Glioblastoma, a highly aggressive brain tumor with diverse molecular and pathological features, poses a diagnostic challenge due to its heterogeneity. Accurate diagnosis and assessment of this heterogeneity are essential for choosing the right treatment and improving patient outcomes. Traditional methods rely on identifying specific features in tissue samples, but deep learning offers a promising approach for improved glioblastoma diagnosis. In this paper, we present our approach to the BraTS-Path Challenge 2024. We leverage a pre-trained model and fine-tune it on the BraTS-Path training dataset. Our model demonstrates poor performance on the challenging BraTS-Path validation set, as rigorously assessed by the Synapse online platform. The model achieves an accuracy of 0.392229, a recall of 0.392229, and a F1-score of 0.392229, indicating a consistent ability to correctly identify instances under the target condition. Notably, our model exhibits perfect specificity of 0.898704, showing an exceptional capacity to correctly classify negative cases. Moreover, a Matthews Correlation Coefficient (MCC) of 0.255267 is calculated, to signify a limited positive correlation between predicted and actual values and highlight our model's overall predictive power. Our solution also achieves the second place during the testing phase.

In scenarios where training data is limited due to observation costs or data scarcity, enriching the label information associated with each instance becomes crucial for building high-accuracy classification models. In such contexts, it is often feasible to obtain not only hard labels but also {\it additional supervision}, such as the confidences for the hard labels. This setting naturally raises fundamental questions: {\it What kinds of additional supervision are intrinsically beneficial?} And {\it how do they contribute to improved generalization performance?} To address these questions, we propose a theoretical framework that treats both hard labels and additional supervision as probability distributions, and constructs soft labels through their affine combination. Our theoretical analysis reveals that the essential component of additional supervision is not the confidence score of the assigned hard label, but rather the information of the distribution over the non-hard-labeled classes. Moreover, we demonstrate that the additional supervision and the mixing coefficient contribute to the refinement of soft labels in complementary roles. Intuitively, in the probability simplex, the additional supervision determines the direction in which the deterministic distribution representing the hard label should be adjusted toward the true label distribution, while the mixing coefficient controls the step size along that direction. Through generalization error analysis, we theoretically characterize how the additional supervision and its mixing coefficient affect both the convergence rate and asymptotic value of the error bound. Finally, we experimentally demonstrate that, based on our theory, designing additional supervision can lead to improved classification accuracy, even when utilized in a simple manner.

Biomedical Foundation Models (FMs) are rapidly transforming AI-enabled healthcare research and entering clinical validation. However, their susceptibility to learning non-biological technical features -- including variations in surgical/endoscopic techniques, laboratory procedures, and scanner hardware -- poses risks for clinical deployment. We present the first systematic investigation of pathology FM robustness to non-biological features. Our work (i) introduces measures to quantify FM robustness, (ii) demonstrates the consequences of limited robustness, and (iii) proposes a framework for FM robustification to mitigate these issues. Specifically, we developed PathoROB, a robustness benchmark with three novel metrics, including the robustness index, and four datasets covering 28 biological classes from 34 medical centers. Our experiments reveal robustness deficits across all 20 evaluated FMs, and substantial robustness differences between them. We found that non-robust FM representations can cause major diagnostic downstream errors and clinical blunders that prevent safe clinical adoption. Using more robust FMs and post-hoc robustification considerably reduced (but did not yet eliminate) the risk of such errors. This work establishes that robustness evaluation is essential for validating pathology FMs before clinical adoption and demonstrates that future FM development must integrate robustness as a core design principle. PathoROB provides a blueprint for assessing robustness across biomedical domains, guiding FM improvement efforts towards more robust, representative, and clinically deployable AI systems that prioritize biological information over technical artifacts.

We study the societal impact of pseudo-scientific assumptions for predicting the behavior of people in a straightforward application of machine learning to risk prediction in financial lending. This use case also exemplifies the impact of survival bias in loan return prediction. We analyze the models in terms of their accuracy and social cost, showing that the socially optimal model may not imply a significant accuracy loss for this downstream task. Our results are verified for commonly used learning methods and datasets. Our findings also show that there is a natural dynamic when training models that suffer survival bias where accuracy slightly deteriorates, and whose recall and precision improves with time. These results act as an illusion, leading the observer to believe that the system is getting better, when in fact the model is suffering from increasingly more unfairness and survival bias.

