A Multiple Layer U-Net, U<sup>n</sup>-Net, for Liver and Liver Tumor Segmentation in CT

Tran, Song-Toan; Cheng, Ching-Hwa; Liu, Don‐Gey

doi:10.1109/access.2020.3047861

Cited by 67 publications

(13 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using a U-Net variation, attention mechanism, and Skip Connections, AHCNet demonstrated global Dice values of 0.734 for tumor segmentation [27]. Un-Net, which uses an n-fold architecture, has a Dice score of 0.7369 for tumor segmentation [28]. In a study of Ayalew, the Dice score was 0.63 ± 0.02 if the tumors were directly segmented from abdominal CT images, and 0.74 ± 0.02 if tumor segmentation was executed after liver segmentation [5].…”

Section: Discussionmentioning

confidence: 99%

Deep Learning Model With Convolutional Neural Network for Detecting and Segmenting Hepatocellular Carcinoma in CT: A Preliminary Study

Duc¹,

Chien²,

Huyen³

et al. 2022

Cureus

View full text Add to dashboard Cite

IntroductionHepatocellular carcinoma (HCC) is one of the most common malignancies in the world. Early detection and accurate diagnosis of HCC play an important role in patient management. This study aimed to develop a convolutional neural network-based model to identify and segment HCC lesions utilizing dynamic contrast agent-enhanced computed tomography (CT). MethodsThis retrospective study used CT image sets of histopathology-confirmed hepatocellular carcinoma over three phases (arterial, venous, and delayed). The proposed convolutional neural network (CNN) segmentation method was based on the U-Net architecture and trained using the domain adaptation technique. The proposed method was evaluated using 115 liver masses of 110 patients (87 men and 23 women; mean age, 56.9 years ± 11.9 (SD); mean mass size, 6.0 cm ± 3.6). The sensitivity for identifying HCC of the model and Dice score for segmentation of liver masses between radiologists and the CNN model were calculated for the test set. ResultsThe sensitivity for HCC identification of the model was 100%. The median Dice score for HCC segmenting between radiologists and the CNN model was 0.81 for the test set. ConclusionDeep learning with CNN had high performance in the identification and segmentation of HCC on dynamic CT.

show abstract

Section: Discussionmentioning

confidence: 99%

Deep Learning Model With Convolutional Neural Network for Detecting and Segmenting Hepatocellular Carcinoma in CT: A Preliminary Study

Duc¹,

Chien²,

Huyen³

et al. 2022

Cureus

View full text Add to dashboard Cite

show abstract

“…Moreover, by looking into the recent work for liver tumors, S.-T. Tran et al [38] proposed an improved U-NET based method by employing the architecture of dense and dilated convolution and achieved a very significant improvement regarding the Dice score. Similarly, H. Seo et al [39] also proposed an improved U-NET that was based on segmenting both the liver and tumors.…”

Section: Comparison With State-of-the-art Approachesmentioning

confidence: 99%

A Residual-Learning-Based Multi-Scale Parallel-Convolutions- Assisted Efficient CAD System for Liver Tumor Detection

et al. 2021

View full text Add to dashboard Cite

Smart multimedia-based medical analytics and decision-making systems are of prime importance in the healthcare sector. Liver cancer is commonly stated to be the sixth most widely diagnosed cancer and requires an early diagnosis to help with treatment planning. Liver tumors have similar intensity levels and contrast as compared to neighboring tissues. Similarly, irregular tumor shapes are another major issue that depends on the cancer stage and tumor type. Generally, liver tumor segmentation comprises two steps: the first one involves liver identification, and the second stage involves tumor segmentation. This research work performed tumor segmentation directly from a CT scan, which tends to be more difficult and important. We propose an efficient algorithm that employs multi-scale parallel convolution blocks (MPCs) and Res blocks based on residual learning. The fundamental idea of utilizing multi-scale parallel convolutions of varying filter sizes in MPCs is to extract multi-scale features for different tumor sizes. Moreover, the utilization of residual connections and residual blocks helps to extract rich features with a reduced number of parameters. Moreover, the proposed work requires no post-processing techniques to refine the segmentation. The proposed work was evaluated using the 3DIRCADb dataset and achieved a Dice score of 77.15% and 93% accuracy.

show abstract

“…F irst, we experiment with two approaches trained on fully annotated 3D data. Fully Supervised (FS)-Same Domain refers to the scenario where the training and testing data come from the same benchmark dataset Results from both state-of-the-art methods [2,10,11,23] and 3D UNets trained by us are reported. On the other hand, FS-Different Domain aims to evaluate the generalizability of FS approaches when training and testing data come from different domains.…”

Section: Baseline Comparisonmentioning

confidence: 99%

Sli2Vol: Annotate a 3D Volume from a Single Slice with Self-Supervised Learning

Yeung¹,

Namburete²,

Xie³

2021

Preprint

View full text Add to dashboard Cite

The objective of this work is to segment any arbitrary structures of interest (SOI) in 3D volumes by only annotating a single slice, (i.e. semi-automatic 3D segmentation). We show that high accuracy can be achieved by simply propagating the 2D slice segmentation with an affinity matrix between consecutive slices, which can be learnt in a selfsupervised manner, namely slice reconstruction. Specifically, we compare the proposed framework, termed as Sli2Vol, with supervised approaches and two other unsupervised/ self-supervised slice registration approaches, on 8 public datasets (both CT and MRI scans), spanning 9 different SOIs. Without any parameter-tuning, the same model achieves superior performance with Dice scores (0-100 scale) of over 80 for most of the benchmarks, including the ones that are unseen during training. Our results show generalizability of the proposed approach across data from different machines and with different SOIs: a major use case of semi-automatic segmentation methods where fully supervised approaches would normally struggle. The source code will be made publicly available at https://github.com/pakheiyeung/Sli2Vol.

show abstract

A Multiple Layer U-Net, Uⁿ-Net, for Liver and Liver Tumor Segmentation in CT

Cited by 67 publications

References 36 publications

Deep Learning Model With Convolutional Neural Network for Detecting and Segmenting Hepatocellular Carcinoma in CT: A Preliminary Study

Deep Learning Model With Convolutional Neural Network for Detecting and Segmenting Hepatocellular Carcinoma in CT: A Preliminary Study

A Residual-Learning-Based Multi-Scale Parallel-Convolutions- Assisted Efficient CAD System for Liver Tumor Detection

Sli2Vol: Annotate a 3D Volume from a Single Slice with Self-Supervised Learning

Contact Info

Product

Resources

About

A Multiple Layer U-Net, Un-Net, for Liver and Liver Tumor Segmentation in CT

Cited by 67 publications

References 36 publications

Deep Learning Model With Convolutional Neural Network for Detecting and Segmenting Hepatocellular Carcinoma in CT: A Preliminary Study

Deep Learning Model With Convolutional Neural Network for Detecting and Segmenting Hepatocellular Carcinoma in CT: A Preliminary Study

A Residual-Learning-Based Multi-Scale Parallel-Convolutions- Assisted Efficient CAD System for Liver Tumor Detection

Sli2Vol: Annotate a 3D Volume from a Single Slice with Self-Supervised Learning

Contact Info

Product

Resources

About

A Multiple Layer U-Net, Uⁿ-Net, for Liver and Liver Tumor Segmentation in CT