Delta Radiomics and Tumor Size: A New Predictive Radiomics Model for Chemotherapy Response in Liver Metastases from Breast and Colorectal Cancer

Nicolò Gennaro; Moataz Soliman; Amir A. Borhani; Linda Kelahan; Hatice Savas; Ryan James Avery; Kamal Subedi; Tugce A. Trabzonlu; Chase Krumpelman; Vahid Yaghmai; Young Kwang Chae; Jochen Lorch; Devalingam Mahalingam; Mary Mulcahy; Al B Benson III; Ulas Bagci; Yuri S. Velichko

doi:10.3390/tomography11030020

Delta Radiomics and Tumor Size: A New Predictive Radiomics Model for Chemotherapy Response in Liver Metastases from Breast and Colorectal Cancer

Nicolò Gennaro, Moataz Soliman, Amir A. Borhani, Linda Kelahan, Hatice Savas, Ryan James Avery, Kamal Subedi, Tugce A. Trabzonlu, Chase Krumpelman, Vahid Yaghmai, Young Kwang Chae, Jochen Lorch, Devalingam Mahalingam, Mary Mulcahy, Al B Benson III, Ulas Bagci, Yuri S. Velichko^*

^*Corresponding author for this work

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

Abstract

Background/Objectives: Radiomic features exhibit a correlation with tumor size on pretreatment images. However, on post-treatment images, this association is influenced by treatment efficacy and varies between responders and non-responders. This study introduces a novel model, called baseline-referenced Delta radiomics, which integrates the association between radiomic features and tumor size into Delta radiomics to predict chemotherapy response in liver metastases from breast cancer (BC) and colorectal cancer (CRC). Materials and Methods: A retrospective study analyzed contrast-enhanced computed tomography (CT) scans of 83 BC patients and 84 CRC patients. Among these, 57 BC patients with 106 liver lesions and 37 CRC patients with 109 lesions underwent post-treatment imaging after systemic chemotherapy. Radiomic features were extracted from up to three lesions per patient following manual segmentation. Tumor response was assessed by measuring the longest diameter and classified according to RECIST 1.1 criteria as progressive disease (PD), partial response (PR), or stable disease (SD). Classification models were developed to predict chemotherapy response using pretreatment data only, Delta radiomics, and baseline-referenced Delta radiomics. Model performance was evaluated using confusion matrix metrics. Results: Baseline-referenced Delta radiomics performed comparably or better than established radiomics models in predicting tumor response in chemotherapy-treated patients with liver metastases. The sensitivity, specificity, and balanced accuracy in predicting response ranged from 0.66 to 0.97, 0.81 to 0.97, and 80% to 90%, respectively. Conclusions: By integrating the relationship between radiomic features and tumor size into Delta radiomics, baseline-referenced Delta radiomics offers a promising approach for predicting chemotherapy response in liver metastases from breast and colorectal cancer.

Original language	English (US)
Article number	20
Journal	Tomography
Volume	11
Issue number	3
DOIs	https://doi.org/10.3390/tomography11030020
State	Published - Mar 2025

Funding

Support for this work was provided by the Department of Radiology, Feinberg School of Medicine, Northwestern University.

Keywords

chemotherapy
computer tomography
Delta radiomics
liver
metastases
radiomics
RECIST 1.1
response assessment

ASJC Scopus subject areas

Radiology Nuclear Medicine and imaging

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.3390/tomography11030020

Cite this

Gennaro, N., Soliman, M., Borhani, A. A., Kelahan, L., Savas, H., Avery, R. J., Subedi, K., Trabzonlu, T. A., Krumpelman, C., Yaghmai, V., Chae, Y. K., Lorch, J., Mahalingam, D., Mulcahy, M., Benson III, A. B., Bagci, U., & Velichko, Y. S. (2025). Delta Radiomics and Tumor Size: A New Predictive Radiomics Model for Chemotherapy Response in Liver Metastases from Breast and Colorectal Cancer. Tomography, 11(3), Article 20. https://doi.org/10.3390/tomography11030020

