On the Within-class Variation Issue in Alzheimer's Disease Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912606667669504 |
|---|---|
| author | Kang, Jiawen Han, Dongrui Meng, Lingwei Zhou, Jingyan Li, Jinchao Wu, Xixin Meng, Helen |
| author_facet | Kang, Jiawen Han, Dongrui Meng, Lingwei Zhou, Jingyan Li, Jinchao Wu, Xixin Meng, Helen |
| contents | Alzheimer's Disease (AD) detection employs machine learning classification models to distinguish between individuals with AD and those without. Different from conventional classification tasks, we identify within-class variation as a critical challenge in AD detection: individuals with AD exhibit a spectrum of cognitive impairments. Therefore, simplistic binary AD classification may overlook two crucial aspects: within-class heterogeneity and instance-level imbalance. In this work, we found using a sample score estimator can generate sample-specific soft scores aligning with cognitive scores. We subsequently propose two simple yet effective methods: Soft Target Distillation (SoTD) and Instance-level Re-balancing (InRe), targeting two problems respectively. Based on the ADReSS and CU-MARVEL corpora, we demonstrated and analyzed the advantages of the proposed approaches in detection performance. These findings provide insights for developing robust and reliable AD detection models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_16322 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Within-class Variation Issue in Alzheimer's Disease Detection Kang, Jiawen Han, Dongrui Meng, Lingwei Zhou, Jingyan Li, Jinchao Wu, Xixin Meng, Helen Audio and Speech Processing Artificial Intelligence Computation and Language Machine Learning Sound Neurons and Cognition Alzheimer's Disease (AD) detection employs machine learning classification models to distinguish between individuals with AD and those without. Different from conventional classification tasks, we identify within-class variation as a critical challenge in AD detection: individuals with AD exhibit a spectrum of cognitive impairments. Therefore, simplistic binary AD classification may overlook two crucial aspects: within-class heterogeneity and instance-level imbalance. In this work, we found using a sample score estimator can generate sample-specific soft scores aligning with cognitive scores. We subsequently propose two simple yet effective methods: Soft Target Distillation (SoTD) and Instance-level Re-balancing (InRe), targeting two problems respectively. Based on the ADReSS and CU-MARVEL corpora, we demonstrated and analyzed the advantages of the proposed approaches in detection performance. These findings provide insights for developing robust and reliable AD detection models. |
| title | On the Within-class Variation Issue in Alzheimer's Disease Detection |
| topic | Audio and Speech Processing Artificial Intelligence Computation and Language Machine Learning Sound Neurons and Cognition |
| url | https://arxiv.org/abs/2409.16322 |