Vezakis Ioannis A, Lambrou George I, Matsopoulos George K
Biomedical Engineering Laboratory, School of Electrical & Computer Engineering, National Technical University of Athens, 9 Iroon Polytechniou St., 15780 Athens, Greece.
Choremeio Research Laboratory, First Department of Pediatrics, National and Kapodistrian University of Athens, Thivon & Levadeias 8, 11527 Athens, Greece.
Cancers (Basel). 2023 Apr 13;15(8):2290. doi: 10.3390/cancers15082290.
Osteosarcoma is the most common primary malignancy of the bone, being most prevalent in childhood and adolescence. Despite recent progress in diagnostic methods, histopathology remains the gold standard for disease staging and therapy decisions. Machine learning and deep learning methods have shown potential for evaluating and classifying histopathological cross-sections.
This study used publicly available images of osteosarcoma cross-sections to analyze and compare the performance of state-of-the-art deep neural networks for histopathological evaluation of osteosarcomas.
The classification performance did not necessarily improve when using larger networks on our dataset. In fact, the smallest network combined with the smallest image input size achieved the best overall performance. When trained using 5-fold cross-validation, the MobileNetV2 network achieved 91% overall accuracy.
The present study highlights the importance of careful selection of network and input image size. Our results indicate that a larger number of parameters is not always better, and the best results can be achieved on smaller and more efficient networks. The identification of an optimal network and training configuration could greatly improve the accuracy of osteosarcoma diagnoses and ultimately lead to better disease outcomes for patients.
骨肉瘤是最常见的原发性骨恶性肿瘤，在儿童和青少年中最为普遍。尽管近年来诊断方法取得了进展，但组织病理学仍然是疾病分期和治疗决策的金标准。机器学习和深度学习方法已显示出评估和分类组织病理学切片的潜力。
本研究使用公开可用的骨肉瘤切片图像，分析和比较用于骨肉瘤组织病理学评估的先进深度神经网络的性能。
在我们的数据集中使用更大的网络时，分类性能不一定会提高。事实上，最小的网络与最小的图像输入尺寸相结合，实现了最佳的整体性能。当使用五折交叉验证进行训练时，MobileNetV2网络的总体准确率达到91%。
本研究强调了仔细选择网络和输入图像尺寸的重要性。我们的结果表明，参数数量越多并不总是越好，在更小、更高效的网络上可以取得最佳结果。确定最佳网络和训练配置可以大大提高骨肉瘤诊断的准确性，并最终为患者带来更好的疾病治疗结果。
