Assessment of Parkinson’s Disease Based on Deep Neural Networks

Tagaris, Athanasios; Kollias, Dimitrios; Stafylopatis, Andreas

doi:10.1007/978-3-319-65172-9_33

Cited by 25 publications

(13 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Deep neural networks, including Convolutional (CNNs), Convolutional and Recurrent (CNN-RNNs) have been developed in [10,23] for PD prediction using the DaTscan and MRI data included in the above-mentioned database [11].…”

Section: Related Workmentioning

confidence: 99%

Unified deep learning approach for prediction of Parkinson's disease

et al. 2020

View full text Add to dashboard Cite

The paper presents a novel approach, based on deep learning, for diagnosis of Parkinson's disease through medical imaging. The approach includes analysis and use of the knowledge extracted by Deep Convolutional and Recurrent Neural Networks (DNNs) when trained with medical images, such as Magnetic Resonance Images and DaTscans. Internal representations of the trained DNNs constitute the extracted knowledge which is used in a transfer learning and domain adaptation manner, so as to create a unified framework for prediction of Parkinson's across different medical environments. A large experimental study is presented illustrating the ability of the proposed approach to effectively predict Parkinson's, using different medical image sets from real environments.

show abstract

Section: Related Workmentioning

confidence: 99%

Unified deep learning approach for prediction of Parkinson's disease

et al. 2020

View full text Add to dashboard Cite

show abstract

“…We then applied the procedure shown in Fig. 2, to train DNN' with the V s vectors extracted from the last hidden layer of the DNN that had been trained on [30,31]. The performance of the network was very high, classifying in the correct PD/NPD category 99.76% of the inputs.…”

Section: Prediction Of Parkinson's Based On Mri and Datscansmentioning

confidence: 99%

Transparent Adaptation in Deep Medical Image Diagnosis

Kollias

Vlaxos

Seferis

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The paper presents a novel deep learning approach, which extracts latent information from trained Deep Neural Networks (DNNs) and derives concise representations that are analyzed in an effective, transparent way for prediction in medical imaging. A novel methodology is presented, in which deep neural architectures that have been trained to provide highly accurate predictions over existing datasets are adapted, in a consistent way, to make predictions over different contexts and datasets. Unified prediction is then achieved over the original and the new datasets. Successful application is illustrated through a large experimental study for prediction of Parkinson's disease from MRI and DaTScans, as well as for prediction of COVID-19 from CT scans and X-rays.

show abstract

“…The research area of facial behaviour analysis includes the problems of: i) the recognition of the so-called six universal expressions (i.e., Anger, Disgust, Fear, Happy, Sad, Surprise), plus Neutral, influenced by the seminal work of Ekman [12], ii) the recognition of spontaneous expressions including mental states (pain intensity [17] and compound expressions [10]), iii) the detection of the facial Action Units (AU) and estimation of their intensity, according to the Facial Action Coding System [11] which provides a standardised taxonomy of facial muscles' movements, iv) the detection of micro-expressions, and v) the estimation of facial affect in a continuous dimensional space (e.g., valence and arousal). Related research can assist in flagging complex behavioral patterns such as deception, depression, autism, spectrum disorders and schizophrenia [1], [20], [27], [44], [56], [57].…”

Section: Introductionmentioning

confidence: 99%

Exploiting Multi-CNN Features in CNN-RNN Based Dimensional Emotion Recognition on the OMG in-the-Wild Dataset

Kollias

Zafeiriou

2021

IEEE Trans. Affective Comput.

Self Cite

113

View full text Add to dashboard Cite

This paper presents a novel CNN-RNN based approach, which exploits multiple CNN features for dimensional emotion recognition in-the-wild, utilizing the One-Minute Gradual-Emotion (OMG-Emotion) dataset. Our approach includes first pre-training with the relevant and large in size, Aff-Wild and Aff-Wild2 emotion databases. Low-, mid-and high-level features are extracted from the trained CNN component and are exploited by RNN subnets in a multi-task framework. Their outputs constitute an intermediate level prediction; final estimates are obtained as the mean or median values of these predictions. Fusion of the networks is also examined for boosting the obtained performance, at Decision-, or at Model-level; in the latter case a RNN was used for the fusion. Our approach, although using only the visual modality, outperformed state-of-the-art methods that utilized audio and visual modalities. Some of our developments have been submitted to the OMG-Emotion Challenge, ranking second among the technologies which used only visual information for valence estimation; ranking third overall. Through extensive experimentation, we further show that arousal estimation is greatly improved when low-level features are combined with high-level ones.

show abstract

Assessment of Parkinson’s Disease Based on Deep Neural Networks

Cited by 25 publications

References 10 publications

Unified deep learning approach for prediction of Parkinson's disease

Unified deep learning approach for prediction of Parkinson's disease

Transparent Adaptation in Deep Medical Image Diagnosis

Exploiting Multi-CNN Features in CNN-RNN Based Dimensional Emotion Recognition on the OMG in-the-Wild Dataset

Contact Info

Product

Resources

About