How Can Artificial Intelligence Change Medical Imaging?  

Advancing medical screenings

By using AI in medical imaging, physicians can identify conditions much quicker, promoting early intervention.

At Tulane University, researchers discovered that AI can accurately detect and diagnose colorectal cancer by analyzing tissue scans as well or better than pathologists.

The purpose of this study was to determine whether artificial intelligence could be a tool to assist pathologists in keeping up with the rising demand for services.

According to the researchers, pathologists regularly evaluate and label thousands of histopathology images to identify whether a patient has cancer. However, their average workload has significantly increased, which could lead to unintended misdiagnoses.

“Even though a lot of their work is repetitive, most pathologists are extremely busy because there’s a huge demand for what they do but there’s a global shortage of qualified pathologists, especially in many developing countries,” Professor and Director of the Tulane Center of Biomedical Informatics and Genomics at Tulane University School of Medicine, Hong-Wen Deng, PhD, said in a press release.

“This study is revolutionary because we successfully leveraged artificial intelligence to identify and diagnose colorectal cancer in a cost-effective way, which could ultimately reduce the workload of pathologists.”

Additionally, AI can be used in assessing cardiovascular complications.

Measuring various structures of the heart can indicate a patient’s risk for cardiovascular disease. In addition, automating the detection of abnormalities in imaging tests can lead to quicker decision-making and fewer diagnostic errors.

With AI, the technology can identify left atrial enlargement from chest x-rays to rule out other cardiac or pulmonary problems, assisting providers in targeting the appropriate treatments for patients. 

Similar AI tools could be used to automate other measurement tasks, including aortic valve analysis, carina angle measurement, and pulmonary artery diameter.

Applying AI to imaging data could also help identify the thickening of certain muscle structures or monitor changes in blood flow through the heart and associated arteries. AI can be used to detect cancerous lesions.

With AI medical imaging, the technology can also detect fractures, diagnose neurological diseases, identify thoracic complications

Improving precision medicine

AI can also be implemented into medical imaging to advance precision medicine. For example, at Stanford University, researchers found that a machine learning tool could differentiate between two types of lung cancer.

Additionally, the machine learning tool predicted patient survival rates better than the standard approach of pathologists classifying tumors by grade and stage.

“Pathology as it is practiced now is very subjective,” professor and chair of genetics, Michael Snyder, PhD, said in a press release.

“Two highly skilled pathologists assessing the same slide will agree only about 60 percent of the time. This approach replaces this subjectivity with sophisticated, quantitative measurements that we feel are likely to improve patient outcomes.”

The use of AI takes the subjectively out of the equation. The tool can identify the type of cancer and determine the best course of treatment for the patient, advancing precision medicine efforts. With precision medicine, physicians can provide a personalized treatment approach to specifically target the illness.

Indicating and assessing risk

While AI can be used in medical imaging to identify current conditions impacting a patient, it can also predict the potential risk for future illnesses.

In a recent study, researchers found that by combining AI imaging techniques with clinical data, physicians could improve predictive models indicating a patient’s risk for heart attacks.

When analyzed together in an artificial intelligence model, researchers discovered that coronary 18F-NaF uptake on PET and quantitative coronary plaque characteristics on CT angiography were complementary and robust predictors of heart attack risk in patients with established coronary artery disease. 

Together, the two techniques could provide more accurate heart attack risk prediction than using clinical data alone. 

“Recently, advanced imaging techniques have demonstrated considerable promise in determining which coronary artery disease patients are most at risk for a heart attack. These techniques include 18F-sodium fluoride (18F-NaF) PET, which assesses disease activity in the coronary arteries, and CT angiography, which provides a quantitative plaque analysis,” Director of Innovation in Imaging at Cedars-Sinai Medical Center Piotr J. Slomka, PhD, FACC, FASNC, FCCPM, said in a press release. 

“Our goal in the study was to investigate whether the information provided by 18F-NaF PET and CT angiography is complementary and could improve prediction of heart attacks with the use of artificial intelligence techniques.” 

According to the researcher team, their findings supported the use of artificial intelligence methods for integrating multimodality imaging and clinical data for accurately predicting heart attacks.

With AI, machine learning methods can advance medical screenings, enhance precision medicine, analyze patient risk factors, and lighten the load for physicians.