TY  - JOUR
A1  - Taleb, Aiham
A1  - Rohrer, Csaba
A1  - Bergner, Benjamin
A1  - De Leon, Guilherme
A1  - Rodrigues, Jonas Almeida
A1  - Schwendicke, Falk
A1  - Lippert, Christoph
A1  - Krois, Joachim
T1  - Self-supervised learning methods for label-efficient dental caries classification
JF  - Diagnostics : open access journal
N2  - High annotation costs are a substantial bottleneck in applying deep learning architectures to clinically relevant use cases, substantiating the need for algorithms to learn from unlabeled data. 

In this work, we propose employing self-supervised methods. To that end, we trained with three self-supervised algorithms on a large corpus of unlabeled dental images, which contained 38K bitewing radiographs (BWRs). We then applied the learned neural network representations on tooth-level dental caries classification, for which we utilized labels extracted from electronic health records (EHRs). Finally, a holdout test-set was established, which consisted of 343 BWRs and was annotated by three dental professionals and approved by a senior dentist. 

This test-set was used to evaluate the fine-tuned caries classification models. Our experimental results demonstrate the obtained gains by pretraining models using self-supervised algorithms. These include improved caries classification performance (6 p.p. increase in sensitivity) and, most importantly, improved label-efficiency. 
In other words, the resulting models can be fine-tuned using few labels (annotations). 

Our results show that using as few as 18 annotations can produce >= 45% sensitivity, which is comparable to human-level diagnostic performance. 
This study shows that self-supervision can provide gains in medical image analysis, particularly when obtaining labels is costly and expensive.
KW  - unsupervised methods
KW  - self-supervised learning
KW  - representation learning
KW  - dental caries classification
KW  - data driven approaches
KW  - annotation
KW  - efficient deep learning
Y1  - 2022
U6  - https://doi.org/10.3390/diagnostics12051237
SN  - 2075-4418
VL  - 12
IS  - 5
PB  - MDPI
CY  - Basel
ER  - 
TY  - JOUR
A1  - Stober, Sebastian
T1  - Toward Studying Music Cognition with Information Retrieval Techniques: Lessons Learned from the OpenMIIR Initiative
JF  - Frontiers in psychology
N2  - As an emerging sub-field of music information retrieval (MIR), music imagery information retrieval (MIIR) aims to retrieve information from brain activity recorded during music cognition-such as listening to or imagining music pieces. This is a highly interdisciplinary endeavor that requires expertise in MIR as well as cognitive neuroscience and psychology. The OpenMIIR initiative strives to foster collaborations between these fields to advance the state of the art in MIIR. As a first step, electroencephalography (EEG) recordings ofmusic perception and imagination have beenmade publicly available, enabling MIR researchers to easily test and adapt their existing approaches for music analysis like fingerprinting, beat tracking or tempo estimation on this new kind of data. This paper reports on first results of MIIR experiments using these OpenMIIR datasets and points out how these findings could drive new research in cognitive neuroscience.
KW  - music cognition
KW  - music perception
KW  - music information retrieval
KW  - deep learning
KW  - representation learning
Y1  - 2017
U6  - https://doi.org/10.3389/fpsyg.2017.01255
SN  - 1664-1078
VL  - 8
PB  - Frontiers Research Foundation
CY  - Lausanne
ER  - 
TY  - JOUR
A1  - Stober, Sebastian
T1  - Toward Studying Music Cognition with Information Retrieval Techniques
BT  - Lessons Learned from the OpenMIIR Initiative
JF  - Frontiers in psychology
N2  - As an emerging sub-field of music information retrieval (MIR), music imagery information retrieval (MIIR) aims to retrieve information from brain activity recorded during music cognition–such as listening to or imagining music pieces. This is a highly inter-disciplinary endeavor that requires expertise in MIR as well as cognitive neuroscience and psychology. The OpenMIIR initiative strives to foster collaborations between these fields to advance the state of the art in MIIR. As a first step, electroencephalography (EEG) recordings of music perception and imagination have been made publicly available, enabling MIR researchers to easily test and adapt their existing approaches for music analysis like fingerprinting, beat tracking or tempo estimation on this new kind of data. This paper reports on first results of MIIR experiments using these OpenMIIR datasets and points out how these findings could drive new research in cognitive neuroscience.
KW  - music cognition
KW  - music perception
KW  - music information retrieval
KW  - deep learning
KW  - representation learning
Y1  - 2017
U6  - https://doi.org/10.3389/fpsyg.2017.01255
SN  - 1664-1078
VL  - 8
PB  - Frontiers Research Foundation
CY  - Lausanne
ER  -