{"type":"ScholarlyArticle","title":"Concept-Level Causal Explanation Method for Brain Function Network Classification","authors":[{"name":"Jinduo Liu","slug":"jinduo-liu","given":"Jinduo","family":"Liu","affiliation":"Beijing University of Technology"},{"name":"Feipeng Wang","slug":"feipeng-wang","given":"Feipeng","family":"Wang","affiliation":"Beijing University of Technology"},{"name":"Junzhong Ji","slug":"junzhong-ji","given":"Junzhong","family":"Ji","affiliation":"Beijing University of Technology"}],"abstract":"Using deep models to classify brain functional networks (BFNs) for the auxiliary diagnosis and treatment of brain diseases has become increasingly popular. However, the unexplainability of deep models has seriously hindered their applications in computer-aided diagnosis. In addition, current explanation methods mostly focus on natural images, which cannot be directly used to explain the deep model for BFN classification. In this paper, we propose a concept-level causal explanation method for BFN classification called CLCEM. First, CLCEM employs the causal learning method to extract concepts that are meaningful to humans from BFNs. Second, it aggregates the same concepts to obtain the contribution of each concept to the model output. Finally, CLCEM adds the contribution of each concept to make a diagnosis. The experimental results show that our CLCEM can not only accurately identify brain regions related to specific brain diseases but also make decisions based on the concepts of these brain regions, which enables humans to understand the decision-making process without performance degradation.","doi":"10.24963/ijcai.2024/342","url":"https://ijcai.org/proceedings/2024/342","pdf":"https://ijcai.org/proceedings/2024/0342.pdf","markdown":"https://ijcai.org/proceedings/2024/342.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/342","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Humans and AI","track":"Main Track","number":342,"pages":{"first":3087,"last":3096},"keywords":["Humans and AI: HAI: Brain sciences","Data Mining: DM: Networks","AI Ethics, Trust, Fairness: ETF: Explainability and interpretability","Machine Learning: ML: Causality"],"videos":[],"references":[{"position":1,"raw":"[Byrne, 2023] Ruth MJ Byrne. Good explanations in ex- plainable artificial intelligence (xai): Evidence from hu- man explanatory reasoning. In Proceedings of the Thirty- Second International Joint Conference on Artificial Intel- ligence, pages 6536-6544, 2023.","title":"Good explanations in explainable artificial intelligence (xai): Evidence from human explanatory reasoning","authors":"M J Ruth, Byrne","year":"2023","venue":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2023/733"},{"position":2,"raw":"[Cauda et al., 2011] Franco Cauda, Elisabetta Geda, Katius- cia Sacco, Federico D'Agata, Sergio Duca, Giuliano Gem- iniani, and Roberto Keller. Grey matter abnormality in autism spectrum disorder: an activation likelihood estima- tion meta-analysis study. Journal of Neurology, Neuro- surgery & Psychiatry, 82(12):1304-1313, 2011.","title":"Grey matter abnormality in autism spectrum disorder: an activation likelihood estimation meta-analysis study","authors":"Franco Cauda, Elisabetta Geda, Katiuscia Sacco, D' Federico, Sergio Agata, Giuliano Duca, Roberto Geminiani, Keller","year":"2011","venue":"Journal of Neurology, Neurosurgery & Psychiatry","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[de Vos et al., 2018] Frank de Vos, Marisa Koini, Tijn M Schouten, Stephan Seiler, Jeroen van der Grond, Anita Lechner, Reinhold Schmidt, Mark de Rooij, and Serge ARB Rombouts. A comprehensive analysis of rest- ing state fmri measures to classify individual patients with alzheimer's disease. Neuroimage, 167:62-72, 2018.","title":"A comprehensive analysis of resting state fmri measures to classify individual patients with alzheimer's disease","authors":"De Vos","year":"2018","venue":"Neuroimage","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Ghorbani et al., 2019] Amirata Ghorbani, James Wexler, James Y Zou, and Been Kim. Towards automatic concept- based explanations. Advances in Neural Information Pro- cessing Systems, 32:9277-9286, 2019.","title":"Towards automatic conceptbased explanations","authors":"Ghorbani","year":"2019","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Goyal et al., 2019] Yash Goyal, Amir Feder, Uri Shalit, and Been Kim. Explaining classifiers with causal concept ef- fect (cace). arXiv preprint arXiv:1907.07165, 2019.","title":"Explaining classifiers with causal concept effect","authors":"Yash Goyal, Amir Feder, Uri Shalit, Been Kim","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gu et al., 2020] Donghao Gu, Yaowei Li, Feng Jiang, Zhao- jing Wen, Shaohui Liu, Wuzhen Shi, Guangming Lu, and Changsheng Zhou. Vinet: A visually interpretable im- age diagnosis network. IEEE Transactions on Multimedia, 22(7):1720-1729, 