@article{6357ef9f91d14a6380a90bb1cf63da93,

title = "Delta Radiomics and Tumor Size: A New Predictive Radiomics Model for Chemotherapy Response in Liver Metastases from Breast and Colorectal Cancer",

abstract = "Background/Objectives: Radiomic features exhibit a correlation with tumor size on pretreatment images. However, on post-treatment images, this association is influenced by treatment efficacy and varies between responders and non-responders. This study introduces a novel model, called baseline-referenced Delta radiomics, which integrates the association between radiomic features and tumor size into Delta radiomics to predict chemotherapy response in liver metastases from breast cancer (BC) and colorectal cancer (CRC). Materials and Methods: A retrospective study analyzed contrast-enhanced computed tomography (CT) scans of 83 BC patients and 84 CRC patients. Among these, 57 BC patients with 106 liver lesions and 37 CRC patients with 109 lesions underwent post-treatment imaging after systemic chemotherapy. Radiomic features were extracted from up to three lesions per patient following manual segmentation. Tumor response was assessed by measuring the longest diameter and classified according to RECIST 1.1 criteria as progressive disease (PD), partial response (PR), or stable disease (SD). Classification models were developed to predict chemotherapy response using pretreatment data only, Delta radiomics, and baseline-referenced Delta radiomics. Model performance was evaluated using confusion matrix metrics. Results: Baseline-referenced Delta radiomics performed comparably or better than established radiomics models in predicting tumor response in chemotherapy-treated patients with liver metastases. The sensitivity, specificity, and balanced accuracy in predicting response ranged from 0.66 to 0.97, 0.81 to 0.97, and 80% to 90%, respectively. Conclusions: By integrating the relationship between radiomic features and tumor size into Delta radiomics, baseline-referenced Delta radiomics offers a promising approach for predicting chemotherapy response in liver metastases from breast and colorectal cancer.",

keywords = "chemotherapy, computer tomography, Delta radiomics, liver, metastases, radiomics, RECIST 1.1, response assessment",

author = "Nicol{\`o} Gennaro and Moataz Soliman and Borhani, {Amir A.} and Linda Kelahan and Hatice Savas and Avery, {Ryan James} and Kamal Subedi and Trabzonlu, {Tugce A.} and Chase Krumpelman and Vahid Yaghmai and Chae, {Young Kwang} and Jochen Lorch and Devalingam Mahalingam and Mary Mulcahy and {Benson III}, {Al B} and Ulas Bagci and Velichko, {Yuri S.}",

note = "Publisher Copyright: {\textcopyright} 2025 by the authors.",

year = "2025",

month = mar,

doi = "10.3390/tomography11030020",

language = "English (US)",

volume = "11",

journal = "Tomography",

issn = "2379-1381",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "3",

}

Gennaro, N, Soliman, M, Borhani, AA , Kelahan, L , Savas, H , Avery, RJ , Subedi, K , Trabzonlu, TA , Krumpelman, C, Yaghmai, V, Chae, YK , Lorch, J , Mahalingam, D , Mulcahy, M , Benson III, AB , Bagci, U & Velichko, YS 2025, 'Delta Radiomics and Tumor Size: A New Predictive Radiomics Model for Chemotherapy Response in Liver Metastases from Breast and Colorectal Cancer', Tomography, vol. 11, no. 3, 20. https://doi.org/10.3390/tomography11030020

TY - JOUR

T1 - Delta Radiomics and Tumor Size

T2 - A New Predictive Radiomics Model for Chemotherapy Response in Liver Metastases from Breast and Colorectal Cancer

AU - Gennaro, Nicolò

AU - Soliman, Moataz

AU - Borhani, Amir A.

AU - Kelahan, Linda

AU - Savas, Hatice

AU - Avery, Ryan James

AU - Subedi, Kamal

AU - Trabzonlu, Tugce A.

AU - Krumpelman, Chase

AU - Yaghmai, Vahid

AU - Chae, Young Kwang

AU - Lorch, Jochen

AU - Mahalingam, Devalingam

AU - Mulcahy, Mary

AU - Benson III, Al B

AU - Bagci, Ulas

AU - Velichko, Yuri S.

