Minh Sao Khue Luu

Minh Sao Khue Luu, Evgeniy N. Pavlovskiy, Bair N. Tuchinov

We propose a unified objective function, termed CATMIL, that augments the base segmentation loss with two auxiliary supervision terms operating at different levels. The first term, Component-Adaptive Tversky, reweights voxel contributions based on connected components to balance the influence of lesions of different sizes. The second term, based on Multiple Instance Learning, introduces lesion-level supervision by encouraging the detection of each lesion instance. These terms are combined with the standard nnU-Net loss to jointly optimize voxel-level segmentation accuracy and lesion-level detection. We evaluate the proposed objective on the MSLesSeg dataset using a consistent nnU-Net framework and 5-fold cross-validation. The results show that CATMIL achieves the most balanced performance across segmentation accuracy, lesion detection, and error control. It improves Dice score (0.7834) and reduces boundary error compared to standard losses. More importantly, it substantially increases small lesion recall and reduces false negatives, while maintaining the lowest false positive volume among compared methods. These findings demonstrate that integrating component-level and lesion-level supervision within a unified objective provides an effective and practical approach for improving small lesion segmentation in highly imbalanced settings. All code and pretrained models are available at \href{https://github.com/luumsk/SmallLesionMRI}{this url}.

Minh Sao Khue Luu, Bair N. Tuchinov

We present a foundation model for brain MRI that can work with different combinations of imaging sequences. The model uses one encoder with learnable modality embeddings, conditional layer normalization, and a masked autoencoding objective that accounts for missing modalities. A variance-covariance regularizer is applied to stabilize feature learning and improve representation diversity. This design removes the need for separate models for each modality and allows the network to adapt when some sequences are missing or unseen. It is trained on about 60,000 multi-center MRIs using self-supervised reconstruction and modality imputation to learn flexible representations. A learnable modality embedding guides feature extraction so the encoder can adjust to different inputs. We describe our planned evaluation on brain tumor and multiple sclerosis segmentation, as well as lesion classification, under various modality settings. Preliminary results show that the method works feasibly, and further experiments are planned to study its performance in more detail. All code and pretrained models are available at https://github.com/BrainFM/brainfm

Minh Sao Khue Luu, Margaret V. Benedichuk, Ekaterina I. Roppert et al.

The development of foundation models for brain MRI depends critically on the scale, diversity, and consistency of available data, yet systematic assessments of these factors remain scarce. In this study, we analyze 54 publicly accessible brain MRI datasets encompassing over 538,031 to provide a structured, multi-level overview tailored to foundation model development. At the dataset level, we characterize modality composition, disease coverage, and dataset scale, revealing strong imbalances between large healthy cohorts and smaller clinical populations. At the image level, we quantify voxel spacing, orientation, and intensity distributions across 15 representative datasets, demonstrating substantial heterogeneity that can influence representation learning. We then perform a quantitative evaluation of preprocessing variability, examining how intensity normalization, bias field correction, skull stripping, spatial registration, and interpolation alter voxel statistics and geometry. While these steps improve within-dataset consistency, residual differences persist between datasets. Finally, feature-space case study using a 3D DenseNet121 shows measurable residual covariate shift after standardized preprocessing, confirming that harmonization alone cannot eliminate inter-dataset bias. Together, these analyses provide a unified characterization of variability in public brain MRI resources and emphasize the need for preprocessing-aware and domain-adaptive strategies in the design of generalizable brain MRI foundation models.

Quy Minh Le, Minh Sao Khue Luu, Khanh-Tung Tran et al.

Effective tool use is essential for agentic AI, yet training agents to utilize tools remains challenging due to manually designed rewards, limited training data, and poor multi-tool selection, resulting in slow adaptation, wasted computational resources, and suboptimal performance. We introduce ToolBrain, a lightweight and user-friendly framework for coaching tool use in agentic models with flexible reinforcement learning (RL), easing the barriers for researchers and practitioners to adapt LLM-based agents to specific domains. It supports a wide range of training strategies, including RL algorithms such as GRPO and DPO, as well as supervised learning. ToolBrain enables custom reward callables directly on an agent's execution traces or simply utilizes an automated LLM-as-a-judge system for reward generation. It is packed with useful capabilities, including knowledge distillation from large to small models for efficient development, automatic task generation from tool descriptions, seamless tool retrieval, efficient fine-tuning pipelines with QLoRA through Unsloth, and quantized inference via bitsandbytes. We demonstrate ToolBrain through diverse use cases, such as training a CodeAct agent to autonomously execute email search tasks, showing fast, targeted improvements (up to 30.0%) in tool-use skills while keeping the codebase simple and extensible in Agentic AI. Our framework is publicly available at https://toolbrain.org.