SCREENDX and FIBRESOLVE:
AI for Lung Fibrosis
ScreenDx, AI to Identify ILD Automatically:
ScreenDx uses AI to automatically analyze medical data for findings suggestive of interstitial lung disease (ILD). ScreenDx is designed to be supplementary for current standard-of‐care workflows, providing adjunctive information as part of a referral pathway to an appropriate, qualified clinician.
Fibresolve, AI to Better Distinguish IPF from other ILDs:
Fibresolve is FDA Breakthrough Designated and Authorized to serve as an adjunct in the diagnosis of idiopathic pulmonary fibrosis (IPF) prior to invasive testing. Fibresolve helps pulmonologists and other qualified clinicians as they work through new diagnosis of patients with suspected ILD including IPF. Fibresolve works like a lab test, but without a procedure, analyzing non-invasively collected data.
Supporting Skilled Clinicians:
Fibresolve and ScreenDx are intended to be used only by clinicians qualified in the care of lung disease, in conjunction with the patient’s clinical history, symptoms, and other diagnostic tests, as well as the clinician’s professional judgment.
the platform
The AI Lab
IMVARIA's AI Lab is a centralized, cloud-based digital lab that operates in a broadly similar fashion to that of a specialty CLIA lab–except that we handle data rather than blood or tissue samples. Clinicians, health systems, and clinical trialists transmit cases to the Lab and IMVARIA analyzes the cases and returns reports with results in minutes. The system capacity crosses imaging modalities (eg. CT, MRI), organ systems, and data types (lab results), and follows international standards for quality compliance (eg. ISO 13485). Projects in new disease areas take weeks to months instead of years to complete, and modern architecture supports deep learning, fusion, and multi-dimensional / multi-modal models.
clinicians and health systems
Clinical Assessment
IMVARIA is on the front lines of utilizing digital data to improve patient lives. Leveraging diverse clinical testing and imaging datasets to identify distinct disease signatures addresses many of the challenges with standard diagnostic methods.
Additionally, quantitative-only techniques, including many prognostic calculators, rarely capture the complexities and variance of disease phenotypes. With de-identified data from numerous sources, our systems drive new insights in predicting outcomes and helping better understand risks.
life sciences
AI Biomarkers in Clinical Trials
Through analysis of wide-ranging data types and data sources, including patient registries, clinical trials, and public datasets, the company’s next-generation data science optimizes for consistent and accurate disease assessments and predictions. Whether it is optimizing study enrollment characteristics, better risk-stratifying patients at trial enrollment, or developing predictions for treatment response, IMVARIA can help.
A New Category of Clinical AI
Led by dual physician-engineers from Google and Stanford Health Care, IMVARIA’s pioneering work with AI biomarkers is redefining how to approach high impact diseases more effectively.
Redefining
Clinical AI
IMVARIA's platform analyzes clinical testing and imaging data to generate AI-only clinical results — driving better understanding of physiology and disease noninvasively.
MAKING Better
decisions
IMVARIA empowers physicians to make the best-informed clinical decisions through the precise application of our AI platform, taking on the greatest challenges in high impact disease states.
Mastering SaMD
IMVARIA's Software-as-Medical-Device (SaMD) tools are transforming the use of clinical AI for clinical decision-making and therapeutic development-focused clinical trials.
About IMVARIA
Based in Berkeley, CA, IMVARIA invented a new category of clinical AI that generates physiologic signatures from clinical testing and imaging data. Founded by physician-engineers from Stanford and Google, the company is deploying it across serious diseases for clinicians, health systems, and biopharma partners.
CO-FOUNDER and CEO
DR. JOSHUA REICHER
Dr. Reicher is CEO and Chairman at IMVARIA. Prior to co-founding IMVARIA in 2019, Dr. Reicher served as a clinical lead at Google's medical AI group, as an analyst in healthcare investing, and as a faculty member at Stanford Health Care and Palo Alto VA in the Dept of Radiology.
CO-FOUNDER and CTO
DR. MICHAEL MUELLY
Dr. Muelly is CTO of IMVARIA. Prior to co-founding IMVARIA in 2019, Dr. Muelly served as a Product Manager at Google Cloud's Healthcare group, an AI research fellow at Google, founder of ClariPACS, and as a faculty member at Stanford Health Care in the Dept of Radiology.
COMMERCIAL ADVISOR
MR. JOHN HANNA
Mr. John Hanna is the lead commercial advisor at IMVARIA. Mr. Hanna is CEO at CareDx, a publicly traded diagnostics company. Mr. Hanna was previously CEO at Apton Biosciences and prior to that CCO at Veracyte, a publicly traded diagnostics company.
CLINICIANS + ENGINEERS BUILD BETTER CARE
Our team blends rare clinical, technical, and operational expertise, spanning medicine, machine learning, and real-world healthcare operations — united by a belief that AI can meaningfully transform patient care.
