文献类型： 会议论文
第一作者： Paul Dubois
作者： Paul Dubois 1 ; Paul-Henry Cournede 1 ; Nikos Paragios 2 ; Pascal Fenoglietto 3 ;
作者机构： 1.Biomathematics, MICS, CentraleSupelec, Universite Paris-Saclay
2.TheraPanacea
3.Institut du Cancer de Montpellier (Val d'Aurelle)
关键词： Radiotherapy;Dose optimization;Reinforcement learning;Deep learning
会议名称： International Conference on Artificial Intelligence in Medicine
主办单位：
页码： 151-160
摘要： A radiation therapy plan finds an equilibrium between goals with no universal prioritization. The delicate balance between multiple objectives is typically done manually. The optimization process is further hindered by complex mathematical aspects, involving non-convex multi-objective inverse problems with a vast solution space. Expert bias introduces variability in clinical practice, as the preferences of radiation oncologists and medical physicists shape treatment planning. To surmount these challenges, we propose a first step towards a fully automated approach, using an innovative deep-learning framework. Using a clinically meaningful distance between doses, we trained a reinforcement learning agent to mimic a set of plans. This method allows automatic navigation toward acceptable solutions via the exploitation of optimal dose distributions found by human planners on previously treated patients. As this is ongoing research, we generated synthetic phantom patients and associated realistic clinical doses. Our deep learning agent successfully learned correct actions leading to treatment plans similar to past cases ones. The incapacity to reproduce human-like dose plans hinders adopting a fully automated treatment planning system; this method could start paving the way towards human-less treatment planning system technologies. In future work, we hope to be able to apply this technique to real cases.
分类号： tp18-53
- 相关文献
[1]Learning Functional Embedding of Genes Governed by Pair-wised Labels. Cao, Jingjun,Wu, Zhengli,Ye, Wenting,Wang, Haohan. 2017
[2]Repairing Segmental Defect with a Composite Associating Collagen Membrane and MBCP~R Combined with Total Bone Marrow Graft in Irradiated Bone Defect: an Experimental Study in Rabbit. F. Jegoux,E. Aguado,R. Cognet,O. Malard,F. Moreau,G. Daculsi,E. Goyenvalle. 2008
[3]Review of Reinforcement Learning-Based Control Algorithms in Artificial Pancreas Systems for Diabetes Mellitus Management. Lehel Dénes-Fazakas,Gy?z? Dénes Fazakas,Gy?rgy Eigner,Levente Kovács,László Szilágyi. 2024
[4]Effect of Hyperparameters of Reinforcement Learning in Blood Glucose Control. Máté Siket,László Szilágyi,Gy?rgy Eigner,Levente Kovács,Dénes-Fazakas Lehel. 2023
[5]Investigation of reward functions for controlling blood glucose level using reinforcement learning. Dénes-Fazakas Lehel,Máté Siket,László Szilágyi,Gyorgy Eigner,Levente Kovács. 2023
[6]Control of Type 1 Diabetes Mellitus using direct reinforcement learning based controller. Lehel Dénes-Fazakas,Máté Siket,Gábor Kertész,László Szilágyi,Levente Kovács,Gyórgy Eigner. 2022
[7]Sleep Apnea Severity Estimation from Respiratory Related Movements Using Deep Learning. Maziar Hafezi,Nasim Montazeri,Kaiyin Zhu,Hisham Alshaer,Azadeh Yadollahi,Babak Taati. 2019
[8]Class Imbalance Correction for Improved Universal Lesion Detection and Tagging in CT. Peter D. Erickson,Tejas Sudharshan Mathai,Ronald M. Summers. 2022
[9]An Intelligent Network Planning Algorithm for Emergency Communication with Deep Learning. Zongzhe Nie,Wei Zhu,Ruopeng Yang,Yu Wang. 2019
[10]Research on the Key Techniques of Semantic Mining of Information Digest in the Field of Agricultural Major Crops Based on Deep Learning. Ping Qian,Hao G. J. M. Gong,Yunpeng Cui. 2019
[11]DEEP LEARNING WITH ORTHOGONAL VOLUMETRIC HED SEGMENTATION AND 3D SURFACE RECONSTRUCTION MODEL OF PROSTATE MRI. Ruida Cheng,Nathan Lay,Francesca Mertan,Baris Turkbey,Holger R. Roth,Le Lu,William Gandler,Evan S. McCreedy,Thomas Pohida,Peter Choyke,Matthew J. McAuliffe,Ronald M. Summers. 2017
[12]Mapping Rice Area Using Sentinel-1 SAR Data and Deep Learning. Guozhuang Shen,Chenwei Nie. 2023
[13]PSPU-Net for Automatic Short Axis Cine MRI Segmentation of Left and Right Ventricles. Manuel Perez-Pelegri,Irene Del-Canto,Jose V. Monmeneu,Vicente Bodi,Maria P. Lopez-Lereu,David Moratal,Silvia Ruiz-Espana. 2020
[14]Detection of Lymph Nodes in T2 MRI Using Neural Network Ensembles. Zhiyong Lu,Ronald M. Summers,Tejas Sudharshan Mathai,Sungwon Lee,Daniel C. Elton,Thomas C. Shen,Yifan Peng. 2021
[15]W-net: Deep Convolutional Network with Gray-Level Co-occurrence Matrix and Hybrid Loss Function for Hyperspectral Image Classification. Jinchao Jiao,Changqing Yin,Fei Teng. 2023
[16]Integration of Raman Spectroscopy, On-Line Microscopic Imaging and Deep Learning-Based Image Analysis for Real-Time Monitoring of Cell Culture Process. Xiaoli Wang,Guangzheng Zhou,Xue Zhong Wang. 2025
[17]Drug Synergistic Combinations Predictions via Large-Scale Pre-training and Graph Structure Learning. Zhihang Hu,Qinze Yu,Yucheng Guo,Taifeng Wang,Irwin King,Xin Gao,Le Song,Yu Li. 2023
[18]On The Local Geometry of the Pet Reconstruction Problem. Ramy Merabet,Florent Sureau,Alain Trouvé. 2024
[19]Learning with Fixed Point Condition for Convergent PNP PET Reconstruction. Marion Savanier,Claude Comtat,Florent Sureau. 2024
[20]Automated Fruit Classification Based on Deep Learning Utilizing Yolov8. Christine Dewi,Oksam M Kamlasi,Gunjan Chhabra,Guowei Dai,Keshav Kaushik,Inam Ullah Khan. 2023
