NSCLC is said to be the most common type of lung cancer, accounting for over 80 percent of cases. It often grows and spreads more slowly than SCLC. Common subtypes include adenocarcinoma, squamous cell carcinoma, and large cell carcinoma. Researchers say SCLC, which represents about 20 percent of cases, is often associated with smoking and tends to grow and spread rapidly. Early-stage lung cancer, according to experts, often shows no symptoms, but when such symptoms appear, they can include a new cough that does not go away or changes; coughing up blood or rust-colored phlegm; shortness of breath or wheezing; persistent chest pain or pain in the shoulders, as well as unexplained weight loss and loss of appetite.
Others are constant tiredness or weakness; recurrent lung infections, such as bronchitis or pneumonia. X-rays or CT scans are usually the first step to identify abnormal spots or tumors through early diagnosis, from which small tissue sample is removed and tested in a lab to confirm cancer and determine the type. Examining phlegm under a microscope to look for cancer cells called Sputum Cytology is another test to detect lung cancer in the body. Another is a diagnosis called bronchoscopy, a thin, lighted tube inserted through the throat to look into the airways.
Treatment depends on the type, stage, and overall health of the patient. Surgery can be performed to remove the tumour and surrounding lung tissue, most commonly in early-stage NSCLC. There is also radiation therapy in which high-energy rays are used to kill cancer cells, then chemotherapy, a medication used to kill fast-growing cancer cells throughout the body through targete therapy. This therapy goes with drugs designed to target specific genetic mutations within cancer cells.
Another treatment is the immunotherapy that helps the immune system recognise and fight cancer cells. The most effective prevention of lung cancer, according to experts, is to avoid smoking and reduce exposure to environmental toxins. Also, Annual low-dose CT scans are recommended for individuals aged 50–80 with a heavy smoking history. Meanwhile, Adepoju’s research project led to the development of a tool known as LungCNET, a deep convolutional neural network designed specifically to identify lung cancer with exceptional accuracy. Research has it that lung cancer has remained the deadliest cancer globally, accounting for about 1.8 million deaths yearly.
Early diagnosis plays a major role in survival, yet traditional methods such as CT scans and biopsies can be influenced by differences in human interpretation. These inconsistencies sometimes result in delayed or incorrect diagnoses. Tackling the dreaded health issue, LungCNET was built from scratch to classify lung tissues into three categories — benign, malignant, and normal. Unlike many AI systems adapted from general image-recognition frameworks, this model was engineered solely for lung cancer detection.
It recorded an impressive 99.09 percent accuracy rate, setting a new performance standard in radiology-focused AI tools. Adepoju explained that his goal was to move beyond theory and create something practical for hospitals and clinics. According to him, late diagnosis remains one of the biggest obstacles in lung cancer treatment. He believes artificial intelligence can support earlier detection and promote consistent diagnostic decisions. It recorded an impressive 99.09% accuracy rate, setting a new performance standard in radiology-focused AI tools.
Adepoju further explained that his goal was to move beyond theory and create something practical for hospitals and clinics. According to him, late diagnosis remains one of the biggest obstacles in lung cancer treatment, but believes artificial intelligence could support earlier detection and promote consistent diagnostic decisions. To measure its performance, LungCNET was compared with well-known AI models such as ResNet50, VGG16, and InceptionV3, which are widely used in medical image analysis.
The comparison showed that LungCNET delivered superior results. In detecting malignant tumors, it achieved 100 percent precision, recall, and F1-score, meaning no cancer cases were incorrectly classified during testing. For benign tumors, which are often harder to distinguish due to similar structural features, the model achieved a 94 percent F1-score, outperforming existing alternatives. He said his motivation stemmed from observing unequal access to advanced diagnostic services, especially in regions with limited medical resources.
While many hospitals lack specialist radiologists and high-end diagnostic systems, Adepoju hopes that a reliable AI-powered tool can help reduce diagnostic errors, ease pressure on medical professionals, and improve patient care. One concern surrounding AI in healthcare is the heavy computational demand of deep learning systems. Many require powerful hardware, which can limit adoption in smaller medical facilities. LungCNET addresses this challenge through an efficient design that balances speed and accuracy. It processes a single image in 55.76 milliseconds and runs effectively on standard medical equipment, making it suitable for broader clinical use. The researcher emphasised that accessibility was as important as performance.
For him, innovation only matters if it can be applied where it is most needed. Although his thesis has already delivered promising outcomes, he plans further improvements. His next focus, according to him, includes expanding the dataset to enhance reliability across diverse patient groups, collaborating with hospitals for clinical trials, and refining the system for use in resource-constrained healthcare environments. Researchers and industry professionals have shown interest in the model’s broader potential. Its adaptable structure could support the detection of other cancers and respiratory conditions, extending its usefulness beyond lung cancer.
For many students, a Master’s thesis marks the completion of an academic requirement. For Adepoju, it represents a practical solution with life-saving potential. His work in artificial intelligence and medical imaging stands among the most encouraging developments in lung cancer screening. LungCNET’s strong accuracy, speed, and efficiency position it as a valuable tool for hospitals and cancer screening centres worldwide. Faster and more reliable diagnosis can significantly improve treatment outcomes. Adepoju believes that if artificial intelligence helps in detecting lung cancer earlier and saves even one life, then the effort has truly mattered.
