IMPROVEMENTS OF 111IN SPECT IMAGES RECONSTRUCTED WITH SPARSELY ACQUIRED PROJECTIONS BY DEEP LEARNING GENERATED SYNTHETIC PROJECTIONS

The aim was to improve single-photon emission computed tomography (SPECT) quality for sparsely acquired 111In projections by adding deep learning generated synthetic intermediate projections (SIPs). Method: The recently constructed deep convolutional network for generating synthetic intermediate projections (CUSIP) was used for improving 20 sparsely acquired 111In-octreotide SPECTs. Reconstruction was performed with 120 (120P) or 30 (30P) projections, or 120 projections with 90 SIPs generated from 30 projections (30-120SIP). The SPECT reconstructions were performed with attenuation, scatter and collimator response corrections. Postfiltered 30P reconstructed SPECT was also analyzed. Image quality were quantitatively evaluated with root-mean-square error, peak signal-to-noise ratio and structural similarity index metrics. Result: The 30-120SIP reconstructed SPECT had statistically significant improved image quality parameters compared to 30P reconstructed SPECT with and without post filtering. The images visual appearance was similar to slightly filtered 120P SPECTs. Thereby, substantial acquisition time reduction with SIPs seems possible without image quality degradation.

The importance of grade 2 ischemic mitral regurgitation in coronary artery bypass grafting

OBJECTIVE

To study if grade 2 ischemic mitral regurgitation (MR) influences outcome after coronary artery bypass grafting (CABG).

METHODS

Results of all CABG patients with grade 2/4 ischemic MR operated during 1995--1998 (n = 89) were compared with all CABG patients without MR (n = 4709) during the same period. To further evaluate patients with grade 2 ischemic MR, a case-control study focusing on functional status was performed. Control patients without MR (n = 89) were matched for age, gender and left ventricular ejection fraction. All patients were interviewed regarding angina symptoms and functional status.

RESULTS

Survival according to Kaplan--Meier at 1 and 3 years were inferior in the MR group compared to all CABG patients (91 vs 96% and 84 vs 92%, respectively (P = 0.0017). However, MR patients were older (68 +/- 9 vs 65 +/- 9 years (mean +/- SD), P = 0.008) and had an inferior preoperative left ventricular ejection fraction (42 +/- 14 vs 58 +/- 14%, P < 0.0001). In the case-control study, New York Heart Association (NYHA) class and Higgins' risk score differed preoperatively between the MR group and controls. Neither 30-day mortality (4,5% in both groups) nor survival at 1 (91 vs 93%) and 3 years (84 vs 88%) differed significantly. NYHA class and angina class (Canadian Cardiovascular Society, CCS) improved similarly in both groups. Postoperatively, 62% of the patients in the MR group had reduced, 36% unchanged and 2% increased MR.

CONCLUSIONS

CABG on patients with grade 2 ischemic MR reduces angina pectoris and improves functional status to the same extent as in CABG patients without MR. Postoperative morbidity and mortality do not differ significantly between the groups. Grade of MR is reduced or unchanged after CABG in patients with grade 2 ischemic MR. The study supports an operative strategy where grade 2 ischemic mitral regurgitation is treated by CABG alone but the result do not exclude that there might be individual patients that would benefit from a valvular or annular procedure in combination with CABG. How these patients should be identified remains unclear.

Likelihood-ratio tests for hidden Markov models

We consider hidden Markov models as a versatile class of models for weakly dependent random phenomena. The topic of the present paper is likelihood-ratio testing for hidden Markov models, and we show that, under appropriate conditions, the standard asymptotic theory of likelihood-ratio tests is valid. Such tests are crucial in the specification of multivariate Gaussian hidden Markov models, which we use to illustrate the applicability of our general results. Finally, the methodology is illustrated by means of a real data set.