Peer-Reviewed Publications

  1. “A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography.” Alina Jade Barnett, Fides Regina Schwartz, Chaofan Tao, Chaofan Chen, Yinhao Ren, Joseph Y. Lo, and Cynthia Rudin. Nature Machine Intelligence. (2021). https://rdcu.be/cDhJ7
  2. “Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes.” Jon Donnelly, Alina Jade Barnett, and Chaofan Chen. CVPR: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. (2022). https://arxiv.org/abs/2111.15000
  3. “A User Interface to Communicate Interpretable AI Decisions to Radiologists.” Yanchen Jessie Ou†, Alina Jade Barnett†, Anika Mitra†, Fides Regina Schwartz, Chaofan Chen, Lars Grimm, Joseph Y. Lo, and Cynthia Rudin. Medical Imaging 2023: Image Perception, Observer Performance, and Technology Assessment. SPIE. (2023). https://doi.org/10.1117/12.2654068
  4. “Interpretable Deep Learning Models for Better Clinician-AI Communication in Clinical Mammography.” Alina Jade Barnett, Vaibhav Sharma, Neel Gajjar, Jerry Fang, Fides Regina Schwartz, Chaofan Chen, Joseph Y. Lo, and Cynthia Rudin. Medical Imaging 2022: Image Perception, Observer Performance, and Technology Assessment. SPIE. (2022). https://doi.org/10.1117/12.2612372
  5. “Interpretable Mammographic Image Classification using Cased-Based Reasoning and Deep Learning.” Alina Jade Barnett, Fides Regina Schwartz, Chaofan Tao, Chaofan Chen, Yinhao Ren, Joseph Y. Lo, and Cynthia Rudin. IJCAI-21 Workshop on Deep Learning, Case-Based Reasoning, and AutoML: Present and Future Synergies. (2021). https://arxiv.org/abs/2107.05605
  6. “This Looks Like That: Deep Learning for Interpretable Image Recognition.” Chaofan Chen†, Oscar Li†, Chaofan Tao, Alina Jade Barnett, Cynthia Rudin, and Jonathan K. Su. NeurIPS: Advances in Neural Information Processing Systems 32 (2019): 8930-8941. Spotlight paper (top 3%) https://arxiv.org/abs/1806.10574
  7. “ProtoEEGNet: an interpretable approach for detecting interictal epileptiform discharges.” Dennis Tang, Frank Willard, Ronan Tegerdine, Luke Triplett, Jon Donnelly, Luke Moffett, Lesia Semenova, Alina Jade Barnett, Jin Jing, Cynthia Rudin, BrandonWestover. Medical Imaging meets NeurIPS workshop. (2023).

Articles Under Review

  1. “Improving Clinician Performance in Classification of EEG Patterns on the Ictal-Interictal-Injury Continuum using Interpretable Machine Learning.” Alina Jade Barnett†, Zhicheng Guo†, Jin Jing†, Wendong Ge, M. Brandon Westover and Cynthia Rudin. (2023). https://arxiv.org/abs/2211.05207
  2. “AsymMirai: Interpretable Breast Cancer Risk Prediction from Mammograms.” Jon Donnelly, Luke Moffett, Alina Jade Barnett, Hari Trivedi, Fides Schwartz, Joseph Lo†, Cynthia Rudin†. (2023).
  3. “Active Learning and Pseudo Labeling for Breast Mass Segmentation in 2D Digital Mammography.” Vaibhav Sharma, Sangwook Cheon, Giyoung Kim, Julia Yang, Alina Jade Barnett, Neal Hall, Avivah Wang, Fides Regina Schwartz, Chaofan Chen, Lars Grimm, Joseph Lo and Cynthia Rudin. (2023).

Working Papers

  1. “High-Resolution ProtoPNet.” Alina Jade Barnett, Julia Yang, Satvik Kishore, Jerry Fang, Chaofan Chen, Fides Regina Schwartz, Joseph Lo and Cynthia Rudin. (2023).

Grants

  1. $19,831.00 PI for a Duke Incubation Fund Award from the Duke Innovation & Entrepreneurship Initiative. A multi-department interdisciplinary project for superior interpretability on neural networks that analyze mammograms. 2019–2021.

Recordings

  1. “Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes.” CVPR: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition 2022. Slides and video capture by Alina Jade Barnett, narrated by Jon Donnelly, script jointly created by Jon and Alina. https://www.youtube.com/watch?v=2cgidJJtGU8
  2. “Introduction and Code Demo for Industry Practitioners: Interpretable Image Classification with ProtoPNet and IAIA-BL.” The Conference on Responsible Machine Learning 2021. https://www.youtube.com/watch?v=-IkQ5CbVTkE