2020.","title":"Vinet: A visually interpretable image diagnosis network","authors":"Donghao Gu, Yaowei Li, Feng Jiang, Zhaojing Wen, Shaohui Liu, Wuzhen Shi, Guangming Lu, Changsheng Zhou","year":"2020","venue":"IEEE Transactions on Multimedia","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Henaff et al., 2015] Mikael Henaff, Joan Bruna, and Yann LeCun. Deep convolutional networks on graph-structured data. arXiv preprint arXiv:1506.05163, 2015.","title":"Deep convolutional networks on graph-structured data","authors":"Mikael Henaff, Joan Bruna, Yann Lecun","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Heskes et al., 2020] Tom Heskes, Evi Sijben, Ioan Gabriel Bucur, and Tom Claassen. Causal shapley values: Exploit- ing causal knowledge to explain individual predictions of complex models. Advances in neural information process- ing systems, 33:4778-4789, 2020.","title":"Causal shapley values: Exploiting causal knowledge to explain individual predictions of complex models","authors":"Heskes","year":"2020","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hu et al., 2021] Wenxing Hu, Xianghe Meng, Yuntong Bai, Aiying Zhang, Gang Qu, Biao Cai, Gemeng Zhang, Tony W Wilson, Julia M Stephen, Vince D Calhoun, et al. Interpretable multimodal fusion networks reveal mecha- nisms of brain cognition. IEEE transactions on medical imaging, 40(5):1474-1483, 2021.","title":"Interpretable multimodal fusion networks reveal mechanisms of brain cognition","authors":"Hu","year":"2021","venue":"IEEE transactions on medical imaging","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Huai et al., 2022] Mengdi Huai, Jinduo Liu, Chenglin Miao, Liuyi Yao, and Aidong Zhang. Towards automat- ing model explanations with certified robustness guaran- tees. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 6935-6943, 2022.","title":"Towards automating model explanations with certified robustness guaran-tees","authors":"Huai","year":"2022","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Jao Keehn et al., 2017] R Joanne Jao Keehn, Sandra S Sanchez, Claire R Stewart, Weiqi Zhao, Emily L Grenesko-Stevens, Brandon Keehn, and Ralph-Axel Müller. Impaired downregulation of visual cortex during auditory processing is associated with autism symptoma- tology in children and adolescents with autism spectrum disorder. Autism Research, 10(1):130-143, 2017.","title":"Impaired downregulation of visual cortex during auditory processing is associated with autism symptomatology in children and adolescents with autism spectrum disorder","authors":"Joanne Jao Keehn, Sandra S Sanchez, Claire R Stewart, Weiqi Zhao, Emily L Grenesko-Stevens, Brandon Keehn, Ralph-Axel Müller","year":"2017","venue":"Autism Research","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ji et al., 2021] Junzhong Ji, Xinying Xing, Yao Yao, Jun- wei Li, and Xiaodan Zhang. Convolutional kernels with an element-wise weighting mechanism for identifying ab- normal brain connectivity patterns. Pattern Recognition, 109:107570, 2021.","title":"Convolutional kernels with an element-wise weighting mechanism for identifying abnormal brain connectivity patterns","authors":"Ji","year":"2021","venue":"Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kana et al., 2016] Rajesh K Kana, Michelle A Patriquin, Briley S Black, Marie M Channell, and Bruno Wicker. Al- tered medial frontal and superior temporal response to im- plicit processing of emotions in autism. Autism Research, 9(1):55-66, 2016.","title":"Altered medial frontal and superior temporal response to implicit processing of emotions in autism","authors":"Michelle A Rajesh K Kana, Patriquin, S Briley, Marie M Black, Bruno Channell, Wicker","year":"2016","venue":"Autism Research","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kawahara et al., 2017] Jeremy Kawahara, Colin J Brown, Steven P Miller, Brian G Booth, Vann Chau, Ruth E Grunau, Jill G Zwicker, and Ghassan Hamarneh. Brain- netcnn: Convolutional neural networks for brain net- works; towards predicting neurodevelopment. NeuroIm- age, 146:1038-1049, 2017.","title":"Brainnetcnn: Convolutional neural networks for brain networks; towards predicting neurodevelopment","authors":"Jeremy Kawahara, Colin J Brown, Steven P Miller, Brian G Booth, Vann Chau, Ruth E Grunau, Jill G Zwicker, Ghassan Hamarneh","year":"2017","venue":"NeuroImage","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kim et al., 2016] Been Kim, Rajiv Khanna, and Oluwasanmi O Koyejo. Examples are not enough, learn to criticize! criticism for interpretability. Advances in neural information processing systems, 29:2288-2296, 2016.","title":"Examples are not enough, learn to criticize! criticism for interpretability","authors":"Kim","year":"2016","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kwon et al., 2019] Bum Chul Kwon, Min-Je Choi, Joanne Taery Kim, Edward Choi, Young Bin Kim, Soon- wook Kwon, Jimeng