Collaborative Unsupervised Domain Adaptation for Medical Image Diagnosis

By Yifan Zhang, Ying Wei, Qingyao Wu, Peilin Zhao, Shuaicheng Niu, Junzhou Huang, Mingkui Tan. 2019

188 citations recorded by the source corpus.

Deep learning based medical image diagnosis has shown great potential in clinical medicine. However, it often suffers two major difficulties in real-world applications: 1) only limited labels are available for model training, due to expensive annotation costs over medical images; 2) labeled images may contain considerable label noise (e.g., mislabeling labels) due to diagnostic difficulties of diseases. To address these, we seek to exploit rich labeled data from relevant domains to help the learning in the target task via Unsupervised Domain Adaptation (UDA). Unlike most UDA methods that rely on clean labeled data or assume samples are equally transferable, we innovatively propose a Collaborative Unsupervised Domain Adaptation algorithm, which conducts transferability-aware adaptation and conquers label noise in a collaborative way. We theoretically analyze the generalization performance of the proposed method, and also empirically evaluate it on both medical and general images. Promising experimental results demonstrate the superiority and generalization of the proposed method.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Mingkui Tan
2. Jiashi Feng
3. Yifan Zhang
4. Shuaicheng Niu
5. Jian Liang
6. Chuang Gan
7. Shuicheng Yan
8. Dapeng Hu

In Computer Vision and Pattern Recognition

1. Jiashi Feng
2. Mingkui Tan
3. Shuicheng Yan
4. Chuang Gan
5. Yifan Zhang
6. Jian Liang
7. Luc Van Gool
8. Trevor Darrell

In Radiology, Nuclear Medicine and Imaging

1. Yifan Zhang
2. Mingkui Tan
3. Shuaicheng Niu
4. Jian Liang
5. Jiashi Feng
6. Yuanda Zhu
7. Shuicheng Yan
8. Chuang Gan

Citations in the corpus

• Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation (2022, background): “Step 6 [50,51,52,53,54,55,56,57,58,59] Flowers, Lamp Shade, Spoon, Candles, Clipboards Scissors, TV, Curtains, Fork, Soda”
• Closed-Loop Matters: Dual Regression Networks for Single Image Super-Resolution (2020, unknown): “44, 6] and many other applications [7, 50, 52, 11, 20].”
• Efficient Test-Time Model Adaptation without Forgetting (2022, methodology): “Conventional UDA tackles distribution shifts by jointly optimizing a source model on both labeled source data and unlabeled target data, such as devising a domain discriminator to learn domain-invariant features (Pei et al., 2018; Saito et al., 2018; Zhang et al., 2020b;a).”
• Unleashing the Power of Contrastive Self-Supervised Visual Models via Contrast-Regularized Fine-Tuning (2021, background): “The key challenge is the distribution discrepancies among domains, leading to poor performance of neural networks on the target domain [71, 74].”
• Advancing Medical Imaging Informatics by Deep Learning-Based Domain Adaptation (2020, background): “The data in these repositories are heterogeneous due to varying hospital processes (image acquisition platforms or data preparation protocols), different demographics of patient populations (ethnicity, gender, age), or different pathological conditions [5].”
• Transfer learning for medical image classification: a literature review (2022, methodology): “Furthermore, multiple kernel active learning [14] and collaborative unsupervised methods [15] have also been utilized for unsupervised TL.”
• Dense Regression Network for Video Grounding (2020, background): “Recently, great progress has been achieved in deep learning [48, 47, 2, 15, 13, 14, 19, 1, 51], which facilitates the development of video grounding.”
• Towards Stable Test-Time Adaptation in Dynamic Wild World (2023, background): “…mitigate distribution shifts, such as devising a domain discrimi-nator to align source and target domains at feature level (Pei et al., 2018; Saito et al., 2018; Zhang et al., 2020b;a) and aligning the prototypes of source and target domains through a contrastive learning manner (Lin et al., 2022).”
• Deep Long-Tailed Learning: A Survey (2021, background): “[80], [81], [82], [83], [84] and domain generalization [85], [86]), inconsistent class distributions (e.”