Generating clinical synthetic text represents an effective solution for common clinical NLP issues like sparsity and privacy. This paper aims to conduct a systematic review on generating synthetic medical free-text by formulating quantitative analysis to three research questions concerning (i) the purpose of generation, (ii) the techniques, and (iii) the evaluation methods. We searched PubMed, ScienceDirect, Web of Science, Scopus, IEEE, Google Scholar, and arXiv databases for publications associated with generating synthetic medical unstructured free-text. We have identified 94 relevant articles out of 1,398 collected ones. A great deal of attention has been given to the generation of synthetic medical text from 2018 onwards, where the main purpose of such a generation is towards text augmentation, assistive writing, corpus building, privacy-preserving, annotation, and usefulness. Transformer architectures were the main predominant technique used to generate the text, especially the GPTs. On the other hand, there were four main aspects of evaluation, including similarity, privacy, structure, and utility, where utility was the most frequent method used to assess the generated synthetic medical text. Although the generated synthetic medical text demonstrated a moderate possibility to act as real medical documents in different downstream NLP tasks, it has proven to be a great asset as augmented, complementary to the real documents, towards improving the accuracy and overcoming sparsity/undersampling issues. Yet, privacy is still a major issue behind generating synthetic medical text, where more human assessments are needed to check for the existence of any sensitive information. Despite that, advances in generating synthetic medical text will considerably accelerate the adoption of workflows and pipeline development, discarding the time-consuming legalities of data transfer.

This research addresses the critical lack of comprehensive studies on feature scaling by systematically evaluating 12 scaling techniques - including several less common transformations - across 14 different Machine Learning algorithms and 16 datasets for classification and regression tasks. We meticulously analyzed impacts on predictive performance (using metrics such as accuracy, MAE, MSE, and $R^2$) and computational costs (training time, inference time, and memory usage). Key findings reveal that while ensemble methods (such as Random Forest and gradient boosting models like XGBoost, CatBoost and LightGBM) demonstrate robust performance largely independent of scaling, other widely used models such as Logistic Regression, SVMs, TabNet, and MLPs show significant performance variations highly dependent on the chosen scaler. This extensive empirical analysis, with all source code, experimental results, and model parameters made publicly available to ensure complete transparency and reproducibility, offers model-specific crucial guidance to practitioners on the need for an optimal selection of feature scaling techniques.

Neural Posterior Estimation (NPE) has emerged as a powerful approach for amortized Bayesian inference when the true posterior $p(θ\mid y)$ is intractable or difficult to sample. But evaluating the accuracy of neural posterior estimates remains challenging, with existing methods suffering from major limitations. One appealing and widely used method is the classifier two-sample test (C2ST), where a classifier is trained to distinguish samples from the true posterior $p(θ\mid y)$ versus the learned NPE approximation $q(θ\mid y)$. Yet despite the appealing simplicity of the C2ST, its theoretical and practical reliability depend upon having access to a near-Bayes-optimal classifier -- a requirement that is rarely met and, at best, difficult to verify. Thus a major open question is: can a weak classifier still be useful for neural posterior validation? We show that the answer is yes. Building on the work of Hu and Lei, we present several key results for a conformal variant of the C2ST, which converts any trained classifier's scores -- even those of weak or over-fitted models -- into exact finite-sample p-values. We establish two key theoretical properties of the conformal C2ST: (i) finite-sample Type-I error control, and (ii) non-trivial power that degrades gently in tandem with the error of the trained classifier. The upshot is that even weak, biased, or overfit classifiers can still yield powerful and reliable tests. Empirically, the Conformal C2ST outperforms classical discriminative tests across a wide range of benchmarks. These results reveal the under appreciated strength of weak classifiers for validating neural posterior estimates, establishing the conformal C2ST as a practical, theoretically grounded diagnostic for modern simulation-based inference.

