Empower your research and healthcare delivery with the latest pathology AI technologies utilizing local, low-cost hardware and secure, cloud-based infrastructure.
We're a team of physicians, engineers, and operators who've spent years at the intersection of AI, cancer medicine, and company building. We've worked across academic medical centers, developed pathology AI methods, and scealed healthcare platforms from research into real clinical workflows. At Slideflow Labs, we're focused on building technology to make cancer diagnostics faster, more accurate, and accessible for every patient.
Akhil Chakravarti is the CEO of Slideflow Labs, where he leads the company's strategic direction and commercial development. He brings extensive experience in healthcare operations, strategy, and business development from both early-stage startups and established biotech companies.
Most recently, Akhil served as Head of Business Operations at LightSpun, an AI startup focused on healthcare administration. Prior to that, he worked in strategy, operations, and corporate development at Resilience, a leading biomanufacturing company, where he drove business operations, acquisitions, partnerships, and venture investments in the biomanufacturing and therapeutics space.
Earlier in his career, Akhil was a senior consultant at ClearView Healthcare Partners, conducting strategic market assessments for pharmaceutical and biotechnology clients. He also advised health tech and biotech startups through the Pennsylvania Small Business Development Centers, supporting commercialization efforts for innovations emerging from Penn Medicine and Children's Hospital of Philadelphia.
Akhil holds dual degrees in Biology (BA) and Economics (BS) from the University of Pennsylvania and The Wharton School. His background spanning life sciences, healthcare strategy, and venture development positions him to drive Slideflow Labs' growth from clinical validation to commercial deployment across health systems.
Dr. James Dolezal is a physician-scientist and Assistant Professor at Geisinger Cancer Institute, where he bridges computational science and medical oncology to advance personalized cancer treatment. As Co-Founder and CTO of Slideflow Labs, he leads the technical development of AI-powered diagnostic tools that bring precision oncology directly into hospital pathology labs.
James earned his MD from University of Pittsburgh School of Medicine and completed his internal medicine residency and hematology/oncology fellowship at the University of Chicago. During his training, he developed Slideflow, the open-source deep learning platform that powers the company's technology and is now used by research institutions worldwide. His pioneering work on uncertainty quantification in AI models has established new standards for reliability and safety in clinical AI applications.
With over 30 publications in leading journals including Nature Communications, Science Advances, and npj Precision Oncology, James has made fundamental contributions to computational pathology. His research spans thyroid and breast cancer biomarker development, methods for mitigating algorithmic bias, and generative AI for model explainability. He has been recognized with the Elwood V. Jensen Scholar award and holds board certification in medical oncology.
James's unique combination of clinical training, software engineering expertise, and entrepreneurial vision drives Slideflow Labs' mission to democratize access to advanced cancer diagnostics and keep critical clinical decision-making tools in the hands of the physicians and hospitals treating patients.
Dr. Sid Ramesh is a physician-scientist at the University of Chicago whose work bridges medicine, artificial intelligence, and translational oncology. As Co-Founder and Chief Scientific Officer of Slideflow Labs, he leads the company's scientific strategy to develop deployable AI-powered biomarkers that advance precision cancer diagnostics.
Sid earned his MD from the University of Chicago Pritzker School of Medicine, graduating Alpha Omega Alpha and receiving the Leon O. Jacobson Award for top basic sciences research. He also holds an MS in Applied Data Science from the University of Chicago and a BA in Biology summa cum laude from the University of Pennsylvania. He is currently training as a resident physician in Internal Medicine with plans to pursue fellowship training in Medical Oncology.
His research focuses on biomarker discovery through classical machine learning and emerging quantum computing approaches, with active collaborations across academic and clinical oncology programs. Sid has co-authored publications in leading journals including Nature Communications, npj Precision Oncology, and npj Digital Medicine, covering topics from AI applications in pediatric oncology to quantum computing for cancer research. He serves as co-investigator on major grants including the Wellcome Leap Quantum for Bio initiative, working at the intersection of quantum algorithms and multimodal cancer data analysis.
Prior to medical school, Sid worked as an analyst at ClearView Healthcare Partners, where he conducted market assessments for pharmaceutical and biotechnology companies, and completed internships at Merck studying clinical data pipelines. His combined clinical training, data science expertise, and life sciences consulting experience helps him translate complex AI methodologies into clinically meaningful diagnostic tools that improve patient outcomes.
Our well-validated software brings the latest foundation models and cutting-edge methods, enabling you to build & deploy digital biomarkers for molecular target identification, risk stratification, and treatment response prediction.
With enterprise-grade tools built on an open-source foundation, we offer unmatched commercial performance to build & deploy powerful models that leverage research-friendly flexibility, allowing seamless transition from exploration to production deployment.
Our technology platform uses Generative AI to explain the pathological features associated with your biomarker. Understanding how and why your model works can guard against confounding & bias and drive scientific discovery.
-poster-00001.jpg)
Our patent-pending uncertainty quantification methods help you build healthcare-ready predictive models that abstain on unfamiliar data.
We have a growing library of published biomarkers ready for research use and prospective clinical validation.
A biomarker capable of performing histologic subtyping and molecular classification in a group of rare pediatric tumors.
Siddhi Ramesh, MD
npj Precision Oncology, 2024
A multi-modal biomarker capable of identifying patients with early-stage breast cancer who are at increased risk of relapse after surgery.
Fred Howard, MD
npj Breast Cancer, 2023
A novel technique for explaining what deep learning pathology models learn during training, facilitating model transparency and driving scientific discovery.
James Dolezal, MD
npj Precision Oncology, 2023
Our patent-pending uncertainty quantification methods help you build healthcare-ready predictive models that abstain on unfamiliar data.
James Dolezal, MD
Nature Communications, 2022
Our comprehensive description of the problems with batch effects and confounders on multi-institution data, which can cause biased models and put patients at risk.
Fred Howard, MD
Nature Communications, 2021
Description of our thyroid cancer biomarker, which identifies a tumor's molecular signature and predicted invasiveness from its histopathological appearance.
James Dolezal, MD
Modern Pathology, 2020
.webp){kind=spacer}
Join our mailing list to stay informed about our emerging technologies & biomarker development.
Subscribe