1
|
Kamran SA, Hossain KF, Ong J, Zaman N, Waisberg E, Paladugu P, Lee AG, Tavakkoli A. SANS-CNN: An automated machine learning technique for spaceflight associated neuro-ocular syndrome with astronaut imaging data. NPJ Microgravity 2024; 10:40. [PMID: 38548790 PMCID: PMC10978911 DOI: 10.1038/s41526-024-00364-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2023] [Accepted: 02/12/2024] [Indexed: 04/01/2024] Open
Abstract
Spaceflight associated neuro-ocular syndrome (SANS) is one of the largest physiologic barriers to spaceflight and requires evaluation and mitigation for future planetary missions. As the spaceflight environment is a clinically limited environment, the purpose of this research is to provide automated, early detection and prognosis of SANS with a machine learning model trained and validated on astronaut SANS optical coherence tomography (OCT) images. In this study, we present a lightweight convolutional neural network (CNN) incorporating an EfficientNet encoder for detecting SANS from OCT images titled "SANS-CNN." We used 6303 OCT B-scan images for training/validation (80%/20% split) and 945 for testing with a combination of terrestrial images and astronaut SANS images for both testing and validation. SANS-CNN was validated with SANS images labeled by NASA to evaluate accuracy, specificity, and sensitivity. To evaluate real-world outcomes, two state-of-the-art pre-trained architectures were also employed on this dataset. We use GRAD-CAM to visualize activation maps of intermediate layers to test the interpretability of SANS-CNN's prediction. SANS-CNN achieved 84.2% accuracy on the test set with an 85.6% specificity, 82.8% sensitivity, and 84.1% F1-score. Moreover, SANS-CNN outperforms two other state-of-the-art pre-trained architectures, ResNet50-v2 and MobileNet-v2, in accuracy by 21.4% and 13.1%, respectively. We also apply two class-activation map techniques to visualize critical SANS features perceived by the model. SANS-CNN represents a CNN model trained and validated with real astronaut OCT images, enabling fast and efficient prediction of SANS-like conditions for spaceflight missions beyond Earth's orbit in which clinical and computational resources are extremely limited.
Collapse
Affiliation(s)
- Sharif Amit Kamran
- Human-Machine Perception Laboratory, Department of Computer Science and Engineering, University of Nevada, Reno, Reno, NV, US
| | - Khondker Fariha Hossain
- Human-Machine Perception Laboratory, Department of Computer Science and Engineering, University of Nevada, Reno, Reno, NV, US
| | - Joshua Ong
- Department of Ophthalmology and Visual Sciences, University of Michigan Kellogg Eye Center, Ann Arbor, MI, US
| | - Nasif Zaman
- Human-Machine Perception Laboratory, Department of Computer Science and Engineering, University of Nevada, Reno, Reno, NV, US
| | - Ethan Waisberg
- Department of Ophthalmology, University of Cambridge, Cambridge, UK
| | - Phani Paladugu
- Brigham and Women's Hospital, Harvard Medical School, Boston, MA, US
- Sidney Kimmel Medical College, Thomas Jefferson University, Philadelphia, PA, US
| | - Andrew G Lee
- Center for Space Medicine, Baylor College of Medicine, Houston, TX, US
- Department of Ophthalmology, Blanton Eye Institute, Houston Methodist Hospital, Houston, TX, US
- The Houston Methodist Research Institute, Houston Methodist Hospital, Houston, TX, US
- Departments of Ophthalmology, Neurology, and Neurosurgery, Weill Cornell Medicine, New York, NY, US
- Department of Ophthalmology, University of Texas Medical Branch, Galveston, TX, US
- University of Texas MD Anderson Cancer Center, Houston, TX, US
- Texas A&M College of Medicine, Bryan, TX, US
- Department of Ophthalmology, The University of Iowa Hospitals and Clinics, Iowa City, IA, US
| | - Alireza Tavakkoli
- Human-Machine Perception Laboratory, Department of Computer Science and Engineering, University of Nevada, Reno, Reno, NV, US.
