Jay Shah

Md Mahfuzur Rahman Siddiquee, Jay Shah, Teresa Wu et al.

Harnessing the power of deep neural networks in the medical imaging domain is challenging due to the difficulties in acquiring large annotated datasets, especially for rare diseases, which involve high costs, time, and effort for annotation. Unsupervised disease detection methods, such as anomaly detection, can significantly reduce human effort in these scenarios. While anomaly detection typically focuses on learning from images of healthy subjects only, real-world situations often present unannotated datasets with a mixture of healthy and diseased subjects. Recent studies have demonstrated that utilizing such unannotated images can improve unsupervised disease and anomaly detection. However, these methods do not utilize knowledge specific to registered neuroimages, resulting in a subpar performance in neurologic disease detection. To address this limitation, we propose Brainomaly, a GAN-based image-to-image translation method specifically designed for neurologic disease detection. Brainomaly not only offers tailored image-to-image translation suitable for neuroimages but also leverages unannotated mixed images to achieve superior neurologic disease detection. Additionally, we address the issue of model selection for inference without annotated samples by proposing a pseudo-AUC metric, further enhancing Brainomaly's detection performance. Extensive experiments and ablation studies demonstrate that Brainomaly outperforms existing state-of-the-art unsupervised disease and anomaly detection methods by significant margins in Alzheimer's disease detection using a publicly available dataset and headache detection using an institutional dataset. The code is available from https://github.com/mahfuzmohammad/Brainomaly.

Md Mahfuzur Rahman Siddiquee, Jay Shah, Teresa Wu et al.

Automated anomaly detection from medical images, such as MRIs and X-rays, can significantly reduce human effort in disease diagnosis. Owing to the complexity of modeling anomalies and the high cost of manual annotation by domain experts (e.g., radiologists), a typical technique in the current medical imaging literature has focused on deriving diagnostic models from healthy subjects only, assuming the model will detect the images from patients as outliers. However, in many real-world scenarios, unannotated datasets with a mix of both healthy and diseased individuals are abundant. Therefore, this paper poses the research question of how to improve unsupervised anomaly detection by utilizing (1) an unannotated set of mixed images, in addition to (2) the set of healthy images as being used in the literature. To answer the question, we propose HealthyGAN, a novel one-directional image-to-image translation method, which learns to translate the images from the mixed dataset to only healthy images. Being one-directional, HealthyGAN relaxes the requirement of cycle consistency of existing unpaired image-to-image translation methods, which is unattainable with mixed unannotated data. Once the translation is learned, we generate a difference map for any given image by subtracting its translated output. Regions of significant responses in the difference map correspond to potential anomalies (if any). Our HealthyGAN outperforms the conventional state-of-the-art methods by significant margins on two publicly available datasets: COVID-19 and NIH ChestX-ray14, and one institutional dataset collected from Mayo Clinic. The implementation is publicly available at https://github.com/mahfuzmohammad/HealthyGAN.

Jay Shah, Md Mahfuzur Rahman Siddiquee, Yi Su et al.

Age is one of the major known risk factors for Alzheimer's Disease (AD). Detecting AD early is crucial for effective treatment and preventing irreversible brain damage. Brain age, a measure derived from brain imaging reflecting structural changes due to aging, may have the potential to identify AD onset, assess disease risk, and plan targeted interventions. Deep learning-based regression techniques to predict brain age from magnetic resonance imaging (MRI) scans have shown great accuracy recently. However, these methods are subject to an inherent regression to the mean effect, which causes a systematic bias resulting in an overestimation of brain age in young subjects and underestimation in old subjects. This weakens the reliability of predicted brain age as a valid biomarker for downstream clinical applications. Here, we reformulate the brain age prediction task from regression to classification to address the issue of systematic bias. Recognizing the importance of preserving ordinal information from ages to understand aging trajectory and monitor aging longitudinally, we propose a novel ORdinal Distance Encoded Regularization (ORDER) loss that incorporates the order of age labels, enhancing the model's ability to capture age-related patterns. Extensive experiments and ablation studies demonstrate that this framework reduces systematic bias, outperforms state-of-art methods by statistically significant margins, and can better capture subtle differences between clinical groups in an independent AD dataset. Our implementation is publicly available at https://github.com/jaygshah/Robust-Brain-Age-Prediction.

