Rethinking Polyp Segmentation from An Out-ofdistribution Perspective  

作　　者：Ge-Peng Ji Jing Zhang Dylan Campbell Huan Xiong Nick Barnes 

机构地区：[1]Australian National University,Canberra 8105,Australia [2]Mohamed bin Zayed University of Artificial Intelligence,Abu Dhabi 999041,UAE

出　　处：《Machine Intelligence Research》2024年第4期631-639,共9页机器智能研究（英文版）

摘　　要：Unlike existing fully-supervised approaches,we rethink colorectal polyp segmentation from an out-of-distribution perspective with a simple but effective self-supervised learning approach.We leverage the ability of masked autoencoders-self-supervised vision transformers trained on a reconstruction task-to learn in-distribution representations,here,the distribution of healthy colon images.We then perform out-of-distribution reconstruction and inference,with feature space standardisation to align the latent distribution of the diverse abnormal samples with the statistics of the healthy samples.We generate per-pixel anomaly scores for each image by calculating the difference between the input and reconstructed images and use this signal for out-of-distribution(i.e.,polyp)segmentation.Experimental results on six benchmarks show that our model has excellent segmentation performance and generalises across datasets.Our code is publicly available at https://github.com/GewelsJI/Polyp-OOD.

关 键 词：Polyp segmentation anomaly segmentation out-of-distribution segmentation masked autoencoder abdomen. 

分 类 号：R318[医药卫生—生物医学工程] TP391.41[医药卫生—基础医学]