Dear reader,

This May 2022 issue is full with echocardiographic papers with extensive interest in Strain applications, plus a number of very nice associated Commentaries, as well as a Letter-to-the-Editor. In addition to these Commentaries, I would like to highlight the following papers:

The first one is the paper by Dr S Kim from Yonsei University College in Seoul, S-Korea under the supervision of Dr H-J Chang, who developed a Deep Learning (DL) approach for the segmentation of the four chambers from TEE echocardiograms. The total data set included 500 patients, of which 80% was used for training, 10% for validation and 10% for testing. They also carried out an inter- and intra-observer variability analyses on 100 cases, which were used as ground-truth. They implemented three different U-NET neural networks. A representative example on the results of the automation from their paper is Fig. 3, which is presented here as Fig. 1.

Fig. 1
figure 1

Representative segmentation results of the three fully automated methods [1]

Full size image

The overall performance of the 3 DL methods was found to be excellent (dice similarity coefficient from 0.91 to 0.95), except for the left ventricular wall area in the parasternal short axis view. The manual annotations were associated with some degree of inter-observer variabilities. Overall, the authors concluded that the three current prominent DL-based fully automated methods are able to reliably perform four-chamber segmentation and quantification of clinical indices.

A second paper that I would like to highlight is the paper on the modern atlas of invasive angiographic views by Drs R Rigatelli, F Gianese and M Zuin from Rovigo General Hospital and University of Ferrara in Italy. The training and recognition of the various X-ray angiographic views for diagnostic and PCI cases remains a very important educational trajectory for interventional cardiologists, as well as researchers and technicians / nurses in this field. The goal of this work is to direct the attention to new and previously under-used projections. Figure 2 below is Fig. 5 from their publication.

Fig. 2
figure 2

Angiographic views for left coronary artery. Right panels refer to angiographic appearance, while left panels present a cartoon for the same view [2]

Full size image

I do hope that you enjoy these highlighted papers plus all the other selected manuscripts in this May 2022 issue of the International Journal of Cardiovascular Imaging.


Johan HC Reiber, PhD

Editor-in-chief

e-mail: J.H.C.Reiber@lumc.nl