Filters








23,719 Hits in 4.1 sec

Improving the quality of image segmentation in Ultrasound images using Reinforcement Learning

Shazan Ghajari, Mohammad Bagher Naghibi Sistani
2017 Communications on Advanced Computational Science with Applications  
In the processing reinforcement learning factor, threshold operator values and opening operator dimensions obtained for image segmentation.  ...  Multi-agent dimensional structure is selected which has the best result in the image segmentation.  ...  In [8] for segmentation medical images a set of reinforcement learning agents are employed.  ... 
doi:10.5899/2017/cacsa-00072 fatcat:t4iknntygzcz7kox7yvujruywe

Left Ventricle Contouring in Cardiac Images Based on Deep Reinforcement Learning [article]

Sixing Yin, Yameng Han, Shufang Li
2021 arXiv   pre-print
In this paper, we propose a new iterative refined interactive segmentation method for medical images based on agent reinforcement learning, which focuses on the problem of target segmentation boundaries  ...  Medical image segmentation is one of the important tasks of computer-aided diagnosis in medical image analysis.  ...  CONCLUSION In this paper, we propose a new iterative and refined interactive segmentation method for medical images based on agent reinforcement learning.  ... 
arXiv:2106.04127v1 fatcat:s4wgporltjcrneeecykt63zmp4

A Comparison of Deep Reinforcement Learning and Deep learning for Complex Image Analysis

Rishi Khajuria, Abdul Quyoom, Abid Sarwar
2020 Journal of multimedia information system  
In such cases the deep reinforcement learning techniques can be used to learn feature from the limited data without losing contextual and spatial information.  ...  Although deep reinforcement learning is a new and emerging technique but very less effort has been made to compare the deep learning and deep reinforcement learning for image analysis.  ...  This task is being addressed by a novel approach based on reinforcement learning by introducing an early classifier agent , an end-to-end reinforcement learning agent i.e.  ... 
doi:10.33851/jmis.2020.7.1.1 fatcat:zfbzlklu4bdmrogzgduaouwqvu

Application of Opposition-Based Reinforcement Learning in Image Segmentation

Farhang Sahba, Hamid R. Tizhoosh, Magdy M. M. A. Salama
2007 2007 IEEE Symposium on Computational Intelligence in Image and Signal Processing  
In this paper a method for image segmentation using an opposition-based reinforcement learning scheme is introduced.  ...  The agent uses an image and its manually segmented version and takes some actions to change the environment (the quality of segmented image).  ...  Also, more appropriate quality measures, usually used in medical imaging, must be apply to evaluate the performance more accurately. Fig. 1 . 1 A general model for Reinforcement learning agent.  ... 
doi:10.1109/ciisp.2007.369176 fatcat:5ximclvdejcb7pcedi7hr4u74u

A Multi-Agent Deep Reinforcement Learning Approach for Enhancement of COVID-19 CT Image Segmentation

Hanane Allioui, Mazin Abed Mohammed, Narjes Benameur, Belal Al-Khateeb, Karrar Hameed Abdulkareem, Begonya Garcia-Zapirain, Robertas Damaševičius, Rytis Maskeliūnas
2022 Journal of Personalized Medicine  
Hence, we introduce a new mask extraction method that is based on multi-agent deep reinforcement learning (DRL) to minimize the long-term manual mask extraction and to enhance medical image segmentation  ...  The use of cooperative agents in mask extraction increases the efficiency of automatic image segmentation.  ...  CT images are often degraded by the mask image. The objective of this work is to extract optimal image masks using a multi-agent reinforcement learning (MARL) process.  ... 
doi:10.3390/jpm12020309 pmid:35207796 pmcid:PMC8880720 fatcat:3j4sievstjhtnlpnujxf3nftnm

Automatic Data Augmentation via Deep Reinforcement Learning for Effective Kidney Tumor Segmentation [article]

Tiexin Qin and Ziyuan Wang and Kelei He and Yinghuan Shi and Yang Gao and Dinggang Shen
2020 arXiv   pre-print
In this paper, we developed a novel automatic learning-based data augmentation method for medical image segmentation which models the augmentation task as a trial-and-error procedure using deep reinforcement  ...  Conventional data augmentation realized by performing simple pre-processing operations (\eg, rotation, crop, \etc) has been validated for its advantage in enhancing the performance for medical image segmentation  ...  We model data augmentation for medical image segmentation as a reinforcement learning problem to learn a data-specific augmentation policy. (2) A joint-learning scheme to integrate a hybrid architecture  ... 
arXiv:2002.09703v1 fatcat:ilt6yxnybndwnlqrs5t4sygete

Application on Reinforcement Learning for Diagnosis Based on Medical Image [chapter]

Stelmo Magalhaes Barros Netto, Vanessa Rodrigues Coelho Leite, Aristofanes Correa, Anselmo Cardoso de Paiva, Areolino de Almeida Neto
2008 Reinforcement Learning  
(Sahba et al, 2006) introduced a new method for medical image segmentation using a reinforcement learning scheme.  ...  On the other hand, we also found in the literature some works using Reinforcement Learning to help the segmentation of medical images.  ... 
doi:10.5772/5291 fatcat:nqh6zocwwrfzjdozxdd2lqijwe

Integrating Reinforcement Learning to Self Training for Pulmonary Nodule Segmentation in Chest X-rays [article]