Sun, and Jaegul Choo. Retainvis: Visual analytics with interpretable and interactive recur- rent neural networks on electronic medical records. IEEE transactions on visualization and computer graphics, 25(1):299-309, 2019.","title":"Retainvis: Visual analytics with interpretable and interactive recurrent neural networks on electronic medical records","authors":"Kwon","year":"2019","venue":"IEEE transactions on visualization and computer graphics","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Li et al., 2014] Hai Li, Zhong Xue, Timothy M Ellmore, Richard E Frye, and Stephen TC Wong. Network-based analysis reveals stronger local diffusion-based connectiv- ity and different correlations with oral language skills in brains of children with high functioning autism spectrum disorders. Human brain mapping, 35(2):396-413, 2014.","title":"Network-based analysis reveals stronger local diffusion-based connectivity and different correlations with oral language skills in brains of children with high functioning autism spectrum disorders","authors":"Hai Li, Zhong Xue, Timothy M Ellmore, Richard E Frye, Stephen Tc Wong","year":"2014","venue":"Human brain mapping","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Li et al., 2018] Oscar Li, Hao Liu, Chaofan Chen, and Cynthia Rudin. Deep learning for case-based reasoning through prototypes: A neural network that explains its pre- dictions. In Proceedings of the AAAI Conference on Arti- ficial Intelligence, volume 32, 2018.","title":"Deep learning for case-based reasoning through prototypes: A neural network that explains its predictions","authors":"Li","year":"2018","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Libero et al., 2014] Lauren E Libero, Jose O Maximo, Hrishikesh D Deshpande, Laura G Klinger, Mark R Klinger, and Rajesh K Kana. The role of mirroring and mentalizing networks in mediating action intentions in autism. Molecular autism, 5(1):1-13, 2014.","title":"The role of mirroring and mentalizing networks in mediating action intentions in autism","authors":"Lauren E Libero, Jose O Maximo, Laura G Hrishikesh D Deshpande, Mark R Klinger, Rajesh K Klinger, Kana","year":"2014","venue":"Molecular autism","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Liu et al., 2022] Jinduo Liu, Junzhong Ji, Guangxu Xun, and Aidong Zhang. Inferring effective connectivity net- works from fmri time series with a temporal entropy-score. IEEE transactions on neural networks and learning sys- tems, 33(10):5993-6006, 2022.","title":"Inferring effective connectivity networks from fmri time series with a temporal entropy-score","authors":"Liu","year":"2022","venue":"IEEE transactions on neural networks and learning systems","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Liu et al., 2024] Jinduo Liu, Lu Han, and Junzhong Ji. Mcan: Multimodal causal adversarial networks for dy- namic effective connectivity learning from fmri and eeg data. IEEE Transactions on Medical Imaging, 2024.","title":"Mcan: Multimodal causal adversarial networks for dynamic effective connectivity learning from fmri and eeg data","authors":"Liu","year":"2024","venue":"IEEE Transactions on Medical Imaging","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Menassa et al., 2017] David A Menassa, Carolyn Sloan, and Steven A Chance. Primary olfactory cortex in autism and epilepsy: increased glial cells in autism. Brain Pathol- ogy, 27(4):437-448, 2017.","title":"Primary olfactory cortex in autism and epilepsy: increased glial cells in autism","authors":"Carolyn David A Menassa, Steven A Sloan, Chance","year":"2017","venue":"Brain Pathology","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[O'Shaughnessy et al., 2020] Matthew O'Shaughnessy, Gregory Canal, Marissa Connor, Christopher Rozell, and Mark Davenport. Generative causal explanations of black-box classifiers. Advances in Neural Information Processing Systems, 33:5453-5467, 2020.","title":"Generative causal explanations of black-box classifiers","authors":"O' Matthew, Gregory Shaughnessy, Marissa Canal, Christopher Connor, Mark Rozell, Davenport","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Ribeiro et al., 2016] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. \" why should i trust you?\" explain- ing the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowl- edge discovery and data mining, pages 1135-1144, 2016.","title":"why should i trust you?