Synthetic tabular data is essential for machine learning workflows, especially for expanding small or imbalanced datasets and enabling privacy-preserving data sharing. However, state-of-the-art generative models (GANs, VAEs, diffusion models) rely on large datasets with thousands of examples. In low-data settings, often the primary motivation for synthetic data, these models can overfit, leak sensitive records, and require frequent retraining. Recent work uses large pre-trained transformers to generate rows via in-context learning (ICL), which needs only a few seed examples and no parameter updates, avoiding retraining. But ICL repeats seed rows verbatim, introducing a new privacy risk that has only been studied in text. The severity of this risk in tabular synthesis-where a single row may identify a person-remains unclear. We address this gap with the first benchmark of three foundation models (GPT-4o-mini, LLaMA 3.3 70B, TabPFN v2) against four baselines on 35 real-world tables from health, finance, and policy. We evaluate statistical fidelity, downstream utility, and membership inference leakage. Results show foundation models consistently have the highest privacy risk. LLaMA 3.3 70B reaches up to 54 percentage points higher true-positive rate at 1% FPR than the safest baseline. GPT-4o-mini and TabPFN are also highly vulnerable. We plot the privacy-utility frontier and show that CTGAN and GPT-4o-mini offer better tradeoffs. A factorial study finds that three zero-cost prompt tweaks-small batch size, low temperature, and using summary statistics-can reduce worst-case AUC by 14 points and rare-class leakage by up to 39 points while maintaining over 90% fidelity. Our benchmark offers a practical guide for safer low-data synthesis with foundation models.

Graph class-incremental learning (GCIL) allows graph neural networks (GNNs) to adapt to evolving graph analytical tasks by incrementally learning new class knowledge while retaining knowledge of old classes. Existing GCIL methods primarily focus on a closed-set assumption, where all test samples are presumed to belong to previously known classes. Such an assumption restricts their applicability in real-world scenarios, where unknown classes naturally emerge during inference, and are absent during training. In this paper, we explore a more challenging open-set graph class-incremental learning scenario with two intertwined challenges: catastrophic forgetting of old classes, which impairs the detection of unknown classes, and inadequate open-set recognition, which destabilizes the retention of learned knowledge. To address the above problems, a novel OGCIL framework is proposed, which utilizes pseudo-sample embedding generation to effectively mitigate catastrophic forgetting and enable robust detection of unknown classes. To be specific, a prototypical conditional variational autoencoder is designed to synthesize node embeddings for old classes, enabling knowledge replay without storing raw graph data. To handle unknown classes, we employ a mixing-based strategy to generate out-of-distribution (OOD) samples from pseudo in-distribution and current node embeddings. A novel prototypical hypersphere classification loss is further proposed, which anchors in-distribution embeddings to their respective class prototypes, while repelling OOD embeddings away. Instead of assigning all unknown samples into one cluster, our proposed objective function explicitly models them as outliers through prototype-aware rejection regions, ensuring a robust open-set recognition. Extensive experiments on five benchmarks demonstrate the effectiveness of OGCIL over existing GCIL and open-set GNN methods.

Skin cancer is one of the most prevalent and preventable types of cancer, yet its early detection remains a challenge, particularly in resource-limited settings where access to specialized healthcare is scarce. This study proposes an AI-driven diagnostic tool optimized for embedded systems to address this gap. Using transfer learning with the MobileNetV2 architecture, the model was adapted for binary classification of skin lesions into "Skin Cancer" and "Other." The TensorRT framework was employed to compress and optimize the model for deployment on the NVIDIA Jetson Orin Nano, balancing performance with energy efficiency. Comprehensive evaluations were conducted across multiple benchmarks, including model size, inference speed, throughput, and power consumption. The optimized models maintained their performance, achieving an F1-Score of 87.18% with a precision of 93.18% and recall of 81.91%. Post-compression results showed reductions in model size of up to 0.41, along with improvements in inference speed and throughput, and a decrease in energy consumption of up to 0.93 in INT8 precision. These findings validate the feasibility of deploying high-performing, energy-efficient diagnostic tools on resource-constrained edge devices. Beyond skin cancer detection, the methodologies applied in this research have broader applications in other medical diagnostics and domains requiring accessible, efficient AI solutions. This study underscores the potential of optimized AI systems to revolutionize healthcare diagnostics, thereby bridging the divide between advanced technology and underserved regions.