DLA-Count: Dynamic Label Assignment Network for Dense Cell Distribution Counting
This addresses the challenge of accurately counting densely distributed cells with diverse morphologies for medical and biological research, representing a strong specific gain rather than an incremental improvement.
The paper tackled the problem of dense cell counting in medical and biological images by introducing DLA-Count, which achieved improvements in Mean Absolute Error of up to 46.7% on the ADI dataset and 42.5% on the MBM dataset.
Cell counting remains a fundamental yet challenging task in medical and biological research due to the diverse morphology of cells, their dense distribution, and variations in image quality. We present DLA-Count, a breakthrough approach to cell counting that introduces three key innovations: (1) K-adjacent Hungarian Matching (KHM), which dramatically improves cell matching in dense regions, (2) Multi-scale Deformable Gaussian Convolution (MDGC), which adapts to varying cell morphologies, and (3) Gaussian-enhanced Feature Decoder (GFD) for efficient multi-scale feature fusion. Our extensive experiments on four challenging cell counting datasets (ADI, MBM, VGG, and DCC) demonstrate that our method outperforms previous methods across diverse datasets, with improvements in Mean Absolute Error of up to 46.7\% on ADI and 42.5\% on MBM datasets. Our code is available at https://anonymous.4open.science/r/DLA-Count.