Deep metric learning for otitis media classification

Sundgaard, Josefine Vilsbøll; Harte, James M.; Bray, Peter; Laugesen, Søren; Kamide, Yosuke; Tanaka, Chiemi; Paulsen, Rasmus Reinhold; Christensen, Anders Nymark

doi:10.1016/j.media.2021.102034

Cited by 53 publications

(42 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this section, we introduce the deep metric learning strategy into the classification of different stages of AD. Metric learning is widely utilized with deep neural networks in classification tasks, especially in problems affected by large intra-class sample changes ( Liu et al, 2017 ; Sundgaard et al, 2021 ). Deep metric learning loss maps features to the embedded space, which is conducive to learning difficult samples and can effectively deal with the imbalance of data ( Sundgaard et al, 2021 ).…”

Section: Methodsmentioning

confidence: 99%

“…Metric learning is widely utilized with deep neural networks in classification tasks, especially in problems affected by large intra-class sample changes ( Liu et al, 2017 ; Sundgaard et al, 2021 ). Deep metric learning loss maps features to the embedded space, which is conducive to learning difficult samples and can effectively deal with the imbalance of data ( Sundgaard et al, 2021 ). Inspired by these, we argue that deep metric learning might be suitable for our classification task.…”

Section: Methodsmentioning

confidence: 99%

“…In deep neural networks, the loss function is a manifestation of metric learning, and there are a variety of different metric learning loss functions. In this paper, we employ two deep metric learning loss functions for automatic diagnosis of early AD, including contrastive loss and triplet loss, which are widely used in recent studies ( Cheng et al, 2016 ; He et al, 2021 ; Sundgaard et al, 2021 ). Contrastive loss employs a pair of positive and negative samples for each training iteration.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

BMNet: A New Region-Based Metric Learning Method for Early Alzheimer’s Disease Identification With FDG-PET Images

Cui

Yan

et al. 2022

Front. Neurosci.

View full text Add to dashboard Cite

18F-fluorodeoxyglucose (FDG)-positron emission tomography (PET) reveals altered brain metabolism in individuals with mild cognitive impairment (MCI) and Alzheimer’s disease (AD). Some biomarkers derived from FDG-PET by computer-aided-diagnosis (CAD) technologies have been proved that they can accurately diagnosis normal control (NC), MCI, and AD. However, existing FDG-PET-based researches are still insufficient for the identification of early MCI (EMCI) and late MCI (LMCI). Compared with methods based other modalities, current methods with FDG-PET are also inadequate in using the inter-region-based features for the diagnosis of early AD. Moreover, considering the variability in different individuals, some hard samples which are very similar with both two classes limit the classification performance. To tackle these problems, in this paper, we propose a novel bilinear pooling and metric learning network (BMNet), which can extract the inter-region representation features and distinguish hard samples by constructing the embedding space. To validate the proposed method, we collect 898 FDG-PET images from Alzheimer’s disease neuroimaging initiative (ADNI) including 263 normal control (NC) patients, 290 EMCI patients, 147 LMCI patients, and 198 AD patients. Following the common preprocessing steps, 90 features are extracted from each FDG-PET image according to the automatic anatomical landmark (AAL) template and then sent into the proposed network. Extensive fivefold cross-validation experiments are performed for multiple two-class classifications. Experiments show that most metrics are improved after adding the bilinear pooling module and metric losses to the Baseline model respectively. Specifically, in the classification task between EMCI and LMCI, the specificity improves 6.38% after adding the triple metric loss, and the negative predictive value (NPV) improves 3.45% after using the bilinear pooling module. In addition, the accuracy of classification between EMCI and LMCI achieves 79.64% using imbalanced FDG-PET images, which illustrates that the proposed method yields a state-of-the-art result of the classification accuracy between EMCI and LMCI based on PET images.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

BMNet: A New Region-Based Metric Learning Method for Early Alzheimer’s Disease Identification With FDG-PET Images

Cui

Yan

et al. 2022

Front. Neurosci.

View full text Add to dashboard Cite

show abstract

“…This technique requires specific training and diagnosis has been shown to be highly subjective [2]. In response to these challenges, the present authors have previously demonstrated the advantages of applying deep learning methods for automatic identification of otitis media in otoscopy images [3].…”

Section: Introductionmentioning

confidence: 92%

A Deep Learning Approach for Detecting Otitis Media From Wideband Tympanometry Measurements

Sundgaard

Bray

Laugesen

et al. 2022

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

Objective: In this study, we propose an automatic diagnostic algorithm for detecting otitis media based on wideband tympanometry measurements. Methods: We develop a convolutional neural network for classification of otitis media based on the analysis of the wideband tympanogram. Saliency maps are computed to gain insight into the decision process of the convolutional neural network. Finally, we attempt to distinguish between otitis media with effusion and acute otitis media, a clinical subclassification important for the choice of treatment. Results: The approach shows high performance on the overall otitis media detection with an accuracy of 92.6%. However, the approach is not able to distinguish between specific types of otitis media. Conclusion: Out approach can detect otitis media with high accuracy and the wideband tympanogram holds more diagnostic information than the commonly used techniques wideband absorbance measurements and simple tympanograms. Significance: This study shows how advanced deep learning methods enable automatic diagnosis of otitis media based on wideband tympanometry measurements, which could become a valuable diagnostic tool.

show abstract

“…These two types of data can both be used for the diagnosis of otitis media. Several studies have developed different approaches for otitis media classification based on either otoscopy images [4][5][6] or WBT measurements [7,8]. A combined deep learning classification approach based on standard single-frequency tympanograms and otoscopy images was proposed by Binol et al [9].…”

Section: Introductionmentioning

confidence: 99%

Multi-modal data generation with a deep metric variational autoencoder

Sundgaard¹,

Hannemose²,

Laugesen³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

We present a deep metric variational autoencoder for multi-modal data generation. The variational autoencoder employs triplet loss in the latent space, which allows for conditional data generation by sampling in the latent space within each class cluster. The approach is evaluated on a multi-modal dataset consisting of otoscopy images of the tympanic membrane with corresponding wideband tympanometry measurements. The modalities in this dataset are correlated, as they represent different aspects of the state of the middle ear, but they do not present a direct pixel-to-pixel correlation. The approach shows promising results for the conditional generation of pairs of images and tympanograms, and will allow for efficient data augmentation of data from multimodal sources.

show abstract

Deep metric learning for otitis media classification

Cited by 53 publications

References 16 publications

BMNet: A New Region-Based Metric Learning Method for Early Alzheimer’s Disease Identification With FDG-PET Images

BMNet: A New Region-Based Metric Learning Method for Early Alzheimer’s Disease Identification With FDG-PET Images

A Deep Learning Approach for Detecting Otitis Media From Wideband Tympanometry Measurements

Multi-modal data generation with a deep metric variational autoencoder

Contact Info

Product

Resources

About