Cancer Prevention Through Early Detection - First International Workshop, CaPTion 2022, Held in Conjunction with MICCAI 2022, Singapore, September 22, 2022, Proceedings
Cancer Prevention Through Early Detection - First International Workshop, CaPTion 2022, Held in Conjunction with MICCAI 2022, Singapore, September 22, 2022, Proceedings
复制标题
通过早期检测预防癌症 - 第一届国际研讨会，CapTion 2022，与 MICCAI 2022 联合举行，新加坡，2022 年 9 月 22 日，会议记录
DOI：
10.1007/978-3-031-17979-2_15
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Gayo I
中科院分区：
文献类型：
--
作者：
Gayo I
如果将术前磁共振（MR）图像中发现的疑似病变用作靶点，则在超声引导活检过程中，临床显著的前列腺癌有更好的机会被采样。然而，活检程序的诊断准确性受到操作者依赖的技能和目标采样经验的限制，这是一个顺序决策过程，涉及导航超声探头并为潜在的多个目标放置一系列采样针。这项工作旨在学习强化学习（RL）策略，该策略优化2D超声视图和活检针相对于引导模板的连续定位的动作，使得可以有效且充分地对MR目标进行采样。我们首先制定的任务作为一个马尔可夫决策过程（MDP），并构建一个环境，允许的目标行动进行虚拟的个人患者，根据他们的解剖结构和病变来自MR图像。因此，在每次活检程序之前，可以通过奖励MDP环境中的阳性采样来优化患者特定的策略。来自54名前列腺癌患者的实验结果表明，所提出的RL学习策略获得了93%的平均命中率（HR）和11 mm的平均癌症核心长度（CCL），这与人类设计的两种替代基线策略相比是有利的，而没有直接最大化这些临床相关指标的手工设计的奖励。也许更有趣的是，发现RL代理学习了适应病变大小的策略，其中针的传播优先于较小的病变。这种策略以前没有报道过，也没有在临床实践中普遍采用，但与直观设计的策略相比，这种策略具有总体上级靶向性能，实现了更高的HR（93% vs 76%）和测量的CCL（11.0 mm vs 9.8 mm）。
Clinically significant prostate cancer has a better chance to be sampled during ultrasound-guided biopsy procedures, if suspected lesions found in pre-operative magnetic resonance (MR) images are used as targets. However, the diagnostic accuracy of the biopsy procedure is limited by the operator-dependent skills and experience in sampling the targets, a sequential decision making process that involves navigating an ultrasound probe and placing a series of sampling needles for potentially multiple targets. This work aims to learn a reinforcement learning (RL) policy that optimises the actions of continuous positioning of 2D ultrasound views and biopsy needles with respect to a guiding template, such that the MR targets can be sampled efficiently and sufficiently. We first formulate the task as a Markov decision process (MDP) and construct an environment that allows the targeting actions to be performed virtually for individual patients, based on their anatomy and lesions derived from MR images. A patient-specific policy can thus be optimised, before each biopsy procedure, by rewarding positive sampling in the MDP environment. Experiment results from fifty four prostate cancer patients show that the proposed RL-learned policies obtained a mean hit rate (HR) of 93% and an average cancer core length (CCL) of 11 mm, which compared favourably to two alternative baseline strategies designed by humans, without hand-engineered rewards that directly maximise these clinically relevant metrics. Perhaps more interestingly, it is found that the RL agents learned strategies that were adaptive to the lesion size, where spread of the needles was prioritised for smaller lesions. Such a strategy has not been previously reported or commonly adopted in clinical practice, but led to an overall superior targeting performance, achieving higher HR (93% vs 76%) and measured CCL (11.0 mm vs 9.8 mm) when compared with intuitively designed strategies.