ABSTRACT
Lung cancer is a major global health concern, and accurate staging is paramount for determining optimal treatment strategies.It is a common malignant tumour disease with high clinical disability and death rates. Meanwhile, the human mind is limited in effectively handling and fully utilizing the accumulation of such enormous amounts of data. Classify lung cancer subtypes through analysis of digital pathological tissue sections and can predict the survival prognosis of NSCLC patients. AI, specifically convolutional neural networks (CNNs), has been harnessed to scrutinize vast datasets of medical images, including X-rays and CT scans.
These AI algorithms excel at not only detecting lung cancer lesions but also precisely delineating them from normal tissue. Beyond mere detection, AI can segment tumours from healthy tissue, enabling precise measurement and localization. This ability to analyse tumour characteristics, including size, location, and lymph node involvement, provides a foundation for accurate staging of lung cancer, which is traditionally categorized from stages 0 to 4. AI Detector Pro's neural network is designed to detect patterns used by GPT based AI text generation models (which make up nearly all of the current online AI content writing or rewriting tools). This software claims to be 99% accurate in detecting AI-generated content. While AI holds the promise of enhancing the accuracy and efficiency of lung cancer staging, it is imperative to emphasize that AI serves as an adjunct to healthcare professionals rather than a substitute. Ultimately, definitive diagnoses and treatment decisions must incorporate the expertise of trained medical practitioners. Striving for stringent testing, adherence to regulatory standards and on-going research is crucial to ensuring the safety and efficacy of AI-driven solutions in the domain of lung cancer diagnosis and staging.
KEYWORDS
1. Artificial intelligence and lung cancer;
2. Lung neoplasms;
3. Tumour characteristics;
4. Prediction;
5. Continuous monitoring;
INTRODUCTION
Artificial intelligence (AI) plays a key role in lung cancer screening workflow for early diagnosis. Particularly, in low-dose computed tomography for screening programs. AI further reduces radiation dose maintaining an optimal image quality. A ground breaking technology that promises to revolutionize lung cancer diagnosis and staging. This introduction provides a comprehensive exploration of the profound implications and advancements facilitated by AI in the context of lung cancer. The Rise of Artificial Intelligence: The advent of Artificial Intelligence (AI) in the medical field has brought about an era of innovation and optimism. AI systems, particularly those employing advanced machine learning models like Convolutional Neural Networks (CNNs), exhibit a remarkable ability to analyse complex medical images, such as X-rays and CT scans, with precision and speed. This capability has proven to be a game-changer in the early detection and diagnosis of lung cancer.
METHODOLOGIES OF LUNG CANCER SCREENING AND DETECTION
1. Pulmonary Nodule Detection: Computer-aided detection (CADe) tools have been commercially available since the early 2000s. The rise of deep learning and the availability of large annotated lung nodule datasets have allowed the development of new CADe tools with fewer false-positive results per examination.
2. Pulmonary Nodule Segmentation: Classical machine learning and deep- learning methods were used for pulmonary nodule segmentation allowing nodule volumetry.
3. Pulmonary Nodule Characterization: For pulmonary nodule characterization, radiomics and deep-learning approaches were used.
4. Image Reconstruction: Low-dose CT scan is the only strategy that has proven to effectively reduce mortality in lung cancer screening in high-risk patients. Despite the development of low-dose CT protocols, repeated scans can expose patients to cumulative radiation risk. To reduce radiation while maintaining accuracy, there are techniques like model-based iterative reconstruction (MBIR) and hybrid iterative reconstruction (HIR). These reconstruction algorithms are widely used to reduce image noise and artifacts but have limitations in low-dose CT scans.
5. Computer-Aided Diagnostic (CADx) Tools: Data from the National Lung Cancer Screening Trial (NLST) allowed the development of several CADx tools for diagnosing lung cancer on chest computed tomography.
6. Virtual Biopsies and Treatment Response Prediction: AI has been used as a means to perform virtual biopsies and to predict response to treatment or survival.
7. Image Processing: AI is effective in processing large datasets, providing accurate and efficient results for cancer detection. However, implementing these systems on a large scale presents several challenges, such as the capture of images, preparation of images, segmentation, and information management.
8. Automatic Segmentation: Two AI-based approaches are available to perform this task: the first one is represented by automatic segmentation with a consequent assessment of the lesion size, volume, and densitometry features; the second consists of segmentation first, followed by radiomic features extraction to characterize the whole abnormalities providing the so- called “virtual biopsy”.
CONCLUSION
The use of artificial intelligence (AI), specifically deep learning and radiomics, has shown promising results in improving the detection and staging of lung cancer. These AI models have demonstrated potential in enhancing diagnostic accuracy, which is crucial for effective treatment planning 1 . Furthermore, AI has been successful in identifying subtle patterns in early scans that were previously overlooked by human radiologists. This advancement could potentially lead to earlier detection of lung cancer, thereby improving survival rates. However, it’s important to note that while these results are encouraging, further research and validation are needed before these AI models can be fully integrated into clinical practice.
REFERENCE
1. Benzekry S. Artificial intelligence and mechanistic modeling for clinical decision making in oncology. Clin Pharmacol Ther 2020;108:471–86.
2. Thai AA, Solomon BJ, Sequist LV, Gainor JF, Heist RS. Lung cancer. Lancet 2021;398:535–54.
3. Bray, F. et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin. 68, 394–424. https://doi.org/10.3322/caac.21492 (2018).
4. LeCun Y, Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444. https://doi.org/10.1038/nature14539 (2015).
5. Manser, R. et al. Screening for lung cancer. Cochrane Database Syst Rev CD001991. https://doi.org/10.1002/14651858.CD001991. pub3 (2013).
6. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8946647/ official government website.
