Local tuning of radiomics-based model for predicting pathological response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer
Abstract Purpose This study aims to further enhance a validated radiomics-based model for predicting pathologic complete response (pCR) after chemo‑radiotherapy in locally advanced rectal cancer (LARC) for use in clinical practice. Methods A generalized linear model (GLM) to predict pCR in LARC pati...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2022-03-01
|
Series: | BMC Medical Imaging |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12880-022-00773-x |
_version_ | 1818357145407586304 |
---|---|
author | Bin Tang Jacopo Lenkowicz Qian Peng Luca Boldrini Qing Hou Nicola Dinapoli Vincenzo Valentini Peng Diao Gang Yin Lucia Clara Orlandini |
author_facet | Bin Tang Jacopo Lenkowicz Qian Peng Luca Boldrini Qing Hou Nicola Dinapoli Vincenzo Valentini Peng Diao Gang Yin Lucia Clara Orlandini |
author_sort | Bin Tang |
collection | DOAJ |
description | Abstract Purpose This study aims to further enhance a validated radiomics-based model for predicting pathologic complete response (pCR) after chemo‑radiotherapy in locally advanced rectal cancer (LARC) for use in clinical practice. Methods A generalized linear model (GLM) to predict pCR in LARC patients previously trained in Europe and validated with an external inter-continental cohort (59 patients), was first examined with further 88 intercontinental patient datasets to assess its reproducibility; then new radiomics and clinical features, and validation methods were investigated to build a new model for enhancing the pCR prediction for patients admitted to our department. The patients were divided into training group (75%) and validation group (25%) according to their demographic. The least absolute shrinkage and selection operator (LASSO) logistic regression was used to reduce the dimensionality of the extracted features of the training group and select the optimal ones; the performance of the reference GLM and enhanced models was compared through the area under curve (AUC) of the receiver operating characteristics. Results The value of AUC of the reference model was 0.831 (95% CI, 0.701–0.961), and 0.828 (95% CI, 0.700–0.956) in the original and new validation cohorts, respectively, showing a reproducibility in the applicability of the GLM model. Eight features were found to be significant with LASSO and used to establish an enhanced model. The AUC of the enhanced model of 0.926 (95% CI, 0.859–0.993) for training, and 0.926 (95% CI, 0.767–1.00) for the validation group shows better performance than the reference model. Conclusions The GLM model shows good reproducibility in predicting pCR in LARC; the enhanced model has the potential to improve prediction accuracy and may be a candidate in clinical practice. |
first_indexed | 2024-12-13T20:08:27Z |
format | Article |
id | doaj.art-20b0d253d3b949458b620cb14427fc92 |
institution | Directory Open Access Journal |
issn | 1471-2342 |
language | English |
last_indexed | 2024-12-13T20:08:27Z |
publishDate | 2022-03-01 |
publisher | BMC |
record_format | Article |
series | BMC Medical Imaging |
spelling | doaj.art-20b0d253d3b949458b620cb14427fc922022-12-21T23:32:58ZengBMCBMC Medical Imaging1471-23422022-03-012211810.1186/s12880-022-00773-xLocal tuning of radiomics-based model for predicting pathological response to neoadjuvant chemoradiotherapy in locally advanced rectal cancerBin Tang0Jacopo Lenkowicz1Qian Peng2Luca Boldrini3Qing Hou4Nicola Dinapoli5Vincenzo Valentini6Peng Diao7Gang Yin8Lucia Clara Orlandini9Key Laboratory of Radiation Physics and Technology of the Ministry of Education, Institute of Nuclear Science and Technology, Sichuan UniversityDipartimento Scienze Radiologiche, Fondazione Policlinico Universitario “A. Gemelli” IRCCSDepartment of Radiation Oncology, Radiation Oncology Key Laboratory of Sichuan Province, Sichuan Cancer Hospital and InstituteDipartimento Scienze Radiologiche, Fondazione Policlinico Universitario “A. Gemelli” IRCCSKey Laboratory of Radiation Physics and Technology of the Ministry of Education, Institute of Nuclear Science and Technology, Sichuan UniversityDipartimento Scienze Radiologiche, Fondazione Policlinico Universitario “A. Gemelli” IRCCSDipartimento Scienze Radiologiche, Fondazione Policlinico Universitario “A. Gemelli” IRCCSDepartment of Radiation Oncology, Radiation Oncology Key Laboratory of Sichuan Province, Sichuan Cancer Hospital and InstituteDepartment of Radiation Oncology, Radiation Oncology Key Laboratory of Sichuan Province, Sichuan Cancer Hospital and InstituteDepartment of Radiation Oncology, Radiation Oncology Key Laboratory of Sichuan Province, Sichuan Cancer Hospital and InstituteAbstract