A novel method for reducing arrhythmia classification from 12-lead ECG signals to single-lead ECG with minimal loss of accuracy through teacher-student knowledge distillation

Sepahvand, Majid; Abdali-Mohammadi, Fardin

doi:10.1016/j.ins.2022.01.030

Cited by 47 publications

(22 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several studies have proposed models for the diagnosis of arrhythmias using Chapman data also used in the present study. The accuracy of DNN [ 43 ], CNN Trees [ 44 ], Meta CNN Trees [ 45 ], Single Classifier [ 46 ], 1-D CNN [ 47 ], RNN [ 48 ], XGBoost [ 49 ], Teacher and Student [ 50 ] models was 92.24%, 97.60%, 98.29%, 92.89%, 94.01%, 96.21%, 89.40%, 98.96%, and 98.13%, respectively. While our proposed GCN-MI had a higher accuracy (99.71%) this may be due to the consideration of the structure of leads.…”

Section: Discussionmentioning

confidence: 99%

Developing Graph Convolutional Networks and Mutual Information for Arrhythmic Diagnosis Based on Multichannel ECG Signals

Andayeshgar

Abdali-Mohammadi

Sepahvand

et al. 2022

IJERPH

Self Cite

View full text Add to dashboard Cite

Cardiovascular diseases, like arrhythmia, as the leading causes of death in the world, can be automatically diagnosed using an electrocardiogram (ECG). The ECG-based diagnostic has notably resulted in reducing human errors. The main aim of this study is to increase the accuracy of arrhythmia diagnosis and classify various types of arrhythmias in individuals (suffering from cardiovascular diseases) using a novel graph convolutional network (GCN) benefitting from mutual information (MI) indices extracted from the ECG leads. In this research, for the first time, the relationships of 12 ECG leads measured using MI as an adjacency matrix were illustrated by the developed GCN and included in the ECG-based diagnostic method. Cross-validation methods were applied to select both training and testing groups. The proposed methodology was validated in practice by applying it to the large ECG database, recently published by Chapman University. The GCN-MI structure with 15 layers was selected as the best model for the selected database, which illustrates a very high accuracy in classifying different types of rhythms. The classification indicators of sensitivity, precision, specificity, and accuracy for classifying heart rhythm type, using GCN-MI, were computed as 98.45%, 97.89%, 99.85%, and 99.71%, respectively. The results of the present study and its comparison with other studies showed that considering the MI index to measure the relationship between cardiac leads has led to the improvement of GCN performance for detecting and classifying the type of arrhythmias, in comparison to the existing methods. For example, the above classification indicators for the GCN with the identity adjacency matrix (or GCN-Id) were reported to be 68.24%, 72.83%, 95.24%, and 92.68%, respectively.

show abstract

Section: Discussionmentioning

confidence: 99%

Developing Graph Convolutional Networks and Mutual Information for Arrhythmic Diagnosis Based on Multichannel ECG Signals

Andayeshgar

Abdali-Mohammadi

Sepahvand

et al. 2022

IJERPH

Self Cite

View full text Add to dashboard Cite

show abstract

“…(Zhao et al, 2020) proposed a large kernel size model SEresnet Zhao based on SE-block (Hu et al, 2018), achieving second place in the PhysioNet 2020 competition (Alday et al, 2020). (Sepahvand & Abdali-Mohammadi, 2022) (KD+FitNet) and (Hong et al, 2018) (KD + attention) also use the distillation idea to bridge the gap between the model with multilead ECG signals and single-lead ECG signals by trying to make the student's output and inner features the same as the teacher's. Compared with KD, Our proposed method performs better and outperforms other SOTA single-lead models.…”

Section: Comparision With State-of-the-art Single Lead Ecg's Classifi...mentioning

confidence: 99%

“…Recently, Knowledge Distillation methods are proposed to improve single-lead ECG's performance (Sepahvand & Abdali-Mohammadi, 2022;Hong et al, 2018), where the teacher model was already developed through multi-lead ECG signals and the student model was developed through single-lead ECG signals. Since the student is educated under the supervision of the teacher to mimic the output space and inner feature or attention maps of its teacher, the internal feature maps to be processed must be strictly consistent.…”

Section: Introductionmentioning

confidence: 99%

“…To achieve model compression of single-lead-based model and minimize the performance gap between the arrhythmia classification model with multi-lead ECG signals and the arrhythmia classification model with single-lead ECG signals, (Sepahvand & Abdali-Mohammadi, 2022) proposed the teacher-student architecture. In order to deploy models in the poor-data environment without requiring direct access to multi-modal data acquired from a rich-data environment, (Hong et al, 2018) proposed a knowledge distillation (KD) method (RDPD) to enhance a predictive model trained on poor data using knowledge distilled from a high-complexity model trained on rich, private data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

MVKT-ECG: Efficient Single-lead ECG Classification on Multi-Label Arrhythmia by Multi-View Knowledge Transferring

Qin¹,

Li²,

Chen³

et al. 2023

Preprint

View full text Add to dashboard Cite

The widespread emergence of smart devices for ECG has sparked demand for intelligent singlelead ECG-based diagnostic systems. However, it is challenging to develop a single-lead-based ECG interpretation model for multiple diseases diagnosis due to the lack of some key disease information. In this work, we propose inter-lead Multi-View Knowledge Transferring of ECG (MVKT-ECG) to boost single-lead ECG's ability for multilabel disease diagnosis. This training strategy can transfer superior disease knowledge from multiple different views of ECG (e.g. 12-lead ECG) to single-lead-based ECG interpretation model to mine details in single-lead ECG signals that are easily overlooked by neural networks. MVKT-ECG allows this lead variety as a supervision signal within a teacher-student paradigm, where the teacher observes multi-lead ECG educates a student who observes only single-lead ECG. Since the mutual disease information between the single-lead ECG and muli-lead ECG plays a key role in knowledge transferring, we present a new disease-aware Contrastive Lead-information Transferring(CLT) to improve the mutual disease information between the single-lead ECG and muli-lead ECG. Moreover, We modify traditional Knowledge Distillation to multi-label disease Knowledge Distillation (MKD) to make it applicable for multi-label disease diagnosis. The comprehensive experiments verify that MVKT-ECG has an excellent performance in improving the diagnostic effect of single-lead ECG.* Equal contribution 1 AUTHORERR: Missing \icmlaffiliation.. AUTHORERR: Missing \icmlcorrespondingauthor.

show abstract

“…Indeed, the student attempts to emulate the teacher's action in a straightforward way in KD framework with least amount of loss [16,17]. This paper presents a novel BAA method with the help of KD paradigm using several ROIs extracted from X-ray images.…”

Section: Introductionmentioning

confidence: 99%

A Bone Age Assessment based on a hybrid Knowledge Distillation Paradigm using single ROI

Mardanpour

Sepahvand

Abdali-Mohammadi

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Bone age assessment (BAA) has been widely used in clinical area from pediatric endocrine diagnosis to estimating height of children for adulthood. Advancements in technology has accelerated the evolution of BAA methodologies, one of which is deep learning algorithms, which overcome the drawbacks of conventional approaches. In spite of excellent effectiveness of deep neural networks in detection of the correct class for bone age, they have a significant degree of complexity due to the numerous parameters they employ for each ROI. Therefore, they are not suitable for implementation in edge devices with limited resources. In this paper, we propose a BAA method using a hybrid knowledge distillation (KD) paradigm in order to conquer this difficulty by mapping different ROIs into a single ROI. In this regard, the student receives knowledge from a teacher network that has been pre-trained on six ROIs including bones of five fingers and the wrist, transfers the knowledge of its final response layer and internal layers to the student. Then, six student models each of which is constructed based on just one of these ROIs, while receiving the information of the teacher model by matching the feature maps of intermediate layers and last output of teacher with those of student in distillation modules. Empirical results on Digital Hand Atlas (DHA) report that our student model trained on one ROI obtains 95% accuracy on 19 classes of bone age makes it appropriate for medical IoT deployment. Also, it has competitive performance compared to the other state-of-the-art BAA studies, and performance analysis of our KD with three base KD models indicates superiority of our introduced method.

show abstract

A novel method for reducing arrhythmia classification from 12-lead ECG signals to single-lead ECG with minimal loss of accuracy through teacher-student knowledge distillation

Cited by 47 publications

References 38 publications

Developing Graph Convolutional Networks and Mutual Information for Arrhythmic Diagnosis Based on Multichannel ECG Signals

Developing Graph Convolutional Networks and Mutual Information for Arrhythmic Diagnosis Based on Multichannel ECG Signals

MVKT-ECG: Efficient Single-lead ECG Classification on Multi-Label Arrhythmia by Multi-View Knowledge Transferring

A Bone Age Assessment based on a hybrid Knowledge Distillation Paradigm using single ROI

Contact Info

Product

Resources

About