Eye Tracking Detection in Radiology

Diagnostic errors in radiology, particularly concerning the detection of small lung nodules on chest CT scans, have remained persistently high, with a miss rate of around 50% for small nodules. This has significant implications for patient outcomes, as early detection of lung cancer is crucial. In a recent study, “Non-conscious detection of ‘missed’ lung nodules by radiologists: Expanding the boundaries of successful processing during the visual assessment of chest CT scans,” published in Radiology, DiGirolamo et al., (2025), shed light on a fascinating aspect of visual processing: radiologists may non-consciously detect abnormalities even when they are not consciously recognized. Their research emphasizes the critical role of eye-tracking technology in uncovering these “unseen detections” and its potential to revolutionize diagnostic accuracy.

Lung cancer is a leading cause of cancer-related deaths, and early detection through CT screening is a key preventative measure. Despite advancements in imaging technology and radiologist training, the challenge of consistently identifying small lung nodules persists. Traditional understanding attributes misses to search errors (not looking at the nodule), decision errors (looking but misidentifying), or recognition errors (looking for insufficient time). However, the DiGirolamo et al. (2025) study proposes that successful visual processing may be occurring independent of conscious recognition.

Radiology and Eye-Tracking Research Study

This prospective study involved six experienced radiologists and six medically naive control participants, who viewed 18 chest CT scans (nine abnormal with 16 nodules, nine normal). The researchers utilized an SR Research EyeLink 1000 eye tracker to measure gaze duration (dwell time) and pupil size—an indicator of physiological arousal—at both missed nodule locations and corresponding normal tissue locations. The goal was to determine if radiologists exhibited non-conscious detection of nodules they failed to report.

Radiologists’ Non-Conscious Processes May Detect Lung Nodules

The results were compelling. Radiologists missed, on average, 59% of the lung nodules. However, for these “missed” nodules, radiologists exhibited:

• Longer Dwell Times: A significantly longer gaze duration (mean, 228 msec vs. 175 msec; P=.005) at missed nodule locations compared to normal tissue.
• Larger Pupil Size: An increase in pupil size (mean, 1446 pixels vs. 1349 pixels; P=.04), indicating heightened physiological arousal at these locations.

In contrast, the control participants showed no significant differences in dwell time or pupil size for missed nodule locations versus normal tissue. This strongly suggests that the observed non-conscious detection is a direct result of general radiology training. The study concluded that radiologists’ non-conscious processes can successfully detect lung nodules even when conscious recognition fails, as evidenced by these objective eye-tracking biomarkers.

This research unequivocally highlights the vital role of eye-tracking technology in understanding and improving diagnostic processes. Without precise measurement of gaze patterns and physiological responses, the phenomenon of “looking without seeing” would remain largely undetected. Eye tracking provided objective, quantifiable evidence of successful non-conscious processing in trained medical professionals.

The study by DiGirolamo et al. (2025) marks a significant step towards “breaking the barrier of the limitations of conscious recognition” in medical imaging. By demonstrating the efficacy of non-conscious processes through eye tracking, the research opens new avenues for improving diagnostic accuracy in radiology. The integration of eye-tracking technology into clinical practice and training could pave the way for a future where even the subtlest, unconsciously detected abnormalities are brought to conscious attention, ultimately improving patient outcomes. Further research is needed to develop methods for leveraging these non-conscious detections to enhance conscious reporting.

For information regarding how eye tracking can help your research, check out our solutions and product pages or contact us. We are happy to help!