Precision and explainability are vital in breast cancer risk assessment for developing personalized screening and prevention strategies. Our paper, "Ordinal Learning: Longitudinal Attention Alignment Model for Predicting Time to Future Breast Cancer Events from Mammograms", introduces OA-BreaCR, a novel method that precisely evaluates both the likelihood and timing of future breast cancer occurrences using sequential mammograms. By employing ordinal learning, OA-BreaCR models temporal information based on the 'time-to-future-event' ordering among patients, improving the precision of time predictions.
Additionally, the method utilizes an attention alignment mechanism to effectively track high-risk breast tissue changes over time, enhancing the model's interpretability, which could help doctors make better healthcare decisions.
As a PhD student, presenting at MICCAI 2024 is an incredible opportunity for me. MICCAI is one of the top conferences in AI for medical image analysis, and it's exciting to share my research with experts in the field. It feels rewarding to have my work recognized at this level, and I'm eager to receive feedback that will help improve my future research.
I'm very interested in learning more about new methodologies for longitudinal data analysis and how these innovations are being integrated into clinical practice to improve patient outcomes—this aligns closely with my current research. Additionally, I'm curious about how recent large language models and foundation models are being applied in medical imaging and how these techniques are being implemented in real clinical settings.
I'm excited to hear valuable insights from renowned researchers and scientists. I'm also looking forward to meeting other students and researchers from around the world who are working in similar areas. The opportunity to network, share ideas, and potentially form new collaborations is something I'm very excited about. Additionally, I'm also looking forward to experiencing Marrakesh and its culture during the conference.