From an early setup experiment, we developed this repository. The repository is a naïve approach to measure and calculate the setup of Tobii Eye Tracker 4C gazing information for usability testing purpose. The Tobii Eye Tracker 4C aims at providing an immersive reality without an headset. Also, with this product nothing stands between the screen and the immersive experience. Therefore, our clinicians will work with no interference of the device. This repository includes software from the GazeTrack: Eye-tracking for Processing (Tobii EyeX and 4C) library developed by Prof. Augusto Esteves (@AugustoEst) for the Processing programming environment. It is also available on GitHub. The GazeTrack is a library that supports basic gaze tracking for our Tobii Eye Tracker 4C device. The repository is part of the work done by SIPg, an ISR-Lisboa research group and M-ITI, two R&D Units of LARSyS. The project also involves the collaborative effort of INESC-ID. Both ISR-Lisboa and INESC-ID are Associate Laboratories of IST from ULisboa.
We kindly ask scientific works and studies that make use of the repository to cite it in their associated publications. Similarly, we ask open-source and closed-source works that make use of the repository to warn us about this use.
You can cite our work using the following BibTeX entry:
@article{CALISTO2021102607,
title = {Introduction of human-centric AI assistant to aid radiologists for multimodal breast image classification},
journal = {International Journal of Human-Computer Studies},
volume = {150},
pages = {102607},
year = {2021},
issn = {1071-5819},
doi = {https://doi.org/10.1016/j.ijhcs.2021.102607},
url = {https://www.sciencedirect.com/science/article/pii/S1071581921000252},
author = {Francisco Maria Calisto and Carlos Santiago and Nuno Nunes and Jacinto C. Nascimento},
keywords = {Human-computer interaction, Artificial intelligence, Healthcare, Medical imaging, Breast cancer},
abstract = {In this research, we take an HCI perspective on the opportunities provided by AI techniques in medical imaging, focusing on workflow efficiency and quality, preventing errors and variability of diagnosis in Breast Cancer. Starting from a holistic understanding of the clinical context, we developed BreastScreening to support Multimodality and integrate AI techniques (using a deep neural network to support automatic and reliable classification) in the medical diagnosis workflow. This was assessed by using a significant number of clinical settings and radiologists. Here we present: i) user study findings of 45 physicians comprising nine clinical institutions; ii) list of design recommendations for visualization to support breast screening radiomics; iii) evaluation results of a proof-of-concept BreastScreening prototype for two conditions Current (without AI assistant) and AI-Assisted; and iv) evidence from the impact of a Multimodality and AI-Assisted strategy in diagnosing and severity classification of lesions. The above strategies will allow us to conclude about the behaviour of clinicians when an AI module is present in a diagnostic system. This behaviour will have a direct impact in the clinicians workflow that is thoroughly addressed herein. Our results show a high level of acceptance of AI techniques from radiologists and point to a significant reduction of cognitive workload and improvement in diagnosis execution.}
}
The following list is showing the set of dependencies for this project. Please, install and build the recommended versions in your machine.
List of dependencies and recommended versions for this repository:
-
Windows 10 (>= v1809)
-
Processing (>= v3.5.3)
-
TobiiStream (>= v2.0.3)
Tobii’s consumer eye trackers are primarily intended for personal interaction use and not for analytical purposes. Any application that stores or transfers eye tracking data must have a special license from Tobii (Read more). Please, apply for a license here.
The instructions are as follows. We assume that you already have knowledge over Git and GitHub. If not, please follow this support information. Any need for support, just open a New issue.
To clone the hereby repository follow the guidelines. It is easy as that.
1.1. Please clone the repository by typing the command:
git clone https://github.com/mida-project/eye-tracker-naive.git
1.2. Get inside of the repository directory:
cd eye-tracker-naive/
1.3. For the installation and running of the source code, follow the next steps;
The running guidelines are as follows. Please, be sure that you follow it correctly.
2.1. Run the sample using the following command:
TobiiStream\TobiiStream.exe > samples\test_3.txt
2.2. Now open the samples/
directory and observe the test_3.txt
file;
2.3. Enjoy our source code!
We developed this repository as a naïve and lazy approach from failing to implement an early, yet complete, solution for our problem. This happens "thanks" to the high availability (NOT) of Tobii's team to provide us (sarcasm, sarcasm and more sarcasm) a license for our study. If you still want to find out how to apply the Upgrade Key (advice: you are losing your time) to a Tobii Eye Tracker 4C, follow the Tobii Pro Upgrade Key – User Instructions document. From there, and if you have any luck, you can try back our old solution. Nevertheless, you can follow the presented steps. Any questions regarding the Eye-Tracking topic just follow the StackOverflow tag for the purpose.
On the next animation, we present a potential Use Case for our future User Tests. In this tests, we aim to apply the Eye Tracking technique across several Medical Imaging (MI) technologies to understand gaze behaviour of the clinicians. A sample of a gaze output can be seen below.
Sample of gaze output:
TobiiStream v2.0.3
SUCCESS: The connection to the GazeTrack Processing library has been correctly set up!
TobiiState Present
TobiiStream 4964391.9978 1409.01264816592 1490.13762876426
TobiiStream 4964403.5532 1412.13326149614 1491.61791154857
TobiiStream 4964414.6863 1413.14194231297 1492.55350841627
TobiiStream 4964425.2119 1412.89475257191 1492.45911056297
TobiiStream 4964436.7849 1414.89398222908 1491.08490976601
TobiiStream 4964447.8616 1415.72645020609 1490.97596126832
TobiiStream 4964458.7331 1398.7559159215 1487.89992585501
The work is also based and higly contributed from the gazetrack
repository. The gazetrack
repository was developed by Augusto Esteves (AugustoEst) that we would like to thank. That repository shows pretty much everything we need to collect information from a Tobii Eye-Tracker, get gaze coordinates and time synchronization data.
Francisco Maria Calisto [ResearchGate | GitHub | Twitter | LinkedIn]
![fct](https://github.com/mida-project/meta/raw/master/brands/fct_footer.png?raw=true)
![fccn](https://github.com/mida-project/meta/raw/master/brands/fccn_footer.png?raw=true)
![ulisboa](https://github.com/mida-project/meta/raw/master/brands/ulisboa_footer.png?raw=true)
![ist](https://github.com/mida-project/meta/raw/master/brands/ist_footer.png?raw=true)
![hff](https://github.com/mida-project/meta/raw/master/brands/hff_footer.png?raw=true)
![dei](https://github.com/mida-project/meta/raw/master/brands/dei_footer.png?raw=true)
![dei](https://github.com/mida-project/meta/raw/master/brands/deec_footer.png?raw=true)
![sipg](https://github.com/mida-project/meta/raw/master/brands/sipg_footer.png?raw=true)
![isr](https://github.com/mida-project/meta/raw/master/brands/isr-lisboa_footer.png?raw=true)
![larsys](https://github.com/mida-project/meta/raw/master/brands/larsys_footer.png?raw=true)
![inesc-id](https://github.com/mida-project/meta/raw/master/brands/miti_footer.png?raw=true)
![inesc-id](https://github.com/mida-project/meta/raw/master/brands/inesc-id_footer.png?raw=true)
![eu](https://github.com/mida-project/meta/raw/master/brands/eu_footer.png?raw=true)
![pt](https://github.com/mida-project/meta/raw/master/brands/pt_footer.png?raw=true)