| |
Collapse
|
2
|
Antonsen E, Reynolds RJ, Charvat J, Connell E, Monti A, Petersen D, Nartey N, Anton W, Abukmail A, Marotta K, Van Baalen M, Buckland DM. Causal diagramming for assessing human system risk in spaceflight. NPJ Microgravity 2024; 10:32. [PMID: 38503732 PMCID: PMC10951288 DOI: 10.1038/s41526-024-00375-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2023] [Accepted: 03/04/2024] [Indexed: 03/21/2024] Open
Abstract
For over a decade, the National Aeronautics and Space Administration (NASA) has tracked and configuration-managed approximately 30 risks that affect astronaut health and performance before, during and after spaceflight. The Human System Risk Board (HSRB) at NASA Johnson Space Center is responsible for setting the official risk posture for each of the human system risks and determining-based on evaluation of the available evidence-when that risk posture changes. The ultimate purpose of tracking and researching these risks is to find ways to reduce spaceflight-induced risk to astronauts. The adverse effects of spaceflight begin at launch and continue throughout the duration of the mission, and in some cases, across the lifetime of the astronaut. Historically, research has been conducted in individual risk "silos" to characterize risk, however, astronauts are exposed to all risks simultaneously. In January of 2020, the HSRB at NASA began assessing the potential value of causal diagramming as a tool to facilitate understanding of the complex causes and effects that contribute to spaceflight-induced human system risk. Causal diagrams in the form of directed acyclic graphs (DAGs) are used to provide HSRB stakeholders with a shared mental model of the causal flow of risk. While primarily improving communication among those stakeholders, DAGs also allow a composite risk network to be created that can be tracked and configuration managed. This paper outlines the HSRB's pilot process for this effort, the lessons learned, and future goals for data-driven risk management approaches.
Collapse
Affiliation(s)
- Erik Antonsen
- Center for Space Medicine, Department of Emergency Medicine, Baylor College of Medicine, Houston, TX, USA.
| | | | | | | | | | | | | | | | | | | | | | - Daniel M Buckland
- NASA Johnson Space Center, Houston, TX, USA
- Duke University, Durham, NC, USA
| |
Collapse
|
3
|
Harris M, Duda PI, Kelman I, Glick N. Addressing disaster and health risks for sustainable outer space. INTEGRATED ENVIRONMENTAL ASSESSMENT AND MANAGEMENT 2022. [PMID: 35974682 DOI: 10.1002/ieam.4668] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/08/2022] [Revised: 07/10/2022] [Accepted: 08/03/2022] [Indexed: 06/15/2023]
Abstract
Any future outer space exploration and exploitation should more fully consider disaster and health risks as part of aiming for sustainability. The advent of the so-called "New Space" race, age, or era characterized by democratization, commercialization, militarization, and overlapping outer space activities such as tourism presents challenges for disaster-related and health-related risks in and for outer space. Such challenges have been extensively researched for earth, but less so for space. This article presents an overview of key aspects for addressing disaster and health risks in outer space within a wider sustainability framing. After an introduction providing background and scope, this article's next section considers some key health and disaster risks within sustainable outer space and offers insights from earth. The following two sections apply this knowledge by focusing on how analogue missions and international legal and voluntary regimes can each be used to reduce risks and potentially make outer space healthier and safer. The findings advocate that there is a wealth of knowledge and experience about mitigating risks to health and disaster risk reduction on earth that can inform spaceflight and exploration. The examples explored include the physical, legal, and regulatory aspects of the "New Space" industry, which highlights the relevance of equating examples on earth. The article concludes that expectations must be managed regarding scenarios for which response, rescue, and recovery are precluded, prompting a necessary focus on prevention and risk reduction. In doing so, earth-based scenarios and aspects of the so-called "Old Space" offer useful insights and should be examined further for "New Space." Integr Environ Assess Manag 2022;00:1-8. © 2022 The Authors. Integrated Environmental Assessment and Management published by Wiley Periodicals LLC on behalf of Society of Environmental Toxicology & Chemistry (SETAC).
Collapse
Affiliation(s)
- Myles Harris
- UCL Institute for Risk and Disaster Reduction, London, UK
- Space Health Research, London, UK
| | | | - Ilan Kelman
- UCL Institute for Risk and Disaster Reduction, London, UK
- UCL Institute for Global Health, University of Agder, Kristiansand, Norway
| | | |
Collapse
|
4
|
Abstract
NASA and commercial spaceflight companies will soon be retuning humans to the Moon and then eventually sending them on to Mars. These distant planetary destinations will pose new risks—in particular for the health of the astronaut crews. The bulk of the evidence characterizing human health and performance in spaceflight has come from missions in Low Earth Orbit. As missions last longer and travel farther from Earth, medical risk is expected to contribute an increasing proportion of total mission risk. To date, there have been no reliable estimates of how much. The Integrated Medical Model (IMM) is a Probabilistic Risk Assessment (PRA) Monte-Carlo simulation tool developed by NASA for medical risk assessment. This paper uses the IMM to provide an evidence-based, quantified medical risk estimate comparison across different spaceflight mission durations. We discuss model limitations and unimplemented capabilities providing insight into the complexity of medical risk estimation for human spaceflight. The results enable prioritization of medical needs in the context of other mission risks. These findings provide a reasonable bounding estimate for medical risk in missions to the Moon and Mars and hold value for risk managers and mission planners in performing cost-benefit trades for mission capability and research investments.
