Abstract:The right ventricular assessment is crucial to heart disease diagnosis. Unfortunately, its segmentation is quite challenging due to its intricate shape, ill-defined thin edges, large variability among patients, and pathologies. Besides, it is a very laborious and time-consuming task to be done manually. Therefore, automated segmentation techniques are very suitable to reduce the strain on the expert. Here, it is attempted to review the taxonomy of the current RV segmentation approaches adopted to handle the af… Show more
“…To tackle the challenges of Right Ventricle segmentation, various works were proposed employing different segmentation techniques [8]. As reviewed in [6] and [9], the most recently proposed methods are more oriented to use deep learning techniques. In fact, Good progress in the medical imaging field has been reached thanks to the introduction of Artificial Intelligence technologies that became a popular approach for detection and segmentation problems due to their powerful feature representation [10].…”
Section: Related Workmentioning
confidence: 99%
“…To analyze the RV function, radiologists have to delineate its boundaries over the entire slices which is a time-consuming task. For this reason, automatic segmentation of this cardiac cavity has been studied using multiple approaches [6]. Despite the inspiring results obtained in the End Diastolic (ED) phase, lower results were detected in the End Systolic (ES) phase for many proposed approaches [7].…”
Segmentation is an important task held to assess and analyze the heart's Right Ventricular (RV) function using CMR images. It has a major role in extracting important information which helps radiologists and doctors with the proper diagnosis. Several approaches have been proposed for RV segmentation showing great results in the End Diastolic (ED) phase but lower results in the End Systolic (ES) phase explained by the great variability of the complex shape of this chamber and its thin borders especially in the last phase. In this work, we aim to analyze the effect of short-axis slices from ED to ES phases on the segmentation task using a U-Net based architecture and two different datasets. Thus, a total of six models were trained to monitor the segmentation behavior.
“…To tackle the challenges of Right Ventricle segmentation, various works were proposed employing different segmentation techniques [8]. As reviewed in [6] and [9], the most recently proposed methods are more oriented to use deep learning techniques. In fact, Good progress in the medical imaging field has been reached thanks to the introduction of Artificial Intelligence technologies that became a popular approach for detection and segmentation problems due to their powerful feature representation [10].…”
Section: Related Workmentioning
confidence: 99%
“…To analyze the RV function, radiologists have to delineate its boundaries over the entire slices which is a time-consuming task. For this reason, automatic segmentation of this cardiac cavity has been studied using multiple approaches [6]. Despite the inspiring results obtained in the End Diastolic (ED) phase, lower results were detected in the End Systolic (ES) phase for many proposed approaches [7].…”
Segmentation is an important task held to assess and analyze the heart's Right Ventricular (RV) function using CMR images. It has a major role in extracting important information which helps radiologists and doctors with the proper diagnosis. Several approaches have been proposed for RV segmentation showing great results in the End Diastolic (ED) phase but lower results in the End Systolic (ES) phase explained by the great variability of the complex shape of this chamber and its thin borders especially in the last phase. In this work, we aim to analyze the effect of short-axis slices from ED to ES phases on the segmentation task using a U-Net based architecture and two different datasets. Thus, a total of six models were trained to monitor the segmentation behavior.
“…Due to the complexity of the physiological geometric structure of the heart, artifacts in the imaging process caused by blood flow, the uneven image grey distribution, and the blurred target boundary caused by the interference of papillary muscles, it is especially difficult to image segments of heart organs [1]. Moreover, the non‐uniformity and anatomical variability of imaging, as well as the inherent geometric and dynamic complexity of the heart, bring great challenges to accurate segmentation of cardiac organs and tissues based on MRI images [2].…”
For semantic segmentation of cardiac magnetic resonance image (MRI) with low recognition and high background noise, a fusion‐attention Swin Transformer is proposed based on cognitive science and deep learning methods. It has a U‐shaped symmetric encoding–decoding structure with an attention‐based skip connection. The encoder realizes self‐attention for deep feature representation and the decoder up‐samples global features to the corresponding input resolution for pixel‐level segmentation. By introducing a skip connection between the encoder and decoder based on fusion attention, the remote interaction of global information is realized, and the attention to local features and specific channels is enhanced. A public ACDC cardiac MRI image dataset is used for experiments. The segmentation of the left ventricle, right ventricle, and myocardial layer is realized. The method performs well on a small sample dataset, for example, the pixel accuracy obtained by the proposed model is 93.68%, the Dice coefficient is 92.28%, and HD coefficient is 11.18. Compared with the state‐of‐the‐art models, the segmentation precision has been significantly improved, especially for the low recognition and heavily occluded targets.
“…This progress requires acquisition based on various slice planes. The main slice planes used for the right ventricle (RV) [9], which is the object of interest in this paper, are: the long axis 4 cavities slice and the short axis slice [10], [11].…”
Section: Introductionmentioning
confidence: 99%
“…The main slice planes used for the RV, 10 which is the object of interest in this paper, are: the long axis 4 cavities slice and the short axis slice. 5,11 Figure 1 presents an example.…”
This paper proposes an adapted ventricular segmentation method based on topological watershed transform. Segmentation will allow spatio-temporal modeling of trajectories of the different points belonging to the borders of the ventricle using a harmonic motion model that is able to describe such motion over the entire cardiac cycle. In addition, extraction of the adopted canonical state vector and the corresponding state equations guarantees an optimal efficacy and a gradual transition from order n to order n+1. To validate the proposed approach, an intern-image base was used. Our results show a promising ability to discern whether subjects are healthy or pathological with an 80% success rate.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.