JZUS - Journal of Zhejiang University SCIENCE

Frontiers of Information Technology & Electronic Engineering 2023 Vol.24 No.9 P.1332-1348

http://doi.org/10.1631/FITEE.2200299

Interactive medical image segmentation with self-adaptive confidence calibration

Author(s): Chuyun SHEN, Wenhao LI, Qisen XU, Bin HU, Bo JIN, Haibin CAI, Fengping ZHU, Yuxin LI, Xiangfeng WANG
Affiliation(s): School of Computer Science and Technology, East China Normal University, Shanghai 200062, China; more
Corresponding email(s): cyshen@stu.ecnu.edu.cn, 52194501026@stu.ecnu.edu.cn, xfwang@cs.ecnu.edu.cn
Key Words: Medical image segmentation, Interactive segmentation, Multi-agent reinforcement learning, Confidence learning, Semi-supervised learning

Share this article to： More <<< Previous Article \|Next Article >>>

Abstract: Interactive medical image segmentation based on human-in-the-loop machine learning is a novel paradigm that draws on human expert knowledge to assist medical image segmentation. However, existing methods often fall into what we call interactive misunderstanding, the essence of which is the dilemma in trading off short- and long-term interaction information. To better use the interaction information at various timescales, we propose an interactive segmentation framework, called interactive medical image segmentation with self-adaptive Confidence CAlibration (MECCA), which combines action-based confidence learning and multi-agent reinforcement learning. A novel confidence network is learned by predicting the alignment level of the action with short-term interaction information. A confidence-based reward-shaping mechanism is then proposed to explicitly incorporate confidence in the policy gradient calculation, thus directly correcting the model’s interactive misunderstanding. MECCA also enables user-friendly interactions by reducing the interaction intensity and difficulty via label generation and interaction guidance, respectively. Numerical experiments on different segmentation tasks show that MECCA can significantly improve short- and long-term interaction information utilization efficiency with remarkably fewer labeled samples. The demo video is available at https://bit.ly/mecca-demo-video.

基于自适应置信度校准的交互式医疗图像分割框架

沈楚云¹，李文浩¹，徐琪森¹，胡斌²，金博¹，蔡海滨³，朱凤平²，李郁欣²，王祥丰¹
¹华东师范大学计算机科学与技术学院，中国上海市，200062
²复旦大学附属华山医院，中国上海市，200040
³华东师范大学软件工程学院，中国上海市，200062
摘要：基于人机交互的医疗图像分割方法是一种新的范式，其通过引入专家交互信息来指导算法完成图像分割任务。然而，现有医疗图像分割模型往往容易产生"交互误解"，即无法合理权衡短期和长期交互信息的重要性。为更好地利用不同时间尺度上的交互信息，本文提出一种基于自适应置信度校准的交互式医疗图像分割框架MECCA，其结合了基于分割决策的置信度学习技术和多智能体强化学习技术，并通过预测分割决策与短期交互信息的对齐水平来学习一个新颖的置信度网络。随后，提出一种基于置信度的奖励塑造机制，在策略梯度计算中引入置信度，从而直接纠正模型产生的交互误解。MECCA还通过标签生成和交互指导来降低交互强度和难度，从而实现用户友好交互。实验结果表明，MECCA在不同分割任务中可以显著提高短期和长期交互信息的利用效率，且仅需较少的标注样本。演示视频可通过https://bit.ly/mecca-demo-video访问。

关键词：医疗图像分割；交互式分割；多智能体强化学习；置信度学习；半监督学习

Reference

[1]Abel D, Jinnai Y, Guo SY, et al., 2018. Policy and value transfer in lifelong reinforcement learning. Proc 35^th Int Conf on Machine Learning, p.20-29.

[2]Achanta R, Shaji A, Smith K, et al., 2012. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Patt Anal Mach Intell, 34(11):2274-2282.

[3]Acuna D, Ling H, Kar A, et al., 2018. Efficient interactive annotation of segmentation datasets with Polygon-RNN++. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.859-868.

