Don’t PANIC: Prototypical Additive Neural Network for Interpretable Classification of Alzheimer’s Disease

Wolf, Tom Nuno; Pölsterl, Sebastian und Wachinger, Christian (2023): Don’t PANIC: Prototypical Additive Neural Network for Interpretable Classification of Alzheimer’s Disease. IPMI 2023 : Information Processing in Medical Imaging, San Carlos De Bariloche, Argentina, 18-23 June 2023. Frangi, Alejandro; de Bruijne, Marleen; Wassermann, Demian und Navab, Nassir (eds.) : In: Information Processing in Medical Imaging : 28th International Conference, IPMI 2023, San Carlos de Bariloche, Argentina, June 18–23, 2023, Proceedings, Vol. 13939 Cham: Springer. pp. 82-94

Abstract

Alzheimer’s disease (AD) has a complex and multifactorial etiology, which requires integrating information about neuroanatomy, genetics, and cerebrospinal fluid biomarkers for accurate diagnosis. Hence, recent deep learning approaches combined image and tabular information to improve diagnostic performance. However, the black-box nature of such neural networks is still a barrier for clinical applications, in which understanding the decision of a heterogeneous model is integral. We propose PANIC, a prototypical additive neural network for interpretable AD classification that integrates 3D image and tabular data. It is interpretable by design and, thus, avoids the need for post-hoc explanations that try to approximate the decision of a network. Our results demonstrate that PANIC achieves state-of-the-art performance in AD classification, while directly providing local and global explanations. Finally, we show that PANIC extracts biologically meaningful signatures of AD, and satisfies a set of desirable desiderata for trustworthy machine learning. Our implementation is available at https://github.com/ai-med/PANIC.

• Item Type: Conference or Workshop Item (Paper)
• Faculties: Medicine > Medical Center of the University of Munich > Clinic and Polyclinic for Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy
• Subjects: 000 Computer science, information and general works > 004 Data processing computer science; 600 Technology > 610 Medicine and health
• ISBN: 978-3-031-34047-5 ; 978-3-031-34048-2
• Place of Publication: Cham
• Language: English