Diagnostic and Prognostic Value of Myocardial Work Indices for Identification of Cancer Therapy-Related Cardiotoxicity.

BACKGROUND: Echocardiographic global longitudinal strain (GLS) is a useful measure for detection of cancer treatment-related cardiac dysfunction (CTRCD) but is influenced by blood pressure changes. This limitation may be overcome by assessment of myocardial work (MW), which incorporates blood pressure into the calculation. OBJECTIVES: This work aims to determine whether myocardial work indices (MWIs) can help diagnose or prognosticate CTRCD. METHODS: In this prospective cohort study, 136 women undergoing anthracycline and trastuzumab treatment for HER2+ breast cancer, underwent serial echocardiograms and cardiac magnetic resonance pre- and post-anthracycline and every 3 months during trastuzumab. GLS, global work index (GWI), global constructive work (GCW), global wasted work, and global work efficiency were measured. CTRCD was defined with cardiac magnetic resonance. Generalized estimating equations quantified the association between changes in GLS and MWIs and CTRCD at the current (diagnosis) and subsequent visit (prognosis). Regression tree analysis was used to explore the combined use of GLS and MW for the diagnostic/prognostic assessment of CTRCD. RESULTS: Baseline left ventricular ejection fraction (LVEF) was 63.2 ± 4.0%. Thirty-seven (27.2%) patients developed CTRCD. An absolute change in GLS (standardized odds ratio [sOR]: 1.97 [95% CI: 1.07-3.66]; P = 0.031) and GWI (sOR: 1.73 [95% CI: 1.04-2.85]; P = 0.033) were associated with concurrent CTRCD. An absolute change in GLS (sOR: 1.79 [95% CI: 1.22-2.62]; P = 0.003), GWI (sOR: 1.67 [95% CI: 1.20-2.32]; P = 0.003), and GCW (sOR: 1.65 [95% CI: 1.17-2.34]; P = 0.005) were associated with subsequent CTRCD. Change in GWI and GCW demonstrated incremental value over GLS and clinical factors for the diagnosis of concurrent CTRCD. In a small group with a GLS change <3.3% (absolute), and a >21 mm Hg reduction in systolic blood pressure, worsening of GWI identified patients with higher probability of concurrent CTRCD (24.0% vs 5.2%). MWIs did not improve identification of subsequent CTRCD beyond knowledge of GLS change. CONCLUSIONS: GLS can be used to diagnose and prognosticate cardiac magnetic resonance (CMR) defined CTRCD, with additional value from MWIs in selected cases. (Evaluation of Myocardial Changes During Breast Adenocarcinoma Therapy to Detect Cardiotoxicity Earlier With MRI [EMBRACE-MRI]; NCT02306538).

Deep learning for whole-body medical image generation.

BACKGROUND: Artificial intelligence (AI) algorithms based on deep convolutional networks have demonstrated remarkable success for image transformation tasks. State-of-the-art results have been achieved by generative adversarial networks (GANs) and training approaches which do not require paired data. Recently, these techniques have been applied in the medical field for cross-domain image translation. PURPOSE: This study investigated deep learning transformation in medical imaging. It was motivated to identify generalizable methods which would satisfy the simultaneous requirements of quality and anatomical accuracy across the entire human body. Specifically, whole-body MR patient data acquired on a PET/MR system were used to generate synthetic CT image volumes. The capacity of these synthetic CT data for use in PET attenuation correction (AC) was evaluated and compared to current MR-based attenuation correction (MR-AC) methods, which typically use multiphase Dixon sequences to segment various tissue types. MATERIALS AND METHODS: This work aimed to investigate the technical performance of a GAN system for general MR-to-CT volumetric transformation and to evaluate the performance of the generated images for PET AC. A dataset comprising matched, same-day PET/MR and PET/CT patient scans was used for validation. RESULTS: A combination of training techniques was used to produce synthetic images which were of high-quality and anatomically accurate. Higher correlation was found between the values of mu maps calculated directly from CT data and those derived from the synthetic CT images than those from the default segmented Dixon approach. Over the entire body, the total amounts of reconstructed PET activities were similar between the two MR-AC methods, but the synthetic CT method yielded higher accuracy for quantifying the tracer uptake in specific regions. CONCLUSION: The findings reported here demonstrate the feasibility of this technique and its potential to improve certain aspects of attenuation correction for PET/MR systems. Moreover, this work may have larger implications for establishing generalized methods for inter-modality, whole-body transformation in medical imaging. Unsupervised deep learning techniques can produce high-quality synthetic images, but additional constraints may be needed to maintain medical integrity in the generated data.