[4]Aljabri M, AlAmir M, AlGhamdi M, et al., 2022. Towards a better understanding of annotation tools for medical imaging: a survey. Multim Tools Appl, 81(18):25877-25911.

[5]Bredell G, Tanner C, Konukoglu E, 2018. Iterative interaction training for segmentation editing networks. Proc 9^th Int Workshop on Machine Learning in Medical Imaging, p.363-370.

[6]Castrejón L, Kundu K, Urtasun R, et al., 2017. Annotating object instances with a polygon-RNN. IEEE Conf on Computer Vision and Pattern Recognition, p.4485-4493.

[7]DeVries T, Taylor GW, 2018a. Learning confidence for out-of-distribution detection in neural networks.

[8]DeVries T, Taylor GW, 2018b. Leveraging uncertainty estimates for predicting segmentation quality.

[9]Feng RW, Zheng XS, Gao TX, et al., 2021. Interactive few-shot learning: limited supervision, better medical image segmentation. IEEE Trans Med Imag, 40(10):2575-2588.

[10]Furuta R, Inoue N, Yamasaki T, 2020. PixelRL: fully convolutional network with reinforcement learning for image processing. IEEE Trans Multim, 22(7):1704-1719.

[11]Glorot X, Bengio Y, 2010. Understanding the difficulty of training deep feedforward neural networks. Proc 13^th Int Conf on Artificial Intelligence and Statistics, p.249-256.

[12]Hung W, Tsai Y, Liou Y, et al., 2018. Adversarial learning for semi-supervised semantic segmentation. Proc British Machine Vision Conf, p.65.

[13]Jungo A, Reyes M, 2019. Assessing reliability and challenges of uncertainty estimations for medical image segmentation. Proc 22^nd Int Conf on Medical Image Computing and Computer-Assisted Intervention, p.48-56.

[14]Kendall A, Gal Y, 2017. What uncertainties do we need in bayesian deep learning for computer vision? Proc 3^rd Int Conf on Neural Information Processing System, p.5580-5590.

[15]Kingma DP, Ba J, 2015. Adam: a method for stochastic optimization. Proc 3^rd Int Conf on Learning Representations.

[16]Lee KM, Song G, 2018. SeedNet: automatic seed generation with deep reinforcement learning for robust interactive segmentation. IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.1760-1768.

[17]Li L, Zimmer VA, Schnabel JA, et al., 2021. AtrialGeneral: domain generalization for left atrial segmentation of multi-center LGE MRIs. Proc 24^th Int Conf on Medical Image Computing and Computer-Assisted Intervention, p.557-566.

[18]Liao X, Li WH, Xu QS, et al., 2020. Iteratively-refined interactive 3D medical image segmentation with multi-agent reinforcement learning. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.9394-9402.

[19]Lin D, Dai JF, Jia JY, et al., 2016. ScribbleSup: scribble-supervised convolutional networks for semantic segmentation. IEEE Conf on Computer Vision and Pattern Recognition, p.3159-3167.

[20]Lin TY, Goyal P, Girshick R, et al., 2017. Focal loss for dense object detection. Proc IEEE Int Conf on Computer Vision, p.2999-3007.

[21]Ma CF, Xu QS, Wang XF, et al., 2021. Boundary-aware supervoxel-level iteratively refined interactive 3D image segmentation with multi-agent reinforcement learning. IEEE Trans Med Imag, 40(10):2563-2574.

[22]Menze BH, Jakab A, Bauer S, et al., 2015. The multimodal brain tumor image segmentation benchmark (BRATS). IEEE Trans Med Imag, 34(10):1993-2024.

[23]Mnih V, Badia AP, Mirza M, et al., 2016. Asynchronous methods for deep reinforcement learning. Proc 33^rd Int Conf on Machine Learning, p.1928-1937.

[24]Moeskops P, Veta M, Lafarge MW, et al., 2017. Adversarial training and dilated convolutions for brain MRI segmentation. Proc 3^rd Int Workshop on Deep Learning in Medical Image Analysis and 7^th Int Workshop on Multimodal Learning for Clinical Decision Support, p.56-64.

