Podlasek Jeremi, Heesch Mateusz, Podlasek Robert, Kilisiński Wojciech, Filip Rafał
Department of Technology, moretho Ltd., Manchester, United Kingdom.
Department of Robotics and Mechatronics, AGH University of Science and Technology, Kraków, Poland.
Endosc Int Open. 2021 May;9(5):E741-E748. doi: 10.1055/a-1388-6735. Epub 2021 Apr 22.
Several computer-assisted polyp detection systems have been proposed, but they have various limitations, from utilizing outdated neural network architectures to a requirement for multi-graphics processing unit (GPU) processing, to validating on small or non-robust datasets. To address these problems, we developed a system based on a state-of-the-art convolutional neural network architecture able to detect polyps in real time on a single GPU and tested on both public datasets and full clinical examination recordings. The study comprised 165 colonoscopy procedure recordings and 2678 still photos gathered retrospectively. The system was trained on 81,962 polyp frames in total and then tested on footage from 42 colonoscopies and CVC-ClinicDB, CVC-ColonDB, Hyper-Kvasir, and ETIS-Larib public datasets. Clinical videos were evaluated for polyp detection and false-positive rates whereas the public datasets were assessed for F1 score. The system was tested for runtime performance on a wide array of hardware. The performance on public datasets varied from an F1 score of 0.727 to 0.942. On full examination videos, it detected 94 % of the polyps found by the endoscopist with a 3 % false-positive rate and identified additional polyps that were missed during initial video assessment. The system's runtime fits within the real-time constraints on all but one of the hardware configurations. We have created a polyp detection system with a post-processing pipeline that works in real time on a wide array of hardware. The system does not require extensive computational power, which could help broaden the adaptation of new commercially available systems.
已经提出了几种计算机辅助息肉检测系统，但它们存在各种局限性，从使用过时的神经网络架构到需要多图形处理单元（GPU）处理，再到在小的或不可靠的数据集上进行验证。为了解决这些问题，我们开发了一种基于先进卷积神经网络架构的系统，该系统能够在单个GPU上实时检测息肉，并在公共数据集和完整的临床检查记录上进行了测试。 该研究回顾性收集了165份结肠镜检查程序记录和2678张静态照片。该系统总共在81962个息肉帧上进行了训练，然后在来自42次结肠镜检查的视频以及CVC-ClinicDB、CVC-ColonDB、Hyper-Kvasir和ETIS-Larib公共数据集上进行了测试。对临床视频进行息肉检测和假阳性率评估，而对公共数据集进行F1分数评估。该系统在各种硬件上测试了运行时性能。 该系统在公共数据集上的性能F1分数从0.727到0.942不等。在完整的检查视频上，它检测到了内镜医师发现的94%的息肉，假阳性率为3%，并识别出了在初始视频评估中遗漏的其他息肉。除了一种硬件配置外，该系统的运行时符合实时限制。 我们创建了一个带有后处理管道的息肉检测系统，该系统可以在各种硬件上实时运行。该系统不需要大量的计算能力，这有助于扩大新的商用系统的适应性。
