Caption. Impact type of nonaccidental trauma: 6-month-old boy. Axial CT scan shows right frontal depressed skull fracture (straight arrow) along with frontoparietal lobe contusion (arrowheads). Subgaleal hematoma is also present (curved arrow).
As technologies advance, patients gain more effective and precise medical imaging options. Both computerized axial tomography (CT or CAT scans) and magnetic resonance imaging (MRIs) have been used for decades. Yet their use is changing in exciting ways as computing advances allow thousands of images to be analyzed together.
Taipei Medical University Hospital Deputy Superintendent Sandy Cheng-Yu Chen explains: “With big image data, we can extract features from images to develop algorithms with machine learning. We can go to the pixel level to observe the smallest details of anatomical structure changes from genomic and molecular alternations, and predict histopathology-alike diagnoses based on evidence and algorithms – not our human experience.”
TMU’s studies are widely noted by research funders and scientific journals. Prof. Chen’s brain tumor study will soon appear in a top-ranked journal, Clinical Cancer Research. (See https://tmu.pure.elsevier.com/en/persons/cheng-yu-chen-2 for his 21 research projects and 231 publications.)
What the study’s model offers is predictive power based on both retrospective and prospective studies. This knowledge can spare patients uncomfortable and invasive diagnostic techniques such as biopsies: “If we follow hundreds or thousands of people through the course of a disease, or who experience similar types of trauma, then we will know how long they lived. We analyze their images, genomic, survival data and other case factors to look for patterns.
“With this [imaging] data, we don’t even need to biopsy to understand how a tumor is likely to behave, based on the facts of how long patients with similar neoplasms survived. I can extrapolate outcomes – just like a fortune teller! – based on separate groups of similar cases.”
TMU received the highest rating of dozens of institutes applying for Ministry of Science and Technology (MOST) support. “This [imaging and artificial intelligence] project came to TMU based on its history of productive work in this area, but also based on our access to a huge archive of data resources,” Prof. Chen said. “It’s a huge, heavy artificial intelligence job.”
Another reason MOST chose TMU was the university’s decades of leadership in traumatic brain injury. A TMU-led alliance with several major hospitals followed 600 trauma patients for six years, and revealed disturbing patterns following even “mild” injuries.
“While concussion seems ‘mild’ in terms of treatment and immediate outcomes – with maybe a week of rest prescribed as treatment – there is great concern about later-onset dementia” and other effects that may take years to emerge, Prof. Chen said. Other research modes benefit from improved imaging technologies as well: “At TMU we also analyze brain injuries in rats, notably by using a very powerful imaging tool, a seven-Tesla MRI.”
Imaging advances can change clinical practices as well, he said: “We physicians love the new artificial intelligence techniques. Yet we also see how they might be able to do our jobs in the future – and radiology is likely to be one of the first [medical subfields] to be mechanized.”
This leadership shows how TMU is prioritizing artificial intelligence, imaging and big data innovations to search for new treatments for injuries and illnesses.
Visit Taipei Medical University for further information.