# Adaptive Logit Fusion for Mitigating Class Imbalance in Multi-Category Sperm Morphology Assessment

## TL;DR

This paper introduces a deep learning method to classify sperm cell morphology into 18 categories, using an ensemble approach to handle class imbalance and improve classification accuracy.

## Contribution

The novel approach uses adaptive logit fusion in an ensemble of CNNs to optimize performance metrics under class imbalance in sperm morphology assessment.

## Key findings

- The ensemble model achieved an overall accuracy of 70.94%, outperforming individual models.
- Structurally distinct abnormalities like PinHead and DoubleTail were classified with high accuracy.
- Less visually distinctive defects showed lower classification performance.

## Abstract

Sperm morphology is one of the most critical indicators of male fertility. This paper presents a deep learning-based approach to classify sperm cells into 18 morphological classes, including one normal and 17 abnormal types. Two state-of-the-art convolutional neural networks, EfficientNetV2-S and ResNet50V2, are employed and fine-tuned using a class-weighted loss function together with extensive data augmentation to improve generalization under class imbalance. Automatic mixed precision training is adopted to reduce memory consumption and accelerate the training process. An ensemble strategy is subsequently constructed by linearly fusing the logits of both architectures, where the fusion weight is optimized to maximize recall, precision, and overall F1-score. Experimental results show that the proposed ensemble achieves an overall accuracy of 70.94%, consistently outperforming the individual models. Sperm cells with pronounced structural abnormalities, such as PinHead and DoubleTail, are classified with high accuracy, whereas less visually distinctive defects result in comparatively lower performance. These findings demonstrate the potential of CNN-based ensemble models to provide consistent and reliable automated sperm morphology classification.