TY - JOUR
T1 - CT radiomics compared to a clinical model for predicting checkpoint inhibitor treatment outcomes in patients with advanced melanoma
AU - Ter Maat, Laurens S
AU - van Duin, Isabella A J
AU - Elias, Sjoerd G
AU - Leiner, Tim
AU - Verhoeff, Joost J C
AU - Arntz, Eran R A N
AU - Troenokarso, Max F
AU - Blokx, Willeke A M
AU - Isgum, Ivana
AU - de Wit, Geraldine A
AU - van den Berkmortel, Franchette W P J
AU - Boers-Sonderen, Marye J
AU - Boomsma, Martijn F
AU - van den Eertwegh, Fons J M
AU - de Groot, Jan Willem B
AU - Piersma, Djura
AU - Vreugdenhil, Art
AU - Westgeest, Hans M
AU - Kapiteijn, Ellen
AU - van Diest, Paul J
AU - Pluim, Josien P W
AU - de Jong, Pim A
AU - Suijkerbuijk, Karijn P M
AU - Veta, Mitko
N1 - Funding Information:
This research was funded by The Netherlands Organization for Health Research and Development (ZonMW, project number 848101007 ) and Philips.
Publisher Copyright:
© 2023 The Author(s)
PY - 2023/5
Y1 - 2023/5
N2 - Introduction: Predicting checkpoint inhibitors treatment outcomes in melanoma is a relevant task, due to the unpredictable and potentially fatal toxicity and high costs for society. However, accurate biomarkers for treatment outcomes are lacking. Radiomics are a technique to quantitatively capture tumour characteristics on readily available computed tomography (CT) imaging. The purpose of this study was to investigate the added value of radiomics for predicting clinical benefit from checkpoint inhibitors in melanoma in a large, multicenter cohort. Methods: Patients who received first-line anti-PD1±anti-CTLA4 treatment for advanced cutaneous melanoma were retrospectively identified from nine participating hospitals. For every patient, up to five representative lesions were segmented on baseline CT, and radiomics features were extracted. A machine learning pipeline was trained on the radiomics features to predict clinical benefit, defined as stable disease for more than 6 months or response per RECIST 1.1 criteria. This approach was evaluated using a leave-one-centre-out cross validation and compared to a model based on previously discovered clinical predictors. Lastly, a combination model was built on the radiomics and clinical model. Results: A total of 620 patients were included, of which 59.2% experienced clinical benefit. The radiomics model achieved an area under the receiver operator characteristic curve (AUROC) of 0.607 [95% CI, 0.562–0.652], lower than that of the clinical model (AUROC=0.646 [95% CI, 0.600–0.692]). The combination model yielded no improvement over the clinical model in terms of discrimination (AUROC=0.636 [95% CI, 0.592–0.680]) or calibration. The output of the radiomics model was significantly correlated with three out of five input variables of the clinical model (p < 0.001). Discussion: The radiomics model achieved a moderate predictive value of clinical benefit, which was statistically significant. However, a radiomics approach was unable to add value to a simpler clinical model, most likely due to the overlap in predictive information learned by both models. Future research should focus on the application of deep learning, spectral CT-derived radiomics, and a multimodal approach for accurately predicting benefit to checkpoint inhibitor treatment in advanced melanoma.
AB - Introduction: Predicting checkpoint inhibitors treatment outcomes in melanoma is a relevant task, due to the unpredictable and potentially fatal toxicity and high costs for society. However, accurate biomarkers for treatment outcomes are lacking. Radiomics are a technique to quantitatively capture tumour characteristics on readily available computed tomography (CT) imaging. The purpose of this study was to investigate the added value of radiomics for predicting clinical benefit from checkpoint inhibitors in melanoma in a large, multicenter cohort. Methods: Patients who received first-line anti-PD1±anti-CTLA4 treatment for advanced cutaneous melanoma were retrospectively identified from nine participating hospitals. For every patient, up to five representative lesions were segmented on baseline CT, and radiomics features were extracted. A machine learning pipeline was trained on the radiomics features to predict clinical benefit, defined as stable disease for more than 6 months or response per RECIST 1.1 criteria. This approach was evaluated using a leave-one-centre-out cross validation and compared to a model based on previously discovered clinical predictors. Lastly, a combination model was built on the radiomics and clinical model. Results: A total of 620 patients were included, of which 59.2% experienced clinical benefit. The radiomics model achieved an area under the receiver operator characteristic curve (AUROC) of 0.607 [95% CI, 0.562–0.652], lower than that of the clinical model (AUROC=0.646 [95% CI, 0.600–0.692]). The combination model yielded no improvement over the clinical model in terms of discrimination (AUROC=0.636 [95% CI, 0.592–0.680]) or calibration. The output of the radiomics model was significantly correlated with three out of five input variables of the clinical model (p < 0.001). Discussion: The radiomics model achieved a moderate predictive value of clinical benefit, which was statistically significant. However, a radiomics approach was unable to add value to a simpler clinical model, most likely due to the overlap in predictive information learned by both models. Future research should focus on the application of deep learning, spectral CT-derived radiomics, and a multimodal approach for accurately predicting benefit to checkpoint inhibitor treatment in advanced melanoma.
KW - Checkpoint inhibition
KW - Computed tomography
KW - Machine learning
KW - Metastatic melanoma
KW - Radiomics
KW - Response prediction
UR - http://www.scopus.com/inward/record.url?scp=85151435876&partnerID=8YFLogxK
U2 - 10.1016/j.ejca.2023.02.017
DO - 10.1016/j.ejca.2023.02.017
M3 - Article
C2 - 36996627
SN - 0959-8049
VL - 185
SP - 167
EP - 177
JO - European Journal of Cancer
JF - European Journal of Cancer
ER -