Purpose This study aims to further enhance a validated radiomics-based model for predicting pathologic complete response (pCR) after chemo‑radiotherapy in locally advanced rectal cancer (LARC) for use in clinical practice. Methods A generalized linear model (GLM) to predict pCR in LARC patients previously trained in Europe and validated with an external inter-continental cohort (59 patients), was first examined with further 88 intercontinental patient datasets to assess its reproducibility; then new radiomics and clinical features, and validation methods were investigated to build a new model for enhancing the pCR prediction for patients admitted to our department. The patients were divided into training group (75%) and validation group (25%) according to their demographic. The least absolute shrinkage and selection operator (LASSO) logistic regression was used to reduce the dimensionality of the extracted features of the training group and select the optimal ones; the performance of the reference GLM and enhanced models was compared through the area under curve (AUC) of the receiver operating characteristics. Results The value of AUC of the reference model was 0.831 (95% CI, 0.701–0.961), and 0.828 (95% CI, 0.700–0.956) in the original and new validation cohorts, respectively, showing a reproducibility in the applicability of the GLM model. Eight features were found to be significant with LASSO and used to establish an enhanced model. The AUC of the enhanced model of 0.926 (95% CI, 0.859–0.993) for training, and 0.926 (95% CI, 0.767–1.00) for the validation group shows better performance than the reference model. Conclusions The GLM model shows good reproducibility in predicting pCR in LARC; the enhanced model has the potential to improve prediction accuracy and may be a candidate in clinical practice.https://doi.org/10.1186/s12880-022-00773-xRadiomicsRectumPredictive modelsPathological complete responseLASSO |
spellingShingle | Bin Tang Jacopo Lenkowicz Qian Peng Luca Boldrini Qing Hou Nicola Dinapoli Vincenzo Valentini Peng Diao Gang Yin Lucia Clara Orlandini Local tuning of radiomics-based model for predicting pathological response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer BMC Medical Imaging Radiomics Rectum Predictive models Pathological complete response LASSO |
title | Local tuning of radiomics-based model for predicting pathological response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer |
title_full | Local tuning of radiomics-based model for predicting pathological response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer |
title_fullStr | Local tuning of radiomics-based model for predicting pathological response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer |
title_full_unstemmed | Local tuning of radiomics-based model for predicting pathological response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer |
title_short | Local tuning of radiomics-based model for predicting pathological response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer |
title_sort | local tuning of radiomics based model for predicting pathological response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer |
topic | Radiomics Rectum Predictive models Pathological complete response LASSO |
url | https://doi.org/10.1186/s12880-022-00773-x |
work_keys_str_mv | AT bintang localtuningofradiomicsbasedmodelforpredictingpathologicalresponsetoneoadjuvantchemoradiotherapyinlocallyadvancedrectalcancer AT jacopolenkowicz localtuningofradiomicsbasedmodelforpredictingpathologicalresponsetoneoadjuvantchemoradiotherapyinlocallyadvancedrectalcancer AT qianpeng localtuningofradiomicsbasedmodelforpredictingpathologicalresponsetoneoadjuvantchemoradiotherapyinlocallyadvancedrectalcancer AT lucaboldrini localtuningofradiomicsbasedmodelforpredictingpathologicalresponsetoneoadjuvantchemoradiotherapyinlocallyadvancedrectalcancer AT qinghou localtuningofradiomicsbasedmodelforpredictingpathologicalresponsetoneoadjuvantchemoradiotherapyinlocallyadvancedrectalcancer AT nicoladinapoli localtuningofradiomicsbasedmodelforpredictingpathologicalresponsetoneoadjuvantchemoradiotherapyinlocallyadvancedrectalcancer AT vincenzovalentini localtuningofradiomicsbasedmodelforpredictingpathologicalresponsetoneoadjuvantchemoradiotherapyinlocallyadvancedrectalcancer AT pengdiao localtuningofradiomicsbasedmodelforpredictingpathologicalresponsetoneoadjuvantchemoradiotherapyinlocallyadvancedrectalcancer AT gangyin localtuningofradiomicsbasedmodelforpredictingpathologicalresponsetoneoadjuvantchemoradiotherapyinlocallyadvancedrectalcancer AT luciaclaraorlandini localtuningofradiomicsbasedmodelforpredictingpathologicalresponsetoneoadjuvantchemoradiotherapyinlocallyadvancedrectalcancer |