Li Tianfu, Zou Yan, Bai Pengfei, Li Shixiao, Wang Huawei, Chen Xingliang, Meng Zhanao, Kang Zhuang, Zhou Guofu
Guangdong Provincial Key Laboratory of Optical Information Materials and Technology & Institute of Electronic Paper Displays, South China Academy of Advanced Optoelectronics, South China Normal University, Guangzhou 510006, China.
Department of Radiology, The Third Affiliated Hospital of Sun Yat-Sen University, Guangzhou, Guangdong, China.
Comput Methods Programs Biomed. 2021 Jun;204:106051. doi: 10.1016/j.cmpb.2021.106051. Epub 2021 Mar 12.
Cerebral microbleeds (CMBs) are cerebral small vascular diseases and are often used to diagnose symptoms such as stroke and dementia. Manual detection of cerebral microbleeds is a time-consuming and error-prone task, so the application of microbleed detection algorithms based on deep learning is of great significance. This study presents the feature enhancement technology applying to improve the performances of detecting CMBs. The primary purpose of the feature enhancement is emphasizing the meaningful features, leading deep learning network easier and correctly to optimize.
In this study, we applied feature enhancement in detecting CMBs from brain MRI images. Feature enhancement enhanced specific intervals and suppressed the useless intervals of the feature map. This method was applied in SSD-512 and SSD-300 algorithm, using VGG architecture pre-trained in the ImageNet dataset.
The proposed method was applied in SSD-512. Moreover, the model was trained and tested on the sequence of SWAN images of brain MRI images. The results of the experiment demonstrate that our method effectively improves the detection performance of the SSD network in detecting CMBs. We train SSD-512 120000 iterations and test results on the test datasets, by applying the feature enhancement layer, improving the precision with 3.3% and the mAP of 2.3%. In the same way, we trained SSD-300, improving the mAP of 2.0%. 2.8% and 7.4% precision are improved by applying feature enhancement layer In ResNet-34 and MobileNet.
The proposed method achieved more effective performance, demonstrated that feature enhancement can be a helpful algorithm to enhance the deep learning model.
脑微出血（CMBs）是脑小血管疾病，常用于诊断中风和痴呆等症状。手动检测脑微出血是一项耗时且容易出错的任务，因此基于深度学习的微出血检测算法的应用具有重要意义。本研究提出了用于提高脑微出血检测性能的特征增强技术。特征增强的主要目的是强调有意义的特征，使深度学习网络更容易且正确地进行优化。
在本研究中，我们将特征增强应用于从脑部MRI图像中检测脑微出血。特征增强增强了特征图的特定区间并抑制了无用区间。该方法应用于SSD-512和SSD-300算法，使用在ImageNet数据集中预训练的VGG架构。
所提出的方法应用于SSD-512。此外，该模型在脑部MRI图像的SWAN图像序列上进行训练和测试。实验结果表明，我们的方法有效地提高了SSD网络在检测脑微出血方面的检测性能。通过应用特征增强层，我们在测试数据集上对SSD-512进行了120000次迭代训练和测试，精度提高了3.3%，平均精度均值（mAP）提高了2.3%。同样地，我们训练了SSD-300，mAP提高了2.0%。在ResNet-34和MobileNet中应用特征增强层，精度分别提高了2.8%和7.4%。
所提出的方法取得了更有效的性能，表明特征增强可以成为增强深度学习模型的有用算法。
