A Systematic Review of Segmentation and Classification Techniques for Lung Cancer Detection on LDCT Scan Images
Abstract
Lung cancer is the leading cause of cancer-related deaths worldwide, with late-stage diagnosis and limited treatment options being the primary reasons for this outcome.Low-dose computed tomography (LDCT) has been established as the preferred imaging technique for early-stage detection and screening, offering higher sensitivity in identifying lung nodules while minimizing radiation expo-sure.However, manual interpretation of LDCT scans is labor-intensive, prone to errors, and suffers from inter-observer variability, underscoring the need for robust computer-aided diagnosis (CAD) systems.In recent years, various seg-mentation and classification techniques have been explored and proposed for the accurate, efficient, and reliable detection of lung cancer.This paper provides a comprehensive review of traditional image processing, machine learning, and deep learning-based methods for segmentation and classification of lung nodules on LDCT images.It discusses the strengths, limitations, and comparative perfor-mance of existing approaches and also delves into emerging trends such as hybrid CAD systems, transfer learning, attention mechanisms, and real-time detection frameworks like YOLOv8.Finally, this review paper also sheds light on existing challenges like false positives, data imbalance, and interpretability issues.Fur-thermore, it envisions potential directions for future research to develop clinically viable and explainable AI-driven lung cancer detection systems.
How strong is the evidence?
Evidence Hub reads this as a systematic review. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- Quantum dots: synthesis, bioapplications, and toxicity
- A Guide to In Silico Drug Design
- Quantum Computing for Healthcare: A Review
- Automated in Silico Design of Homogeneous Catalysts
- Identification of Novel 3-Hydroxy-pyran-4-One Derivatives as Potent HIV-1 Integrase Inhibitors Using in silico Structure-Based Combinatorial Library Design Approach
- In silico structural elucidation of RNA-dependent RNA polymerase towards the identification of potential Crimean-Congo Hemorrhagic Fever Virus inhibitors
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.