IMVARIA Publications and Abstracts
- Taha A, Kheir F. Integration of closed-loop fully-automated AI model with clinician assessment for lung nodule stratification: a multi-reader study. Respir Investig. 2026;64(5):101507. [link]
- Tambe AP, Boente RD, George G, Kheir F, Tahamtani Omran O, Selvan KC. Clinical utility of an FDA-authorized artificial intelligence imaging platform in interstitial lung disease diagnosis. Diagnostics. 2026;16(15):2445. [link]
- Tahamtani-Omran O, Kalra A, Muelly M, Reicher J, Ahmed R. Paired validation of a multimodal vision-transformer system for the non-invasive diagnosis of idiopathic pulmonary fibrosis. Diagnostics. 2026;16(15):2398. [link]
- Taha A, Kalra A, Muelly M, Reicher J, Kheir F. Sequential integration of Bronchosolve for indeterminate pulmonary nodule stratification: diagnostic gains in moderate-risk nodules [abstract]. Am J Respir Crit Care Med. 2026;212(suppl 1):aamag162.3792. [link]
- Taha A, Kalra A, Muelly M, Reicher J, Kheir F. Clinician performance in indeterminate pulmonary nodule risk stratification using Bronchosolve: a multi-reader multi-case study [abstract]. Am J Respir Crit Care Med. 2026;212(suppl 1):aamag162.3791. [link]
- Liu H, Grewal H, Reicher J, Omran O, Batra H. Risk stratification of incidental lung nodules: a fully automated approach to CT imaging analysis [abstract]. Am J Respir Crit Care Med. 2026;212(suppl 1):aamag162.3794. [link]
- Tambe A, Selvan KC. Clinical utility of Fibresolve, an imaging artificial intelligence tool, in the diagnosis of idiopathic pulmonary fibrosis [abstract]. Am J Respir Crit Care Med. 2026;212(suppl 1):aamag162.2459. [link]
- Taha A, Muneer MS, Kalra A, Muelly M, Reicher J. Performance validation of a closed-loop fully automated AI model for lung nodule stratification in screening cases. Respir Investig. 2026;64(2):101373. [link]
- Batchu S, Callahan S, Kalra A. Automated AI detection of interstitial lung disease on CT in the COPDGene trial: sub-analysis of COPD vs non-COPD patients. Eur Respir J. 2025;66(suppl 69):PA4033. [link]
- Batchu S, Kalra A, Muelly M, Reicher J, Taha A. Closed loop, fully automated lung nodule risk assessment AI software: subanalysis of former vs current smokers. Chest. 2025;168(4)(suppl):A4776-A4777. [link]
- Chen SJ, Kalra A, Muelly M, Reicher J, Callahan S, Scholand MB, Kulkarni T. Automated artificial intelligence detection of early or under-diagnosed interstitial lung disease by computed tomography in the COPDGene trial. Respir Med. 2025;250:108545. [link]
- Callahan SJ, Scholand MB, Kalra A, Muelly M, Reicher JJ. Multi-modal machine learning classifier for idiopathic pulmonary fibrosis predicts mortality in interstitial lung diseases. Respir Investig. 2025 Aug 6;63(5):1012-1017. doi: 10.1016/j.resinv.2025.07.021. [link]
- Uribe J, Kalra J, Muelly M, Reicher J, Kheir F. Clinical experience with the first FDA-authorized artificial intelligence tool in interstitial lung disease and idiopathic pulmonary fibrosis [abstract]. Am J Respir Crit Care Med. 2025;211:A1709. [link]
- Batchu S, Callahan SJ, Scholand MB, Kalra A, Muelly M, Reicher J, Kulkarni T. Automated AI detection of interstitial lung disease by computed tomography (CT) in the COPDGene trial; subanalysis and characteristics of accurately detected cases [abstract]. Am J Respir Crit Care Med. 2025;211:A2087. [link]
- Taha A, Reisenauer J, Kalra A, Muelly M, Reicher J. Closed loop, full automation of suspicious lung nodule risk assessment with AI in screening cases [abstract]. Am J Respir Crit Care Med. 2025;211:A5226. [link]
- Batchu S, Kalra A, Muelly M, Reicher J, Taha A. Age-stratified subanalysis of a closed loop, fully automated lung nodule risk assessment AI software [abstract]. Am J Respir Crit Care Med. 2025;211:A4823. [link]
- Toulomes N, Gagianas G, Bradley J, et al. ScreenDx, an artificial intelligence-based algorithm for the incidental detection of pulmonary fibrosis. AJMS. 2025; pre-proof published online February 27, 2025. [link]
- Callahan SJ, Scholand MB, Kalra A, Muelly M, et al. Expert Center External Validation of a CT-Based Deep Learning Algorithm to Predict Diagnosis of Idiopathic Pulmonary Fibrosis. Chest. 2024;166(4):A3312-A3313. [link]
- Selvan KC, Reicher J, Muelly M, Kalra A, Adegunsoye A. Machine learning classifier is associated with mortality in interstitial lung disease: a retrospective validation study leveraging registry data. BMC Pulm Med. 2024 May 23;24(1):254. [link]
- Selvan K, Reicher J, Muelly M, Kalra A, Adegunsoye A. Machine learning classifier predicts mortality in interstitial lung disease: a validation study. Poster presented at: 2024 American Thoracic Society Conference; May, 2024; San Diego, CA. [link]
