A Self-Interpretable Deep Learning Model for Seizure Prediction Using a Multi-Scale Prototypical Part Network
The epileptic seizure prediction (ESP) method aims to timely forecast the occurrence of seizures, which is crucial to improving patients’ quality of life. Many deep learning-based methods have been developed to tackle this issue and achieve significant progress in recent years. However, t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10078917/ |
| _version_ | 1797805172885291008 |
|---|---|
| author | Yikai Gao Aiping Liu Lanlan Wang Ruobing Qian Xun Chen |
| author_facet | Yikai Gao Aiping Liu Lanlan Wang Ruobing Qian Xun Chen |
| author_sort | Yikai Gao |
| collection | DOAJ |
| description | The epileptic seizure prediction (ESP) method aims to timely forecast the occurrence of seizures, which is crucial to improving patients’ quality of life. Many deep learning-based methods have been developed to tackle this issue and achieve significant progress in recent years. However, the “black-box” nature of deep learning models makes the clinician mistrust the prediction results, severely limiting its clinical application. For this purpose, in this study, we propose a self-interpretable deep learning model for patient-specific epileptic seizure prediction: Multi-Scale Prototypical Part Network (MSPPNet). This model attempts to measure the similarity between the inputs and prototypes (learned during training) as evidence to make final predictions, which could provide a transparent reasoning process and decision basis (e.g., significant prototypes for inputs and corresponding similarity score). Furthermore, we assign different sizes to the prototypes in latent space to capture the multi-scale features of EEG signals. To the best of our knowledge, this is the first study that develops a self-interpretable deep learning model for seizure prediction, other than the existing post hoc interpretation studies. Our proposed model is evaluated on two public epileptic EEG datasets (CHB-MIT: 16 patients with a total of 85 seizures, Kaggle: 5 dogs with a total of 42 seizures), with a sensitivity of 93.8% and a false prediction rate of 0.054/h in the CHB-MIT dataset and a sensitivity of 88.6% and a false prediction rate of 0.146/h in the Kaggle dataset, achieving the current state-of-the-art performance with self-interpretable evidence. |
| first_indexed | 2024-03-13T05:48:02Z |
| format | Article |
| id | doaj.art-a6b3ebf2629141b083f77e4cc7239ac3 |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-13T05:48:02Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-a6b3ebf2629141b083f77e4cc7239ac32023-06-13T20:07:00ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102023-01-01311847185610.1109/TNSRE.2023.326084510078917A Self-Interpretable Deep Learning Model for Seizure Prediction Using a Multi-Scale Prototypical Part NetworkYikai Gao0https://orcid.org/0000-0003-1164-9529Aiping Liu1https://orcid.org/0000-0001-8849-5228Lanlan Wang2Ruobing Qian3Xun Chen4https://orcid.org/0000-0002-4922-8116School of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, ChinaSchool of Information Science and Technology, University of Science and Technology of China (USTC), Hefei, ChinaDepartment of Neurosurgery, Epilepsy Center, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Anhui, Hefei, ChinaDepartment of Neurosurgery, Epilepsy Center, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Anhui, Hefei, ChinaDepartment of Neurosurgery, Department of Electronic Engineering and Information Science, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, ChinaThe epileptic seizure prediction (ESP) method aims to timely forecast the occurrence of seizures, which is crucial to improving patients’ quality of life. Many deep learning-based methods have been developed to tackle this issue and achieve significant progress in recent years. However, the “black-box” nature of deep learning models makes the clinician mistrust the prediction results, severely limiting its clinical application. For this purpose, in this study, we propose a self-interpretable deep learning model for patient-specific epileptic seizure prediction: Multi-Scale Prototypical Part Network (MSPPNet). This model attempts to measure the similarity between the inputs and prototypes (learned during training) as evidence to make final predictions, which could provide a transparent reasoning process and decision basis (e.g., significant prototypes for inputs and corresponding similarity score). Furthermore, we assign different sizes to the prototypes in latent space to capture the multi-scale features of EEG signals. To the best of our knowledge, this is the first study that develops a self-interpretable deep learning model for seizure prediction, other than the existing post hoc interpretation studies. Our proposed model is evaluated on two public epileptic EEG datasets (CHB-MIT: 16 patients with a total of 85 seizures, Kaggle: 5 dogs with a total of 42 seizures), with a sensitivity of 93.8% and a false prediction rate of 0.054/h in the CHB-MIT dataset and a sensitivity of 88.6% and a false prediction rate of 0.146/h in the Kaggle dataset, achieving the current state-of-the-art performance with self-interpretable evidence.https://ieeexplore.ieee.org/document/10078917/Deep learninginterpretabilitysignal processingseizure predictionelectroencephalography |
| spellingShingle | Yikai Gao Aiping Liu Lanlan Wang Ruobing Qian Xun Chen A Self-Interpretable Deep Learning Model for Seizure Prediction Using a Multi-Scale Prototypical Part Network IEEE Transactions on Neural Systems and Rehabilitation Engineering Deep learning interpretability signal processing seizure prediction electroencephalography |
| title | A Self-Interpretable Deep Learning Model for Seizure Prediction Using a Multi-Scale Prototypical Part Network |
| title_full | A Self-Interpretable Deep Learning Model for Seizure Prediction Using a Multi-Scale Prototypical Part Network |
| title_fullStr | A Self-Interpretable Deep Learning Model for Seizure Prediction Using a Multi-Scale Prototypical Part Network |
| title_full_unstemmed | A Self-Interpretable Deep Learning Model for Seizure Prediction Using a Multi-Scale Prototypical Part Network |
| title_short | A Self-Interpretable Deep Learning Model for Seizure Prediction Using a Multi-Scale Prototypical Part Network |
| title_sort | self interpretable deep learning model for seizure prediction using a multi scale prototypical part network |
| topic | Deep learning interpretability signal processing seizure prediction electroencephalography |
| url | https://ieeexplore.ieee.org/document/10078917/ |
| work_keys_str_mv | AT yikaigao aselfinterpretabledeeplearningmodelforseizurepredictionusingamultiscaleprototypicalpartnetwork AT aipingliu aselfinterpretabledeeplearningmodelforseizurepredictionusingamultiscaleprototypicalpartnetwork AT lanlanwang aselfinterpretabledeeplearningmodelforseizurepredictionusingamultiscaleprototypicalpartnetwork AT ruobingqian aselfinterpretabledeeplearningmodelforseizurepredictionusingamultiscaleprototypicalpartnetwork AT xunchen aselfinterpretabledeeplearningmodelforseizurepredictionusingamultiscaleprototypicalpartnetwork AT yikaigao selfinterpretabledeeplearningmodelforseizurepredictionusingamultiscaleprototypicalpartnetwork AT aipingliu selfinterpretabledeeplearningmodelforseizurepredictionusingamultiscaleprototypicalpartnetwork AT lanlanwang selfinterpretabledeeplearningmodelforseizurepredictionusingamultiscaleprototypicalpartnetwork AT ruobingqian selfinterpretabledeeplearningmodelforseizurepredictionusingamultiscaleprototypicalpartnetwork AT xunchen selfinterpretabledeeplearningmodelforseizurepredictionusingamultiscaleprototypicalpartnetwork |