Multi-immunohistochemistry (mIHC) is a crucial technique for simultaneous detection of multiple cellular phenotypes within a single tissue section. Its application in cancer diagnosis and treatment underscores the importance of developing reliable automated cell detection and classification methods for mIHC images. However, existing approaches face significant challenges due to high cell density, heterogeneity, and the laborious nature of annotation. This study presents a novel automated cell detection and classification model specifically designed to address these limitations. The proposed model leverages a simplified point-based annotation approach, significantly reducing annotation effort compared to conventional methods. A hybrid masking strategy combining Gaussian and circular masks is introduced to accurately capture the diverse morphological characteristics of different cell types. To enhance detail detection against complex backgrounds and robustness in highly heterogeneous environments, a novel Upsampling Attention Gate (UAG) is proposed. This module effectively improves feature extraction by focusing on relevant information within the image. Finally, a post-processing module is incorporated to address cell adhesion issues during detection, further enhancing the accuracy of the model. Extensive experiments on the mIHC dataset demonstrate that the proposed method achieves F1 scores of 0.772 and 0.747 for cell detection and classification, respectively, outperforming existing methods across various performance metrics. This study offers a promising solution to the challenges of automated cell detection and classification in mIHC images, paving the way for improved diagnosis and treatment in cancer research. The code has been made publicly available: https://github.com/s153g/mIHC_Cell_Recognition.
