论文标题
用卷积神经网络检测有丝分裂的MIDOG 2022挑战
Detecting Mitoses with a Convolutional Neural Network for MIDOG 2022 Challenge
论文作者
论文摘要
这项工作提出了一种有丝分裂检测方法，只有一个香草卷积神经网络（CNN）。我们的方法由两个步骤组成：给定图像，我们首先使用滑动窗口技术应用CNN来提取具有有丝线的斑块。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。为了提高高域差异病理图像的模型性能，我们使用数据增强管道训练CNN，耐噪声的损失，与未标记的图像应对，以及多轮的主动学习策略。在MIDOG 2022挑战中，我们的方法具有有效的B3 CNN模型，在初步测试阶段的总F1得分为0.7323，在最终测试阶段达到0.6847（任务1）。我们的方法阐明了类激活图对病理图像中对象检测的更广泛适用性。
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.
