Decoding dementia
UC Davis researchers using AI to transform how scientists study brain disease
The path to a world without dementia starts with a brain tissue sample. Researchers at the University of California, Davis are developing AI-driven tools to analyze vast digital archives of brain tissue scans — work that cannot be done at scale by humans alone — to better understand dementia and improve diagnosis and treatment.
The multi-year initiative, called AggieBrain: AI for Next-Generation Neuropathology, is led by a collaboration between Brittany Dugger, leader of the UC Davis Neuropathology Core and associate professor at UC Davis Health and Chen-Nee Chuah, Child Family Professor in Engineering and co-director of the UC Davis AI Center in Engineering.
“We hope this research leads to new opportunities for precision medicine for dementia so that people can receive the right treatment at the right time,” said Dugger. “The ultimate goal is to make these tools freely available to researchers worldwide, ensuring no scientist is limited by computational resources or dataset constraints.”
The AggieBrain initiative is made possible by a generous gift of $420,500 from the Susan and Charles Berghoff Foundation with major support from Darrin Mollett and William “Bill” Ballhaus ’89.
Formed in 2021, the Susan and Charles Berghoff Foundation’s slogan, we envision a dementia-free world™, was inspired by its co-founder, the late Sue Berghoff. She transformed her dementia diagnosis into something positive through advocacy and
philanthropy. For several years she spoke at Continuing Medical Education presentations attended by thousands of physicians from Sacramento to Monterey, and she established the foundation’s first postdoctoral research fellowship at Stanford University. Her legacy continues with the foundation’s generous support of university research as well as education and caregiver support programs.
“We are so grateful to the Susan and Charles Berghoff Foundation for their confidence in us and our vision,” said Chuah. “Their philanthropy equips us to conduct more interdisciplinary, exploratory dementia research and advance the science."
Tackling a complex challenge
Dementia is a public health crisis: Over 7 million people in the U.S. are living with the affliction, and by 2050 this number is expected to rise to 15 million.
One of the current challenges in dementia research is it can only be definitively diagnosed with an autopsy after death. Brain donation — made possible by the deeply personal decisions of individuals or families to donate their own or a loved one’s brain to science — is the only means to confirm and type the disease.
Dugger points to cancer as an analogy: Decades ago, cancer was diagnosed and treated as a single disease, but today tumors can be deeply profiled and therapies tailored to specific types of malignancies.
Similarly, dementia is a broad term for a brain disorder associated with different neurodegenerative diseases such as Alzheimer, Lewy body, and vascular dementia; frontotemporal degeneration; and mixed-etiology dementia where individuals have more than one dementia type.
“An important message we want to convey is people can have different or multiple types of dementia, and that informs the prognosis and recommended course of treatment,” said Dugger.
In her work as the leader of the Neuropathology Core at the UC Davis Alzheimer’s Disease Research Center, Dugger studies images of the human brain. Per case, she assesses an average of 44 slides — a labor-intensive process that involves identifying core pathological features like lesions, and segmenting brain regions. However, current methods often miss microscopic details that distinguish different types of dementia.
For example, Lewy body disease is characterized by abnormal aggregates of alpha synuclein protein (Lewy bodies and Lewy neurites), while Alzheimer disease is characterized by aggregates of amyloid-beta and tau proteins (amyloid-beta plaques and neurofibrillary tangles).
“We are focusing on workflows that can automate identifying these main hallmarks, augmenting the ability of the expert to help us understand each disease better and advance precision medicine,” said Dugger.
Training reliable and accurate models
The review of glass slides containing brain tissues has long been the approach to studying neurodegenerative diseases and dementia, but it can be both time-consuming and demanding. Machine learning can automate this process to be completed in minutes.
Chuah’s team is developing AI infrastructure and workflows to identify hallmarks of disease on a wide scale, referencing a large digital image archive with microscopic-level pathology annotations
“We are creating a one-stop research workflow, a centralized collection of carefully labeled brain tissue data, that serves as a trusted reference both scientists and AI users can easily access and analyze in one place,” said Chuah.
To ensure the AI models are accurate and reliable, the researchers are creating shared sets of benchmark data and standardized frameworks — a litmus test — to compare models and evaluate them for large-scale performance.
Incorporating the knowledge of human experts — leveraging close collaboration between Chuah’s and Dugger’s labs — is necessary to assess that models are interpreting and classifying data correctly.
This close collaboration is integral, ensuring students and staff from engineering and medicine are deeply involved in AggieBrain from start to finish.
“Meaningful student engagement is important to train the next generation of researchers who are able to collaborate on complex interdisciplinary projects,” said Dugger.
Personal experience driving change
The Susan and Charles Berghoff Foundation has also established a research fellowship at Stanford and a nurse education and scholarship program at San Jose State University and several Community Colleges.
“Dementia is a growing public health crisis and we’re simply not prepared for it,” said Charles “Chuck” Berghoff, foundation chairman and devoted caregiver for his wife during her difficult journey with dementia.
“We are pleased to support innovative researchers such as Brittany Dugger and Chen-Nee Chuah and we look forward to their progress with the AggieBrain Initiative,” he added.
College of Engineering alum Ballhaus is the eldest son of Sue Berghoff and a respected aerospace engineer and technology leader. His wife, Darrin Mollett, shares a tragic family legacy: She also lost a parent, her father, to dementia. Together, the couple sees hope through support for focused dementia research.
“Convening the knowledge and talent of neuropathology and AI/Machine Learning experts to tackle dementia makes good sense,” said Ballhaus. “Providing an accessible framework and tools for researchers to share deep knowledge and large data sets from brain banks is critical to solving the dementia challenge.”
Dugger and Chuah are not only united in their research focus but are also inspired by personal experiences with loved ones affected by dementia.
“I've always wanted to be able to do something to help advance the research in this space,” said Chuah. “When I met Dr. Dugger, I welcomed the opportunity to use my engineering knowledge and skills in data science and machine learning, to have a positive impact on neurodegenerative diseases including Alzheimer's disease, vascular dementia, dementia with Lewy bodies, frontotemporal degeneration and mixed-etiology dementia."
A path to accelerate and scale dementia research
AggieBrain builds on several of Chuah and Dugger’s ongoing collaborations that have received funding from the UC Noyce Initiative, the Chan Zuckerberg Initiative and the National Institutes of Health (NIH).
For example, they are collaborating on the UC Davis segment of the Brain Digital Slide Archive (BDSA) — an NIH initiative involving more than 10 U.S. research institutions and co-led by Dugger. The BDSA aims to provide infrastructure for sharing digital slide images of human brain and associated data across participating universities to facilitate data analysis.
“We couldn’t be here without the resources of the UC Davis Alzheimer’s Disease Research Center. UC Davis has established infrastructure, and our work is poised to enhance it,” said Dugger.
In addition to advancing dementia research, Dugger and Chuah believe AggieBrain will unlock opportunities to train next-generation AI models capable of advancing understanding of a range of neurodegenerative diseases — laying the groundwork for breakthroughs in diagnosis and treatment.
“AggieBrain's impact is poised to extend well beyond its initial scope. The computational methods at its core, including computer vision, large language vision models and pathology foundation models, translate naturally to medical image analysis challenges in radiology, neuroengineering and other disciplines” said Chuah.