Aaron Lee

Natalia Espinosa-Dice, Nicholas J. Jackson, Chao Yan et al.

Synthetic data generation (SDG) is a promising approach for enabling data sharing in biomedical studies while preserving patient privacy. Yet, state-of-the-art generative models often require large datasets and complex training procedures, limiting their applicability in small-sample settings common in biomedical research. This study aims to develop a more principled and efficient approach to SDG and evaluate its efficacy for biomedical applications. In this work, we reframe SDG as a reinforcement learning (RL) problem and introduce RLSyn, a novel framework that models the data generator as a stochastic policy over patient records and optimizes it using Proximal Policy Optimization with discriminator-derived rewards. We evaluate RLSyn on two biomedical datasets--AI-READI and MIMIC-IV--and benchmark it against state-of-the-art generative adversarial networks (GANs) and diffusion-based methods across extensive privacy, utility, and fidelity evaluations. On MIMIC-IV, RLSyn achieves predictive utility comparable to diffusion models (S2R AUC 0.902 vs 0.906 respectively) while slightly outperforming them in fidelity (NMI 0.001 vs. 0.003; DWD 2.073 vs. 2.797) and achieving comparable, low privacy risk (~0.50 membership inference risk AUC). On the smaller AI-READI dataset, RLSyn again matches diffusion-based utility (S2R AUC 0.873 vs. 0.871), while achieving higher fidelity (NMI 0.001 vs. 0.002; DWD 13.352 vs. 16.441) and significantly lower vulnerability to membership inference attacks (AUC 0.544 vs. 0.601). Both RLSyn and diffusion-based models substantially outperform GANs across utility and fidelity on both datasets. Our results suggest that reinforcement learning provides a principled and effective approach for synthetic biomedical data generation, particularly in data-scarce regimes.

Shirley Wu, Parth Sarthi, Shiyu Zhao et al.

Compound AI systems integrating multiple components, such as Large Language Models, specialized tools, and traditional machine learning models, are increasingly deployed to solve complex real-world tasks. However, optimizing compound systems remains challenging due to their non-differentiable structures and diverse configuration types across components, including prompts, hyperparameters, and model parameters. To address this challenge, we propose Optimas, a unified framework for effective optimization of compound systems. The core idea of Optimas is to maintain one Local Reward Function (LRF) per component, each satisfying a local-global alignment property, i.e., each component's local reward correlates with the global system performance. In each iteration, Optimas efficiently adapts the LRFs to maintain this property while simultaneously maximizing each component's local reward. This approach enables independent updates of heterogeneous configurations using the designated optimization method, while ensuring that local improvements consistently lead to performance gains. We present extensive evaluations across five real-world compound systems to demonstrate that Optimas outperforms strong baselines by an average improvement of 11.92%, offering a general and effective approach for improving compound systems. Our website is at https://optimas.stanford.edu.

Yue Wu, Abraham Olvera Barrios, Ryan Yanagihara et al.

Unsupervised cross domain adaptation for OCT 7 layer segmentation and other medical applications where labeled training data is only available in a source domain and unavailable in the target domain. Our proposed method helps generalize of deep learning to many areas in the medical field where labeled training data are expensive and time consuming to acquire or where target domains are too novel to have had labelling.

Robert Robinson, Ozan Oktay, Wenjia Bai et al.

Recent advances in deep learning based image segmentation methods have enabled real-time performance with human-level accuracy. However, occasionally even the best method fails due to low image quality, artifacts or unexpected behaviour of black box algorithms. Being able to predict segmentation quality in the absence of ground truth is of paramount importance in clinical practice, but also in large-scale studies to avoid the inclusion of invalid data in subsequent analysis. In this work, we propose two approaches of real-time automated quality control for cardiovascular MR segmentations using deep learning. First, we train a neural network on 12,880 samples to predict Dice Similarity Coefficients (DSC) on a per-case basis. We report a mean average error (MAE) of 0.03 on 1,610 test samples and 97% binary classification accuracy for separating low and high quality segmentations. Secondly, in the scenario where no manually annotated data is available, we train a network to predict DSC scores from estimated quality obtained via a reverse testing strategy. We report an MAE=0.14 and 91% binary classification accuracy for this case. Predictions are obtained in real-time which, when combined with real-time segmentation methods, enables instant feedback on whether an acquired scan is analysable while the patient is still in the scanner. This further enables new applications of optimising image acquisition towards best possible analysis results.

Aaron Lee, Livia King

In this paper, we implement Ant Colony Optimization (ACO) for sequence alignment. ACO is a meta-heuristic recently developed for nearest neighbor approximations in large, NP-hard search spaces. Here we use a genetic algorithm approach to evolve the best parameters for an ACO designed to align two sequences. We then used the best parameters found to interpolate approximate optimal parameters for a given string length within a range. The basis of our comparison is the alignment given by the Needleman-Wunsch algorithm. We found that ACO can indeed be applied to sequence alignment. While it is computationally expensive compared to other equivalent algorithms, it is a promising algorithm that can be readily applied to a variety of other biological problems.