NuNext: Reframing Nucleus Detection as Next-Point Detection
This work addresses the problem of efficient and accurate nucleus detection for clinical applications in histopathology, offering an incremental improvement over existing methods.
This paper reframes nucleus detection as a next-point prediction task, using a multimodal large language model to directly output nucleus centroids from histopathology images. The method demonstrates superior performance across nine widely used benchmarks.
Nucleus detection in histopathology is pivotal for a wide range of clinical applications. Existing approaches either regress nuclear proxy maps that require complex post-processing, or employ dense anchors or queries that introduce severe foreground-background imbalance. In this work, we reformulate nucleus detection as next-point prediction, wherein a multimodal large language model is developed to directly output foreground nucleus centroids from the input image. The model is trained in two stages. In the supervised learning stage, we propose spatial-aware soft supervision to relax strict centroid matching and a chain-of-visual-thought strategy to incorporate visual priors that facilitate coordinate prediction. In the reinforcement fine-tuning stage, we design distribution matching reward, low-variance group filtering, and fine-grained advantage shaping to further improve the model's detection quality. Extensive experiments on nine widely used benchmarks demonstrate the superiority of our method. Code will be released soon.