The rapid advancement of Artificial Intelligence (AI) in radiology is set to revolutionise the healthcare sector, with experts predicting a surge in its application over the next decade.
Dr Henno Schoombee, a seasoned radiologist at SCP Radiology, sheds light on the transformative power of AI in the realm of medical imaging.
"We have been using AI a lot longer than most people realise," Dr Schoombee says, noting that the technology is poised for a significant growth spurt. "I believe that after 10 years we are at the bottom of a growth curve which is about to take off."
AI in radiology encompasses a vast array of algorithms, machine learning tools, and sophisticated neural networks. These tools are not only transforming image acquisition and interpretation, but also streamlining workflow, enhancing report accuracy, and improving communication of results.
One of the stand-out features of AI in radiology is the AI-powered Natural Processing Language (NPL).
This technology enables computers to understand text and spoken words similarly to humans.
NPL tools can extract relevant information from radiology reports, enhance documentation accuracy and facilitate data mining for research purposes," Schoombee explained.
Deep learning, a subset of AI, is particularly promising. It allows for the analysis of vast volumes of medical images at unprecedented speeds, enabling radiologists to detect diseases such as cancer, strokes, and fractures with heightened precision. "Deep learning can interpret thousands of existing images, together with their diagnoses, to apply in future diagnoses," he added.
The benefits of AI are manifold.
For patients, automated image triage systems can prioritise urgent cases, ensuring timely care.
For radiologists, AI assists in routine tasks, saving invaluable time.
"One of the most important applications is faster, more accurate results," Schoombee emphasised, highlighting the importance of clinician-AI collaboration.
AI's tangible impact is evident in its ability to detect anomalies that might otherwise be overlooked.
From detecting lumps in mammograms before they become visible, through to identifying hairline fractures, AI is proving indispensable.
"One of the greatest time-savers is automatic measuring by AI," Schoombee said, though he stressed that findings must still be validated by a radiologist.
Addressing the looming question of whether AI will ever replace radiologists, Schoombee was optimistic.
"Never say ‘never’, but I don’t believe so," he said, adding that we should see AI more as a tool to enhance patient care, rather than replace human expertise.
Looking ahead, the future of radiology is bright, with AI set to empower radiologists with robust tools to improve diagnostics and patient care. SCP Radiology, where Schoombee practices, has been at the forefront of medical imaging in the Western Cape since 1950 and is poised to continue its legacy of innovation.