Abstract
To address the low efficiency and high subjectivity of manual interpretation in fluorescence in situ hybridization (FISH) tissue and cell images, this study proposes an intelligent FISH image classification model based on an improved ResNet50 architecture. By analyzing the characteristics of multi-channel fluorescence signals and the bottlenecks of clinical interpretation, a Convolutional Block Attention Module (CBAM) is introduced to enhance the representation of salient fluorescence features through dual channel-spatial attention mechanisms. A Pyramid Pooling Module (PPM) is integrated to fuse multi-scale contextual information, improving the detection accuracy of small targets such as microdeletions. Furthermore, the shortcut connections in residual blocks are optimized to reduce feature loss. To mitigate the limitation of insufficient annotated samples, transfer learning is employed, combined with a focal loss function to enhance classification performance under class-imbalanced conditions. Experiments conducted on a clinical dataset of 12,000 FISH images demonstrate that the proposed model achieves an overall classification accuracy of 92.4%, representing a 9.9% improvement over the original ResNet50. The recall rate for complex categories (e.g., translocation and fusion) exceeds 90.7%, with an inference time of 22.3 ms per sample, meeting the real-time requirements of clinical diagnosis. These results provide an efficient and practical solution for the automated intelligent interpretation of FISH images, offering significant potential for precision-assisted diagnosis of tumors and genetic disorders.