[Paper Review] Leveraging object detection for the identification of lung cancer

Karthick Prasad Gunasekaran|arXiv (Cornell University)|May 25, 2023

Radiomics and Machine Learning in Medical Imaging12 citations

TL;DR

The study applies YOLOv5 object detection to chest X-rays to identify lung cancer lesions, trained on a Kaggle dataset, achieving high accuracy/recall and supporting real-time detection.

ABSTRACT

Lung cancer poses a significant global public health challenge, emphasizing the importance of early detection for improved patient outcomes. Recent advancements in deep learning algorithms have shown promising results in medical image analysis. This study aims to explore the application of object detection particularly YOLOv5, an advanced object identification system, in medical imaging for lung cancer identification. To train and evaluate the algorithm, a dataset comprising chest X-rays and corresponding annotations was obtained from Kaggle. The YOLOv5 model was employed to train an algorithm capable of detecting cancerous lung lesions. The training process involved optimizing hyperparameters and utilizing augmentation techniques to enhance the model's performance. The trained YOLOv5 model exhibited exceptional proficiency in identifying lung cancer lesions, displaying high accuracy and recall rates. It successfully pinpointed malignant areas in chest radiographs, as validated by a separate test set where it outperformed previous techniques. Additionally, the YOLOv5 model demonstrated computational efficiency, enabling real-time detection and making it suitable for integration into clinical procedures. This proposed approach holds promise in assisting radiologists in the early discovery and diagnosis of lung cancer, ultimately leading to prompt treatment and improved patient outcomes.

Motivation & Objective

• Motivate early detection of lung cancer and explore deep learning for medical image analysis.
• Investigate applying an object detection model (YOLOv5) to identify cancerous lung lesions in chest radiographs.
• Train and optimize hyperparameters with data augmentation to improve performance.
• Evaluate the model on a separate test set and assess computational efficiency for clinical integration.

Proposed method

• Use YOLOv5 for lesion detection in chest X-ray images.
• Train on a Kaggle dataset with corresponding annotations.
• Optimize hyperparameters and apply augmentation to enhance robustness.
• Evaluate performance on a separate test set and compare to prior techniques.
• Assess computational efficiency to support potential real-time deployment.

Experimental results

Research questions

• RQ1 Can YOLOv5 accurately detect malignant lung lesions in chest radiographs?
• RQ2 What are the model's accuracy and recall on a held-out test set?
• RQ3 Is the approach computationally efficient enough for real-time or near-real-time clinical use?
• RQ4 How does the YOLOv5-based method compare to previous techniques in this domain?

Key findings

• The YOLOv5 model exhibited high accuracy and recall in identifying lung cancer lesions.
• It successfully pinpointed malignant areas in chest radiographs.
• Performance was validated on a separate test set and outperformed previous techniques.
• The model demonstrated computational efficiency suitable for real-time detection.
• The approach shows promise for assisting radiologists in early discovery and diagnosis.