Key result
Deep learning on pre-therapy CMR predicts CTRCD with an AUC of 0.85, outperforming clinical models.
Why the study?
Predicting the risk of cancer therapy-related cardiac dysfunction remains challenging.
Does a deep learning model using pre-cancer therapy CMR images improve prediction of cancer therapy-related cardiac dysfunction compared to clinical and conventional imaging models in women with HER2+ breast cancer?
Cohort (n=229)
Yes
Does a deep learning model using pre-cancer therapy CMR images improve prediction of cancer therapy-related cardiac dysfunction compared to clinical and conventional imaging models in women with HER2+ breast cancer?
Answers are grounded in this paper and cite their sources.
A deep learning model using pre-cancer therapy CMR images can predict future cancer therapy-related cardiac dysfunction risk better than clinical or manually quantified imaging models.
BACKGROUND: Predicting risk of cancer therapy-related cardiac dysfunction (CTRCD) remains challenging. OBJECTIVES: The purpose of this study was to assess if deep learning (DL) approaches using cardiac magnetic resonance (CMR) images before cancer therapy can predict subsequent CTRCD and compare them with clinical and conventional imaging models. METHODS: Women with HER2+ breast cancer receiving anthracyclines and trastuzumab from 3 prospective studies (Toronto, Canada: EMBRACE-MRI, SPARE-HF; and Calgary, Canada: CIROC) were included. Patients were assessed before cancer therapy, after anthracycline, and trimonthly with repeated echocardiography and CMR. CTRCD was defined according to CMR. We calculated the HFA-ICOS risk score and measured CMR and echocardiography volumetric and functional parameters. Deep convolutional neural network architectures were used with pre-cancer therapy CMR short-axis cine images to develop image-based DL models to predict CTRCD. The Toronto patients were used for model derivation and internal validation; the Calgary patients were used for external validation. RESULTS: A total of 229 patients (mean age 50.4 ± 9.7 years) were included: 176 in the internal (52 CTRCD events) development cohort and 53 in the external data set (14 CTRCD events). Our pre-cancer therapy CMR DL model demonstrated an AUC of 0.85 (95% CI: 0.69-0.97) and F1 score 0.69 (95% CI: 0.47-0.86) to predict CTRCD. On external validation, the DL model had an AUC of 0.80 (95% CI: 0.58-0.86) and F1 score of 0.55 (95% CI: 0.32-0.69). In comparison, the best-performing models using HFA-ICOS risk score, CMR, and echocardiographic parameters demonstrated, respectively, AUCs of 0.66 (95% CI: 0.53-0.75), 0.59 (95% CI: 0.41-0.73), 0.62 (95% CI: 0.44-0.78) and F1 scores of 0.56 (95% CI: 0.47-0.61), 0.20 (95% CI: 0.00-0.42) and 0.36 (95% CI: 0.12-0.62) to predict CTRCD. CONCLUSIONS: A DL model using pre-cancer therapy CMR short-axis cines can predict future CTRCD risk better than clinical or manually quantified imaging models.
No takes yet. Share an insight, caveat, or question.
Yu et al. (2026) conducted a cohort in HER2+ breast cancer (n=229). Deep learning model using pre-cancer therapy CMR images vs. HFA-ICOS risk score, CMR, and echocardiographic parameters was evaluated on Cancer therapy-related cardiac dysfunction (CTRCD) (AUC 0.85, 95% CI 0.69-0.97). A deep learning model using pre-cancer therapy CMR images predicted future cancer therapy-related cardiac dysfunction with an AUC of 0.85, outperforming clinical models.
Synapse has enriched 10 related papers. Consider them for comparative context: