AI-Pathology: AI-Driven Neuropathologic Deep Phenotyping of Human Brains

Shedding Lights on Alzheimer's, Dementia, and Other Neurodegenerative Dieases

brainsec

Alzheimer's disease pathologies have been reported in both grey matter (GM) and white matter (WM) with different density distributions, making the automated separation task of GM and WM necessary to neuropathologic deep phenotyping. Standard segmentation and plaque detection methods typically involve manual annotations, where a trained researcher traces the boundary of GM and WM in ultra-high resolution whole slide images (WSIs). This method can be time-consuming and subjective, preventing the analysis of large amounts of WSIs in a scalable way. This project aims to develop a robust data- and label-efficient deep-learning based pipeline to automate a variety of neuropatholoy image analysis tasks (including GM/WM segmentation, blood vessel detection, and localization of different pathologies). While supervised learning techniques such as convolutional neural networks (CNNs) or UNET achieve promising results, procuring a sufficiently large dataset with annotations is labor intensive and time consuming. In this interdisciplinary project, we aim to contribute to the advancement of science in both the digital pathology domain as well as the computational methods of AI.

In the project funded by UC Noyce Initiative, we have explored semi-supervised learning and active-learning approaches to construct a label-efficient learning framework. We also explored computational efficient adaptation of large language models (LLMs) for our learning tasks. We will continue to investigate efficient adaptation methods to tap the potential of emerging foundational models and multimodal large language models (MLLMs) that are at the forefront of AI.

In 2024, our multi-disciplinary team has been awarded a five-year grant from the National Institute on Aging (NIA) to provide a quantitative understanding of whether there are differences in the neuropathologic landscape of Alzheimer's disease among Hispanic and Latino individuals. More details can be found in our newsroom stories posted on UC Davis Health News and College of Engineering News.

Most recently, together with Dr. Dugger and Dr. Gutman, our team received a grant from Chan Zuckerberg Initiative DAF as part of the CZI Neuroscience Program to develop and validate scalable, generalizable, & computationally-efficient ML approaches for quantitative neuropathology assessments of digital whole slide images in Alzheimer's.

People

Faculty Investigators for NIH R01

  • Dr. Brittany Dugger, Alzheimer's Disease Center/UCDH-Pathology and Laboratory Medicine (Lead PI)
  • Dr. Chen-Nee Chuah, Electrical & Computer Engineering (Co-I)
  • Dr. Lorena Garcia, UCDH-Epidemiology (Co-I)
  • Dr Laurel Beckett, UCDH-Public Health Sciences (Co-I)
  • Dr. Dan Mungas, UCDH-Neurology (Co-I)
  • Dr. Luis Carvajal-Carmona, UCDH-Biochemistry and Molecular Medicine, (Co-I)
  • Dr. Paul Lott, UCDH-Biochemistry and Molecular Medicine, (Co-I)
  • Dr. David Gutman, Biomedical Informatics, Emory University (Co-PI)
  • Dr. Pietro Michelucci, Executive Director, Human Computation Institute (Co-PI)

Faculty Investigators for CZI Neuroscience Program

  • Dr. Chen-Nee Chuah, Electrical & Computer Engineering (Lead PI)
  • Dr. Brittany Dugger, Alzheimer's Disease Center/UC Davis Health-Pathology and Laboratory Medicine (Co-PI)
  • Dr. David Gutman, Biomedical Informatics, Emory University (Co-PI)

Faculty Investigators for Noyce UC Initiative

  • Dr. Chen-Nee Chuah, Electrical & Computer Engineering (Lead PI)
  • Dr. Brittany Dugger, Alzheimer's Disease Center/UC Davis Health-Pathology and Laboratory Medicine (Co-I)
  • Dr. Peter Chang, UC Irvine (Co-PI)
  • Dr. Michael Keiser, UCSF (Co-PI)

Faculty Investigators for Cypres Grant

  • Dr. Brittany Dugger, Alzheimer's Disease Center/UC Davis Health-Pathology and Laboratory Medicine (Lead PI)
  • Dr. Chen-Nee Chuah, Electrical & Computer Engineering (Co-I)
  • Dr. Samson Cheung, Electrical & Computer Engineering, University of Kentucky (Co-I)

UC Davis Students

  • Luca Cerny Oliveira, ECE (PhD)
  • Shivam Rai Sharma, CS (PhD)
  • Smit Modi, CS (MS)
  • Ajinkya Chaudhari, CS( MS)
  • Olivia Shen, CS (Undergraduate)
  • Kyle Luo, CS (Undergraduate)

UC Davis Alumni

  • Zhenfeng (Jeff) Lai, ECE (PhD, 2019-23), Noyce Fellow
  • Joohi Chauhan, ECE (Postdoc, 2023-24)
  • Zhuoheng Li, CS (BS, 2024)
  • Kolin Guo, ECE (BS, 2019-20)
  • Wenda Xu, ECE (BS, 2019-20)

