Dr. Joel Arun Sursas Discusses Artificial Intelligence in Imaging

Radiologists and pathologists depend on extensive training, expertise, and experience when interpreting X-rays, CAT scans, MRIs, and other testing images. However, even the most skilled and thorough human user is limited by the physical limitations all of us deal with. Modern advances in artificial intelligence and machine learning are rapidly becoming vital to supplementing and supporting human users. In some critical ways, artificial intelligence can provide results that are beyond the capacity of any human user. In this article, Dr. Joel Arun Sursas discusses some recent developments in the use of artificial intelligence in medical imaging.


Artificial Intelligence and Cardiovascular Imaging

Patients who present with symptoms indicating the possibility of a heart-related disease are routinely given chest radiograph imaging immediately. This initial imaging serves as a useful initial screening tool for heart disease. However, initial human assessments in these situations can be inaccurate. Artificial intelligence tools can quickly and accurately identify classic problems with specific heart structures, allowing cardiologists to prioritize their analysis of the imaging. Algorithms and other analytical software can quickly produce reports and point out any abnormal findings for immediate use by cardiologists and emergency care providers.

Using Artificial Intelligence In Imaging of Bone Fractures and Musculoskeletal Injuries

Many fractures, dislocations, and soft tissue injuries are well-known to be hard to see and interpret accurately by human users. Assessment of trauma patients often initially focuses on higher priority injuries than bone fractures, such as organ damage and internal bleeding. Using artificial intelligence analysis of musculoskeletal injuries can be very useful in supplementing an immediate treatment plan with necessary information regarding the need for stabilization or surgery. Artificial intelligence analysis is also beneficial in follow up treatment for procedures like joint replacements.

Artificial Intelligence and Common Cancer Screenings

Medical imaging is an integral part of many preventive and routine cancer screenings. Many cancer tissues are notoriously difficult to identify conclusively through imaging. Misreadings can lead to unnecessary additional testing or can result in the serious problem of missed malignancy. Artificial intelligence is instrumental in increasing consistency and accuracy in measuring and classifying abnormal imaging. Artificial intelligence can help level the outcomes between more experienced and less experienced radiologists.

Why Artificial Intelligence Is Not Ready to Replace Humans

Radiologists have been at the forefront of the development of artificial intelligence technology in medical imaging. As the amount of data collected has continued to grow at an amazing rate, the sensitivity of imaging hardware continues to improve. It is more capable of capturing information not detectable by the human eye. Neurological, musculoskeletal, cardiovascular, lung, and abdominal imaging are all advancing in ways not imaginable even in the recent past. Artificial intelligence will continue to be central to processing and interpreting medical imaging, but it will not be replacing human users anytime soon. Humans are still needed to finalize interpretations, consult and communicate regarding diagnoses, work directly with patients, and use professional judgment. Artificial intelligence in medical imaging is a fantastic tool. Still, it is not ready to pass the Turing test (a test to determine if a computer processor has true human capabilities in addition to mechanical powers of observation) yet.

About Dr. Joel Arun Sursas

Dr. Joel Arun Sursas is a Medical Doctor and Health Informatician and works tirelessly at solving administrative problems in healthcare through the design and implementation of advanced medical information technologies. He facilitates technological advances between doctors and engineers to improve patient outcomes through improved monitoring while protecting patient privacy. His interest in the field of Medical Informatics emerged when he began working as a Project Officer for PACES — the Patient Care Enhancement System for Singapore Armed Forces (SAF). Dr. Sursas holds degrees in Medicine and Surgery from the National University of Singapore and is currently working on post-graduate Health Science Informatics from Harvard Medical School and Johns Hopkins University. He is currently engaged with Biorithm, a medical device start-up company as Head of Clinical Affairs.


  1. Pesapane, F., Codari, M., & Sardanelli, F. (2018). Artificial intelligence in medical imaging: threat or opportunity? Radiologists again at the forefront of innovation in medicine. European radiology experimental, 2(1), 35. DOI:10.1186/s41747-018-0061-6.
  1. Hosny, A., Parmar, C., Quackenbush, J., Schwartz, L. H., & Aerts, H. (2018). Artificial intelligence in radiology. Nature reviews. Cancer, 18(8), 500–510. DOI:10.1038/s41568-018-0016-5.