Detecting Mitoses with a Convolutional Neural Network for MIDOG 2022 Challenge
Detecting Mitoses with a Convolutional Neural Network for MIDOG 2022 Challenge
复制标题
DOI：
10.48550/arxiv.2208.12437
复制
发表时间：
2022-08
期刊：
影响因子：
--
通讯作者：
H. Gu;Mohammad Haeri;Shuo Ni;Christopher Kazu Williams;N. Zarrin-Khameh;S. Magaki;Xiangdong Chen
中科院分区：
文献类型：
--
作者：
H. Gu;Mohammad Haeri;Shuo Ni;Christopher Kazu Williams;N. Zarrin-Khameh;S. Magaki;Xiangdong Chen
本文提出了一种仅使用一个vanilla卷积神经网络（CNN）的有丝分裂检测方法。我们的方法包括两个步骤：给定一张图像，我们首先使用滑动窗口技术应用CNN来提取有丝分裂的斑块；然后，我们计算每个提取的斑块的类激活图，以获得有丝分裂的精确位置。为了提高模型在高域方差病理图像上的性能，我们使用数据增强管道、处理未标记图像的耐噪声损失和多轮主动学习策略来训练CNN。在MIDOG 2022挑战中，我们的方法使用了一个EfficientNet-b3 CNN模型，在初步测试阶段获得了0.7323的F1总分，在最终测试阶段（任务1）获得了0.6847的F1总分。我们的方法揭示了类激活图在病理图像中对象检测的更广泛的适用性。
This work presents a mitosis detection method with only one vanilla Convolutional Neural Network (CNN). Our method consists of two steps: given an image, we first apply a CNN using a sliding window technique to extract patches that have mitoses; we then calculate each extracted patch's class activation map to obtain the mitosis's precise location. To increase the model performance on high-domain-variance pathology images, we train the CNN with a data augmentation pipeline, a noise-tolerant loss that copes with unlabeled images, and a multi-rounded active learning strategy. In the MIDOG 2022 challenge, our approach, with an EfficientNet-b3 CNN model, achieved an overall F1 score of 0.7323 in the preliminary test phase, and 0.6847 in the final test phase (task 1). Our approach sheds light on the broader applicability of class activation maps for object detections in pathology images.