A Cognitive-Driven Ordinal Preservation for Multimodal Imbalanced Brain Disease Diagnosis

Zhu, Qi; Zhu, Ting; Zhang, Rui; Ye, Haizhou; Sun, Kening; Xu, Yang; Zhang, Daoqiang

doi:10.1109/tcds.2022.3175360

Cited by 8 publications

(3 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another contribution is that a triplet-based ordinal locality regularization was added to reveal the underlying ranking information of multi-site subjects from different classes, and jointly selected the common features in different modalities. Most of the previous methods focused on the relationships between labels and samples or the simple dependence between samples after mapping the original feature space into a new space, ignoring the discriminative information among samples [17]. Our method accurately preserves intrinsic structural information among subjects in each modality by retaining ranking information within each sample's neighborhood.…”

Section: Discussionmentioning

confidence: 99%

“…The use of pairwise similarity measures or other simple metrics to represent complex structural relationships among subjects results in the loss of topological structure information. Besides, due to intra-modality heterogeneity, including class imbalance, data distribution heterogeneity, and label inconsistencies [17], brings challenges in selecting discriminative features. Moreover, these methods overlook the challenges of the use of multisite data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Joint multi-site domain adaptation and multi-modality feature selection for the diagnosis of psychiatric disorders

Ji,

Silva,

Adali

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

Identifying biomarkers for computer-aided diagnosis (CAD) is crucial for early intervention of psychiatric disorders. Multi-site data have been utilized to increase the sample size and improve statistical power, while multi-modality classification offers significant advantages over traditional single-modality based approaches for diagnosing psychiatric disorders. However, inter-site heterogeneity and intra-modality heterogeneity present challenges to multi-site and multi-modality based classification. In this paper, brain functional and structural networks (BFNs/BSNs) from multiple sites were constructed to establish a joint multi-site multi-modality framework for psychiatric diagnosis. To do this we developed a hypergraph based multi-source domain adaptation (HMSDA) which allows us to transform source domain subjects into a target domain. A local ordinal structure based multi-task feature selection (LOSMFS) approach was developed by integrating the transformed functional and structural connections (FCs/SCs). The effectiveness of our method was validated by evaluating diagnosis of both schizophrenia (SZ) and autism spectrum disorder (ASD). The proposed method obtained accuracies of 92.2%±2.22% and 84.8%±2.68% for the diagnosis of SZ and ASD, respectively. We also compared with 6 domain adaptation (DA), 10 multi-modality feature selection, and 8 multi-site and multi-modality methods. Results showed the proposed HMSDA + LOSMFS effectively integrates multi-site and multi-modality data to enhance psychiatric diagnosis and identify disorder-specific diagnostic brain connections.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Joint multi-site domain adaptation and multi-modality feature selection for the diagnosis of psychiatric disorders

Ji,

Silva,

Adali

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The evaluation metrics AUC, F-measure and G-mean are widely used to evaluate the classification performance of machine learning models for imbalanced data classification [12][13][14]. To facilitate the introduction of the calculation rules of the evaluation metrics, the confusion matrix was first established, as detailed in Table 1.…”

Section: Performance Evaluation Metricmentioning

confidence: 99%

A Method for Analyzing the Performance Impact of Imbalanced Binary Data on Machine Learning Models

Zheng

Wang

et al. 2022

Axioms

View full text Add to dashboard Cite

Machine learning models may not be able to effectively learn and predict from imbalanced data in the fields of machine learning and data mining. This study proposed a method for analyzing the performance impact of imbalanced binary data on machine learning models. It systematically analyzes 1. the relationship between varying performance in machine learning models and imbalance rate (IR); 2. the performance stability of machine learning models on imbalanced binary data. In the proposed method, the imbalanced data augmentation algorithms are first designed to obtain the imbalanced dataset with gradually varying IR. Then, in order to obtain more objective classification results, the evaluation metric AFG, arithmetic mean of area under the receiver operating characteristic curve (AUC), F-measure and G-mean are used to evaluate the classification performance of machine learning models. Finally, based on AFG and coefficient of variation (CV), the performance stability evaluation method of machine learning models is proposed. Experiments of eight widely used machine learning models on 48 different imbalanced datasets demonstrate that the classification performance of machine learning models decreases with the increase of IR on the same imbalanced data. Meanwhile, the classification performances of LR, DT and SVC are unstable, while GNB, BNB, KNN, RF and GBDT are relatively stable and not susceptible to imbalanced data. In particular, the BNB has the most stable classification performance. The Friedman and Nemenyi post hoc statistical tests also confirmed this result. The SMOTE method is used in oversampling-based imbalanced data augmentation, and determining whether other oversampling methods can obtain consistent results needs further research. In the future, an imbalanced data augmentation algorithm based on undersampling and hybrid sampling should be used to analyze the performance impact of imbalanced binary data on machine learning models.

show abstract

Iterative minority oversampling and its ensemble for ordinal imbalanced datasets

Wang,

Zhang,

Luo

2024

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

A Cognitive-Driven Ordinal Preservation for Multimodal Imbalanced Brain Disease Diagnosis

Cited by 8 publications

References 56 publications

Joint multi-site domain adaptation and multi-modality feature selection for the diagnosis of psychiatric disorders

Joint multi-site domain adaptation and multi-modality feature selection for the diagnosis of psychiatric disorders

A Method for Analyzing the Performance Impact of Imbalanced Binary Data on Machine Learning Models

Iterative minority oversampling and its ensemble for ordinal imbalanced datasets

Contact Info

Product

Resources

About