Sejin Park, Woochan Hwang, Kyu-Hwan Jung
2018 arXiv   pre-print
Machine learning applications in medical imaging are frequently limited by the lack of quality labeled data.  ...  By integrating reinforcement learning, we were able to expand the application of self training to complex segmentation networks without any further human annotation.  ...  Introduction Supervised learning applications in medical imaging face a common obstacle of obtaining quality labeled data.  ... 
arXiv:1811.08840v1 fatcat:coged3hdrrelhhgut7n3imhfpi

Application of reinforcement learning for segmentation of transrectal ultrasound images

Farhang Sahba, Hamid R Tizhoosh, Magdy MA Salama
2008 BMC Medical Imaging  
It contains an offline stage, where the reinforcement learning agent uses some images and manually segmented versions of these images to learn from.  ...  Methods: We introduce a new method for the segmentation of the prostate in transrectal ultrasound images, using a reinforcement learning scheme.  ...  Acknowledgements The subject matter in this work is covered by a US provisional patent application.  ... 
doi:10.1186/1471-2342-8-8 pmid:18430220 pmcid:PMC2397386 fatcat:glxg3ti3gvavjiajalbcx6nohi

Edge-Sensitive Left Ventricle Segmentation Using Deep Reinforcement Learning

Jingjing Xiong, Lai-Man Po, Kwok Wai Cheung, Pengfei Xian, Yuzhi Zhao, Yasar Abbas Ur Rehman, Yujia Zhang
2021 Sensors  
Reinforcement learning-based methods in earlier works often rely on learning proper thresholds to perform segmentation, and the segmentation results are inaccurate due to the sensitivity of the threshold  ...  However, relatively few DRL methods have been proposed in the area of image segmentation, particularly in left ventricle segmentation.  ...  Reinforcement learning-based medical image segmentation.  ... 
doi:10.3390/s21072375 pmid:33805558 pmcid:PMC8037138 fatcat:lgrr7s7kczdc5enthydpyh2exm

Deep reinforcement learning in medical imaging: A literature review [article]

S. Kevin Zhou, Hoang Ngan Le, Khoa Luu, Hien V. Nguyen, Nicholas Ayache
2021 arXiv   pre-print
Deep reinforcement learning (DRL) augments the reinforcement learning framework, which learns a sequence of actions that maximizes the expected reward, with the representative power of deep neural networks  ...  We then cover existing DRL applications for medical imaging, which are roughly divided into three main categories: (I) parametric medical image analysis tasks including landmark detection, object/lesion  ...  Wang et al. (2013) present an online reinforcement learning framework for medical image segmentation.The so-called context specific segmentation is first introduced such that the model not only uses a  ... 
arXiv:2103.05115v1 fatcat:ocr6kq7atnbhxazj7twvvhl5uy

Adaptable image quality assessment using meta-reinforcement learning of task amenability [article]

Shaheer U. Saeed, Yunguan Fu, Vasilis Stavrinides, Zachary M. C. Baum, Qianye Yang, Mirabela Rusu, Richard E. Fan, Geoffrey A. Sonn, J. Alison Noble, Dean C. Barratt, Yipeng Hu
2021 arXiv   pre-print
To predict task amenability, an IQA agent is trained using reinforcement learning (RL) with a simultaneously optimised task predictor, such as a classification or segmentation neural network.  ...  The performance of many medical image analysis tasks are strongly associated with image data quality.  ...  To predict task amenability, an IQA agent is trained using reinforcement learning (RL) with a simultaneously optimised task predictor, such as a classification or segmentation neural network.  ... 
arXiv:2108.04359v1 fatcat:cblijrasljanjgdasbfzpcvdcu

Reinforcement Learning for Context Aware Segmentation [chapter]

Lichao Wang, Robert Merrifield, Guang-Zhong Yang
2011 Lecture Notes in Computer Science  
In this paper, a general segmentation framework based on reinforcement learning is proposed.  ...  The ability to learn from user behavior during image segmentation to replicate the innate human ability to adapt shape delineation to contextually specific local information is an important area of study  ...  Conclusion In this paper, we have presented a general semi-automatic scheme that learns from the user behavior to perform medical image segmentation.  ... 
doi:10.1007/978-3-642-23626-6_77 fatcat:z3onhxa7kzap3ahvcbob55qhsu

A Multi-Agents Architecture to Learn Vision Operators and their Parameters [article]

Issam Qaffou, Mohammed Sadgal, Abdelaziz Elfazziki
2012 arXiv   pre-print
In this paper we present a multi-agent architecture to learn the best operators to apply and their best parameters for a class of images.  ...  The Operator Agent constructs all possible combinations of operators and the Parameter Agent, the core of the architecture, adjusts the parameters of each combination by treating a large number of images  ...  Segmentation parameters are represented by a team of stochastic automata that use connectionist techniques of reinforcement learning.  ... 
arXiv:1207.2426v1 fatcat:pbqrpavwrzewdphhsu7msnbxry

Quantitative Analysis Method of Immunochromatographic Strip Based on Reinforcement Learning

Songming Liu, Shaojun Zeng
2020 Journal of Physics, Conference Series  
The RL agent provides an adaptive segmentation model for the newly obtained GICS images by learning the state features of the preprocessed images.  ...  As a research hotspot of machine learning (ML), reinforcement learning (RL) has made many progresses in the field of image segmentation.  ...  Q-Learning algorithm is one of the classic techniques proposed by Watkins that is used to learn the strategy for agent in model-free reinforcement learning system.  ... 
doi:10.1088/1742-6596/1449/1/012058 fatcat:agipx66prbduho6l522ofxqsve
« Previous Showing results 1 — 15 out of 23,719 results