School of Electrical Engineering and Informatics, Institut Teknologi Bandung, Bandung, 40132, Indonesia; Computer Engineering and Informatics Department, Politeknik Negeri Bandung, Kabupaten Bandung Barat, 40559, Indonesia.
Department of Information and Communication Engineering, The University of Tokyo, Tokyo, 113-8656, Japan.
Comput Methods Programs Biomed. 2021 Sep;209:106302. doi: 10.1016/j.cmpb.2021.106302. Epub 2021 Jul 27.
Object detection is a primary research interest in computer vision. Sperm-cell detection in a densely populated bull semen microscopic observation video presents challenges that are more difficult than those presented by other general object-detection cases. These challenges include partial occlusion, vast number of objects in a single video frame, tiny size of the object, artifacts, low contrast, low video resolution, and blurry objects because of the rapid movement of the sperm cells. This study proposes a deep neural network architecture, called DeepSperm, that solves the aforementioned problems and is more accurate and faster than state-of-the-art architectures.
In the proposed architecture, we use only one detection layer, which is specific for small object detection. For handling overfitting and increasing accuracy, we set a higher input network resolution, use a dropout layer, and perform data augmentation on saturation and exposure. Several hyper-parameters are tuned to achieve better performance. Mean average precision (mAP), confusion matrix, precision, recall, and F1-score are used to measure accuracy. Frame per second (fps) is used to measure speed. We compare our proposed method with you only look once (YOLO) v3 and YOLOv4.
In our experiment, we achieve 94.11 mAP on the test dataset, F1-score of 0.93, and a processing speed of 51.9 fps. In comparison with YOLOv4, our proposed method is 2.18 x faster on testing, and 2.9 x faster on training with a small dataset, while achieving comparative detection accuracy. The weights file size was also reduced significantly, with one-twentieth that of YOLOv4. Moreover, it requires a 1.07 x less graphical processing unit (GPU) memory than YOLOv4.
This study proposes DeepSperm, which is a simple, effective, and efficient deep neural network architecture with its hyper-parameters and configuration to detect bull sperm cells robustly in real time. In our experiments, we surpass the state-of-the-art in terms of accuracy, speed, and resource needs.
目标检测是计算机视觉的主要研究兴趣之一。在密集的公牛精液显微镜观察视频中检测精子细胞比其他一般目标检测情况更具挑战性。这些挑战包括部分遮挡、单个视频帧中对象数量众多、对象尺寸微小、伪影、对比度低、视频分辨率低以及由于精子细胞快速运动导致的对象模糊。本研究提出了一种名为 DeepSperm 的深度神经网络架构，该架构解决了上述问题，并且比最先进的架构更准确和快速。
在提出的架构中，我们仅使用一个特定于小目标检测的检测层。为了处理过拟合并提高准确性，我们设置了更高的输入网络分辨率，使用了 dropout 层，并对饱和度和曝光度进行了数据增强。调整了几个超参数以获得更好的性能。平均精度均值（mAP）、混淆矩阵、精度、召回率和 F1 分数用于衡量准确性。帧率（fps）用于衡量速度。我们将我们提出的方法与只看一次（YOLO）v3 和 YOLOv4 进行了比较。
在我们的实验中，我们在测试数据集上达到了 94.11 的 mAP、0.93 的 F1 分数和 51.9 fps 的处理速度。与 YOLOv4 相比，我们提出的方法在测试时快 2.18 倍，在训练小数据集时快 2.9 倍，同时实现了相当的检测精度。权重文件大小也显著减小，仅为 YOLOv4 的二十分之一。此外，它需要比 YOLOv4 少 1.07 倍的图形处理单元（GPU）内存。
本研究提出了 DeepSperm，这是一种简单、有效和高效的深度神经网络架构，具有其超参数和配置，可以实时稳健地检测公牛精子细胞。在我们的实验中，我们在准确性、速度和资源需求方面超越了最先进的技术。
