Quantization-based deep diversified ensemble for medical image segmentation

Recent advancements in fully convolutional networks (FCNs) have significantly improved medical image segmentation. Ensemble methods are often used to further enhance performance, with diversity among learners being a critical factor. However, many current approaches focus on diversifying training samples or predictions while overlooking the diversity of internal multi-scale features. This oversight can lead to high correlations among features across different learners, limiting overall effectiveness. Additionally, traditional quantization methods aim to minimize accuracy loss by maintaining a rigid quantization process. This rigidity can eliminate the randomness introduced by quantization, further reducing ensemble diversity and effectiveness. In this paper, we propose a novel approach called Quantization-based Deep Diversified Ensemble (QDD-Ens) for medical image segmentation. Our method enhances the diversity of internal features among ensemble learners through two mechanisms: deep diversified loss, which focuses on feature diversity rather than segmentation accuracy, and deep diversified quantization, which preserves beneficial randomness in quantization process. Furthermore, QDD-Ens facilitates a deeper form of ensemble learning by employing a meta-learner to integrate diversified features at multiple resolution levels from various base learners, which are diversified by two above diversify enhancement mechanisms. Extensive experiments on five public medical image segmentation datasets show that our method significantly improves segmentation accuracy and outperforms existing ensemble techniques. The source code is publicly available to support future research. ( https://github.com/JerRuy/QDD-Ens ) • We provide valuable insights into the importance of the diversity of the internal feature from ensemble learners. • We propose a deep diversified loss to enhance diversity by directly diversifying the internal features from different base learners. • We propose a deep diversified quantization to enhance diversity that selectively preserves the randomness brought about by quantization. • We propose a deep ensemble, in which a meta learner is used to fuse the internal diversified features from various base learners. • Comprehensive experimental results across five popular datasets and various networks demonstrate the superiority of our method over existing approaches.