Bert Vankeirsbilck
Research Subjects
Bert Vankeirsbilck has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Bart Dhoedt
IDLab, Department of Information Technology Ghent University–IMEC Ghent Belgium
2 shared publications - Tim Verbelen
VERSES Research Lab, Los Angeles, USA
2 shared publications - Cedric De Boom
Department of Information Technology Ghent University -imec Technologiepark-Zwijnaarde 126 B-9052 Ghent Belgium
1 shared publication - Elias De Coninck
Ghent University - imec, IDLab, Department of Information Technology
1 shared publication - Evelien Verhaeghe
Dermatology Department, Ghent University Hospital, Ghent, Oost-Vlaanderen, Belgium
1 shared publication - Femke Ongenae
Universiteit Gent
1 shared publication
Latest Publications
- 3 August 2023
- Published by Wiley in Experimental Dermatology
- Vol. 32 (10) , 1744-1751
Dermatologist versus artificial intelligence confidence in dermoscopy diagnosis: Complementary information that may affect decision‐making
In dermatology, deep learning may be applied for skin lesion classification. However, for a given input image, a neural network only outputs a label, obtained using the class probabilities, which do not model uncertainty. Our group developed a novel method to quantify uncertainty in stochastic neural networks. In this study, we aimed to train such network for skin lesion classification and evaluate its diagnostic performance and uncertainty, and compare the results to the assessments by a group of dermatologists. By passing duplicates of an image through such a stochastic neural network, we obtained distributions per class, rather than a single probability value. We interpreted the overlap between these distributions as the output uncertainty, where a high overlap indicated a high uncertainty, and vice versa. We had 29 dermatologists diagnose a series of skin lesions and rate their confidence. We compared these results to those of the network. The network achieved a sensitivity and specificity of 50% and 88%, comparable to the average dermatologist (respectively 68% and 73%). Higher confidence/less uncertainty was associated with better diagnostic performance both in the neural network and in dermatologists. We found no correlation between the uncertainty of the neural network and the confidence of dermatologists (R = −0.06, p = 0.77). Dermatologists should not blindly trust the output of a neural network, especially when its uncertainty is high. The addition of an uncertainty score may stimulate the human‐computer interaction.
- 3 August 2023
- Published by Wiley in Experimental Dermatology
- Vol. 32 (10) , 1744-1751
Dermatologist versus artificial intelligence confidence in dermoscopy diagnosis: Complementary information that may affect decision‐making
In dermatology, deep learning may be applied for skin lesion classification. However, for a given input image, a neural network only outputs a label, obtained using the class probabilities, which do not model uncertainty. Our group developed a novel method to quantify uncertainty in stochastic neural networks. In this study, we aimed to train such network for skin lesion classification and evaluate its diagnostic performance and uncertainty, and compare the results to the assessments by a group of dermatologists. By passing duplicates of an image through such a stochastic neural network, we obtained distributions per class, rather than a single probability value. We interpreted the overlap between these distributions as the output uncertainty, where a high overlap indicated a high uncertainty, and vice versa. We had 29 dermatologists diagnose a series of skin lesions and rate their confidence. We compared these results to those of the network. The network achieved a sensitivity and specificity of 50% and 88%, comparable to the average dermatologist (respectively 68% and 73%). Higher confidence/less uncertainty was associated with better diagnostic performance both in the neural network and in dermatologists. We found no correlation between the uncertainty of the neural network and the confidence of dermatologists (R = −0.06, p = 0.77). Dermatologists should not blindly trust the output of a neural network, especially when its uncertainty is high. The addition of an uncertainty score may stimulate the human‐computer interaction.
- Open Access
- 8 November 2017
- Published by Springer Nature
- p. 167-171
Context-Aware and Self-learning Dynamic Transport Scheduling in Hospitals
- 8 November 2017
- Published by Springer Nature
- p. 167-171
Open AccessContext-Aware and Self-learning Dynamic Transport Scheduling in Hospitals
- Open Access
- 1 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2365-2370
Sensor fusion for robot control through deep reinforcement learning
Deep reinforcement learning is becoming increasingly popular for robot control algorithms, with the aim for a robot to self-learn useful feature representations from unstructured sensory input leading to the optimal actuation policy. In addition to sensors mounted on the robot, sensors might also be deployed in the environment, although these might need to be accessed via an unreliable wireless connection. In this paper, we demonstrate deep neural network architectures that are able to fuse information generated by multiple sensors and are robust to sensor failures at runtime. We evaluate our method on a search and pick task for a robot both in simulation and the real world.
- 1 September 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2365-2370
Open AccessSensor fusion for robot control through deep reinforcement learning
Deep reinforcement learning is becoming increasingly popular for robot control algorithms, with the aim for a robot to self-learn useful feature representations from unstructured sensory input leading to the optimal actuation policy. In addition to sensors mounted on the robot, sensors might also be deployed in the environment, although these might need to be accessed via an unreliable wireless connection. In this paper, we demonstrate deep neural network architectures that are able to fuse information generated by multiple sensors and are robust to sensor failures at runtime. We evaluate our method on a search and pick task for a robot both in simulation and the real world.