Predictive power of deep-learning segmentation based prognostication model in non-small cell lung cancer
PurposeThe study aims to create a model to predict survival outcomes for non-small cell lung cancer (NSCLC) after treatment with stereotactic body radiotherapy (SBRT) using deep-learning segmentation based prognostication (DESEP).MethodsThe DESEP model was trained using imaging from 108 patients wit...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-04-01
|
| Series: | Frontiers in Oncology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fonc.2023.868471/full |
| _version_ | 1827973731627040768 |
|---|---|
| author | Jordan C. Gainey Yusen He Robert Zhu Stephen S. Baek Xiaodong Wu John M. Buatti Bryan G. Allen Brian J. Smith Yusung Kim |
| author_facet | Jordan C. Gainey Yusen He Robert Zhu Stephen S. Baek Xiaodong Wu John M. Buatti Bryan G. Allen Brian J. Smith Yusung Kim |
| author_sort | Jordan C. Gainey |
| collection | DOAJ |
| description | PurposeThe study aims to create a model to predict survival outcomes for non-small cell lung cancer (NSCLC) after treatment with stereotactic body radiotherapy (SBRT) using deep-learning segmentation based prognostication (DESEP).MethodsThe DESEP model was trained using imaging from 108 patients with NSCLC with various clinical stages and treatment histories. The model generated predictions based on unsupervised features learned by a deep-segmentation network from computed tomography imaging to categorize patients into high and low risk groups for overall survival (DESEP-predicted-OS), disease specific survival (DESEP-predicted-DSS), and local progression free survival (DESEP-predicted-LPFS). Serial assessments were also performed using auto-segmentation based volumetric RECISTv1.1 and computer-based unidimensional RECISTv1.1 patients was performed.ResultsThere was a concordance between the DESEP-predicted-LPFS risk category and manually calculated RECISTv1.1 (φ=0.544, p=0.001). Neither the auto-segmentation based volumetric RECISTv1.1 nor the computer-based unidimensional RECISTv1.1 correlated with manual RECISTv1.1 (p=0.081 and p=0.144, respectively). While manual RECISTv1.1 correlated with LPFS (HR=6.97,3.51-13.85, c=0.70, p<0.001), it could not provide insight regarding DSS (p=0.942) or OS (p=0.662). In contrast, the DESEP-predicted methods were predictive of LPFS (HR=3.58, 1.66-7.18, c=0.60, p<0.001), OS (HR=6.31, 3.65-10.93, c=0.71, p<0.001) and DSS (HR=9.25, 4.50-19.02, c=0.69, p<0.001). The promising results of the DESEP model were reproduced for the independent, external datasets of Stanford University, classifying survival and ‘dead’ group in their Kaplan-Meyer curves (p = 0.019).ConclusionDeep-learning segmentation based prognostication can predict LPFS as well as OS, and DSS after SBRT for NSCLC. It can be used in conjunction with current standard of care, manual RECISTv1.1 to provide additional insights regarding DSS and OS in NSCLC patients receiving SBRT.SummaryWhile current standard of care, manual RECISTv1.1 correlated with local progression free survival (LPFS) (HR=6.97,3.51-13.85, c=0.70, p<0.001), it could not provide insight regarding disease specific survival (DSS) (p=0.942) or overall survival (OS) (p=0.662). In contrast, the deep-learning segmentation based prognostication (DESEP)-predicted methods were predictive of LPFS (HR=3.58, 1.66-7.18, c=0.60, p<0.001), OS (HR=6.31, 3.65-10.93, c=0.71, p<0.001) and DSS (HR=9.25, 4.50-19.02, c=0.69, p<0.001). DESEP can be used in conjunction with current standard of care, manual RECISTv1.1 to provide additional insights regarding DSS and OS in NSCLC patients. |
| first_indexed | 2024-04-09T19:42:26Z |
| format | Article |
| id | doaj.art-beb20cf64bfd494ca15fe9ab24bfc9d1 |
| institution | Directory Open Access Journal |
| issn | 2234-943X |
| language | English |
| last_indexed | 2024-04-09T19:42:26Z |
| publishDate | 2023-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Oncology |
| spelling | doaj.art-beb20cf64bfd494ca15fe9ab24bfc9d12023-04-04T05:05:42ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2023-04-011310.3389/fonc.2023.868471868471Predictive power of deep-learning segmentation based prognostication model in non-small cell lung cancerJordan C. Gainey0Yusen He1Robert Zhu2Stephen S. Baek3Xiaodong Wu4John M. Buatti5Bryan G. Allen6Brian J. Smith7Yusung Kim8Department of Radiation Oncology, The University of Iowa, Iowa City, IA, United StatesDepartment of Data Science, Grinnell College, Grinnell, IA, United StatesDepartment of Radiation Oncology, The University of Iowa, Iowa City, IA, United StatesDepartment of Data Science, University of Virginia, Charlottesville, VA, United StatesDepartment of Radiation Oncology, The University of Iowa, Iowa City, IA, United StatesDepartment of Radiation Oncology, The University of Iowa, Iowa City, IA, United StatesDepartment of Radiation Oncology, The University of Iowa, Iowa City, IA, United StatesDepartment of Radiation Oncology, The University of Iowa, Iowa City, IA, United StatesDepartment of Radiation Oncology, MD Anderson Cancer Center, Houston, TX, United StatesPurposeThe study aims to create a model to predict survival outcomes for non-small cell lung cancer (NSCLC) after treatment with stereotactic body radiotherapy (SBRT) using deep-learning segmentation based prognostication (DESEP).MethodsThe DESEP model was trained using imaging from 108 patients with NSCLC with various clinical stages and treatment histories. The model generated predictions based on unsupervised features learned by a deep-segmentation network from computed tomography imaging to categorize patients into high and low risk groups for overall survival (DESEP-predicted-OS), disease specific survival (DESEP-predicted-DSS), and local progression free survival (DESEP-predicted-LPFS). Serial assessments were also performed using auto-segmentation based volumetric RECISTv1.1 and computer-based unidimensional RECISTv1.1 patients was performed.ResultsThere was a concordance between the DESEP-predicted-LPFS risk category and manually calculated RECISTv1.1 (φ=0.544, p=0.001). Neither the auto-segmentation based volumetric RECISTv1.1 nor the computer-based unidimensional RECISTv1.1 correlated with manual RECISTv1.1 (p=0.081 and p=0.144, respectively). While manual RECISTv1.1 correlated with LPFS (HR=6.97,3.51-13.85, c=0.70, p<0.001), it could not provide insight regarding DSS (p=0.942) or OS (p=0.662). In contrast, the DESEP-predicted methods were predictive of LPFS (HR=3.58, 1.66-7.18, c=0.60, p<0.001), OS (HR=6.31, 3.65-10.93, c=0.71, p<0.001) and DSS (HR=9.25, 4.50-19.02, c=0.69, p<0.001). The promising results of the DESEP model were reproduced for the independent, external datasets of Stanford University, classifying survival and ‘dead’ group in their Kaplan-Meyer curves (p = 0.019).ConclusionDeep-learning segmentation based prognostication can predict LPFS as well as OS, and DSS after SBRT for NSCLC. It can be used in conjunction with current standard of care, manual RECISTv1.1 to provide additional insights regarding DSS and OS in NSCLC patients receiving SBRT.SummaryWhile current standard of care, manual RECISTv1.1 correlated with local progression free survival (LPFS) (HR=6.97,3.51-13.85, c=0.70, p<0.001), it could not provide insight regarding disease specific survival (DSS) (p=0.942) or overall survival (OS) (p=0.662). In contrast, the deep-learning segmentation based prognostication (DESEP)-predicted methods were predictive of LPFS (HR=3.58, 1.66-7.18, c=0.60, p<0.001), OS (HR=6.31, 3.65-10.93, c=0.71, p<0.001) and DSS (HR=9.25, 4.50-19.02, c=0.69, p<0.001). DESEP can be used in conjunction with current standard of care, manual RECISTv1.1 to provide additional insights regarding DSS and OS in NSCLC patients.https://www.frontiersin.org/articles/10.3389/fonc.2023.868471/fullprognosticationnon-small cell lung cancerdeep learningRECIST (response evaluation criteria in solid tumors)lung cancer |
| spellingShingle | Jordan C. Gainey Yusen He Robert Zhu Stephen S. Baek Xiaodong Wu John M. Buatti Bryan G. Allen Brian J. Smith Yusung Kim Predictive power of deep-learning segmentation based prognostication model in non-small cell lung cancer Frontiers in Oncology prognostication non-small cell lung cancer deep learning RECIST (response evaluation criteria in solid tumors) lung cancer |
| title | Predictive power of deep-learning segmentation based prognostication model in non-small cell lung cancer |
| title_full | Predictive power of deep-learning segmentation based prognostication model in non-small cell lung cancer |
| title_fullStr | Predictive power of deep-learning segmentation based prognostication model in non-small cell lung cancer |
| title_full_unstemmed | Predictive power of deep-learning segmentation based prognostication model in non-small cell lung cancer |
| title_short | Predictive power of deep-learning segmentation based prognostication model in non-small cell lung cancer |
| title_sort | predictive power of deep learning segmentation based prognostication model in non small cell lung cancer |
| topic | prognostication non-small cell lung cancer deep learning RECIST (response evaluation criteria in solid tumors) lung cancer |
| url | https://www.frontiersin.org/articles/10.3389/fonc.2023.868471/full |
| work_keys_str_mv | AT jordancgainey predictivepowerofdeeplearningsegmentationbasedprognosticationmodelinnonsmallcelllungcancer AT yusenhe predictivepowerofdeeplearningsegmentationbasedprognosticationmodelinnonsmallcelllungcancer AT robertzhu predictivepowerofdeeplearningsegmentationbasedprognosticationmodelinnonsmallcelllungcancer AT stephensbaek predictivepowerofdeeplearningsegmentationbasedprognosticationmodelinnonsmallcelllungcancer AT xiaodongwu predictivepowerofdeeplearningsegmentationbasedprognosticationmodelinnonsmallcelllungcancer AT johnmbuatti predictivepowerofdeeplearningsegmentationbasedprognosticationmodelinnonsmallcelllungcancer AT bryangallen predictivepowerofdeeplearningsegmentationbasedprognosticationmodelinnonsmallcelllungcancer AT brianjsmith predictivepowerofdeeplearningsegmentationbasedprognosticationmodelinnonsmallcelllungcancer AT yusungkim predictivepowerofdeeplearningsegmentationbasedprognosticationmodelinnonsmallcelllungcancer |