PY - 2025/3

Y1 - 2025/3

N2 - Background/Objectives: Radiomic features exhibit a correlation with tumor size on pretreatment images. However, on post-treatment images, this association is influenced by treatment efficacy and varies between responders and non-responders. This study introduces a novel model, called baseline-referenced Delta radiomics, which integrates the association between radiomic features and tumor size into Delta radiomics to predict chemotherapy response in liver metastases from breast cancer (BC) and colorectal cancer (CRC). Materials and Methods: A retrospective study analyzed contrast-enhanced computed tomography (CT) scans of 83 BC patients and 84 CRC patients. Among these, 57 BC patients with 106 liver lesions and 37 CRC patients with 109 lesions underwent post-treatment imaging after systemic chemotherapy. Radiomic features were extracted from up to three lesions per patient following manual segmentation. Tumor response was assessed by measuring the longest diameter and classified according to RECIST 1.1 criteria as progressive disease (PD), partial response (PR), or stable disease (SD). Classification models were developed to predict chemotherapy response using pretreatment data only, Delta radiomics, and baseline-referenced Delta radiomics. Model performance was evaluated using confusion matrix metrics. Results: Baseline-referenced Delta radiomics performed comparably or better than established radiomics models in predicting tumor response in chemotherapy-treated patients with liver metastases. The sensitivity, specificity, and balanced accuracy in predicting response ranged from 0.66 to 0.97, 0.81 to 0.97, and 80% to 90%, respectively. Conclusions: By integrating the relationship between radiomic features and tumor size into Delta radiomics, baseline-referenced Delta radiomics offers a promising approach for predicting chemotherapy response in liver metastases from breast and colorectal cancer.

AB - Background/Objectives: Radiomic features exhibit a correlation with tumor size on pretreatment images. However, on post-treatment images, this association is influenced by treatment efficacy and varies between responders and non-responders. This study introduces a novel model, called baseline-referenced Delta radiomics, which integrates the association between radiomic features and tumor size into Delta radiomics to predict chemotherapy response in liver metastases from breast cancer (BC) and colorectal cancer (CRC). Materials and Methods: A retrospective study analyzed contrast-enhanced computed tomography (CT) scans of 83 BC patients and 84 CRC patients. Among these, 57 BC patients with 106 liver lesions and 37 CRC patients with 109 lesions underwent post-treatment imaging after systemic chemotherapy. Radiomic features were extracted from up to three lesions per patient following manual segmentation. Tumor response was assessed by measuring the longest diameter and classified according to RECIST 1.1 criteria as progressive disease (PD), partial response (PR), or stable disease (SD). Classification models were developed to predict chemotherapy response using pretreatment data only, Delta radiomics, and baseline-referenced Delta radiomics. Model performance was evaluated using confusion matrix metrics. Results: Baseline-referenced Delta radiomics performed comparably or better than established radiomics models in predicting tumor response in chemotherapy-treated patients with liver metastases. The sensitivity, specificity, and balanced accuracy in predicting response ranged from 0.66 to 0.97, 0.81 to 0.97, and 80% to 90%, respectively. Conclusions: By integrating the relationship between radiomic features and tumor size into Delta radiomics, baseline-referenced Delta radiomics offers a promising approach for predicting chemotherapy response in liver metastases from breast and colorectal cancer.

KW - chemotherapy

KW - computer tomography

KW - Delta radiomics

KW - liver

KW - metastases

KW - radiomics

KW - RECIST 1.1

KW - response assessment

UR - http://www.scopus.com/inward/record.url?scp=105001106312&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=105001106312&partnerID=8YFLogxK

U2 - 10.3390/tomography11030020

DO - 10.3390/tomography11030020

M3 - Article

C2 - 40137560

AN - SCOPUS:105001106312

SN - 2379-1381

VL - 11

JO - Tomography

JF - Tomography

IS - 3

M1 - 20

ER -

Delta Radiomics and Tumor Size: A New Predictive Radiomics Model for Chemotherapy Response in Liver Metastases from Breast and Colorectal Cancer

Abstract

Funding

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this