Artificial intelligence-based analysis of body composition predicts outcome in patients receiving long-term mechanical circulatory support.

BACKGROUND: Obesity is a known cardiovascular risk factor and associated with higher postoperative complication rates in patients undergoing cardiac surgery. In heart failure (HF), conflicting evidence in terms of survival has been reported, whereas sarcopenia is associated with poor prognosis. An increasing number of HF patients require left ventricular assist device (LVAD) implantations. The postoperative mortality has improved in recent years but is still relatively high. The impact of body composition on outcome in this population remains unclear. The aim of this investigation was to examine the preoperative computed tomography (CT) body composition as a predictor of the postoperative outcome in advanced HF patients, who receive LVAD implantations. METHODS: Preoperative CT scans of 137 patients who received LVADs between 2015 and 2020 were retrospectively analysed using an artificial intelligence (AI)-powered automated software tool based on a convolutional neural network, U-net, developed for image segmentation (Visage Version 7.1, Visage Imaging GmbH, Berlin, Germany). Assessment of body composition included visceral and subcutaneous adipose tissue areas (VAT and SAT), psoas and total abdominal muscle areas and sarcopenia (defined by lumbar skeletal muscle indexes). The body composition parameters were correlated with postoperative major complication rates, survival and postoperative 6-min walk distance (6MWD) and quality of life (QoL). RESULTS: The mean age of patients was 58.21 ± 11.9 years; 122 (89.1%) were male. Most patients had severe HF requiring inotropes (Interagency Registry for Mechanically Assisted Circulatory Support [INTERMACS] profile I-III, 71.9%) secondary to coronary artery diseases or dilated cardiomyopathy (96.4%). Forty-four (32.1%) patients were obese (body mass index ≥ 30 kg/m2 ), 96 (70.1%) were sarcopene and 19 (13.9%) were sarcopene obese. Adipose tissue was associated with a significantly higher risk of postoperative infections (VAT 172.23 cm2 [54.96, 288.32 cm2 ] vs. 124.04 cm2 [56.57, 186.25 cm2 ], P = 0.022) and in-hospital mortality (VAT 168.11 cm2 [134.19, 285.27 cm2 ] vs. 135.42 cm2 [49.44, 227.91 cm2 ], P = 0.033; SAT 227.28 cm2 [139.38, 304.35 cm2 ] vs. 173.81 cm2 [97.65, 254.16 cm2 ], P = 0.009). Obese patients showed no improvement of 6MWD and QoL within 6 months postoperatively (obese: +0.94 ± 161.44 months, P = 0.982; non-obese: +166.90 ± 139.00 months, P < 0.000; obese: +0.088 ± 0.421, P = 0.376; non-obese: +0.199 ± 0.324, P = 0.002, respectively). Sarcopenia did not influence the postoperative outcome and survival within 1 year after LVAD implantation. CONCLUSIONS: Preoperative AI-based CT body composition identifies patients with poor outcome after LVAD implantation. Greater adipose tissue areas are associated with an increased risk for postoperative infections, in-hospital mortality and impaired 6MWD and QoL within 6 months postoperatively.

Split-bolus vs. multiphasic contrast bolus protocol in patients with pancreatic cancer or cholangiocarcinoma.

PURPOSE: To investigate the image quality, diagnostic accuracy, and dose reduction potential of a split-bolus protocol(SBP) compared with a multiphasic protocol(MPP) in the detection of recurrent or progressive pancreatic ductal adenocarcinoma(PDAC) or cholangiocarcinoma(CC) using contrast- enhanced computed tomography(CECT). MATERIALS AND METHODS: This prospective study included 56 patients who underwent CECT, 28 with our institutional standard MPP(100 ml contrast bolus) and 28 with a novel SBP(110 ml). Radiation exposure was determined in terms of total dose- length product(DLP) and computed tomography dose index(CTDI). Image quality was measured objectively by analysis of attenuation in Hounsfield units(HU) in regions of interest(ROIs) and subjectively by two blinded readers using a Likert scale. Diagnostic accuracy and interreader variability were tested. RESULTS: The total DLP of the SBP group(498.1 ± 43.7 mGy*cm) was significantly lower than in the MPP group(1,092.5 ± 106.9 mGy*cm; p < 0.001). The SBP showed higher contrast enhancement of all critical anatomical structures including portal vein, liver, and pancreas compared with the MPP, except for the aorta(SBP: 326.9 ± 15.7 HU vs. MPP: 246.7 ± 12.2 HU; p < 0.001). Subjective analysis revealed poorer image quality ratings for important landmarks with the MPP (resection surface: p = 0.624, portal vein: p = 0.395, liver p = 0.361). The two blinded readers correlated significantly. Sensitivity, specificity, positive and negative predictive values (PPV/NPV), and overall interreader variabilities correlated significantly. Furthermore, significantly fewer slices per exam were required for the SBP(1,823 vs. 3,235; p < 0.001). CONCLUSION: The SBP provides the same image quality and diagnostic accuracy as an MPP while significantly lowering radiation exposure in CT follow-up of PDAC or CC.