Abidoye Itunuoluwa, Ikeji Frances, Coupland Charlie A, Calaminus Simon D J, Sander Nick, Sousa Eva
Centre of Excellence for Data Science, Artificial Intelligence and Modelling, University of Hull, Hull HU6 7RX, UK.
Biomedical Institute for Multimorbidity, Centre for Biomedicine, Hull York Medical School, University of Hull, Hull HU6 7RX, UK.
J Imaging. 2025 Jun 4;11(6):183. doi: 10.3390/jimaging11060183.
Platelets play a crucial role in diagnosing and detecting various diseases, influencing the progression of conditions and guiding treatment options. Accurate identification and classification of platelets are essential for these purposes. The present study aims to create a synthetic database of platelet images using Generative Adversarial Networks (GANs) and validate its effectiveness by comparing it with datasets of increasing sizes generated through traditional augmentation techniques. Starting from an initial dataset of 71 platelet images, the dataset was expanded to 141 images (Level 1) using random oversampling and basic transformations and further to 1463 images (Level 2) through extensive augmentation (rotation, shear, zoom). Additionally, a synthetic dataset of 300 images was generated using a Wasserstein GAN with Gradient Penalty (WGAN-GP). Eight pre-trained deep learning models (DenseNet121, DenseNet169, DenseNet201, VGG16, VGG19, InceptionV3, InceptionResNetV2, and AlexNet) and two custom CNNs were evaluated across these datasets. Performance was measured using accuracy, precision, recall, and F1-score. On the extensively augmented dataset (Level 2), InceptionV3 and InceptionResNetV2 reached 99% accuracy and 99% precision/recall/F1-score, while DenseNet201 closely followed, with 98% accuracy, precision, recall and F1-score. GAN-augmented data further improved DenseNet's performance, demonstrating the potential of GAN-generated images in enhancing platelet classification, especially where data are limited. These findings highlight the benefits of combining traditional and GAN-based augmentation techniques to improve classification performance in medical imaging tasks.
血小板在各种疾病的诊断和检测中起着至关重要的作用，影响病情的发展并指导治疗方案的选择。准确识别和分类血小板对于这些目的至关重要。本研究旨在使用生成对抗网络（GAN）创建一个血小板图像合成数据库，并通过将其与通过传统增强技术生成的尺寸不断增加的数据集进行比较来验证其有效性。从71张血小板图像的初始数据集开始，使用随机过采样和基本变换将数据集扩展到141张图像（第1级），并通过广泛增强（旋转、剪切、缩放）进一步扩展到1463张图像（第2级）。此外，使用带有梯度惩罚的 Wasserstein GAN（WGAN-GP）生成了一个包含300张图像的合成数据集。在这些数据集上评估了八个预训练的深度学习模型（DenseNet121、DenseNet169、DenseNet201、VGG16、VGG19、InceptionV3、InceptionResNetV2和AlexNet）以及两个自定义卷积神经网络。使用准确率、精确率、召回率和F1分数来衡量性能。在广泛增强的数据集（第2级）上，InceptionV3和InceptionResNetV2的准确率达到99%，精确率/召回率/F1分数达到99%，而DenseNet201紧随其后，准确率、精确率、召回率和F1分数均为98%。GAN增强的数据进一步提高了DenseNet的性能，证明了GAN生成的图像在增强血小板分类方面的潜力，特别是在数据有限的情况下。这些发现突出了结合传统和基于GAN的增强技术以提高医学成像任务中分类性能的好处。