Collapse
|
5
|
Miller MJ, Miller MJ, Santiago-Materese D, Seibert MA, Lim DSS. A Flexible Telecommunication Architecture for Human Planetary Exploration Based on the BASALT Science-Driven Mars Analog. ASTROBIOLOGY 2019; 19:478-496. [PMID: 30840502 DOI: 10.1089/ast.2018.1906] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/09/2023]
Abstract
There is a synergistic relationship between analog field testing and the deep space telecommunication capabilities necessary for future human exploration. The BASALT (Biologic Analog Science Associated with Lava Terrains) research project developed and implemented a telecommunications architecture that serves as a high-fidelity analog of future telecommunication capabilities for Mars. This paper presents the architecture and its constituent elements. The rationale for the various protocols and radio frequency (RF) link types required to enable an interdisciplinary field mission are discussed, and the performance results from the BASALT field tests are provided. Extravehicular Informatics Backpacks (EVIB) designed for BASALT and tested by human subjects are also discussed, and the proceeding sections show how these prototype extravehicular activity (EVA) information systems can augment future human exploration. The paper concludes with an aggregate analysis of the data product types and data volumes generated, transferred, and utilized by the ground team and explorers over the course of the field deployments.
Collapse
Affiliation(s)
| | | | | | - Marc A Seibert
- 4 ASRC Federal Technical Services, NASA SCaN Office, PSE Division, NASA Headquarters, Washington, DC
| | - Darlene S S Lim
- 3 NASA Ames Research Center, Moffett Field, California
- 5 Bay Area Environmental Research Institute/NASA Ames Research Center, Moffett Field, California
| |
Collapse
|
6
|
Beaton K, Chappell S, Abercromby A, Miller M, Kobs Nawotniak S, Brady A, Stevens A, Payler S, Hughes S, Lim D. Assessing the Acceptability of Science Operations Concepts and the Level of Mission Enhancement of Capabilities for Human Mars Exploration Extravehicular Activity. ASTROBIOLOGY 2019; 19:321-346. [PMID: 30840507 PMCID: PMC6442237 DOI: 10.1089/ast.2018.1912] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/31/2018] [Accepted: 01/14/2019] [Indexed: 05/31/2023]
Abstract
The Biologic Analog Science Associated with Lava Terrains (BASALT) research project is investigating tools, techniques, and strategies for conducting Mars scientific exploration extravehicular activity (EVA). This has been accomplished through three science-driven terrestrial field tests (BASALT-1, BASALT-2, and BASALT-3) during which the iterative development, testing, assessment, and refinement of concepts of operations (ConOps) and capabilities were conducted. ConOps are the instantiation of operational design elements that guide the organization and flow of personnel, communication, hardware, software, and data products to enable a mission concept. Capabilities include the hardware, software, data products, and protocols that comprise and enable the ConOps. This paper describes the simulation quality and acceptability of the Mars-forward ConOps evaluated during BASALT-2. It also presents the level of mission enhancement and acceptability of the associated Mars-forward capabilities. Together, these results inform science operations for human planetary exploration.
Collapse
Affiliation(s)
- K.H. Beaton
- KBRwyle, Houston, Texas, USA
- NASA Johnson Space Center, Houston, Texas, USA
| | - S.P. Chappell
- KBRwyle, Houston, Texas, USA
- NASA Johnson Space Center, Houston, Texas, USA
| | | | | | | | - A.L. Brady
- School of Geography and Earth Sciences, McMaster University, Hamilton, Ontario, Canada
| | - A.H. Stevens
- European Astronaut Centre, European Space Agency, Cologne, Germany
| | - S.J. Payler
- European Astronaut Centre, European Space Agency, Cologne, Germany
| | - S.S. Hughes
- Department of Geosciences, Idaho State University, Pocatello, Idaho, USA
| | - D.S.S. Lim
- BAER Institute, Moffett Field, California, USA
- NASA Ames Research Center, Moffett Field, California, USA
| |
Collapse
|