A new study has found a growing connection between pathology and radiology. According to researchers at the University of Pennsylvania and the Scripps Research Institute, the two specialties should be combined into one role called the “information specialist.” Not only would this individual interpret diagnostic images, but they would oversee artificial intelligence disease-screening technology.
Since the dawning of the specialty, radiologists have come to rely on computers to make accurate assessments. The study authors hypothesize that since interpreting these images is a form of pattern recognition, we should use automated computer systems to identify and assess patterns in diagnostic images.
Over the years, radiologists’ imaging responsibilities have grown more complex and challenging. “The abundance of data has changed how radiologists interpret images; from pattern recognition, with clinical context, to searching for needles in haystacks; from inference to detection,” they write. “The radiologist, once a maestro with a chest radiograph, is now often visually fatigued searching for an occult fracture in a pan scan.” These changes, the researchers attest, indicate that radiologists should give their work to computers, and in turn, radiologists should spend their time managing AI systems “in the clinical context of the patient.”
How will radiologists and pathologists work in conjunction with AI? Take for example, screening lung cancer. An AI program could detect, measure, and characterize a lung nodule. The “information specialist” would manage these results and determine the next steps.
If pigeons are capable of detecting roentgenographic patterns, then radiologists might be able to pivot their role in the diagnostic imaging arena. “The history of automation in the broader economy has a reassuring message,” write the researchers. “Jobs are not lost; rather, roles are redefined; humans are displaced to tasks needing a human element. Radiologists and pathologists need not fear artificial intelligence but rather must adapt incrementally to artificial intelligence, retaining their own services for cognitively challenging tasks.”