An Zeng, Xianyang Lin, Jingliang Zhao, Dan Pan, Baoyao Yang, Xin Liu
{"title":"[基于强化学习的 B 型主动脉夹层定位方法]。","authors":"An Zeng, Xianyang Lin, Jingliang Zhao, Dan Pan, Baoyao Yang, Xin Liu","doi":"10.7507/1001-5515.202309047","DOIUrl":null,"url":null,"abstract":"<p><p>In the segmentation of aortic dissection, there are issues such as low contrast between the aortic dissection and surrounding organs and vessels, significant differences in dissection morphology, and high background noise. To address these issues, this paper proposed a reinforcement learning-based method for type B aortic dissection localization. With the assistance of a two-stage segmentation model, the deep reinforcement learning was utilized to perform the first-stage aortic dissection localization task, ensuring the integrity of the localization target. In the second stage, the coarse segmentation results from the first stage were used as input to obtain refined segmentation results. To improve the recall rate of the first-stage segmentation results and include the segmentation target more completely in the localization results, this paper designed a reinforcement learning reward function based on the direction of recall changes. Additionally, the localization window was separated from the field of view window to reduce the occurrence of segmentation target loss. Unet, TransUnet, SwinUnet, and MT-Unet were selected as benchmark segmentation models. Through experiments, it was verified that the majority of the metrics in the two-stage segmentation process of this paper performed better than the benchmark results. Specifically, the Dice index improved by 1.34%, 0.89%, 27.66%, and 7.37% for each respective model. In conclusion, by incorporating the type B aortic dissection localization method proposed in this paper into the segmentation process, the overall segmentation accuracy is improved compared to the benchmark models. The improvement is particularly significant for models with poorer segmentation performance.</p>","PeriodicalId":39324,"journal":{"name":"生物医学工程学杂志","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"[Reinforcement learning-based method for type B aortic dissection localization].\",\"authors\":\"An Zeng, Xianyang Lin, Jingliang Zhao, Dan Pan, Baoyao Yang, Xin Liu\",\"doi\":\"10.7507/1001-5515.202309047\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>In the segmentation of aortic dissection, there are issues such as low contrast between the aortic dissection and surrounding organs and vessels, significant differences in dissection morphology, and high background noise. To address these issues, this paper proposed a reinforcement learning-based method for type B aortic dissection localization. With the assistance of a two-stage segmentation model, the deep reinforcement learning was utilized to perform the first-stage aortic dissection localization task, ensuring the integrity of the localization target. In the second stage, the coarse segmentation results from the first stage were used as input to obtain refined segmentation results. To improve the recall rate of the first-stage segmentation results and include the segmentation target more completely in the localization results, this paper designed a reinforcement learning reward function based on the direction of recall changes. Additionally, the localization window was separated from the field of view window to reduce the occurrence of segmentation target loss. Unet, TransUnet, SwinUnet, and MT-Unet were selected as benchmark segmentation models. Through experiments, it was verified that the majority of the metrics in the two-stage segmentation process of this paper performed better than the benchmark results. Specifically, the Dice index improved by 1.34%, 0.89%, 27.66%, and 7.37% for each respective model. In conclusion, by incorporating the type B aortic dissection localization method proposed in this paper into the segmentation process, the overall segmentation accuracy is improved compared to the benchmark models. The improvement is particularly significant for models with poorer segmentation performance.</p>\",\"PeriodicalId\":39324,\"journal\":{\"name\":\"生物医学工程学杂志\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-10-25\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"生物医学工程学杂志\",\"FirstCategoryId\":\"1087\",\"ListUrlMain\":\"https://doi.org/10.7507/1001-5515.202309047\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"Medicine\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"生物医学工程学杂志","FirstCategoryId":"1087","ListUrlMain":"https://doi.org/10.7507/1001-5515.202309047","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 0
摘要
在主动脉夹层的分割中,存在主动脉夹层与周围器官和血管对比度低、夹层形态差异大、背景噪声高等问题。针对这些问题,本文提出了一种基于强化学习的 B 型主动脉夹层定位方法。在两阶段分割模型的辅助下,利用深度强化学习完成第一阶段主动脉夹层定位任务,确保定位目标的完整性。在第二阶段,将第一阶段的粗分割结果作为输入,获得精细分割结果。为了提高第一阶段分割结果的召回率,并将分割目标更完整地纳入定位结果,本文设计了基于召回率变化方向的强化学习奖励函数。此外,还将定位窗口与视场窗口分开,以减少分割目标丢失的发生。本文选择 Unet、TransUnet、SwinUnet 和 MTUnet 作为基准分割模型。通过实验验证,本文两阶段分割过程中的大多数指标都优于基准结果。具体来说,每个模型的 Dice 指数分别提高了 1.34%、0.89%、27.66% 和 7.37%。总之,通过将本文提出的 B 型主动脉夹层定位方法纳入分割过程,与基准模型相比,整体分割准确性得到了提高。对于分割性能较差的模型,这种改进尤为明显。
[Reinforcement learning-based method for type B aortic dissection localization].
In the segmentation of aortic dissection, there are issues such as low contrast between the aortic dissection and surrounding organs and vessels, significant differences in dissection morphology, and high background noise. To address these issues, this paper proposed a reinforcement learning-based method for type B aortic dissection localization. With the assistance of a two-stage segmentation model, the deep reinforcement learning was utilized to perform the first-stage aortic dissection localization task, ensuring the integrity of the localization target. In the second stage, the coarse segmentation results from the first stage were used as input to obtain refined segmentation results. To improve the recall rate of the first-stage segmentation results and include the segmentation target more completely in the localization results, this paper designed a reinforcement learning reward function based on the direction of recall changes. Additionally, the localization window was separated from the field of view window to reduce the occurrence of segmentation target loss. Unet, TransUnet, SwinUnet, and MT-Unet were selected as benchmark segmentation models. Through experiments, it was verified that the majority of the metrics in the two-stage segmentation process of this paper performed better than the benchmark results. Specifically, the Dice index improved by 1.34%, 0.89%, 27.66%, and 7.37% for each respective model. In conclusion, by incorporating the type B aortic dissection localization method proposed in this paper into the segmentation process, the overall segmentation accuracy is improved compared to the benchmark models. The improvement is particularly significant for models with poorer segmentation performance.