What does this research mean for the field?

The RV-UNet deep learning model outperforms existing advanced techniques for the automatic segmentation of liver tumors from abdominal CT scans, achieving a Dice Similarity Coefficient of 88.96%. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This research aims to enhance the automatic segmentation of liver tumors from CT images using a deep learning model.

July 27, 2026Discover Artificial IntelligenceOpen Access

Automatic segmentation of liver tumors from computed tomographic images using hybrid deep learning model

View Full Paper

Ask AI

Bookmark

Authors

NMNiranjan Muchandi PKPallavi Kulkarni SSSalma S. Shahapur

Discussion

Member takes

Overview

Randomized trial demonstrates improved tumor segmentation in liver cancer using a deep learning model, suggesting better diagnostic capabilities.

Key Points

This research aims to enhance the automatic segmentation of liver tumors from CT images using a deep learning model.
Developed a hybrid deep learning model named RV-UNet for segmenting liver tumors.
Utilized the Liver Tumor Segmentation (LiTS) dataset focusing on primary hepatocellular carcinoma images.
Evaluated model performance using metrics like Dice Similarity Coefficient and Jaccard Index.
Achieved a Dice Similarity Coefficient of 88.96% for liver tumor segmentation.
Obtained a Jaccard Index of 80.59%, indicating a strong overlap with the ground truth.
Reached a Volumetric Overlap Error of 20.38%, demonstrating effective segmentation capability.

Cite This Study

Muchandi et al. (2026) studied this question.

synapsesocial.com/papers/6a6700bd40bca442e0d4aba0 https://doi.org/10.1007/s44163-026-01552-1

View Full Paper

Ask AI

Bookmark

July 27, 2026Discover Artificial IntelligenceOpen Access

Automatic segmentation of liver tumors from computed tomographic images using hybrid deep learning model

View Full Paper

Ask AI

Bookmark

Authors

NMNiranjan Muchandi PKPallavi Kulkarni SSSalma S. Shahapur

Discussion

Member takes

Overview

Randomized trial demonstrates improved tumor segmentation in liver cancer using a deep learning model, suggesting better diagnostic capabilities.

Key Points

This research aims to enhance the automatic segmentation of liver tumors from CT images using a deep learning model.
Developed a hybrid deep learning model named RV-UNet for segmenting liver tumors.
Utilized the Liver Tumor Segmentation (LiTS) dataset focusing on primary hepatocellular carcinoma images.
Evaluated model performance using metrics like Dice Similarity Coefficient and Jaccard Index.
Achieved a Dice Similarity Coefficient of 88.96% for liver tumor segmentation.
Obtained a Jaccard Index of 80.59%, indicating a strong overlap with the ground truth.
Reached a Volumetric Overlap Error of 20.38%, demonstrating effective segmentation capability.

Cite This Study

Muchandi et al. (2026) studied this question.

synapsesocial.com/papers/6a6700bd40bca442e0d4aba0 https://doi.org/10.1007/s44163-026-01552-1

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark