Incremental Utility of First-Pass Perfusion CMR for Prognostic Risk Stratification of Cancer-Associated Cardiac Masses

Abstract

Background: Cardiac magnetic resonance (CMR) differentiates cardiac metastasis (C_MET) and cardiac thrombus (C_THR) based on tissue characteristics stemming from vascularity on late gadolinium enhancement (LGE). Perfusion CMR can assess magnitude of vascularity; utility for cardiac masses (C_MASS) is unknown.

Objectives: This study sought to determine if perfusion CMR provides diagnostic and prognostic utility for C_MASS beyond binary differentiation of C_MET and C_THR.

Methods: The population comprised adult cancer patients with C_MASS on CMR; C_MET and C_THR were defined using LGE-CMR: C_MASS+ patients were matched to C_MASS- control subjects for cancer type/stage. First-pass perfusion CMR was interpreted visually and semiquantitatively for C_MASS vascularity, including contrast enhancement ratio (CER) (plateau vs baseline) and contrast uptake rate (CUR) (slope). Follow-up was performed for all-cause mortality.

Results: A total of 462 cancer patients were studied, including patients with (C_MET = 173, C_THR = 69) and without C_MASS on LGE-CMR. On perfusion CMR, CER and CUR were higher within C_MET vs C_THR (P < 0.001); CUR yielded better performance (AUC: 0.89-0.93) than CER (AUC: 0.66-0.72) (both P < 0.001) to differentiate LGE-CMR-evidenced C_MET and C_THR, although both CUR (P = 0.10) and CER (P = 0.01) typically misclassified C_MET with minimal enhancement. During follow-up, mortality among C_MET patients was high but variable; 47% of patients were alive 1 year post-CMR. Patients with semiquantitative perfusion CMR-evidenced C_MET had higher mortality than control subjects (HR: 1.42 [95% CI: 1.06-1.90]; P = 0.02), paralleling visual perfusion CMR (HR: 1.47 [95% CI: 1.12-1.94]; P = 0.006) and LGE-CMR (HR: 1.52 [95% CI: 1.16-2.00]; P = 0.003). Among patients with C_MET on LGE-CMR, mortality was highest among patients (P = 0.002) with lesions in the bottom perfusion (CER) tertile, corresponding to low vascularity. Among C_MET and cancer-matched control subjects, mortality was equivalent (P = NS) among patients with lesions in the upper CER tertile (corresponding to higher lesion vascularity). Conversely, patients with C_MET in the middle (P = 0.03) and lowest (lowest vascularity) (P = 0.001) CER tertiles had increased mortality.

Conclusions: Perfusion CMR yields prognostic utility that complements LGE-CMR: Among cancer patients with LGE-CMR defined C_MET, mortality increases in proportion to magnitude of lesion hypoperfusion.

Keywords: cardiac magnetic resonance; cardiac masses; cardio-oncology; late gadolinium enhancement; perfusion.

Figure 1.. Representative Examples

Representative examples of left (1A) and right (1B) sided C_MET and C_THR as respectively assessed by LGE and perfusion-CMR (top), as well as corresponding perfusion analyses to measure contrast kinetics (bottom). In brief, regions of interest (ROI) were placed over lesions and tracked throughout the cardiac cycle so as to measure slope (contrast uptake rate [CUR]) and plateau enhancement (contrast enhancement ratio [CER]). Note that for both examples, C_MET (blue) demonstrated higher contrast enhancement than did C_THR (purple), consistent with presence of vascular supply. However, a range of vascularity was evident among C_MET cases for which lesions with minimal enhancement on LGE-CMR (center; dark blue outline) demonstrated lower magnitude of semi-quantitative perfusion than did diffusely enhancing lesions (left; light blue outline), corresponding to lesser differentiation from C_THR.

Figure 2.. Perfusion-CMR for Differentiation of Cardiac Metastasis and Thrombus

Receiver operating characteristics (ROC) curves for perfusion-CMR cutoffs in relation to C_MET as established by the reference of LGE-CMR (red = contrast uptake rate [CUR], blue = enhancement ratio [CER]; solid and dashed lines correspond to absolute and blood pool normalized data for each). Note good overall diagnostic performance for semi-quantitative CUR (AUC 0.89–0.93), which was higher than that of CER (0.66–0.72). Corresponding diagnostic test parameters derived from ROC curves shown in Table 3.

