Applications of interpretable deep learning in neuroimaging: a comprehensive review
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909231544795136 |
|---|---|
| author | Munroe, Lindsay da Silva, Mariana Heidari, Faezeh Grigorescu, Irina Dahan, Simon Robinson, Emma C. Deprez, Maria So, Po-Wah |
| author_facet | Munroe, Lindsay da Silva, Mariana Heidari, Faezeh Grigorescu, Irina Dahan, Simon Robinson, Emma C. Deprez, Maria So, Po-Wah |
| contents | Clinical adoption of deep learning models has been hindered, in part, because the black-box nature of neural networks leads to concerns regarding their trustworthiness and reliability. These concerns are particularly relevant in the field of neuroimaging due to the complex brain phenotypes and inter-subject heterogeneity often encountered. The challenge can be addressed by interpretable deep learning (iDL) methods that enable the visualisation and interpretation of the inner workings of deep learning models. This study systematically reviewed the literature on neuroimaging applications of iDL methods and critically analysed how iDL explanation properties were evaluated. Seventy-five studies were included, and ten categories of iDL methods were identified. We also reviewed five properties of iDL explanations that were analysed in the included studies: biological validity, robustness, continuity, selectivity, and downstream task performance. We found that the most popular iDL approaches used in the literature may be sub-optimal for neuroimaging data, and we discussed possible future directions for the field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_17792 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Applications of interpretable deep learning in neuroimaging: a comprehensive review Munroe, Lindsay da Silva, Mariana Heidari, Faezeh Grigorescu, Irina Dahan, Simon Robinson, Emma C. Deprez, Maria So, Po-Wah Image and Video Processing Computer Vision and Pattern Recognition Neurons and Cognition Clinical adoption of deep learning models has been hindered, in part, because the black-box nature of neural networks leads to concerns regarding their trustworthiness and reliability. These concerns are particularly relevant in the field of neuroimaging due to the complex brain phenotypes and inter-subject heterogeneity often encountered. The challenge can be addressed by interpretable deep learning (iDL) methods that enable the visualisation and interpretation of the inner workings of deep learning models. This study systematically reviewed the literature on neuroimaging applications of iDL methods and critically analysed how iDL explanation properties were evaluated. Seventy-five studies were included, and ten categories of iDL methods were identified. We also reviewed five properties of iDL explanations that were analysed in the included studies: biological validity, robustness, continuity, selectivity, and downstream task performance. We found that the most popular iDL approaches used in the literature may be sub-optimal for neuroimaging data, and we discussed possible future directions for the field. |
| title | Applications of interpretable deep learning in neuroimaging: a comprehensive review |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Neurons and Cognition |
| url | https://arxiv.org/abs/2406.17792 |