Jay Shah, Ganesh Bikshandi, Ying Zhang et al.

Attention, as a core layer of the ubiquitous Transformer architecture, is the bottleneck for large language models and long-context applications. FlashAttention elaborated an approach to speed up attention on GPUs through minimizing memory reads/writes. However, it has yet to take advantage of new capabilities present in recent hardware, with FlashAttention-2 achieving only 35% utilization on the H100 GPU. We develop three main techniques to speed up attention on Hopper GPUs: exploiting asynchrony of the Tensor Cores and TMA to (1) overlap overall computation and data movement via warp-specialization and (2) interleave block-wise matmul and softmax operations, and (3) block quantization and incoherent processing that leverages hardware support for FP8 low-precision. We demonstrate that our method, FlashAttention-3, achieves speedup on H100 GPUs by 1.5-2.0$\times$ with FP16 reaching up to 740 TFLOPs/s (75% utilization), and with FP8 reaching close to 1.2 PFLOPs/s. We validate that FP8 FlashAttention-3 achieves 2.6$\times$ lower numerical error than a baseline FP8 attention.

Ganesh Bikshandi, Jay Shah

We provide an optimized implementation of the forward pass of FlashAttention-2, a popular memory-aware scaled dot-product attention algorithm, as a custom fused CUDA kernel targeting NVIDIA Hopper architecture and written using the open-source CUTLASS library. In doing so, we explain the challenges and techniques involved in fusing online-softmax with back-to-back GEMM kernels, utilizing the Hopper-specific Tensor Memory Accelerator (TMA) and Warpgroup Matrix-Multiply-Accumulate (WGMMA) instructions, defining and transforming CUTLASS Layouts and Tensors, overlapping copy and GEMM operations, and choosing optimal tile sizes for the Q, K and V attention matrices while balancing the register pressure and shared memory utilization. In head-to-head benchmarks on a single H100 PCIe GPU for some common choices of hyperparameters, we observe 20-50% higher FLOPs/s over a version of FlashAttention-2 optimized for last-generation NVIDIA Ampere architecture.

Fazle Rafsani, Jay Shah, Catherine D. Chong et al.

Anomaly detection and classification in medical imaging are critical for early diagnosis but remain challenging due to limited annotated data, class imbalance, and the high cost of expert labeling. Emerging vision foundation models such as DINOv2, pretrained on extensive, unlabeled datasets, offer generalized representations that can potentially alleviate these limitations. In this study, we propose an attention-based global aggregation framework tailored specifically for 3D medical image anomaly classification. Leveraging the self-supervised DINOv2 model as a pretrained feature extractor, our method processes individual 2D axial slices of brain MRIs, assigning adaptive slice-level importance weights through a soft attention mechanism. To further address data scarcity, we employ a composite loss function combining supervised contrastive learning with class-variance regularization, enhancing inter-class separability and intra-class consistency. We validate our framework on the ADNI dataset and an institutional multi-class headache cohort, demonstrating strong anomaly classification performance despite limited data availability and significant class imbalance. Our results highlight the efficacy of utilizing pretrained 2D foundation models combined with attention-based slice aggregation for robust volumetric anomaly detection in medical imaging. Our implementation is publicly available at https://github.com/Rafsani/DinoAtten3D.git.

Ted Zadouri, Markus Hoehnerbach, Jay Shah et al.