\" explaining the predictions of any classifier","authors":"Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin","year":"2016","venue":"Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Seguin et al., 2023] Caio Seguin, Olaf Sporns, and Andrew Zalesky. Brain network communication: concepts, models and applications. Nature reviews neuroscience, 24(9):557- 574, 2023.","title":"Brain network communication: concepts, models and applications","authors":"Caio Seguin, Olaf Sporns, Andrew Zalesky","year":"2023","venue":"Nature reviews neuroscience","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Selvaraju et al., 2019] Ramprasaath R Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. Grad-cam: Visual explanations from deep networks via gradient-based localization. In- ternational Journal of Computer Vision, 128(2):336-359, 2019.","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","authors":"Michael Ramprasaath R Selvaraju, Abhishek Cogswell, Ramakrishna Das, Devi Vedantam, Dhruv Parikh, Batra","year":"2019","venue":"International Journal of Computer Vision","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Sen and Parhi, 2021] Bhaskar Sen and Keshab K Parhi. Pre- dicting biological gender and intelligence from fmri via dynamic functional connectivity. IEEE Transactions on Biomedical Engineering, 68(3):815-825, 2021.","title":"Predicting biological gender and intelligence from fmri via dynamic functional connectivity","authors":"Bhaskar Sen, K Keshab, Parhi","year":"2021","venue":"IEEE Transactions on Biomedical Engineering","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Steward et al., 2023] Anna Steward, Davina Biel, Matthias Brendel, Anna Dewenter, Sebastian Roemer, Anna Rubin- ski, Ying Luan, Martin Dichgans, Michael Ewers, Nicolai Franzmeier, et al. Functional network segregation is as- sociated with attenuated tau spreading in alzheimer's dis- ease. Alzheimer's & Dementia, 19(5):2034-2046, 2023.","title":"Functional network segregation is associated with attenuated tau spreading in alzheimer's disease","authors":"Anna Steward, Davina Biel, Matthias Brendel, Anna Dewenter, Sebastian Roemer, Anna Rubinski, Ying Luan, Martin Dichgans, Michael Ewers, Nicolai Franzmeier","year":"2023","venue":"Alzheimer's & Dementia","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[van Kooten et al., 2008] Imke AJ van Kooten, Saskia JMC Palmen, Patricia von Cappeln, Harry WM Steinbusch, Hu- bert Korr, Helmut Heinsen, Patrick R Hof, Herman van Engeland, and Christoph Schmitz. Neurons in the fusiform gyrus are fewer and smaller in autism. Brain, 131(4):987- 999, 2008.","title":"Neurons in the fusiform gyrus are fewer and smaller in autism","authors":"Imke Aj Van Kooten, Jmc Saskia, Patricia Palmen, Von Cappeln, W M Harry, Hubert Steinbusch, Helmut Korr, Heinsen, Herman Patrick R Hof, Christoph Van Engeland, Schmitz","year":"2008","venue":"Brain","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wagner et al., 2019] Jorg Wagner, Jan Mathias Kohler, To- bias Gindele, Leon Hetzel, Jakob Thaddaus Wiedemer, and Sven Behnke. Interpretable and fine-grained visual ex- planations for convolutional neural networks. In Proceed- ings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9097-9107, 2019.","title":"Interpretable and fine-grained visual explanations for convolutional neural networks","authors":"Jorg Wagner, Jan Mathias Kohler, Tobias Gindele, Leon Hetzel, Jakob Thaddaus Wiedemer, Sven Behnke","year":"2019","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Woo et al., 2018] Sanghyun Woo, Jongchan Park, Joon- Young Lee, and In So Kweon. Cbam: Convolutional block attention module. In Proceedings of the European confer- ence on computer vision (ECCV), pages 3-19, 2018.","title":"Cbam: Convolutional block attention module","authors":"Sanghyun Woo, Jongchan Park, Joon-Young Lee, In So Kweon","year":"2018","venue":"Proceedings of the European conference on computer vision (ECCV)","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Yao et al., 2023] Liuyi Yao, Yaliang Li, Sheng Li, Jin- duo Liu, Mengdi Huai, Aidong Zhang, and Jing Gao. Concept-level model interpretation from the causal aspect. IEEE Transactions on Knowledge and Data Engineering, 35(9):8799-8810, 2023.","title":"Concept-level model interpretation from the causal aspect","authors":"Yao","year":"2023","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Yerys et al., 2015] Benjamin E Yerys, Ligia Antezana, Rachel Weinblatt, Kathryn F Jankowski, John Strang, Chandan J Vaidya, Robert T Schultz, William D Gaillard, and Lauren Kenworthy. Neural correlates of set-shifting in children with autism. Autism Research, 8(4):386-397, 2015.","title":"Neural correlates of set-shifting in children with autism","authors":"Ligia Benjamin E Yerys, Rachel Antezana, Kathryn F Weinblatt, John Jankowski, Strang, J Chandan, Robert T Vaidya, William D Schultz, Lauren Gaillard, Kenworthy","year":"2015","venue":"Autism Research","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zhang et al., 2024] Zuozhen Zhang, Junzhong Ji, and Jin- duo Liu. Metarlec: Meta-reinforcement learning for dis- covery of brain effective connectivity. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 10261-10269, 2024.","title":"Metarlec: Meta-reinforcement learning for discovery of brain effective connectivity","authors":"Zhang","year":"2024","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}