Publications, Presentations, and Achievements

Health Focused Publications

  • L. Cerny-Oliveira, J. Chauhan, A. Chaudhari, S. Cheung, V. Patel, A. C. Villablanca, L-W. Jin, C. DeCarli, C-N. Chuah, B. N. Dugger, "A Machine Learning Approach to Automate Microinfarct Screening in Hematoxylin and Eosin-stained Human Brain Tissues," to appear in the Journal of Neuropathology and Experimental Neurology (JNEN).
  • R. Scalco, L. Cerny-Oliveira, Z. Lai, D. Harvey L. Abujamil, C. DeCarli, L-W. Jin, C-N. Chuah, and B. N. Dugger, "Machine learning quantification of Amyloid-b in temporal lobe of 131 Brain Bank Cases," Acta Neuropathologica Communications, 12(1):134, Aug 2024. [DOI: 10.1186/s40478-024-01827-7]
  • Z. Lai, J. Chauhan, D. Chen, B. Dugger, S-C. Cheung, and C-N. Chuah, "Semi-Path: An Interactive Semi-supervised Learning Framework for Gigapixel Pathology Image Analysis," Elsevier Smart Health Journal, presented at IEEE/ACM CHASE, June 2024.
  • A. Villablanca, B. N. Dugger, S. Nuthikattu, J. Chauhan, S. Cheung, C-N. Chuah, S. L. Garrison, D. Milenkovic, J. E. Norman, L. C. Oliveira, B. P. Smith, and S. D. Brown, "How cy pres promotes transdisciplinary convergence science: an academic health center for women's cardiovascular and brain health," Journal of Clinical and Translational Science, vol. 8, issue 1, 2024, e16, 1-12. [DOI: 10.1017/cts.2023.705]
  • Z. Lai, Z. Li, L. Cerny Oliveira, J. Chauhan, B. Dugger, and C-N. Chuah, "CLIPath: Fine-tune CLIP with Visual Feature Fusion for Pathology Image Analysis Towards Minimizing Data Collection Efforts," ICCV 2nd Workshop on Computer Vision for Automated Medical Diagnosis (CVAMD), Oct 2023.
  • L. Cerny Oliveira, Z. Lai, D. Harvey, K. Nzenkue, L-W. Jim, C. DeCarlie, C-N. Chuah, and B. N. Dugger, "Pre-analytic variable effects on segmentation and quantification machine learning algorithms for amyloid beta analyzes on digitized human brain slides," Journal of Neuropathology and Experimental Neurology, Jan 2023. [PMID: 36692190]
  • Z. Lai, L. Cerny Oliveira, R. Guo, W. Xu, Z. Hu, K. Mifflin, C. DeCarlie, S-C. Cheung, C-N. Chuah, and B. N. Dugger, "BrainSec: Automated Brain Tissue Segmentation Pipeline for Scalable Neuropathological Analysis," IEEE Access, May 2022. [DOI: 10.1109/ACCESS.2022.3171927]
  • Z. Lai, C. Wang, Z. Hu, B. N. Dugger, S-C. Cheung, C-N. Chuah, "A Semi-supervised Learning for Segmentation of Gigapixel Histopathology Images from Brain Tissues," 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Oct 31-Nov 4, 2021. [DOI: 10.1109/EMBC46164.2021.9629715]
  • Z. Lai, C. Wang, L. Cerny Oliveira, B. Dugger, S-C. Cheung, and C.N. Chuah, "Joint Semi-supervised and Active Learning for Segmentation of Gigapixel Pathology Images with Cost-Effective Labeling," ICCV Workshop on Computational Challenges in Digital Pathology (CDpath), Oct 11 2021. [DOI: 10.1109/ICCVW54120.2021.00072]
  • Z. Lai, K. Guo, W. Xu, Z. Hu, B. Dugger, S. Cheung, and C-N. Chuah, "Automated Grey and White Matter Segmentation in Digitized Ab Human Brain Tissue Slide Images," IEEE ICME 2020 Workshop on Multimedia Services and Technologies for Smart Health (MUST-SH), July 2020. [URL]

Technical Focused Publications

  • Z. Lai, H. Bai, H. Zhang, X. Du, J. Shan, Y. Yang, C-N. Chuah, M. Cao, "Empowering Unsupervised Domain Adaptation with Large-scale Pre-trained Vision-Language Models," Winter Conference on Applications of Computer Vision (WACV), January 2024.
  • Z. Lai, N. Vesdapunt, N. Zhou, J. Wu, C. P. Huynh, X. Li, K K. Fu, and C-N Chuah, "PADCLIP: Pseudo-labeling with Adaptive Debiasing in CLIP for Unsupervised Domain Adaptation," International Conference on Computer Vision (ICCV), October 2023.
  • Z. Lai, C. Wang, H. Gunawan, S-C. Cheung, and C-N. Chuah, "Smoothed Adaptive Weighting for Imbalanced Semi-Supervised Learning: Improve Reliability Against Unknown Distribution Data," The 39th International Conference on Machine Learning (ICML), July 17-23, 2022. (Lai received ICML 2022 Participation Grant)
  • Z. Lai, C. Wang, S-C. Cheung, and C-N. Chuah, "SaR: Self-Adaptive Refinement on Pseudo Labels for Multiclass-Imbalanced Semi-Supervised Learning," Computer Vision and Pattern Recognition (CVPR) Workshop on Learning with Limited Labeled Data for Image and Video Understanding (L3DIVU), June 20, 2022. (Best Paper Award)
  • C. Wang, M. Tao, C-N. Chuah, J. Ngay, and Y. Lou, "Minimizing L1 over L2 norms on the gradient," Inverse Problem, IOP Publishing, May 6, 2022. [URL]