Attention, as a core layer of the ubiquitous Transformer architecture, is the bottleneck for large language models and long-context applications. While FlashAttention-3 optimized attention for Hopper GPUs through asynchronous execution and warp specialization, it primarily targets the H100 architecture. The AI industry has rapidly transitioned to deploying Blackwell-based systems such as the B200 and GB200, which exhibit fundamentally different performance characteristics due to asymmetric hardware scaling: tensor core throughput doubles while other functional units (shared memory bandwidth, exponential units) scale more slowly or remain unchanged. We develop several techniques to address these shifting bottlenecks on Blackwell GPUs: (1) redesigned pipelines that exploit fully asynchronous MMA operations and larger tile sizes, (2) software-emulated exponential and conditional softmax rescaling that reduces non-matmul operations, and (3) leveraging tensor memory and the 2-CTA MMA mode to reduce shared memory traffic and atomic adds in the backward pass. We demonstrate that our method, FlashAttention-4, achieves up to 1.3$\times$ speedup over cuDNN 9.13 and 2.7$\times$ over Triton on B200 GPUs with BF16, reaching up to 1613 TFLOPs/s (71% utilization). Beyond algorithmic innovations, we implement FlashAttention-4 entirely in CuTe-DSL embedded in Python, achieving 20-30$\times$ faster compile times compared to traditional C++ template-based approaches while maintaining full expressivity.

Yiming Che, Fazle Rafsani, Jay Shah et al.

Weakly-supervised diffusion models (DMs) in anomaly segmentation, leveraging image-level labels, have attracted significant attention for their superior performance compared to unsupervised methods. It eliminates the need for pixel-level labels in training, offering a more cost-effective alternative to supervised methods. However, existing methods are not fully weakly-supervised because they heavily rely on costly pixel-level labels for hyperparameter tuning in inference. To tackle this challenge, we introduce Anomaly Segmentation with Forward Process of Diffusion Models (AnoFPDM), a fully weakly-supervised framework that operates without the need of pixel-level labels. Leveraging the unguided forward process as a reference for the guided forward process, we select hyperparameters such as the noise scale, the threshold for segmentation and the guidance strength. We aggregate anomaly maps from guided forward process, enhancing the signal strength of anomalous regions. Remarkably, our proposed method outperforms recent state-of-the-art weakly-supervised approaches, even without utilizing pixel-level labels.

Nitant Gupta, Sri V. V. R. Akepati, Simona Bianco et al.

In this paper, we extend a recently developed machine-learning (ML) based CREASE-2D method to analyze the entire two-dimensional (2D) scattering pattern obtained from small angle X-ray scattering measurements of supramolecular dipeptide micellar systems. Traditional analysis of such scattering data would involve use of approximate or incorrect analytical models to fit to azimuthally-averaged 1D scattering patterns that can miss the anisotropic arrangements. Analysis of the 2D scattering profiles of such micellar solutions using CREASE-2D allows us to understand both isotropic and anisotropic structural arrangements that are present in these systems of assembled dipeptides in water and in the presence of added solvents/salts. CREASE-2D outputs distributions of relevant structural features including ones that cannot be identified with existing analytical models (e.g., assembled tubes, cross-sectional eccentricity, tortuosity, orientational order). The representative three-dimensional (3D) real-space structures for the optimized values of these structural features further facilitate visualization of the structures. Through this detailed interpretation of these 2D SAXS profiles we are able to characterize the shapes of the assembled tube structures as a function of dipeptide chemistry, solution conditions with varying salts and solvents, and relative concentrations of all components. This paper demonstrates how CREASE-2D analysis of entire SAXS profiles can provide an unprecedented level of understanding of structural arrangements which has not been possible through traditional analytical model fits to the 1D SAXS data.

Jay Shah, Ayan Mahalanobis

In Europe and North America, the most widely used stream cipher to ensure privacy and confidentiality of conversations in GSM mobile phones is the A5/1. In this paper, we present a new attack on the A5/1 stream cipher with an average time complexity of 2^(48.5), which is much less than the brute-force attack with a complexity of 2^(64). The attack has a 100% success rate and requires about 5.65GB storage. We provide a detailed description of our new attack along with its implementation and results.