Visual Illusions in Radiology: Untrue Perceptions in Medical Images and Their Implications for Diagnostic Accuracy

Abstract

Errors in radiologic interpretation are largely the result of failures of perception. This remains true despite the increasing use of computer-aided detection and diagnosis. We surveyed the literature on visual illusions during the viewing of radiologic images. Misperception of anatomical structures is a potential cause of error that can lead to patient harm if disease is seen when none is present. However, visual illusions can also help enhance the ability of radiologists to detect and characterize abnormalities. Indeed, radiologists have learned to exploit certain perceptual biases in diagnostic findings and as training tools. We propose that further detailed study of radiologic illusions would help clarify the mechanisms underlying radiologic performance and provide additional heuristics to improve radiologist training and reduce medical error.

U‐Net enhanced real‐time LED‐based photoacoustic imaging

“…Last, we also performed a study to verify the noise distribution-type invariancy of the network with Gaussian and Salt & Pepper (S&P) noise. Though U-Net is unable to handle the S&P noise, it would not possibly create any major hurdle in real life clinics, as most of the electronic noise follow Gaussian noise distribution, and our U-Net is well adapted to the Gaussian noise [43][44][45]. In summary, the simple U-Net architecture can provide high SNR PA images by compensating for the low light fluence in LED-based systems and this might yield a closer step toward the clinical translation (or from bench to bedside) of PA imaging even though the network is susceptible to brightness contrast illusions and produces a blurry image comparative to the ground truth.…”

No common factor for illusory percepts, but a link between pareidolia and delusion tendency: A test of predictive coding theory

“…Pareidolia is a tendency to recognize familiar forms, most commonly faces, in other meaningful or random objects or patterns ( Zhou and Meng, 2020 ). Examples of pareidolia include recognizing animals in cloud formations, in old tree trunks, or even in radiological images ( Alexander et al, 2021 ). The predictive coding framework offers the most straightforward account of this phenomenon.…”

No common factor for illusory percepts, but a link between pareidolia and delusion tendency: a test of predictive coding theory

“…Pareidolia is a tendency to recognize familiar forms, most commonly faces, in other meaningful or random objects or patterns (Zhou and Meng, 2020). Examples of pareidolia includes recognizing animals in cloud formations, in old tree trunks, or even in radiological images (Alexander et al, 2021). The predictive coding framework offers the most straightforward account of this phenomenon.…”