Remote-store-and-forward teledermatology has recently grown exponentially in popularity and use as an efficient, accurate, and cost-effective way to improve the health and well-being of countless patients. Despite advances in machine learning and computer vision, the screening and reading of dermatological images still depends on the visual system of human observers (e.g., clinicians), who receive extensive training to best recognize lesions and anomalies. In remote store-and-forward teledermatology settings, clinicians may examine hundreds of images on a daily basis, seeing several images one after the other. A main underlying assumption of their work is that clinician percepts and decisions about a current image are completely independent from prior viewings. However, we and other groups demonstrated that the visual system has visual serial dependencies (VSDs) at many levels, from perception to decision making, including in clinical tasks. These sequential dependencies, replicated hundreds of times in the literature, mean that what was seen in the past influences (and captures) what is seen and reported at this moment. Theoretically, VSDs are helpful in an autocorrelated natural world, but they are suboptimal in visual tasks conducted in artificial situations where images are not always related. Importantly, serial dependencies in perceptual processing could thus produce significant errors during diagnostic judgments of dermatological images. Our central hypothesis is that VSD can have a disruptive effect in asynchronous remote-store-and-forward teledermatology judgments that impairs accurate detection and recognition of lesions. This hypothesis is supported by our robust pilot data, which show that VSD strongly biases lesion classification in both untrained observers and expert clinicians. The rationale for the proposed research projects is that once it is known how serial dependence arises and how it impacts judgments, we can understand how to control for it. Hence, accuracy of lesion detection and diagnosis can significantly improve. The specific objectives of this proposal are to establish (Aim 1), identify (Aim 2) and mitigate (Aim 3) the impact of VSD on remote-store-and-forward dermatological judgments.
Our proposal is designed to investigate the detrimental impact of visual serial dependencies in a remote store and forward teledermatology setting. Serial dependencies likely underlie much of our perceptual experience, but little is known about their negative consequences when dermatologists are tasked with recognizing lesions in remote store and forward teledermatology. The final goal of our research project is to develop recommendation and guidelines to mitigate the negative effect of serial effects in remote store and forward teledermatology, improving accuracy of clinical judgments. Each experiment will involve a group of observers, dermatologists or untrained observers. Each subject will complete all conditions of the assigned experiment. The procedure will be psychophysical (BESH) across all the experiments. Observers will see images of skin lesions and they will be asked to classify/detect/and recognize features and structures about the lesion images.
Study Type
INTERVENTIONAL
Allocation
RANDOMIZED
Purpose
BASIC_SCIENCE
Masking
DOUBLE
Enrollment
10,120
Psychophysical experiment on sequential effects in medical image perception. Observers, including clinicians, perform psychophysical continuous report match-to-sample and forced-choice discrimination judgments of medical images. Observer discrimination accuracy is measured on a trial-wise basis and sequential effects in those judgments are measured. Images can be presented with different interstimulus intervals and in different spatial locations and in different orders. Accuracy, and other signal detection metrics are computed as a function of these factors.
University of California, Berkeley
Berkeley, California, United States
RECRUITINGSerial Dependence Assessment using psychophysical procedures
This is a medical image perception experiment using psychophysical methods, including continuous report match-to-sample and method-of-constant stimuli designs. Human observers, including clinicians and untrained observers, are recruited to classify or discriminate medical images. Each observer participates in approximately 300 trials in a session. On each trial, observers view a medical image on a computer monitor and are asked to make either a match-to-sample or a two-alternative forced choice decisions about the image. Observer responses on each trial are classified in terms of their accuracy. Outcome measures include hit rate, false alarm rate, sensitivity, selectivity, d', and criterion. Changes in these metrics from trial-to-trial throughout the course of the experiment are quantified as metrics of sequential biases that might be present in observer judgments.
Time frame: Each participant is tested for 30-60 minutes in a psychophysical experiment.
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.