APRIL: Anatomical prior-guided reinforcement learning for accurate carotid lumen diameter and intima-media thickness measurement

Lian，Sheng1,3,4; Luo，Zhiming1; Feng，Cheng2; Li，Shaozi1; Li，Shuo3,4

2021-07-01

10.1016/j.media.2021.102040

MEDICAL IMAGE ANALYSIS   影响因子和分区

1361-8415

1361-8423

Carotid artery lumen diameter (CALD) and carotid artery intima-media thickness (CIMT) are essential factors for estimating the risk of many cardiovascular diseases. The automatic measurement of them in ultrasound (US) images is an efficient assisting diagnostic procedure. Despite the advances, existing methods still suffer the issue of low measuring accuracy and poor prediction stability, mainly due to the following disadvantages: (1) ignore anatomical prior and prone to give anatomically inaccurate estimation; (2) require carefully designed post-processing, which may introduce more estimation errors; (3) rely on massive pixel-wise annotations during training; (4) can not estimate the uncertainty of the predictions. In this study, we propose the Anatomical Prior-guided ReInforcement Learning model (APRIL), which innovatively formulate the measurement of CALD & CIMT as an RL problem and dynamically incorporate anatomical prior (AP) into the system through a novel reward. With the guidance of AP, the designed keypoints in APRIL can avoid various anatomy impossible mis-locations, and accurately measure the CALD & CIMT based on their corresponding locations. Moreover, this formulation significantly reduces human annotation effort by only using several keypoints and can help to eliminate the extra post-processing steps. Further, we introduce an uncertainty module for measuring the prediction variance, which can guide us to adaptively rectify the estimation of those frames with considerable uncertainty. Experiments on a challenging carotid US dataset show that APRIL can achieve MAE (in pixel/mm) of 3.02±2.23 / 0.18±0.13 for CALD, and 0.96±0.70 / 0.06±0.04 for CIMT, which significantly surpass popular approaches that use more annotations.

Anatomical prior (AP) CALD and CIMT measurement Reinforcement learning (RL)

SCI ; EI

英语

其他

National Nature Science Foundation of China[61876159,61806172,"U1705286"] ; Fundamental Research Funds for the Central Universities, Xiamen University[20720200030] ; China Postdoctoral Science Foundation[2019M652257]

Computer Science ; Engineering ; Radiology, Nuclear Medicine & Medical Imaging

Computer Science, Artificial Intelligence ; Computer Science, Interdisciplinary Applications ; Engineering, Biomedical ; Radiology, Nuclear Medicine & Medical Imaging

WOS:000663616000001

ELSEVIER

20211410166807

Diagnosis ; Forecasting ; Pixels ; Reinforcement learning ; Risk perception ; Thickness measurement

Medicine and Pharmacology:461.6 ; Artificial Intelligence:723.4 ; Accidents and Accident Prevention:914.1 ; Probability Theory:922.1 ; Mechanical Variables Measurements:943.2

COMPUTER SCIENCE

2-s2.0-85103380805

Scopus

1.Department of Artificial Intelligence,Xiamen University,Xiamen,China
2.Department of Ultrasound,The Second Affiliated Hospital,Southern University of Science and Technology,Shenzhen Third Peoples Hospital,Shenzhen,China
3.Digital Image Group (DIG),London,Canada
4.School of Biomedical Engineering,Western University,London,Canada

Lian，Sheng,Luo，Zhiming,Feng，Cheng,et al. APRIL: Anatomical prior-guided reinforcement learning for accurate carotid lumen diameter and intima-media thickness measurement[J]. MEDICAL IMAGE ANALYSIS,2021,71.

Lian，Sheng,Luo，Zhiming,Feng，Cheng,Li，Shaozi,&Li，Shuo.(2021).APRIL: Anatomical prior-guided reinforcement learning for accurate carotid lumen diameter and intima-media thickness measurement.MEDICAL IMAGE ANALYSIS,71.

Lian，Sheng,et al."APRIL: Anatomical prior-guided reinforcement learning for accurate carotid lumen diameter and intima-media thickness measurement".MEDICAL IMAGE ANALYSIS 71(2021).