Towards Building a Computerized System for Modelling Advanced HCC Tumors, in Order to Assist Their Minimum Invasive Surgical Treatment

Mitrea, Delia; Mariţa, Tiberiu; Vancea, Flaviu; Nedevschi, Sergiu; Mitrea, Paulina; Neamt, Gabriel Mihai; Timoftei, Sanda; Florian, Vlad; Radu, Corina; Socaciu, Mihai; Ştefănescu, Horia; Hajjar, Nadim Al

doi:10.1007/978-3-030-55061-5_25

Cited by 1 publication

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ERFNet CNN architecture with an IoU loss function led to an IoU of 70%, which was superior to that provided by the EDANet architecture. The DeepLabV3 CNN architecture with a ResNet-101 backbone [ 38 ] provided an IoU of 73.20% in the first case when only the original, unprocessed images were provided at the entrances [ 36 ]. The U-Net architecture led to an IoU near 70% as well.…”

Section: Resultsmentioning

confidence: 99%

“…Furthermore, the computerized system is able to highlight the most important blood vessels that possibly intersect a tumor, e.g., the veins from the portal vein and from the lower cavity system, and also some arteries. The IF system is designed for the robotic-assisted targeted treatment of HCC and has the following components [ 36 ]: The segmentation module, performing the segmentation (detection and spatial delimitation) of the liver, HCC tumor, and blood vessels using specific methods, such as clustering, region growing, and convolutional neural networks (CNN); this module receives CT images acquired before surgery. …”

Section: Methodsmentioning

confidence: 99%

“…In order to perform HCC fully automated segmentation, both traditional and deep learning techniques were experimented with, as described below: Traditional methods: In order to achieve HCC segmentation through conventional methods, the fast and robust fuzzy-C-means clustering (FRFCM) technique [ 36 ] was adopted. FRFCM assumed a preprocessing phase of morphological reconstruction, and then a fuzzy-C-means clustering algorithm was employed, modified in order to obtain speed improvement.…”

Section: Methodsmentioning

confidence: 99%

Section: Computerized System For 3d Reconstruction Image Fusion and Hcc Detectionmentioning

confidence: 99%

See 3 more Smart Citations

Integration of Real-Time Image Fusion in the Robotic-Assisted Treatment of Hepatocellular Carcinoma

Radu

Fisher

Mitrea

et al. 2020

Biology

Self Cite

View full text Add to dashboard Cite

Hepatocellular carcinoma (HCC) is one of the leading causes of cancer-related deaths worldwide, with its mortality rate correlated with the tumor staging; i.e., early detection and treatment are important factors for the survival rate of patients. This paper presents the development of a novel visualization and detection system for HCC, which is a composing module of a robotic system for the targeted treatment of HCC. The system has two modules, one for the tumor visualization that uses image fusion (IF) between computerized tomography (CT) obtained preoperatively and real-time ultrasound (US), and the second module for HCC automatic detection from CT images. Convolutional neural networks (CNN) are used for the tumor segmentation which were trained using 152 contrast-enhanced CT images. Probabilistic maps are shown as well as 3D representation of HCC within the liver tissue. The development of the visualization and detection system represents a milestone in testing the feasibility of a novel robotic system in the targeted treatment of HCC. Further optimizations are planned for the tumor visualization and detection system with the aim of introducing more relevant functions and increase its accuracy.

show abstract

Section: Resultsmentioning

confidence: 99%