Abstracts/Posters

  • L. Cerny Oliveira, J. Chauhan, Z. Lai, S. Cheung, A. Villablanca, L-W. Jin, C. DeCarli, C-N Chuah, B-N Dugger, "Automating Microinfarct Screening in Hematoxylin and Eosin-stained Human Brain Tissues: A Machine Learning Approach," 100th Annual Meeting of the American Association of Neuropathologists (AANP), June 2024.
  • R. Scalco, L. Cerny-Oliveira, Z. Lai, D. Harvey L. Abujamil, C. DeCarli, L-W. Jin, C-N. Chuah, and B. N. Dugger, "Machine learning analysis of Amyloid-b pathologies and their correlations in 131 cases from an Alzheimer's Disease Research Center," AANP, 100th Annual Meeting of the American Association of Neuropathologists, June 2024.
  • L. Cerny Oliveira, J. Chauhan, A. Chaudhari, Z. Lai, S. Cheung, A. Villablanca, L-W. Jin, C. DeCarli, C-N Chuah, B-N Dugger, "Automating Microinfarct Screening in Hematoxylin and Eosin-stained Human Brain Tissues: A Machine Learning Approach," April Krueger Annual Women's Health, May 2024.
  • L. Cerny Oliveira, J. Chauhan, Z. Lai, S. Cheung, A. Villablanca, L-W. Jin, C. DeCarli, C-N Chuah, B-N Dugger, "Automating Microinfarct Screening in Hematoxylin and Eosin-stained Human Brain Tissues: A Machine Learning Approach," Alzheimer's Association Neuroscience Next, April 2024.
  • L. Cerny Oliveira, Z. Lai, D. Harvey, K. Nzenkue, L-W. Jin, C. DeCarli, C-N Chuah, B-N Dugger, "Pre-analytic Variables Effect on Segmentation and Quantification Machine Learning Algorithms for Amyloid Beta Analysis in Human Brain," UC Davis Alzheimer's Disease Research Center (ADRC) Research Symposium, Sep 2023.
  • L. Cerny Oliveira, J. Chauhan, Z. Lai, S. Cheung, A. Villablanca, L-W. Jin, C. DeCarli, C-N Chuah, B-N Dugger, "Machine Learning for Infarct Detection in Gigapixel Whole Slide Images of Human Brain," UC Davis Alzheimer's Disease Research Center (ADRC) Research Symposium, Sep 2023.
  • J. Chauhan, L. Cerny Oliveira, Z. Lai, C-N Chuah CN, B-N Dugger, "Computationally Efficient AI frameworks for Neuropathology Image Analysis," 8th annual UC Davis Postdoctoral Research Symposium, University of California, Davis, March 17, 2023.
  • Z. Lai, L. Cerny Oliveira, D. Harvey, K. Nzenkue, L-W. Jin, C. DeCarli, C-N. Chuah, and B. N. Dugger, "Generalizability of Deep Learning Frameworks for Amyloid Beta Deposit Assessment, Evaluation of Pre-analytic Variables," American Association of Neuropathologists (AANP) Annual Meeting, June 2022. (Lai received R13 Grant Travel Award designated for trainee with the best basic or clinical abstract)

Awards & Achievements

  • 2024: Zhengfeng (Jeff) Lai, our PhD alum and Noyce Fellow, received the ECE Anil Jain Memorial Award for Best Dissertation and the 2024 College of Engineering Excellence in Graduate Student Reseach Award.
  • 2024: PhD student - Luca Cerny Oliveira received the Khadar B. Shaik Memorial Award, which ecognizes a graduate student who has advanced to candidacy and has shown great promise for intellectual contributions to the field of electrical and computer engineering.
  • 2022: Our paper won the Best Paper Award at the Computer Vision and Pattern Recognition (CVPR) Workshop on Learning with Limited Labeled Data for Image and Video Understanding (L3DIVU).
  • 2022: Zhengfeng (Jeff) Lai received ICML 2022 Participation Grant and R13 Grant Travel Awards from the American Association of Neuropathologists Annual meeting to present his papers at the two conferences, respectively.

Funding

This collaborative work is supported by Grant# 2024-351073 from the Chan Zuckerberg Initiative DAF (an advised fund of the Silicon Valley Community Foundation), Noyce Initiative UC Partnerships in Computational Transformation Program, NSF HDR: TRIPODS grant CCF-1934568, NIH-National Institute On Aging awards #R01AG062517, #2R01-AG0652517, #P30AG072972, and #P30AG062429; University of California office of the president research grant MRI-19-599956; and residual class settlement funds in the matter of April Krueger v. Wyeth, Inc., Case No. 03-cv-2496 (US District Court, SD of California).