Malware tricks radiologists by using fake nodules on CT scans

What happens when a software virus runs up against a physician trained to spot ailments? In a recent study, malware designed to create fake nodules on images successfully fooled radiologists into making incorrect diagnoses.

A team of researchers from Ben Gurion University Cyber Security Research Center in Israel spoke to the Washington Post about how their malware could target specific patients, alter follow-up scans after treatment and even change scans from drug trials to create false results.

They published solid proof of this in January, in which the malware altered 70 real CT lung scans; in those images with fake cancerous nodules a radiologist diagnosed cancer 99 percent of the time. In images where malware erased actual cancerous findings, the radiologists diagnosed the patient as healthy 94 percent of the time.

How does this happen? According to Yisroel Mirsky, of Ben Gurion University, in Israel, the problem is that hospitals don’t digitally sign scans nor do they encrypt information on PACS systems. Data shared outside the hospital is treated differently than that shared within.

“…what happens within the [hospital] system itself, which no regular person should have access to in general, they tend to be pretty lenient [about],” Mirsky told the Post. “It’s not...that they don’t care. It’s just that their priorities are set elsewhere.”

Read the entire story below.

""

Matt joined Chicago’s TriMed team in 2018 covering all areas of health imaging after two years reporting on the hospital field. He holds a bachelor’s in English from UIC, and enjoys a good cup of coffee and an interesting documentary.

Around the web

GE HealthCare's flurpiridaz, the PET radiotracer that recently received FDA approval, offers several key benefits over SPECT. Jamshid Maddahi, MD, discussed the details in an exclusive interview. 

Ultrafast MCE could go on to become a go-to treatment option for obstructive coronary artery disease, according to the authors of a new first-in-human clinical study.

Elucid's PlaqueIQ was trained to turn CCTA images into interactive 3D reports that help physicians visualize the presence of atherosclerosis.

Trimed Popup
Trimed Popup