MRDFF: A deep forest based framework for CT whole heart segmentation

• Published in: Methods (San Diego, Calif.) Calif.), 2022-12, Vol.208, p.48-58
• Main Authors: Xu, Fei, Lin, Lingli, Li, Zihan, Hong, Qingqi, Liu, Kunhong, Wu, Qingqiang, Li, Qingde, Zheng, Yinhuan, Tian, Jie
• Format: Article
• Language: English
• Subjects: Cardiac CT image segmentation; Deep forest; Medical image segmentation; Whole heart segmentation
• ISSN: 1046-2023; 1095-9130
• DOI: 10.1016/j.ymeth.2022.10.005

•Unlike common neural network models, we propose a new whole heart segmentation framework based on improved Deep Forest, which is interpretable. It adopts the idea of ensemble learning and combines the methods of bagging and boosting.•We employ hybrid feature fusion, multi-scale fusion and multi-resolution fusion to increase model diversity and segmentation accuracy, and further compare different feature’s importance.•Compared to the neural network models, our model can complete training in a shorter time and is more efficient. Automatic whole heart segmentation plays an important role in the treatment and research of cardiovascular diseases. In this paper, we propose an improved Deep Forest framework, named Multi-Resolution Deep Forest Framework (MRDFF), which accomplishes whole heart segmentation in two stages. We extract the heart region by binary classification in the first stage, thus avoiding the class imbalance problem caused by too much background. The results of the first stage are then subdivided in the second stage to obtain accurate cardiac substructures. In addition, we also propose hybrid feature fusion, multi-resolution fusion and multi-scale fusion to further improve the segmentation accuracy. Experiments on the public dataset MM-WHS show that our model can achieve comparable accuracy in about half the training time of neural network models.