Inicio  /  Information  /  Vol: 13 Par: 10 (2022)  /  Artículo
ARTÍCULO
TITULO

Multi-Organ Segmentation Using a Low-Resource Architecture

Valentin Ogrean and Remus Brad    

Resumen

Since their inception, deep-learning architectures have shown promising results for automatic segmentation. However, despite the technical advances introduced by fully convolutional networks, generative adversarial networks or recurrent neural networks, and their usage in hybrid architectures, automatic segmentation in the medical field is still not used at scale. One main reason is related to data scarcity and quality, which in turn generates a lack of annotated data that hinder the generalization of the models. The second main issue refers to challenges in training deep models. This process uses large amounts of GPU memory (that might exceed current hardware limitations) and requires high training times. In this article, we want to prove that despite these issues, good results can be obtained even when using a lower resource architecture, thus opening the way for more researchers to employ and use deep neural networks. In achieving the multi-organ segmentation, we are employing modern pre-processing techniques, a smart model design and fusion between several models trained on the same dataset. Our architecture is compared against state-of-the-art methods employed in a publicly available challenge and the notable results prove the effectiveness of our method.

 Artículos similares

       
 
Nataliia Vodolazskaya     Pág. 47 - 54
The author considers questions of management by human resources as one of the primary functions of management in the banking sphere. It is specified that the basis of the management concept of the personnel structure of an organisation is the increasing ... ver más

 
Nadia Shmygol     Pág. 47 - 54
This article deals with the prospects and trends of crop production development in Ukraine, as well as the methods and ways of supporting this industry by the state.According to the article, the primary objective of the state is to create conditions thro... ver más

 
Enrique Fernández Escalante, Jon San Sebastián Sauto and Rodrigo Calero Gil    
In this article, the authors will support Managed Aquifer Recharge (MAR) as a tool to combat Climate Change (CC) adverse impacts on the basis of real sites, indicators, and specific cases located Spain. MAR has been used in Spain in combination with othe... ver más
Revista: Water

 
Yaru Guo, Tian-Chyi Jim Yeh and Yonghong Hao    
Karst aquifers are prominent sources of water worldwide; they store large amounts of water and are known for their beautiful springs. However, extensive groundwater development and climate variation has resulted in a decline in the flow of most karst spr... ver más
Revista: Water

 
Emilio Grande, Ate Visser, Pamela Beitz and Jean Moran    
Water bodies in the East Bay Regional Park District (EBRPD), California, United States, provide aesthetic value and critical ecosystem services, but are often adversely affected by the activities and infrastructure of the intensely urban environment that... ver más
Revista: Water