Those of us who recognize our frailties -- the prejudices and biases that creep almost imperceptibly into our decision making -- would welcome a quantifiable means for ensuring that those decisions are best made. Last month, prosecutors successfully convinced a court in Mumbai, India, that a scan that records activity in distinct areas of the brain can be such a measure. On the basis of a “Brain Electrical Oscillations Signature” test, the court convicted and sentenced to life in prison a 24-year-old woman for murdering her fiancé.
Those of us who recognize our frailties -- the prejudices and biases that creep almost imperceptibly into our decision making -- would welcome a quantifiable means for ensuring that those decisions are best made. Last month, prosecutors successfully convinced a court in Mumbai, India, that a scan that records activity in distinct areas of the brain can be such a measure. On the basis of a "Brain Electrical Oscillations Signature" test, the court convicted and sentenced to life in prison a 24-year-old woman for murdering her fiancé.When specific crime details were read out loud, 32 electrodes placed on the accused woman's head recorded incriminating activity in parts of the brain that are believed to be associated with memory. It was the first time an Indian court had accepted brain scan results as proof of guilt. Previously, the courts had accepted such results only as corroborating evidence of a criminal act.The case is both fascinating and frightening. It exemplifies how far technology has come and how willing people are to accept its use.For those who just felt a shiver, you can shrug it off as a strange twist in a world where strange things get more than their share of attention. On its website, La Jolla, CA-based No Lie MRI claims it "provides unbiased methods for the detection of deception and other information stored in the brain." How? By using functional MRI, which enables the firm to measure "intent, prior knowledge, and deception."
Need a second opinion? Try Cephos. The Tyngsboro, MA-based company tries to make good on its motto "When Truth Matters" through expert DNA testing, private detectives, and -- you guessed it -- fMRI. Click on a tab for the "legal admissibility" of fMRI, and you'll find the following assertions:
Cephos claims that the ability of fMRI to distinguish between truth and lies has been documented in 18 peer-reviewed, published papers. The company does not list the titles of these papers, but it's clear that research supporting the use of fMRI as a lie detector technology has been reported at least since the 2004 RSNA meeting.
Given the history of fMRI and our predilection as a society to adopt high technology from everything from PCs to cruise control, it's surprising that more companies like Cephos and No Lie MRI have not popped up. If fMRI proves effective at detecting lies, and its use is accepted in the U.S. legal system, this technology could have an enormous social impact, equivalent to DNA testing but potentially much more intrusive. And this is only the beginning. How it might be used outside the legal system -- by the intelligence community, for example -- in combination with morally suspect information-gathering techniques conjures an Orwellian picture.While truth is a laudable goal, it is mitigated by how it is obtained. Now rather than later is the time for the imaging community to consider its role in this process, both as developer and user of such lie detection technologies.
Emerging AI Algorithm Shows Promise for Abbreviated Breast MRI in Multicenter Study
April 25th 2025An artificial intelligence algorithm for dynamic contrast-enhanced breast MRI offered a 93.9 percent AUC for breast cancer detection, and a 92.3 percent sensitivity in BI-RADS 3 cases, according to new research presented at the Society for Breast Imaging (SBI) conference.
Could AI-Powered Abbreviated MRI Reinvent Detection for Structural Abnormalities of the Knee?
April 24th 2025Employing deep learning image reconstruction, parallel imaging and multi-slice acceleration in a sub-five-minute 3T knee MRI, researchers noted 100 percent sensitivity and 99 percent specificity for anterior cruciate ligament (ACL) tears.
New bpMRI Study Suggests AI Offers Comparable Results to Radiologists for PCa Detection
April 15th 2025Demonstrating no significant difference with radiologist detection of clinically significant prostate cancer (csPCa), a biparametric MRI-based AI model provided an 88.4 percent sensitivity rate in a recent study.