Personalized modeling of human gaze

Exploratory investigation on mammogram readings

Sophie Voisin, Hong Jun Yoon, Georgia Tourassi, Garnetta Morin-Ducote, Kathleen Hudson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Eye tracking studies in medical imaging typically focus on studying radiologists' visual search process and how it relates to the clinical interpretation task at hand. In this pilot study, we have investigated gaze patterns to gain insight into their association with radiologists' expertise level as well as the presence of individual differences to facilitate personalized modeling and recognition of radiologists. First, we collected gaze data from six radiologists viewing 40 mammographic images each. Then, the collected gaze data were analyzed with two different approaches: 1) using a multilayer perceptron and 2) using a hidden Markov model. Both approaches confirmed that the experience level of a radiologist can be inferred with high accuracy by simply studying their gaze pattern. Personalized modeling and identification of radiologists was successful with both approaches with accuracy significantly higher than random guessing. The results of this pilot study confirm that a radiologist's perceptual behavior is not only a function of clinical training and level of experience, but there are individual aspects that could serve as a personal biomarker when developing models of human perception and cognition in medical image interpretation.

Original languageEnglish (US)
Title of host publicationProceedings of the 2013 4th Annual ORNL Biomedical Sciences and Engineering Conference
Subtitle of host publicationCollaborative Biomedical Innovations, BSEC 2013
DOIs
StatePublished - Nov 21 2013
Event2013 4th Annual ORNL Biomedical Sciences and Engineering Conference: Collaborative Biomedical Innovations, BSEC 2013 - Oak Ridge, TN, United States
Duration: May 21 2013May 23 2013

Other

Other2013 4th Annual ORNL Biomedical Sciences and Engineering Conference: Collaborative Biomedical Innovations, BSEC 2013
CountryUnited States
CityOak Ridge, TN
Period5/21/135/23/13

Fingerprint

Medical imaging
Biomarkers
Multilayer neural networks
Hidden Markov models
Association reactions

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

Voisin, S., Yoon, H. J., Tourassi, G., Morin-Ducote, G., & Hudson, K. (2013). Personalized modeling of human gaze: Exploratory investigation on mammogram readings. In Proceedings of the 2013 4th Annual ORNL Biomedical Sciences and Engineering Conference: Collaborative Biomedical Innovations, BSEC 2013 [6618495] https://doi.org/10.1109/BSEC.2013.6618495

Personalized modeling of human gaze : Exploratory investigation on mammogram readings. / Voisin, Sophie; Yoon, Hong Jun; Tourassi, Georgia; Morin-Ducote, Garnetta; Hudson, Kathleen.