- Bradley J, Kalra A, Muelly M, Reicher J. The impact of CT manufacturer and slice thickness on the ability of ScreenDx, an AI-based algorithm, to detect incidental pulmonary fibrosis. Poster presented at: 2024 American Thoracic Society Conference; May, 2024; San Diego, CA. [link]
- Callahan S, Scholand MB, Kalra A, Muelly M, Reicher J. Multi-modal machine learning classifier for idiopathic pulmonary fibrosis predicts mortality in interstitial lung diseases. Poster presented at: 2024 American Thoracic Society Conference; May, 2024; San Diego, CA. [link]
- Kulkarni T, Kalra A, Muelly M, Reicher J. Automated AI detection of clinical interstitial lung disease by CT in the COPDGene trial. Poster presented at: 2024 American Thoracic Society Conference; May, 2024; San Diego, CA. [link]
- Moran-Mendoza O, Singla A, Kalra A, Muelly M, Reicher JJ. Computed tomography machine learning classifier correlates with mortality in interstitial lung disease. Respir Investig. 2024 May 20;62(4):670-676. [link]
- Ahmad Y, Mooney J, Allen IE, et al. A machine learning system to indicate diagnosis of idiopathic pulmonary fibrosis non-invasively in challenging cases. Diagnostics (2024). [link]
- Chang M, Reicher JJ, Kalra A, et al. Chang M, Reicher JJ, Kalra A, Muelly M, Ahmad Y. Analysis of validation performance of a machine learning classifier in interstitial lung disease cases without definite or probable usual interstitial pneumonia pattern on CT using clinical and pathology-supported diagnostic labels. J Imaging Inform Med. 2024 Feb;37(1):297-307. [link]
- Bradley J, Huang J, Kalra A, Reicher J. External validation of Fibresolve, a machine-learning algorithm, to non-invasively diagnose idiopathic pulmonary fibrosis. Am J Med Sci. 2023 Dec 24:S0002-9629(23)01475-1. doi: 10.1016/j.amjms.2023.12.009. [link]
- Bradley J, Huang J, Kalra A, Reicher J. External validation of Fibresolve, a machine-learning algorithm, to non-invasively diagnose idiopathic pulmonary fibrosis. Poster presented at: 2023 Pulmonary Fibrosis Foundation Summit; November, 2023; Orlando, FL.
- Maddali MV, Kalra A, Muelly M, Reicher JJ. Development and validation of a CT-based deep learning algorithm to augment non-invasive diagnosis of idiopathic pulmonary fibrosis. Respir Med. 2023 Oct 13;219:107428. [link]
- Toulomes N, Kalra A, Bradley JA, Gagianas G, Muelly M, Reicher J. Artificial intelligence in incidental detection of lung fibrosis by computed tomography. Oral presentation at: 2023 CHEST Conference; October, 2023; Honolulu, HI. [link]
- Selvan KC, Kalra A, Reicher J, Muelly M, Adegunsoye A. Computer-Aided Pulmonary Fibrosis Detection Leveraging an Advanced Artificial Intelligence Triage and Notification Software. J Clin Med Res. 2023 Sep;15(8-9):423-429. [link]
- Maddali M, Kalra A, Muelly M, Reicher J. Development and validation of a CT-based deep learning algorithm to augment non-invasive diagnosis of idiopathic pulmonary fibrosis. Poster presented at: 2023 American Thoracic Society Conference; May, 2023; Washington DC. [link]
- Ahmad Y, Li J, Mooney J, Allen I, Seaman J, Kalra A, Muelly M, Reicher J. Predicting interstitial pulmonary fibrosis using a machine learning classifier in cases without definite or probable usual interstitial pneumonia pattern on computed tomography. Poster presented at: 2023 American Thoracic Society Conference; May, 2023; Washington DC. [link]
- Ahmad Y, Mooney J, Allen I, Seaman J, Kalra A, Muelly M, Reicher J. A machine learning system to predict diagnosis of idiopathic pulmonary fibrosis non-invasively in challenging cases. Poster presented at: 2023 American Thoracic Society Conference; May, 2023; Washington DC. [link]
- Moran Mendoza O, Reicher J, Singla A. Chest computed tomography machine learning classifier for idiopathic pulmonary fibrosis predicts mortality in interstitial lung diseases. Oral presentation at: 2023 American Thoracic Society Conference; May, 2023; Washington DC. [link]
- Jonas A, Muelly M, Gupta N, Reicher JJ. Machine learning to distinguish lymphangioleiomyomatosis from other diffuse cystic lung diseases. Respir Investig. 2022 May;60(3):430-433. [link]
Careers
As a health tech company with a strong clinical and technical founding team with backgrounds at Stanford and Google, we are growing core engineering and commercial teams to build and deploy a medical-grade software platform. You'll get to help shape the trajectory of this mission-driven company, while receiving a hands-on education in building and commercializing medical AI.
IMVARIA is a remote-first company: we welcome flexible schedules, work from home, and digital collaboration. Join us!
Jobs posted on Wellfound