[25]Nie D, Wang L, Xiang L, et al., 2019. Difficulty-aware attention network with confidence learning for medical image segmentation. Proc 33^rd AAAI Conf on Artificial Intelligence, 31^st Innovative Applications of Artificial Intelligence Conf, and 9^th AAAI Symp on Educational Advances in Artificial Intelligence, p.1085-1092.

[26]Open AI, 2022. ChatGPT: Optimizing Language Models for Dialogue. https://openai.casa/blog/chatgpt/ [Accessed on July 10, 2022].

[27]Paszke A, Gross S, Massa F, et al., 2019. PyTorch: an imperative style, high-performance deep learning library. Proc 33^rd Int Conf on Neural Information Processing Systems, p.8026-8037.

[28]Prabhu A, Torr PHS, Dokania PK, 2020. GDumb: a simple approach that questions our progress in continual learning. Proc 16^th European Conf on Computer Vision, p.524-540.

[29]Rajchl M, Lee MCH, Oktay O, et al., 2017. DeepCut: object segmentation from bounding box annotations using convolutional neural networks. IEEE Trans Med Imag, 36(2):674-683.

[30]Rebuffi SA, Kolesnikov A, Sperl G, 2017. iCaRL: incremental classifier and representation learning. IEEE Conf on Computer Vision and Pattern Recognition, p.5533-5542.

[31]Robinson R, Oktay O, Bai WJ, et al., 2018. Real-time prediction of segmentation quality. Proc 21^st Int Conf on Medical Image Computing and Computer-Assisted Intervention, p.578-585.

[32]Ronneberger O, Fischer P, Brox T, 2015. U-Net: convolutional networks for biomedical image segmentation. Proc 18^th Int Conf on Medical Image Computing and Computer-Assisted Intervention, p.234-241.

[33]Shrivastava A, Gupta A, Girshick R, 2016. Training region-based object detectors with online hard example mining. IEEE Conf on Computer Vision and Pattern Recognition, p.761-769.

[34]Simpson AL, Antonelli M, Bakas S, et al., 2019. A large annotated medical image dataset for the development and evaluation of segmentation algorithms.

[35]Wang GT, Li WQ, Zuluaga MA, et al., 2018. Interactive medical image segmentation using deep learning with image-specific fine tuning. IEEE Trans Med Imag, 37(7):1562-1573.

[36]Wang GT, Zuluaga MA, Li WQ, et al., 2019. DeepIGeoS: a deep interactive geodesic framework for medical image segmentation. IEEE Trans Patt Anal Mach Intell, 41(7):1559-1572.

[37]Xie AN, Harrison J, Finn C, 2020. Deep reinforcement learning amidst lifelong non-stationarity.

[38]Xu N, Price B, Cohen S, et al., 2016. Deep interactive object selection. IEEE Conf on Computer Vision and Pattern Recognition, p.373-381.

[39]Ye QH, Gao Y, Ding WP, et al., 2022. Robust weakly supervised learning for COVID-19 recognition using multi-center CT images. Appl Soft Comput, 116:108291.

[40]Yu LQ, Wang SJ, Li XM, et al., 2019. Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation. Proc 22^nd Int Conf on Medical Image Computing and Computer-Assisted Intervention, p.605-613.

[41]Zhang KQ, Yang ZR, Basar T, 2021. Decentralized multi-agent reinforcement learning with networked agents: recent advances. Front Inform Technol Electron Eng, 22(6):802-814.

[42]Zhang SY, Liew JH, Wei YC, et al., 2020. Interactive object segmentation with inside-outside guidance. Proc IEEE/CVF Conf on Computer Vision and Pattern Recognition, p.12231-12241.

[43]Zhuang XH, Shen J, 2016. Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI. Med Image Anal, 31:77-87.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Similar articles

- Go to

基于自适应置信度校准的交互式医疗图像分割框架

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference