From CNNs to SAM: A Survey of Deep Learning Techniques for Liver Tumor Segmentation in CT Images

Accurate liver tumor segmentation is a critical component of clinical assessment, forming the basis for treatment planning, therapy response monitoring, prognostic assessment, and the delivery of precision medicine. However, in real-world clinical practice, this task remains particularly challenging. The intrinsic diversity of liver tumors —manifested in variations of shape, texture, size, and location—combined with the similarity of neighboring organs, indistinct tumor boundaries, and inconsistencies in image acquisition conditions, makes accurate liver lesion segmentation particularly difficult. In clinical practice, traditional segmentation methods are often used due to their interpretability and lower computational requirements. These approaches are labor-intensive and time-consuming, especially when dealing with 3D medical images, making them impractical for large-scale or real-time applications. In recent years, deep learning (DL) models have gained considerable attention for automating liver lesion segmentation. In this comprehensive review, we analyze over 100 research papers focused on DL-based segmentation of liver tumors from computed tomography (CT) images. This survey examines these studies across multiple dimensions, including input data, model architecture, and evaluation metrics. By exploring both pioneering contributions and emerging trends, we highlight the impact of various methodological choices and address the associated limitations of current approaches.

• Publication year

  2025

• Venue

  IEEE Access

• Publication date

  2025-11-10

• Fields of study

  Medicine, Computer Science

• Identifiers
  DOI 10.1109/access.2025.3631322PMID 41550585PMCID 12807525
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• Liver margin segmentation in abdominal CT images using U-Net and Detectron2: annotated dataset for deep learning models

  2025cited by this paper
• Automatic computed tomography image segmentation method for liver tumor based on a modified tokenized multilayer perceptron and attention mechanism

  2025cited by this paper
• RIS-UNet: A Multi-Level Hierarchical Framework for Liver Tumor Segmentation in CT Images

  2025cited by this paper
• T-MPEDNet: Unveiling the Synergy of Transformer-aware Multiscale Progressive Encoder-Decoder Network with Feature Recalibration for Tumor and Liver Segmentation

  2025cited by this paper
• SPARS: Self-Play Adversarial Reinforcement Learning for Segmentation of Liver Tumours

  2025cited by this paper
• Automatic Liver Tumor Classification Using UNet70 a Deep Learning Model.

  2025cited by this paper
• Cancer statistics, 2025

  2025cited by this paper
• Improved SwinUNet with fusion transformer and large kernel convolutional attention for liver and tumor segmentation in CT images

  2025cited by this paper
• Volumetric medical image segmentation via fully 3D adaptation of Segment Anything Model

  2025cited by this paper
• HANS-Net: Hyperbolic Convolution and Adaptive Temporal Attention for Accurate and Generalizable Liver and Tumor Segmentation in CT Imaging

  2025cited by this paper
• MA-SAM: Modality-agnostic SAM adaptation for 3D medical image segmentation

  2024cited by this paper
• Challenges and solutions of deep learning-based automated liver segmentation: A systematic review

  2024cited by this paper
• Impact of tumor size on the outcomes of hepatic resection for hepatocellular carcinoma: a retrospective study

  2024cited by this paper
• Comparison of Vision Transformers and Convolutional Neural Networks in Medical Image Analysis: A Systematic Review

  2024cited by this paper
• MaskSAM: Towards Auto-prompt SAM with Mask Classification for Volumetric Medical Image Segmentation

  2024cited by this paper
• Liver tumor segmentation method combining multi-axis attention and conditional generative adversarial networks

  2024cited by this paper
• Interactive 3D Medical Image Segmentation with SAM 2

  2024cited by this paper
• CT image denoising methods for image quality improvement and radiation dose reduction

  2024cited by this paper
• Synthetic Data in Radiological Imaging: Current State and Future Outlook

  2024cited by this paper
• Semi-supervised segmentation of abdominal organs and liver tumor: uncertainty rectified curriculum labeling meets X-fuse

  2024cited by this paper
• S2DA-Net: Spatial and spectral-learning double-branch aggregation network for liver tumor segmentation in CT images

  2024cited by this paper
• Towards Generalizable Tumor Synthesis

  2024cited by this paper
• RefSAM3D: Adapting SAM with Cross-modal Reference for 3D Medical Image Segmentation

  2024cited by this paper
• Image Segmentation in Foundation Model Era: A Survey

  2024influential reference
• Is SAM 2 better than SAM in medical image segmentation?

  2024cited by this paper
• A review of deep learning approaches for multimodal image segmentation of liver cancer

  2024influential reference
• Medical Image Segmentation with SAM-generated Annotations

  2024cited by this paper
• Foundation Models for Biomedical Image Segmentation: A Survey

  2024cited by this paper
• A Systematic Review of Synthetic Data Generation Techniques Using Generative AI

  2024cited by this paper
• Generalizability of lesion detection and segmentation when ScaleNAS is trained on a large multi-organ dataset and validated in the liver.

  2024cited by this paper
• DEAP-3DSAM: Decoder Enhanced and Auto Prompt SAM for 3D Medical Image Segmentation

  2024cited by this paper
• Diffusion-Based Approaches in Medical Image Generation and Analysis

  2024cited by this paper
• Recent developments in denoising medical images using deep learning: An overview of models, techniques, and challenges.

  2024cited by this paper
• Semi-Mamba: Improving Medical Image Segmentation via Semi-Automatic Mamba Network

  2024cited by this paper
• Biomedical Image Segmentation Using Denoising Diffusion Probabilistic Models: A Comprehensive Review and Analysis

  2024cited by this paper
• Deep Learning Technique for automatic Liver and Liver Tumor Segmentation in CT Images

  2024cited by this paper
• Universal 3D CT lesion segmentation using SAM with RECIST annotation

  2024cited by this paper
• Segment Anything Model for Medical Image Segmentation: Current Applications and Future Directions

  2024cited by this paper
• GAN-Driven Liver Tumor Segmentation: Enhancing Accuracy in Biomedical Imaging

  2024cited by this paper
• Automated Segmentation of Liver Tumors from Computed Tomographic Scans

  2024cited by this paper
• Medical SAM 2: Segment medical images as video via Segment Anything Model 2

  2024cited by this paper
• LeSAM: Adapt Segment Anything Model for Medical Lesion Segmentation

  2024cited by this paper
• Trans-SAM: Transfer Segment Anything Model to medical image segmentation with Parameter-Efficient Fine-Tuning

  2024cited by this paper
• Attention Connect Network for Liver Tumor Segmentation from CT and MRI Images

  2024influential reference
• Literature survey on deep learning methods for liver segmentation from CT images: a comprehensive review

  2024cited by this paper
• Deep learning for medical image segmentation: State-of-the-art advancements and challenges

  2024cited by this paper
• Light&fast generative adversarial network for high-fidelity CT image synthesis of liver tumor

  2024cited by this paper
• S-SAM: SVD-based Fine-Tuning of Segment Anything Model for Medical Image Segmentation

  2024cited by this paper
• ASLSEG: Adapting Sam in the Loop for Semi-Supervised Liver Tumor Segmentation

  2023cited by this paper
• Dual encoding DDS-UNet liver tumour segmentation based on multi-scale deep and shallow feature fusion

  2023cited by this paper
• DHT-Net: Dynamic Hierarchical Transformer Network for Liver and Tumor Segmentation

  2023cited by this paper
• MANet: a multi-attention network for automatic liver tumor segmentation in computed tomography (CT) imaging

  2023cited by this paper
• SemiSAM: Enhancing Semi-Supervised Medical Image Segmentation via SAM-Assisted Consistency Regularization

  2023cited by this paper
• Segment Anything in Medical Images

  2023influential reference
• DA-Tran: Multiphase liver tumor segmentation with a domain-adaptive transformer network

  2023cited by this paper
• MDAU-Net: A Liver and Liver Tumor Segmentation Method Combining an Attention Mechanism and Multi-Scale Features

  2023cited by this paper
• When SAM Meets Medical Images: An Investigation of Segment Anything Model (SAM) on Multi-phase Liver Tumor Segmentation

  2023cited by this paper
• Segment Anything

  2023cited by this paper
• Iterative Semi-Supervised Learning for Abdominal Organs and Tumor Segmentation

  2023cited by this paper
• Segment anything in medical images

  2023cited by this paper
• Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey

  2023cited by this paper
• ACF-TransUNet: Attention-based Coarse-Fine Transformer U-Net for Automatic Liver Tumor Segmentation in CT Images

