Prediction of Uncertainty Estimation and Confidence Calibration Using Fully Convolutional Neural Network

作     者：Karim Gasmi Lassaad Ben Ammar Hmoud Elshammari Fadwa Yahya 

作者机构：Department of Computer ScienceCollege of Arts and Sciences at TabarjalJouf UniversityJoufSaudi Arabia College of Sciences and HumanitiesPrince Sattam Bin Abdulaziz UniversityAl-KharjSaudi Arabia University of SfaxSfaxTunisia Department of Information SystemsCollege of Computer and Information SciencesJouf UniversityJoufSaudi Arabia 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2023年第75卷第5期

页      面：2557-2573页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 080203[工学-机械设计及理论] 0835[工学-软件工程] 0802[工学-机械工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

主　　题：Medical image segmentation confidence calibration uncertainty estimation fully convolutional neural network 

摘      要：Convolution neural networks(CNNs)have proven to be effective clinical *** study highlighted some of the key issues within these *** is difficult to train these systems in a limited clinical image databases,and many publications present strategies including such learning ***,these patterns are known formaking a highly reliable *** addition,normalization of volume and losses of dice have been used effectively to accelerate and stabilize the ***,these systems are improperly regulated,resulting in more confident ratings for correct and incorrect classification,which are inaccurate and difficult to *** study examines the risk assessment of Fully Convolutional Neural Networks(FCNNs)for clinical image *** contributions have been made to this planned work:1)dice loss and cross-entropy loss are compared on the basis of segment quality and uncertain assessment of FCNNs;2)proposal for a group model for assurance measurement of full convolutional neural networks trained with dice loss and group normalization;And 3)the ability of the measured FCNs to evaluate the segment quality of the structures and to identify test examples outside the *** evaluate the study’s contributions,it conducted a series of tests in three clinical image division applications such as heart,brain and *** findings of the study provide significant insights into the predictive ambiguity assessment and a practical strategies for outside-distribution identification and reliable measurement in the clinical image *** approaches presented in this research significantly enhance the reliability and accuracy rating of CNNbased clinical imaging methods.