Less-supervised learning with knowledge distillation for sperm morphology analysis
| Autor: | Ali Nabipour, Mohammad Javad Shams Nejati, Yasaman Boreshban, Seyed Abolghasem Mirroshandel |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2024 |
| Předmět: | |
| Zdroj: | Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, Vol 12, Iss 1 (2024) |
| Druh dokumentu: | article |
| ISSN: | 21681163 2168-1171 2168-1163 |
| DOI: | 10.1080/21681163.2024.2347978 |
| Popis: | Sperm Morphology Analysis (SMA) is pivotal in diagnosing male infertility. However, manual analysis is subjective and time-intensive. Artificial intelligence presents automated alternatives, but hurdles like limited data and image quality constraints hinder its efficacy. These challenges impede Deep Learning (DL) models from grasping crucial sperm features. A solution enabling DL models to learn sample nuances, even with limited data, would be invaluable. This study proposes a Knowledge Distillation (KD) method to distinguish normal from abnormal sperm cells, leveraging the Modified Human Sperm Morphology Analysis dataset. Despite low-resolution, blurry images, our method yields relevant results. We exclusively utilize normal samples to train the model for anomaly detection, crucial in scenarios lacking abnormal data – a common issue in medical tasks. Our aim is to train an Anomaly Detection model using a dataset comprising unclear images and limited samples, without direct exposure to abnormal data. Our method achieves Receiver ROC/AUC scores of 70.4%, 87.6%, and 71.1% for head, vacuole, and acrosome, respectively, our method matches traditional DL model performance with less than 70% of the data. This less-supervised approach shows promise in advancing SMA despite data scarcity. Furthermore, KD enables model adaptability to edge devices in fertility clinics, requiring less processing power. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|