Breast Exams at Home: How AI Expands Access Beyond Traditional Screening

Breast cancer screening fails most often where access is constrained: limited appointments, geographic gaps, dense breast tissue, and reliance on self-exams that depend entirely on human touch. Awareness alone doesn’t close those gaps.

In this episode, Dr. Karny Ilan, co-founder and CEO of Feminai, shares how physician-led product design, multidisciplinary collaboration, and rigorous clinical trials shaped a new model for breast screening access. The conversation explores a shift in how breast health is managed—from episodic screening to continuous, individualized monitoring. Rather than relying on infrequent appointments alone, it examines tools designed to track changes over time, at home, while remaining connected to clinical decision-making.

Timestamps

• (00:11) Breast cancer risk shaped by genetics and lived exposure
• (08:37) Limits of traditional self-breast exams
• (09:09) Personal experience shaping breast health urgency
• (10:15) How at-home breast scanning detects change over time
• (12:42) Designing screening tools for dense breast tissue
• (17:03) Addressing breast size, shape, and post-surgical variation
• (18:31) Clinical trials revealing real-world usability gaps
• (20:13) Why ease of use affects screening reliability
• (29:29) Access gaps amplified by pandemic-era screening delays
• (38:09) Broad inclusion across age, risk, and body types

Guest Bio

Dr. Karny Ilan — Co-Founder and CEO, Feminai
Dr. Karny Ilan is a general surgery resident at Sheba Medical Center and the co-founder and CEO of Feminai, a breast health company developing an AI-enabled disposable wearable patch and app for at-home breast exams. With a strong family history of breast cancer, she brings clinical experience and patient-centered design to building scalable screening tools that expand access and personalization.
LinkedIn: https://www.linkedin.com/in/karny-ilan/

Key Points

• Access constraints drive missed detection: Feminai targets screening gaps caused by geography, capacity, and avoidance.
• Physician-led design builds trust: Clinical credibility accelerated adoption with providers and investors.
• Dense breast tissue is a priority use case: The technology is designed to perform well where mammography often struggles.
• Personalized baselines change detection logic: Each scan is compared against the user’s own prior data.
• Usability directly affects accuracy: Instructions, fit, and behavior shape downstream AI performance.

Deep Dives

1. At-home breast exams as infrastructure

• Designed for frequent, low-friction use
• Complements rather than replaces imaging

2. Patch and app workflow

• Risk stratification via medical questionnaire
• Bluetooth-enabled scan uploads to secure cloud
• AI analysis with physician review

3. Designing for every body

• Stretch materials accommodate size variation
• Dense tissue explicitly accounted for
• Additional sizes planned as rollout expands

4. Clinical trials beyond performance metrics

• Usability drove multiple design iterations
• Instruction format affected adherence
• Shape changes required algorithm updates

5. Personalized longitudinal tracking

• Each woman compared only to herself
• Changes flagged based on deviation, not population averages

6. Leadership and multidisciplinary teams

• Engineers exposed to clinical sites
• Patient stories shared to reinforce mission
• Stability in leadership communication protected execution

Links & References

• Breast cancer screening beyond mammography (Mayo Clinic): https://www.mayoclinic.org/tests-procedures/mammogram/in-depth/breast-cancer/art-20047233
• Breast cancer screening recommendations (USPSTF): https://www.uspreventiveservicestaskforce.org/uspstf/recommendation/breast-cancer-screening