SAFARI: shape analysis for AI-segmented images

Esteban Fernández; Shengjie Yang; Sy Han Chiou; Chul Moon; Cong Zhang; Bo Yao; Guanghua Xiao; Qiwei Li

doi:10.1186/s12880-022-00849-8

SAFARI: shape analysis for AI-segmented images

Esteban Fernández, Shengjie Yang, Sy Han Chiou, Chul Moon, Cong Zhang, Bo Yao, Guanghua Xiao, Qiwei Li

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

Background: Recent developments to segment and characterize the regions of interest (ROI) within medical images have led to promising shape analysis studies. However, the procedures to analyze the ROI are arbitrary and vary by study. A tool to translate the ROI to analyzable shape representations and features is greatly needed. Results: We developed SAFARI (shape analysis for AI-segmented images), an open-source R package with a user-friendly online tool kit for ROI labelling and shape feature extraction of segmented maps, provided by AI-algorithms or manual segmentation. We demonstrated that half of the shape features extracted by SAFARI were significantly associated with survival outcomes in a case study on 143 consecutive patients with stage I–IV lung cancer and another case study on 61 glioblastoma patients. Conclusions: SAFARI is an efficient and easy-to-use toolkit for segmenting and analyzing ROI in medical images. It can be downloaded from the comprehensive R archive network (CRAN) and accessed at https://lce.biohpc.swmed.edu/safari/.

Original language	English (US)
Article number	129
Journal	BMC Medical Imaging
Volume	22
Issue number	1
DOIs	https://doi.org/10.1186/s12880-022-00849-8
State	Published - Dec 2022

Keywords

Machine learning
Medical imaging
Shape descriptors
Shape representations

ASJC Scopus subject areas

Radiology Nuclear Medicine and imaging

Access to Document

10.1186/s12880-022-00849-8

Cite this

@article{6645ea17278b4c48816b9401b68e86c4,

title = "SAFARI: shape analysis for AI-segmented images",

abstract = "Background: Recent developments to segment and characterize the regions of interest (ROI) within medical images have led to promising shape analysis studies. However, the procedures to analyze the ROI are arbitrary and vary by study. A tool to translate the ROI to analyzable shape representations and features is greatly needed. Results: We developed SAFARI (shape analysis for AI-segmented images), an open-source R package with a user-friendly online tool kit for ROI labelling and shape feature extraction of segmented maps, provided by AI-algorithms or manual segmentation. We demonstrated that half of the shape features extracted by SAFARI were significantly associated with survival outcomes in a case study on 143 consecutive patients with stage I–IV lung cancer and another case study on 61 glioblastoma patients. Conclusions: SAFARI is an efficient and easy-to-use toolkit for segmenting and analyzing ROI in medical images. It can be downloaded from the comprehensive R archive network (CRAN) and accessed at https://lce.biohpc.swmed.edu/safari/.",

keywords = "Machine learning, Medical imaging, Shape descriptors, Shape representations",

author = "Esteban Fern{\'a}ndez and Shengjie Yang and Chiou, {Sy Han} and Chul Moon and Cong Zhang and Bo Yao and Guanghua Xiao and Qiwei Li",

note = "Publisher Copyright: {\textcopyright} 2022, The Author(s).",

year = "2022",

month = dec,

doi = "10.1186/s12880-022-00849-8",

language = "English (US)",

volume = "22",

journal = "BMC Medical Imaging",

issn = "1471-2342",

publisher = "BioMed Central",

number = "1",

}

TY - JOUR

T1 - SAFARI

T2 - shape analysis for AI-segmented images

AU - Fernández, Esteban

AU - Yang, Shengjie

AU - Chiou, Sy Han

AU - Moon, Chul

AU - Zhang, Cong

AU - Yao, Bo

AU - Xiao, Guanghua

AU - Li, Qiwei

PY - 2022/12

Y1 - 2022/12

N2 - Background: Recent developments to segment and characterize the regions of interest (ROI) within medical images have led to promising shape analysis studies. However, the procedures to analyze the ROI are arbitrary and vary by study. A tool to translate the ROI to analyzable shape representations and features is greatly needed. Results: We developed SAFARI (shape analysis for AI-segmented images), an open-source R package with a user-friendly online tool kit for ROI labelling and shape feature extraction of segmented maps, provided by AI-algorithms or manual segmentation. We demonstrated that half of the shape features extracted by SAFARI were significantly associated with survival outcomes in a case study on 143 consecutive patients with stage I–IV lung cancer and another case study on 61 glioblastoma patients. Conclusions: SAFARI is an efficient and easy-to-use toolkit for segmenting and analyzing ROI in medical images. It can be downloaded from the comprehensive R archive network (CRAN) and accessed at https://lce.biohpc.swmed.edu/safari/.

AB - Background: Recent developments to segment and characterize the regions of interest (ROI) within medical images have led to promising shape analysis studies. However, the procedures to analyze the ROI are arbitrary and vary by study. A tool to translate the ROI to analyzable shape representations and features is greatly needed. Results: We developed SAFARI (shape analysis for AI-segmented images), an open-source R package with a user-friendly online tool kit for ROI labelling and shape feature extraction of segmented maps, provided by AI-algorithms or manual segmentation. We demonstrated that half of the shape features extracted by SAFARI were significantly associated with survival outcomes in a case study on 143 consecutive patients with stage I–IV lung cancer and another case study on 61 glioblastoma patients. Conclusions: SAFARI is an efficient and easy-to-use toolkit for segmenting and analyzing ROI in medical images. It can be downloaded from the comprehensive R archive network (CRAN) and accessed at https://lce.biohpc.swmed.edu/safari/.

KW - Machine learning

KW - Medical imaging

KW - Shape descriptors

KW - Shape representations

UR - http://www.scopus.com/inward/record.url?scp=85134623604&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85134623604&partnerID=8YFLogxK

U2 - 10.1186/s12880-022-00849-8

DO - 10.1186/s12880-022-00849-8

M3 - Article

C2 - 35869424

AN - SCOPUS:85134623604

SN - 1471-2342

VL - 22

JO - BMC Medical Imaging

JF - BMC Medical Imaging

IS - 1

M1 - 129

ER -

SAFARI: shape analysis for AI-segmented images

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this