  2023influential reference
• Unified automated deep learning framework for segmentation and classification of liver tumors

  2023cited by this paper
• Vision-Language Models for Vision Tasks: A Survey

  2023cited by this paper
• Segment Anything Model for Medical Image Analysis: an Experimental Study

  2023cited by this paper
• Cheap Lunch for Medical Image Segmentation by Fine-tuning SAM on Few Exemplars

  2023cited by this paper
• A Review on Few-shot Learning for Medical Image Segmentation

  2023cited by this paper
• TDS-U-Net: Automatic liver and tumor separate segmentation of CT volumes using attention gates

  2023cited by this paper
• 3DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentation

  2023cited by this paper
• Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation

  2023cited by this paper
• How to Efficiently Adapt Large Segmentation Model(SAM) to Medical Images

  2023cited by this paper
• Self-Supervised Tumor Segmentation With Sim2Real Adaptation

  2023cited by this paper
• Leverage prior texture information in deep learning-based liver tumor segmentation: A plug-and-play Texture-Based Auto Pseudo Label module

  2023cited by this paper
• Comparison of survival rates as predicted by total tumor volume or tumor burden score in patients with hepatocellular carcinoma concurrent with fatty liver disease and hepatitis B virus

  2023cited by this paper
• AD-UNet: A Multi-Attention Mechanism Densely Connected U-Net for Liver Tumor Segmentation

  2023cited by this paper
• Attention Mechanisms in Medical Image Segmentation: A Survey

  2023influential reference
• All-in-SAM: from Weak Annotation to Pixel-wise Nuclei Segmentation with Prompt-based Finetuning

  2023cited by this paper
• SAM on Medical Images: A Comprehensive Study on Three Prompt Modes

  2023cited by this paper
• Polyp-SAM: transfer SAM for polyp segmentation

  2023cited by this paper
• Customized Segment Anything Model for Medical Image Segmentation

  2023cited by this paper
• SkinSAM: Empowering Skin Cancer Segmentation with Segment Anything Model

  2023cited by this paper
• Liver Tumor Segmentation From Computed Tomography Images Through Convolutional Neural Networks

  2023cited by this paper
• Prognostic Analysis on Different Tumor Sizes for 14634 Hepatocellular Carcinoma Patients

  2023cited by this paper
• Zero-Shot Performance of the Segment Anything Model (SAM) in 2D Medical Imaging: A Comprehensive Evaluation and Practical Guidelines

  2023cited by this paper
• Liver Tumor Screening and Diagnosis in CT with Pixel-Lesion-Patient Network

  2023cited by this paper
• Label-Free Liver Tumor Segmentation

  2023influential reference
• Natural language processing in radiology: Clinical applications and future directions.

  2023cited by this paper
• Learning What Not to Segment: A New Perspective on Few-Shot Segmentation

  2022cited by this paper
• Learning From Synthetic CT Images via Test-Time Training for Liver Tumor Segmentation

  2022cited by this paper
• RECISTSup: Weakly-Supervised Lesion Volume Segmentation Using RECIST Measurement

  2022cited by this paper
• Joint liver and hepatic lesion segmentation in MRI using a hybrid CNN with transformer layers

  2022cited by this paper
• Large Language Models are Zero-Shot Reasoners

  2022cited by this paper
• Weakly Supervised Liver Tumor Segmentation Based on Anchor Box and Adversarial Complementary Learning

  2022cited by this paper
• Radiation-induced liver disease: beyond DNA damage

  2022cited by this paper
• Medical Image Segmentation: A Review of Modern Architectures

  2022cited by this paper
• Automatic liver tumor segmentation on multiphase computed tomography volume using SegNet deep neural network and K‐means clustering

  2022cited by this paper
• Diffusion models in medical imaging: A comprehensive survey

  2022cited by this paper
• Semi-supervised Spatial Temporal Attention Network for Video Polyp Segmentation

  2022cited by this paper
• A Deep Learning model to segment liver metastases on CT images acquired at different time-points during chemotherapy

  2022cited by this paper
• Efficient two-step liver and tumour segmentation on abdominal CT via deep learning and a conditional random field

  2022influential reference

• No citing papers are available for this paper.