SBIR-STTR Award

Automated lab identification and sorting (Rapid-IDX) for mosquito surveillance
Award last edited on: 8/19/2024

Sponsored Program
SBIR
Awarding Agency
NIH : CGH
Total Award Amount
$2,238,626
Award Phase
2
Solicitation Topic Code
326
Principal Investigator
Jewell A Brey

Company Information

Vectech LLC

3600 Clipper Mill Road Suite 205
Baltimore, MD 21211
   (858) 442-4658
   contact@vectech.io
   www.vectech.io
Location: Single
Congr. District: 07
County: Baltimore City

Phase I

Contract Number: 1R43GH002369-01A1
Start Date: 9/30/2022    Completed: 3/31/2023
Phase I year
2022
Phase I Amount
$275,766
Mosquitoes are responsible for nearly half-a-million deaths each year. Mosquitovector control efforts have reduced the burden of mosquito-borne diseases over the past several decades, but limitations in data-driven vector control decision making hinders progress. Mosquito surveillance-monitoring an area to understand mosquito species composition, abundance, and spatial distribution-enables mosquito control organizations to make effective,efficient, and judicious mosquito control decisions. Despite the importance of mosquito speciesidentification in surveillance, morphological identification remains highly resource, time, andlabor intensive. Hiring seasonal staff, a significant recurring cost to mosquito controlorganizations, is the conventional practice to expand capacity. Entomological expertise can alsovary widely based on individual training and experience, and result in incorrect speciesidentifications. We seek to develop the first automated lab identification and sorting (ALIDAS)system for mosquito vector surveillance, to increase surveillance capacity and generate timelydata for targeted mosquito vector control. Computer vision has potential to scale identificationacross diverse mosquito species; however, automating the entomological lab workflow tomaximize operational savings, requires a systematic approach to mosquito handling andmovement, while preserving and capturing diagnostic morphological characters in images forclassification. This proposal will utilize novel optics, pneumatics, and computer visionapproaches to isolate, handle, and identify mosquito specimens to species with computer vision.Ultimately the approaches developed here will allow mosquito control organizations to leverageimage recognition in a practical system that will increase entomological lab capability andcapacity, while reducing operational costs.

Public Health Relevance Statement:
Project Narrative. The goal of this project is to develop the first automated lab identification and sorting (ALIDAS) system to expand mosquito vector surveillance capacity while reducing operational costs. Accurate and timely mosquito species identification is a critical but highly resource intensive environmental health activity. Leveraging our expertise in computer vision, optics, and pneumatics, we seek to develop a practical system that will increase global biosurveillance capacity and capability.

Project Terms:

Phase II

Contract Number: 2R44GH002369-02
Start Date: 9/30/2023    Completed: 9/30/2025
Phase II year
2023
Phase II Amount
$1,962,860
Overview. The proposed work will advance state of the art mosquito surveillance technology throughdevelopment of an automated species identification and sorting system, Rapid-IDX. The proposal buildson Phase I results, during which the mechanical subcomponents for isolation, separation, andtransportation, multi-angle optics system, and prototype algorithm were designed and validated. For phaseII, the optics and mechanical systems designed will be integrated into functional prototypes for aminimum viable product (MVP), an image database will be developed to focus algorithm development onkey medically-relevant mosquito species, and iterative functionality and usability testing will beconducted with potential customers.Intellectual Merit. Rapid-IDX will allow for rapid data generation of high-resolution, multi-angle imagesof mosquito specimens for training of Convolutional Neural Networks (CNNs) for identification; the largeand robust dataset enabled with this technology will help push Vectech's technology towards morenuanced and powerful algorithms. This phase II work centered on StarAttGAN represents the state of theart with regard to generative models for dataset augmentation. These developments will enable addressinga critical issue in computer vision: that of sampling bias in vast noisy, fine-grained, openset multiclassclassification problems.Broader Impacts. The proposed work supports United States critical public health infrastructure andpublic health literacy in the face of growing incidence of vector borne disease as a result of climatechange, globalization, and other factors. The system will provide Vector control organizations (VCOs),which protect local communities in the US from disease-carrying insects, with more robust capacity invector surveillance data gathering, a critical component of integrated vector management. Additionally,US Armed Forces face a significant threat of vector-borne diseases around the world, making theDepartment of Defense one of the largest customers for vector surveillance and control products. We areseeing emerging competitors in the pest information space in Germany, Israel, China, and South Korea(see commercialization plan). Investment in Vectech ensures there's an American company to compete inthe global market. We will collaborate with leading US-based MCOs for development and optimization ofthis product, ensuring product-market fit. Furthermore, the technical team leading this phase II proposalrepresents several underrepresented groups in STEM, including women, BIPOC, and the LGBTQcommunity.

Public Health Relevance Statement:
Project Narrative. The goal of this project is to develop the first automated lab identification and sorting (Rapid-IDX) system to expand mosquito vector surveillance capacity while reducing operational costs. Accurate and timely mosquito species identification is a critical but highly resource intensive environmental health activity. Leveraging our expertise in computer vision and optics, we seek to develop a practical system that will increase global biosurveillance capacity and capability.

Project Terms: