Limited by the expensive labeling, polyp segmentation models are plagued by data shortages. To tackle this, we propose the mixed supervised polyp segmentation paradigm (MixPolyp). Unlike traditional models relying on a single type of annotation, MixPolyp combines diverse annotation types (mask, box, and scribble) within a single model, thereby expanding the range of available data and reducing labeling costs. To achieve this, MixPolyp introduces three novel supervision losses to handle various annotations: Subspace Projection loss $\left({{{\mathcal{L}}_{{\mathcal{S}}{\mathcal{P}}}}}\right)$, Binary Minimum Entropy loss $\left({{{\mathcal{L}}_{{\mathcal{B}}{\mathcal{M}}{\mathcal{E}}}}}\right)$, and Linear Regularization loss $\left({{{\mathcal{L}}_{{\mathcal{L}}{\mathcal{R}}}}}\right)$. For box annotations, ${{\mathcal{L}}_{{\mathcal{S}}{\mathcal{P}}}}$ eliminates shape inconsistencies between the prediction and the supervision. For scribble annotations, ${{\mathcal{L}}_{{\mathcal{B}}{\mathcal{M}}{\mathcal{E}}}}$ provides supervision for unlabeled pixels through minimum entropy constraint, thereby alleviating supervision sparsity. Furthermore, ${{\mathcal{L}}_{{\mathcal{L}}{\mathcal{R}}}}$ provides dense supervision by enforcing consistency among the predictions, thus reducing the non-uniqueness. These losses are independent of the model structure, making them generally applicable. They are used only during training, adding no computational cost during inference. Extensive experiments on five datasets demonstrate MixPolyp’s effectiveness.

Tumor segmentation plays a crucial role in clinical diagnosis and treatment. However, the presence of low contrast, blurred boundaries, and complex morphology in tumor images often leads to inaccuracies in tumor target segmentation. Recent approaches leveraging the Segment Anything Model (SAM) have made significant strides in tumor image segmentation, but they typically rely on precise pixel-level annotations, which are both costly and time-consuming, presenting a major challenge for effective tumor segmentation. To address these issues, we propose MWS-SAM, a novel SAM-based tumor segmentation framework that enables model training using only bounding box annotations, significantly reducing annotation costs while maintaining high segmentation accuracy. Specifically, the Multi-scale Feature Fusion Decoder (MFD) module significantly enhances the model’s capacity to capture tumor edge information by integrating multi-scale features from tumor images. To ease the noise introduced by bounding box annotations, we propose the Prediction-Box-Supervision (PBS) module, which transforms the predicted mask into a box mask aligned with the bounding box annotations, effectively addressing potential misrepresentations due to box bias. Additionally, we implement a consistency loss among varying predictions within the same image, which successfully reduces excessive prediction diversity and enhances overall model robustness. Results obtained from four distinct tumor segmentation datasets validate the efficacy of MWS-SAM, demonstrating comparable performance to fully supervised models without the necessity for accurate annotation.

Accurate polyp detection is critical for early colorectal cancer diagnosis. Although remarkable progress has been achieved in recent years, the complex colon environment and concealed polyps with unclear boundaries still pose severe challenges in this area. Existing methods either involve computationally expensive context aggregation or lack prior modeling of polyps, resulting in poor performance in challenging cases. In this paper, we propose the Enhanced CenterNet with Contrastive Learning (ECC-PolypDet), a two-stage training & end-to-end inference framework that leverages images and bounding box annotations to train a general model and fine-tune it based on the inference score to obtain a final robust model. Specifically, we conduct Box-assisted Contrastive Learning (BCL) during training to minimize the intra-class difference and maximize the inter-class difference between foreground polyps and backgrounds, enabling our model to capture concealed polyps. Moreover, to enhance the recognition of small polyps, we design the Semantic Flow-guided Feature Pyramid Network (SFFPN) to aggregate multi-scale features and the Heatmap Propagation (HP) module to boost the model's attention on polyp targets. In the fine-tuning stage, we introduce the IoU-guided Sample Re-weighting (ISR) mechanism to prioritize hard samples by adaptively adjusting the loss weight for each sample during fine-tuning. Extensive experiments on six large-scale colonoscopy datasets demonstrate the superiority of our model compared with previous state-of-the-art detectors.