Domain Adversarial RetinaNet as a Reference Algorithm for the MItosis DOmain Generalization Challenge

Multi tasks RetinaNet for mitosis detection

The account of mitotic cells is a key feature in tumor diagnosis. However, due to the variability of mitotic cell morphology, it is a highly challenging task to detect mitotic cells in tumor tissues. At the same time, although advanced deep learning method have achieved great success in cell detection, the performance is often unsatisfactory when tested data from another domain (i.e. the different tumor types and different scanners). Therefore, it is necessary to develop algorithms for detecting mitotic cells with robustness in domain shifts scenarios. Our work further proposes a foreground de…

MitoDet: Simple and robust mitosis detection

Mitotic figure detection is a challenging task in digital pathology that has a direct impact on therapeutic decisions. While automated methods often achieve acceptable results under laboratory conditions, they frequently fail in the clinical deployment phase. This problem can be mainly attributed to a phenomenon called domain shift. An important source of a domain shift is introduced by different microscopes and their camera systems, which noticeably change the color representation of digitized images. In this method description we present our submitted algorithm for the Mitosis Domain General…

虚拟染色在乳腺组织学中的应用

Virtual staining for mitosis detection in Breast Histopathology

我们提出了一种基于生成对抗网络的虚拟染色方法，将乳腺癌组织的组织病理学图像从H&E染色映射到PHH3，反之亦然。我们使用由此产生的合成图像来构建卷积神经网络（CNN），用于自动检测有丝分裂像，这是一种用于常规乳腺癌诊断和分级的强预后生物标志物。我们提出了几种方案，其中用合成生成的组织病理学图像训练的CNN与用真实图像训练的相同基线模型表现相当，甚至更好。我们讨论了这个应用程序的潜力，以规模的训练样本的数量，而不需要手动注释。

Assessing domain adaptation techniques for mitosis detection in multi-scanner breast cancer histopathology images

Breast cancer is the most commonly diagnosed cancer worldwide, with over two million new cases each year. During diagnostic tumour grading, pathologists manually count the number of dividing cells (mitotic figures) in biopsy or tumour resection specimens. Since the process is subjective and time-consuming, data-driven artificial intelligence (AI) methods have been developed to automatically detect mitotic figures. However, these methods often generalise poorly, with performance reduced by variations in tissue types, staining protocols, or the scanners used to digitise whole-slide images. Domai…

领域对抗神经网络解决组织病理学图像的外观变化

Domain-adversarial neural networks to address the appearance variability of histopathology images

制备和扫描组织病理学载玻片包括几个步骤，每个步骤都有许多参数。这些参数在病理学实验室之间以及在同一实验室内可能随时间而变化，从而导致组织外观的显著变化，这阻碍了自动图像分析方法的推广。通常情况下，这是解决与ad-hoc方法，如染色标准化，旨在减少外观的变化。在本文中，我们提出了一个系统的解决方案的基础上领域对抗神经网络。我们假设从模型表示中删除域信息会导致更好的泛化。我们测试了我们的假设，在乳腺癌组织病理学图像中的有丝分裂检测的问题，并与其他两种方法进行了比较分析。我们表明，将颜色增强与领域对抗训练相结合是比标准方法更好的选择，可以提高深度学习方法的泛化能力。

评估用于X射线安全图像中威胁目标检测和分类的卷积神经网络的可转移性和对抗性辨别

Evaluating the Transferability and Adversarial Discrimination of Convolutional Neural Networks for Threat Object Detection and Classification within X-Ray Security Imagery

X射线图像安全检查对于维护运输安全，防止各种威胁或违禁物品至关重要。特别感兴趣的是在复杂和杂乱的X射线安全图像中自动检测和分类武器，如枪支和刀具。在这里，我们通过探索各种端到端目标检测卷积神经网络（CNN）架构来解决这个问题。我们评估了几种领先的变体，包括Faster R-CNN、Mask R-CNN和RetinaNet架构，以探索这些模型在具有不同成像几何形状、图像分辨率和材料颜色配置文件的不同X射线扫描仪之间的可转移性。虽然有限的可用性的X射线威胁图像可能会构成挑战，我们采用了迁移学习的方法来评估这种扫描仪间的泛化是否可能存在多类检测问题。总的来说，我们使用具有ResNet $_{101}$分类网络的Faster R-CNN架构实现了最大的检测性能，从不同的X射线成像源获得了三类和两类项目的平均平均精度（mAP）为0.88和0.86。我们的研究结果表现出显着程度的概括性，在跨扫描仪的性能（mAP：0.87，枪支检测：0.94 AP）。此外，我们使用专门生成的用于枪支检测的对抗性数据集来检查这种网络的固有对抗性判别能力-具有可变的低误报，低至5%，这表明了X射线安全图像中这种威胁检测的挑战和前景。