To address the challenges posed by complex background interference, varying target sizes, and high species diversity in bird detection tasks in the Dongting Lake region, this paper proposes an enhanced bird detection model named Birds-YOLO, based on the YOLOv11 framework. First, the EMA mechanism is introduced to replace the original C2PSA module. This mechanism synchronously captures global dependencies in the channel dimension and local detailed features in the spatial dimension, thereby enhancing the model’s robustness in cluttered environments. Second, the model incorporates an improved RepNCSPELAN4-ECO module, by reasonably integrating depthwise separable convolution modules and combining them with an adaptive channel compression mechanism, to strengthen feature extraction and multi-scale feature fusion, effectively enhances the detection capability for bird targets at different scales. Finally, the neck component of the network is redesigned using lightweight GSConv convolution, which integrates the principles of grouped and spatial convolutions. This design preserves the feature modeling capacity of standard convolution while incorporating the computational efficiency of depthwise separable convolution, thereby reducing model complexity without sacrificing accuracy. Experimental results show that, compared to the baseline YOLOv11n, Birds-YOLO achieves a 5.0% improvement in recall and a 3.5% increase in mAP@0.5 on the CUB200-2011 dataset. On the in-house DTH-Birds dataset, it gains 3.7% in precision, 3.7% in recall, and 2.6% in mAP@0.5, demonstrating consistent performance enhancement across both public and private benchmarks. The model’s generalization ability and robustness are further validated through extensive ablation studies and comparative experiments, indicating its strong potential for practical deployment in bird detection tasks in complex natural environments such as Dongting Lake.

Objectives Although primary tumour surgery could prolong survival for patients with stage IV breast cancer, how to select candidates for primary tumour surgery is still a challenging problem for medical oncologists. Design This study is a retrospective database study. Setting and participants In this study, we aimed at evaluating the primary site surgery effect and select the beneficial subgroups. 13 618 patients with stage IV breast cancer, diagnosed between 2010 and 2015, were collected from SEER*Stat database. Interventions Based on the local surgery at primary tumour site, patients were categorised into three groups: primary tumour surgery performed group, recommended for primary tumour surgery but refused (RBR) group and surgery not recommended (NR) group. Primary and secondary outcome measures All-cause survival and breast cancer-specific survival (BCSS). Results Univariate Cox regression analyses showed that, compared with surgery group, patients in non-surgery (RBR and NR) groups tend to be older, T4, N0/NX, triple-negative and visceral metastatic. For both all-cause survival and BCSS, non-surgery, advanced T stage, triple-negative BC (TNBC) and visceral metastases were significant risk factors. Primary tumour surgery showed benefits for both all-cause survival (HR=0.44, 95% CI=0.39–0.49, p<0.0001) and BCSS (HR=0.43, 95% CI=0.38–0.49, p<0.0001). However, after propensity score matching, primary tumour surgery failed to demonstrate significant benefits for TNBC (HR=0.96, 95% CI=0.60–1.53, p=0.851) and patients with visceral metastases (HR=0.90, 95% CI=0.60–1.36, p=0.62). Conclusion Surgery was associated with prolonged survival in stage IV breast cancers, but not in patients with TNBC and visceral metastases.

East Dongting Lake is an important habitat for migratory birds. Accurately counting the number of migratory birds is crucial to assessing the health of the wetland ecological environment. Traditional manual observation and low-precision methods make it difficult to meet this demand. To this end, this paper proposes a weighted feature fusion network based on multi-level supervision (MS-WFFNet) to count migratory birds. MS-WFFNet consists of three parts: an EEMA-VGG16 sub-network, a multi-source feature aggregation (MSFA) module, and a density map regression (DMR) module. Among them, the EEMA-VGG16 sub-network cross-injects enhanced efficient multi-scale attention (EEMA) into the truncated VGG16 structure. It uses multi-head attention to nonlinearly learn the relative importance of different positions in the same direction. With only a few parameters added, EEMA effectively suppresses the noise interference caused by a cluttered background. The MSFA module integrates a weighted mechanism to fully preserve low-level detail information and high-level semantic information. It achieves this by aggregating multi-source features and enhancing the expression of key features. The DMR module applies density map regression to the output of each path in the MSFA module. It ensures local consistency and spatial correlation among multiple regression results by using distributed supervision. In addition, this paper presents the migratory bird counting dataset DTH, collected using local monitoring equipment in East Dongting Lake. It is combined with other object counting datasets for extensive experiments, showcasing the proposed method’s excellent performance and generalization capability.