← Back to Computer Vision cs.CV
Can AI detect when prostate scans are too blurry for diagnosis?
Haoran Sun, Lixia Wang, Yin-Chen Hsu, Hsu-Lei Lee, Chang Gao, Fei Han, Robert Grimm, Vibhas Deshpande, Ziyang Long, Hsin-Jung Yang, Rola Saouaf, Alessandro D'Agnolo, Timothy Daskivich, Hyung Kim, Debiao Li, Yibin Xie
May 29, 2026
Geometric distortion in prostate MRI scans can hide tumors and force costly repeats. AutoIQ combines two automated methods—measuring boundary mismatch between scan types and estimating deformation after alignment—then blends their outputs via ensemble voting. On 140 clinical exams, it achieved 95% accuracy distinguishing scans requiring repeat acquisition from acceptable ones, outperforming either method alone.
Read the original paper →