Figure 3.. C_MET Perfusion on CMR in Relation to Pathology-Evidenced Lesion Vascularity

Representative examples of C_MET with variable magnitude of perfusion (top) together with semi-quantitative perfusion-CMR analysis (middle) and pathology-evidenced lesion vascularity (bottom). As shown, variability in contrast kinetics on perfusion-CMR paralleled differential vascular and cell density on pathology. 3A: Two cases of minimally enhancing CMET on perfusion-CMR, including thymoma (left) for which pathology demonstrated high tumor cell burden with minimal vascular content and melanoma (right) for which pathology demonstrated scattered vascular content (melanoma) with prominent tumor necrosis. 3B: Two cases of prominently enhancing CMET on perfusion-CMR (left: neuroendocrine, right: spindle cell sarcoma), both of which had high vascular density on pathology. Legend: asterisk = tumor necrosis, dagger = myocardium; inserts = high power views of tumor components (pathology images obtained using hematoxylin and eosin staining).

Figure 4.. Mortality Based on Diagnostic Categorization by CMR Tissue Characterization Methods

Kaplan-Meier analyses for patients with C_MET and C_THR as established by LGE (left), semi-quantitative perfusion-CMR (middle) and visual perfusion-CMR (right), as well as among respective cancer-matched controls. As shown, both CMR tissue characterization methods demonstrated mortality to be higher among patients with C_MET, although adverse prognosis conferred by LGE was higher (HR=1.52 [1.16–2.00], p=0.003) than that conferred by perfusion, irrespective of whether interpreted using semi-quantitative (HR=1.42 [1.06–1.90], p=0.02) or visual (HR=1.47 [1.12–1.94], p=0.006) based diagnostic classifications. Conversely, LGE-CMR demonstrated patients with C_THR to have similar mortality to controls, whereas mortality was higher when C_THR was established based on perfusion, consistent with study analysis showing tumors with minimal enhancement (on LGE) to often be misclassified as C_THR based on perfusion cutoffs.

Figure 5.. Mortality Among Patients with Cardiac Metastases in Relation to Lesion Hypoperfusion

5A: Kaplan-Meier curve encompassing patients with CMET (defined by the reference of LGE-CMR) stratified based on population-based tertiles of lesion vascularity (CER) as measured on semi-quantitative perfusion-CMR. As shown, there was a stepwise association between C_MET hypoperfusion and risk for death: Patients in the lowest tertile had higher mortality (p=0.002) than those in the upper-most tertile, paralleling a similar trend for patients in the middle tertile (p=0.09). Primary data from which tertile partitions derived shown in upper right. 5B: Comparisons between CMET cases and cancer-matched controls within each respective semi-quantitative perfusion tertile. As shown, patients within lowest tertile of perfusion-CMR evidenced vascularity (CER) had higher risk for death than did controls (p=0.001), paralleling a similar pattern but lesser magnitude of difference in the middle perfusion tertile (p=0.03). Conversely, mortality for patients with lesions in the highest perfusion tertile (corresponding to highest vascularity) was equivalent to that of cancer-matched controls (p=0.67).

Central Illustration. Perfusion CMR for Cancer-Associated Cardiac Masses

Multicenter data from two cancer centers demonstrated perfusion-CMR evidenced contrast kinetics to differ between vascular and avascular masses, as evidenced by higher uptake (slope) and plateau enhancement for cardiac metastasis vs. thrombus. While perfusion performed well in relation to LGE, performance as a primary method to differentiate mass types and stratify prognosis was compromised by misclassification of metastases with minimal enhancement: Among patients with CMET on LGE-CMR, perfusion-CMR demonstrated mortality to increase with lesion hypo-perfusion and to be augmented for patients with low vascularity lesions and equivalent (to that of controls) for patients with high vascularity lesions. Findings support utility of integrated CMR tissue characterization for cardiac masses, in which initial diagnosis is established by LGE and prognosis for CMET further stratified based on perfusion-CMR evidenced lesion hypo-vascularity.