Colin Cooke
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Interests
Colin Cooke has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Roarke Horstmeyer
Department of Biomedical Engineering, Duke University, Durham, USA
3 shared publications - Amey Chaware
Department of Biomedical Engineering, Duke University, Durham, NC, USA
2 shared publications - Jaehee Park
Department of Electronic Engineering, Keimyung University, Daegu, South Korea
2 shared publications Kanghyun Kim
Biomedical Engineering department, Duke University
2 shared publications- Kevin C. Zhou
Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, USA
2 shared publications - Mark Harfouche
Ramona Optics, Inc
2 shared publications
Latest Publications
- Open Access
- 18 September 2026
- Published by Center for Open Science in PsyArXiv
Communicating the Economic Impact of Science Funding Cuts Changes Attitudes and Motivates Action
Federal science funding cuts in the United States negatively impact research, healthcare, and the economy. Despite prior research investigating strategies to communicate scientific findings to the public, there is substantially less evidence on strategies to communicate how policy shapes the process and societal impact of science. Here, we demonstrate that across political divides, behavioral interventions that interactively communicate the impact of science funding cuts influence policy support, awareness, and intentions to take action in support of science funding. In two preregistered experiments with politically-balanced samples (N=5,177), we tested novel text, quiz, and map-based interventions illustrating economic losses resulting from science funding cuts. Across the political spectrum, the interventions robustly decreased approval of funding cuts and increased perceived knowledge and perceived negative local impact. We scaled these interventions via a public website (https://scienceimpacts.org/); a third study analyzing data from >24,000 website users revealed converging evidence of effectiveness. Crucially, we demonstrate that even simple text interventions that highlighted local economic impact effectively changed attitudes. However, adding active engagement via interactive quizzes and maps selectively increased action intentions (e.g., contacting representatives, sharing information). Surprise in response to the information, and time spent actively engaging with impact maps, predicted intervention effects on policy approval, knowledge, action intentions, and sharing behavior. Overall, interactive interventions revealing community-level economic impact changed attitudes and increased action intentions related to science funding cuts.
- 18 September 2026
- Published by Center for Open Science in PsyArXiv
Open AccessCommunicating the Economic Impact of Science Funding Cuts Changes Attitudes and Motivates Action
Federal science funding cuts in the United States negatively impact research, healthcare, and the economy. Despite prior research investigating strategies to communicate scientific findings to the public, there is substantially less evidence on strategies to communicate how policy shapes the process and societal impact of science. Here, we demonstrate that across political divides, behavioral interventions that interactively communicate the impact of science funding cuts influence policy support, awareness, and intentions to take action in support of science funding. In two preregistered experiments with politically-balanced samples (N=5,177), we tested novel text, quiz, and map-based interventions illustrating economic losses resulting from science funding cuts. Across the political spectrum, the interventions robustly decreased approval of funding cuts and increased perceived knowledge and perceived negative local impact. We scaled these interventions via a public website (https://scienceimpacts.org/); a third study analyzing data from >24,000 website users revealed converging evidence of effectiveness. Crucially, we demonstrate that even simple text interventions that highlighted local economic impact effectively changed attitudes. However, adding active engagement via interactive quizzes and maps selectively increased action intentions (e.g., contacting representatives, sharing information). Surprise in response to the information, and time spent actively engaging with impact maps, predicted intervention effects on policy approval, knowledge, action intentions, and sharing behavior. Overall, interactive interventions revealing community-level economic impact changed attitudes and increased action intentions related to science funding cuts.
- 1 January 2022
- Published by Optica Publishing Group
- p. JW4C.4
Gigapixel-per-second, wide-field 3D topographic imaging with physics-supervised learning
We present a new interleaved multi-camera microscope architecture and a physics-supervised multi-ocular stereo neural network that enable simultaneous photometric and 3D topographic imaging of freely-moving organisms over 135 cm2 at throughputs exceeding 5 gigapixels per second.
- 1 January 2022
- Published by Optica Publishing Group
- p. JW4C.4
Gigapixel-per-second, wide-field 3D topographic imaging with physics-supervised learning
We present a new interleaved multi-camera microscope architecture and a physics-supervised multi-ocular stereo neural network that enable simultaneous photometric and 3D topographic imaging of freely-moving organisms over 135 cm2 at throughputs exceeding 5 gigapixels per second.
- Open Access
Deep Optical Blood Analysis: COVID-19 Detection as a Case Study in Next Generation Blood Screening
A wide variety of diseases are commonly diagnosed via the visual examination of cell morphology within a peripheral blood smear. For certain diseases, such as COVID-19, morphological impact across the multitude of blood cell types is still poorly understood. In this paper, we present a multiple instance learning-based approach to aggregate high-resolution morphological information across many blood cells and cell types to automatically diagnose disease at a per-patient level. We integrated image and diagnostic information from across 236 patients to demonstrate not only that there is a significant link between blood and a patient’s COVID-19 infection status, but also that novel machine learning approaches offer a powerful and scalable means to analyze peripheral blood smears. Our results both backup and enhance hematological findings relating blood cell morphology to COVID-19, and offer a high diagnostic efficacy; with a 79% accuracy and a ROC-AUC of 0.90.
Open AccessDeep Optical Blood Analysis: COVID-19 Detection as a Case Study in Next Generation Blood Screening
A wide variety of diseases are commonly diagnosed via the visual examination of cell morphology within a peripheral blood smear. For certain diseases, such as COVID-19, morphological impact across the multitude of blood cell types is still poorly understood. In this paper, we present a multiple instance learning-based approach to aggregate high-resolution morphological information across many blood cells and cell types to automatically diagnose disease at a per-patient level. We integrated image and diagnostic information from across 236 patients to demonstrate not only that there is a significant link between blood and a patient’s COVID-19 infection status, but also that novel machine learning approaches offer a powerful and scalable means to analyze peripheral blood smears. Our results both backup and enhance hematological findings relating blood cell morphology to COVID-19, and offer a high diagnostic efficacy; with a 79% accuracy and a ROC-AUC of 0.90.
- 5 March 2021
- Published by SPIE-Intl Soc Optical Eng
- p. 6
Snapshot 3D imaging with a gigapixel-scale multi-aperture microscope
SPIE Digital Library Proceedings
- 5 March 2021
- Published by SPIE-Intl Soc Optical Eng
- p. 6
Snapshot 3D imaging with a gigapixel-scale multi-aperture microscope
SPIE Digital Library Proceedings
- 1 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9284-9288
Towards an Intelligent Microscope: Adaptively Learned Illumination for Optimal Sample Classification
Recent machine learning techniques have dramatically changed how we process digital images. However, the way in which we capture images is still largely driven by human intuition and experience. This restriction is in part due to the many available degrees of freedom that alter the image acquisition process (lens focus, exposure, filtering, etc). Here we focus on one such degree of freedom - illumination within a microscope - which can drastically alter information captured by the image sensor. We present a reinforcement learning system that adaptively explores optimal patterns to illuminate specimens for immediate classification. The agent uses a recurrent latent space to encode a large set of variably-illuminated samples and illumination patterns. We train our agent using a reward that balances classification confidence with image acquisition cost. By synthesizing knowledge over multiple snapshots, the agent can classify on the basis of all previous images with higher accuracy than from naively illuminated images, thus demonstrating a smarter way to physically capture task-specific information.
- 1 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9284-9288
Towards an Intelligent Microscope: Adaptively Learned Illumination for Optimal Sample Classification
Recent machine learning techniques have dramatically changed how we process digital images. However, the way in which we capture images is still largely driven by human intuition and experience. This restriction is in part due to the many available degrees of freedom that alter the image acquisition process (lens focus, exposure, filtering, etc). Here we focus on one such degree of freedom - illumination within a microscope - which can drastically alter information captured by the image sensor. We present a reinforcement learning system that adaptively explores optimal patterns to illuminate specimens for immediate classification. The agent uses a recurrent latent space to encode a large set of variably-illuminated samples and illumination patterns. We train our agent using a reward that balances classification confidence with image acquisition cost. By synthesizing knowledge over multiple snapshots, the agent can classify on the basis of all previous images with higher accuracy than from naively illuminated images, thus demonstrating a smarter way to physically capture task-specific information.
- 6 February 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 57 (7) , 4735-4747
Estimating Sea Ice Concentration From SAR: Training Convolutional Neural Networks With Passive Microwave Data
- 6 February 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 57 (7) , 4735-4747
Estimating Sea Ice Concentration From SAR: Training Convolutional Neural Networks With Passive Microwave Data