Deep Machine Learning Methodology for Space Exploration Medical Diagnosis, Year 1 (DML/MD)

Medical ultrasound is an important imaging modality for crew health and medical research. Ultrasound requires significant operator skill to acquire quality images, and those images need expert interpretation to make clinical decisions. Kidney stones are considered a great risk for spaceflight (and are very common on Earth), and ultrasound is an excellent way to diagnose them. We aim to apply DML techniques to aid in the diagnosis of kidney stones by ultrasound. It is unlikely that untrained ultrasound operators could perform kidney ultrasounds of sufficient quality to make a diagnosis. We are therefore supporting the development of Augmented Realty (AR)-assisted ultrasound scanning to make the data collection process consistently effective. We are collecting a large kidney ultrasound dataset to be fed into our DML system to identify the presence or absence of stones. The required renal ultrasound imagery is collected following a set scanning protocol that is being used in our AR scanning process with the aim to create an end-to-end system, from scanning the patient to establishing a diagnosis. This system, once complete, will be of great use in deep Space exploration as well as in terrestrial medical settings, especially in resource-limited or remote areas. Even experts can struggle in making accurate ultrasound diagnoses. Radiologists recognize that variations in image interpretation can lead to misdiagnosis. Medical images contain huge amounts of information, subtle features, variation of characteristics and for this reason, there is a need to engage technologies of advanced computer-aided image analysis, plus standardized protocols. Deep Machine Learning (DML) technology is developing, and we expect that such will be used to aid in interpreting medical imagery. Risk for renal stone formation is 1 of 30 risks for Deep Space Journey, Habitation & Planetary. Technology Gaps being addressed include: HRR-GAP-Med10: Lack of computed medical decision support capability during exploration missions and HRR-GAP-Med 05: Lack of knowledge in crew training for medical decision making and medical skills to enable extended missions and autonomous operations. This gap identifies the need for autonomous medical decision support to augment knowledge of decision-making crewmembers. Our aim is to use closed-loop ultrasound guidance and AI/DML for medical image interpretation. Learning how to perform scans autonomously is of great medical benefit to NASA for deep-space missions with delayed communication, and supports crew autonomy, preventive care and crew health for cis-lunar gateway/lunar outpost and extended exploration missions.

HRR-GAP- Med 10: We lack the ability to assist the crewmembers in making a kidney stone diagnosis during exploration missions & HRR-GAP- Med 05: Crewmembers are currently unable to perform kidney ultrasounds adequate to diagnose without real-time guidance from the ground. This gap identifies the need for autonomous medical decision support to augment the knowledge of the decision-making crewmember with algorithmic support including medical image gathering & interpretation. This project also supports crew autonomy, preventive care and crew health for gateway/Artemis/lunar outpost and exploration.

This is early/mid-stage (TRL 4) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.