A5084312082- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- COVID-19 diagnosis using AI
- Anomaly Detection Techniques and Applications
- Artificial Intelligence in Healthcare and Education
- Cutaneous Melanoma Detection and Management
- Digital Imaging for Blood Diseases
- Machine Learning in Healthcare
- AI-based Problem Solving and Planning
- Machine Learning and Data Classification
- Semantic Web and Ontologies
- Cognitive Science and Education Research
- Advanced Statistical Methods and Models
- Radiology practices and education
- Imbalanced Data Classification Techniques
- Bacillus and Francisella bacterial research
Google (United States)
2021-2025
Recent progress in Medical Artificial Intelligence (AI) has delivered systems that can reach clinical expert level performance. However, such tend to demonstrate sub-optimal "out-of-distribution" performance when evaluated settings different from the training environment. A common mitigation strategy is develop separate for each setting using site-specific data [1]. this quickly becomes impractical as medical time-consuming acquire and expensive annotate [2]. Thus, problem of "data-efficient...
Transfer learning is a standard technique to improve performance on tasks with limited data. However, for medical imaging, the value of transfer less clear. This likely due large domain mismatch between usual natural-image pre-training (e.g. ImageNet) and images. recent advances in have shown substantial improvements from scale. We investigate whether modern methods can change fortune imaging. For this, we study class large-scale pre-trained networks presented by Kolesnikov et al. three...
During the diagnostic process, doctors incorporate multimodal information including imaging and medical history - similarly AI development has increasingly become multimodal. In this paper we tackle a more subtle challenge: take targeted to obtain only most pertinent pieces of information; how do enable same? We develop wrapper method named MINT (Make your model INTeractive) that automatically determines what are valuable at each step, ask for useful information. demonstrate efficacy...
While multimodal foundation models can now natively work with data beyond text, they remain underutilized in analyzing the considerable amounts of multi-dimensional time-series fields like healthcare, finance, and social sciences, representing a missed opportunity for richer, data-driven insights. This paper proposes simple but effective method that leverages existing vision encoders these to "see" via plots, avoiding need additional, potentially costly, model training. Our empirical...
For safety, AI systems in health undergo thorough evaluations before deployment, validating their predictions against a ground truth that is assumed certain. However, this actually not the case and may be uncertain. Unfortunately, largely ignored standard evaluation of models but can have severe consequences such as overestimating future performance. To avoid this, we measure effects uncertainty, which assume decomposes into two main components: annotation uncertainty stems from lack...