BACKGROUND Hepatic steatosis is a major cause of chronic liver disease.Two-dimensional(2D)ultrasound is the most widely used non-invasive tool for screening and monitoring,but associated diagnoses are highly subjectiv...BACKGROUND Hepatic steatosis is a major cause of chronic liver disease.Two-dimensional(2D)ultrasound is the most widely used non-invasive tool for screening and monitoring,but associated diagnoses are highly subjective.AIM To develop a scalable deep learning(DL)algorithm for quantitative scoring of liver steatosis from 2D ultrasound images.METHODS Using multi-view ultrasound data from 3310 patients,19513 studies,and 228075 images from a retrospective cohort of patients received elastography,we trained a DL algorithm to diagnose steatosis stages(healthy,mild,moderate,or severe)from clinical ultrasound diagnoses.Performance was validated on two multiscanner unblinded and blinded(initially to DL developer)histology-proven cohorts(147 and 112 patients)with histopathology fatty cell percentage diagnoses and a subset with FibroScan diagnoses.We also quantified reliability across scanners and viewpoints.Results were evaluated using Bland-Altman and receiver operating characteristic(ROC)analysis.RESULTS The DL algorithm demonstrated repeatable measurements with a moderate number of images(three for each viewpoint)and high agreement across three premium ultrasound scanners.High diagnostic performance was observed across all viewpoints:Areas under the curve of the ROC to classify mild,moderate,and severe steatosis grades were 0.85,0.91,and 0.93,respectively.The DL algorithm outperformed or performed at least comparably to FibroScan control attenuation parameter(CAP)with statistically significant improvements for all levels on the unblinded histology-proven cohort and for“=severe”steatosis on the blinded histology-proven cohort.CONCLUSION The DL algorithm provides a reliable quantitative steatosis assessment across view and scanners on two multi-scanner cohorts.Diagnostic performance was high with comparable or better performance than the CAP.展开更多
Rudolf Arnheim’s Gestalt art theory examines visual perceptual forces and the phenomenon of“isomorphism”in psychological movement by exemplifying Chinese images as T’ai-chi tu.By raising these Chinese examples,he ...Rudolf Arnheim’s Gestalt art theory examines visual perceptual forces and the phenomenon of“isomorphism”in psychological movement by exemplifying Chinese images as T’ai-chi tu.By raising these Chinese examples,he points out the similarities of western and Chinese aesthetic theories.He deploys Chinese thought,especially Taoism,to complement the deficiency of western thought.Taoist thought enlightened him to a new path to critically reflect the western traditions of dichotomies,which sharply divides perception from thinking,and art from science.Arnheim examines Chinese art from a perspective of western psychology,and also reflectson western theories taking Chinese culture as a mirror,in order to supplement western experience and construct a universal scientific aesthetic theory.展开更多
基金Supported by the Maintenance Project of the Center for Artificial Intelligence,No.CLRPG3H0012 and No.SMRPG3I0011.
文摘BACKGROUND Hepatic steatosis is a major cause of chronic liver disease.Two-dimensional(2D)ultrasound is the most widely used non-invasive tool for screening and monitoring,but associated diagnoses are highly subjective.AIM To develop a scalable deep learning(DL)algorithm for quantitative scoring of liver steatosis from 2D ultrasound images.METHODS Using multi-view ultrasound data from 3310 patients,19513 studies,and 228075 images from a retrospective cohort of patients received elastography,we trained a DL algorithm to diagnose steatosis stages(healthy,mild,moderate,or severe)from clinical ultrasound diagnoses.Performance was validated on two multiscanner unblinded and blinded(initially to DL developer)histology-proven cohorts(147 and 112 patients)with histopathology fatty cell percentage diagnoses and a subset with FibroScan diagnoses.We also quantified reliability across scanners and viewpoints.Results were evaluated using Bland-Altman and receiver operating characteristic(ROC)analysis.RESULTS The DL algorithm demonstrated repeatable measurements with a moderate number of images(three for each viewpoint)and high agreement across three premium ultrasound scanners.High diagnostic performance was observed across all viewpoints:Areas under the curve of the ROC to classify mild,moderate,and severe steatosis grades were 0.85,0.91,and 0.93,respectively.The DL algorithm outperformed or performed at least comparably to FibroScan control attenuation parameter(CAP)with statistically significant improvements for all levels on the unblinded histology-proven cohort and for“=severe”steatosis on the blinded histology-proven cohort.CONCLUSION The DL algorithm provides a reliable quantitative steatosis assessment across view and scanners on two multi-scanner cohorts.Diagnostic performance was high with comparable or better performance than the CAP.
文摘Rudolf Arnheim’s Gestalt art theory examines visual perceptual forces and the phenomenon of“isomorphism”in psychological movement by exemplifying Chinese images as T’ai-chi tu.By raising these Chinese examples,he points out the similarities of western and Chinese aesthetic theories.He deploys Chinese thought,especially Taoism,to complement the deficiency of western thought.Taoist thought enlightened him to a new path to critically reflect the western traditions of dichotomies,which sharply divides perception from thinking,and art from science.Arnheim examines Chinese art from a perspective of western psychology,and also reflectson western theories taking Chinese culture as a mirror,in order to supplement western experience and construct a universal scientific aesthetic theory.