Cross-patient Seizure Onset Zone Classification by Patient-Dependent Weight

TL;DR

This paper introduces a patient-dependent weight fine-tuning approach for seizure onset zone classification, significantly improving accuracy across diverse patient datasets by customizing models for individual patients.

Contribution

It proposes a novel method to fine-tune pretrained models with patient-specific weights, addressing the cross-patient variability challenge in seizure zone classification.

Findings

Achieved over 10% average accuracy improvement in leave-one-patient-out tests.

Demonstrated effectiveness of patient-dependent weights in enhancing model performance.

Validated approach across multiple patient datasets with consistent improvements.

Abstract

Identifying the seizure onset zone (SOZ) in patients with focal epilepsy is essential for surgical treatment and remains challenging due to its dependence on visual judgment by clinical experts. The development of machine learning can assist in diagnosis and has made promising progress. However, unlike data in other fields, medical data is usually collected from individual patients, and each patient has different illnesses, physical conditions, and medical histories, which leads to differences in the distribution of each patient's data. This makes it difficult for a machine learning model to achieve consistently reliable performance in every new patient dataset, which we refer to as the "cross-patient problem." In this paper, we propose a method to fine-tune a pretrained model using patient-specific weights for every new test patient to improve diagnostic performance. First, the supervised learning method is used to train a machine learning model. Next, using the intermediate features of the trained model obtained through the test patient data, the similarity between the test patient data and each training patient's data is defined to determine the weight of each training patient to be used in the following fine-tuning. Finally, we fine-tune all parameters in the pretrained model with training data and patient weights. In the experiment, the leave-one-patient-out method is used to evaluate the proposed method, and the results show improved classification accuracy for every test patient, with an average improvement of more than 10%.