Domain adaptation strategies for cancer-independent detection of lymph node metastases
This work addresses the problem of efficient cancer metastasis detection for medical applications, but it is incremental as it builds on existing domain adaptation methods.
The paper tackled the challenge of detecting lymph node metastases across multiple cancer types without needing large annotated datasets for each, by leveraging existing high-quality datasets through domain adaptation strategies. Results showed state-of-the-art performance on colon and head-and-neck cancer metastasis detection, with significant performance boosts and effective mitigation of catastrophic forgetting.
Recently, large, high-quality public datasets have led to the development of convolutional neural networks that can detect lymph node metastases of breast cancer at the level of expert pathologists. Many cancers, regardless of the site of origin, can metastasize to lymph nodes. However, collecting and annotating high-volume, high-quality datasets for every cancer type is challenging. In this paper we investigate how to leverage existing high-quality datasets most efficiently in multi-task settings for closely related tasks. Specifically, we will explore different training and domain adaptation strategies, including prevention of catastrophic forgetting, for colon and head-and-neck cancer metastasis detection in lymph nodes. Our results show state-of-the-art performance on both cancer metastasis detection tasks. Furthermore, we show the effectiveness of repeated adaptation of networks from one cancer type to another to obtain multi-task metastasis detection networks. Last, we show that leveraging existing high-quality datasets can significantly boost performance on new target tasks and that catastrophic forgetting can be effectively mitigated using regularization.