnormal or normal. 

What does AI do that a radiographer doesn’t already? AI is structured in the way it gives the findings for example a pre-populated report with its findings or an impression summary and its consistent without reader variability. So, the question now becomes what AI can do beyond the red dot system, here the explanation is straightforward, often a radiographer wouldn’t go to the extent of trying to name what they have seen, especially in more complex x-rays like the chest where there are multiple structures and pathologies. For example a radiographer would mention, right lower lobe and may not go beyond this, often due to confidence and level of experience. 

AI can fill this gap, it can empower radiographers and other healthcare professionals with its classification of pathologies identifying exactly what has been identified on the image, based on research and training of billions of data sets with high accuracy. 

The radiographers may have the upper hand with reading the clinical indication on the request form and seeing the patient physically, which undoubtable is of significant value, however the red dot system has many variables specific to that individual radiographer’s skills and understanding. It is also limited to giving details of what they have noted to just the radiologist, what about the referring clinician who doesn’t have access to the radiology information system (RIS) where the alert and notes are? Do some radiographers add a text note on the x-ray itself? 

Summary 

Yes, AI is a technological advancement of the red dot system and will continue to evolve. It is structured in how it gives the findings, it does this consistently with confidence. Adding value to early intervention, accurate patient diagnosis, contributing to reducing misdiagnosis and near misses. AI is empowering radiographers, radiologist, referring clinicians and junior doctors by enhancing and leveraging their current knowledge to a level where there is consistent alerts and classified findings that can even be learned from. This doesn’t replace the red dot system but indeed enhances it. 

The unique value a radiographer adds to the patient care, experience and physical interaction can easily be supplemented with AI, allowing them to alert with confidence and manage patients, focusing the clinician time more effectively. 

About Shamie Kumar 

Shamie Kumar is a practicing HCPC Diagnostic Radiographer; graduating from City University London, BSc Honors in Diagnostic Radiography in 2009 and part of Society of Radiographers with over 10 years of clinical knowledge and skills within all aspects of radiography. She studied further in leadership, management and counselling with a keen interest in artificial intelligence in radiology. 

Heart failure affects 6.2 million Americans each year, costing the US healthcare system $30.7 billion. Heart failure occurs when the heart cannot pump enough blood to meet the body’s needs. Early detection is critical in the treatment and management of heart failure. The use of AI in detecting heart failure on chest X-rays has the potential to improve the accuracy and speed of diagnoses significantly.

“I think AI has a great potential to help Radiology departments maintain their service levels with increasing workloads, allowing Consultant Radiologists to focus on more complex patient-facing cases." – Dr. Amrita Kumar  

Consultant Radiologist and AI Clinical Lead, Frimley Health NHS Foundation Trust