Proceedings of the 2013 4th Annual ORNL Biomedical Sciences and Engineering Conference: Collaborative Biomedical Innovations, BSEC 2013. 2013. 6618495.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Voisin, S, Yoon, HJ, Tourassi, G, Morin-Ducote, G & Hudson, K 2013, Personalized modeling of human gaze: Exploratory investigation on mammogram readings. in Proceedings of the 2013 4th Annual ORNL Biomedical Sciences and Engineering Conference: Collaborative Biomedical Innovations, BSEC 2013., 6618495, 2013 4th Annual ORNL Biomedical Sciences and Engineering Conference: Collaborative Biomedical Innovations, BSEC 2013, Oak Ridge, TN, United States, 5/21/13. https://doi.org/10.1109/BSEC.2013.6618495
Voisin S, Yoon HJ, Tourassi G, Morin-Ducote G, Hudson K. Personalized modeling of human gaze: Exploratory investigation on mammogram readings. In Proceedings of the 2013 4th Annual ORNL Biomedical Sciences and Engineering Conference: Collaborative Biomedical Innovations, BSEC 2013. 2013. 6618495 https://doi.org/10.1109/BSEC.2013.6618495
Voisin, Sophie ; Yoon, Hong Jun ; Tourassi, Georgia ; Morin-Ducote, Garnetta ; Hudson, Kathleen. / Personalized modeling of human gaze : Exploratory investigation on mammogram readings. Proceedings of the 2013 4th Annual ORNL Biomedical Sciences and Engineering Conference: Collaborative Biomedical Innovations, BSEC 2013. 2013.
@inproceedings{2500bee18a9b4736b0bdef870a58fd4c,
title = "Personalized modeling of human gaze: Exploratory investigation on mammogram readings",
abstract = "Eye tracking studies in medical imaging typically focus on studying radiologists' visual search process and how it relates to the clinical interpretation task at hand. In this pilot study, we have investigated gaze patterns to gain insight into their association with radiologists' expertise level as well as the presence of individual differences to facilitate personalized modeling and recognition of radiologists. First, we collected gaze data from six radiologists viewing 40 mammographic images each. Then, the collected gaze data were analyzed with two different approaches: 1) using a multilayer perceptron and 2) using a hidden Markov model. Both approaches confirmed that the experience level of a radiologist can be inferred with high accuracy by simply studying their gaze pattern. Personalized modeling and identification of radiologists was successful with both approaches with accuracy significantly higher than random guessing. The results of this pilot study confirm that a radiologist's perceptual behavior is not only a function of clinical training and level of experience, but there are individual aspects that could serve as a personal biomarker when developing models of human perception and cognition in medical image interpretation.",
author = "Sophie Voisin and Yoon, {Hong Jun} and Georgia Tourassi and Garnetta Morin-Ducote and Kathleen Hudson",
year = "2013",
month = "11",
day = "21",
doi = "10.1109/BSEC.2013.6618495",
language = "English (US)",
isbn = "9781479921188",
booktitle = "Proceedings of the 2013 4th Annual ORNL Biomedical Sciences and Engineering Conference",

}

TY - GEN

T1 - Personalized modeling of human gaze

T2 - Exploratory investigation on mammogram readings

AU - Voisin, Sophie

AU - Yoon, Hong Jun

AU - Tourassi, Georgia

AU - Morin-Ducote, Garnetta

AU - Hudson, Kathleen

PY - 2013/11/21

Y1 - 2013/11/21

N2 - Eye tracking studies in medical imaging typically focus on studying radiologists' visual search process and how it relates to the clinical interpretation task at hand. In this pilot study, we have investigated gaze patterns to gain insight into their association with radiologists' expertise level as well as the presence of individual differences to facilitate personalized modeling and recognition of radiologists. First, we collected gaze data from six radiologists viewing 40 mammographic images each. Then, the collected gaze data were analyzed with two different approaches: 1) using a multilayer perceptron and 2) using a hidden Markov model. Both approaches confirmed that the experience level of a radiologist can be inferred with high accuracy by simply studying their gaze pattern. Personalized modeling and identification of radiologists was successful with both approaches with accuracy significantly higher than random guessing. The results of this pilot study confirm that a radiologist's perceptual behavior is not only a function of clinical training and level of experience, but there are individual aspects that could serve as a personal biomarker when developing models of human perception and cognition in medical image interpretation.

AB - Eye tracking studies in medical imaging typically focus on studying radiologists' visual search process and how it relates to the clinical interpretation task at hand. In this pilot study, we have investigated gaze patterns to gain insight into their association with radiologists' expertise level as well as the presence of individual differences to facilitate personalized modeling and recognition of radiologists. First, we collected gaze data from six radiologists viewing 40 mammographic images each. Then, the collected gaze data were analyzed with two different approaches: 1) using a multilayer perceptron and 2) using a hidden Markov model. Both approaches confirmed that the experience level of a radiologist can be inferred with high accuracy by simply studying their gaze pattern. Personalized modeling and identification of radiologists was successful with both approaches with accuracy significantly higher than random guessing. The results of this pilot study confirm that a radiologist's perceptual behavior is not only a function of clinical training and level of experience, but there are individual aspects that could serve as a personal biomarker when developing models of human perception and cognition in medical image interpretation.

UR - http://www.scopus.com/inward/record.url?scp=84887759712&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887759712&partnerID=8YFLogxK

U2 - 10.1109/BSEC.2013.6618495

DO - 10.1109/BSEC.2013.6618495

M3 - Conference contribution

SN - 9781479921188

BT - Proceedings of the 2013 4th Annual ORNL Biomedical Sciences and Engineering Conference

ER -