Artificial intelligence technology helps detect and diagnose lung cancer.
Artificial intelligence (AI) is revolutionizing the field of healthcare, particularly in the diagnosis of cancer. One of the most notable applications of AI is its ability to detect lung cancer early and accurately.
AI is being widely applied in the healthcare field to improve diagnostic efficiency. A clear example is the emergence of a new digital pathology platform, leveraging AI's image analysis capabilities to support accurate and rapid lung cancer diagnosis. This is a significant step forward, opening up new prospects for effective treatment of this dangerous disease.
In a recent study, scientists at the Faculty of Medicine and University Hospital Cologne (Germany), led by Doctor Yuri Tolkach and Professor Dr. Reinhard Büttner, have created a highly effective tool to aid in the diagnosis of lung cancer.
.jpg)
The research team has successfully developed a digital pathology platform that uses AI to automatically analyze lung tissue samples. This tool not only increases the accuracy of the diagnostic process but also saves time and effort for doctors.
Lung cancer is one of the most dangerous silent killers, claiming the lives of millions of people worldwide every year. In particular, non-small cell lung cancer (NSCLC), which accounts for over 80% of all lung cancer cases, is the leading cause of death from carcinoma and poses a serious threat to public health.
Accurate diagnosis is crucial for effective cancer treatment. Pathology, particularly in tissue sample analysis, plays a vital role in this process. Thanks to advancements in digital technology and artificial intelligence, pathologists today can analyze samples more quickly and accurately, enabling physicians to develop personalized and appropriate treatment plans for each patient.
Dr. Tolkach stated, “The application of new AI tools not only helps us diagnose diseases more accurately but also ushers in a new era in cancer treatment. By providing detailed information about each patient's condition, we can make smarter and more personalized treatment decisions, increasing the likelihood of treatment success.”
Scientists trained the AI on a massive dataset of the highest quality currently available. As a result, the AI is able to quickly and accurately analyze biopsy samples, clearly distinguishing between 11 types of tumors and benign tissues at the pixel level.
In a study published in the prestigious journal Cell Reports Medicine, the research team demonstrated that their AI tool can accurately classify different types of non-small cell lung cancer. This was confirmed by comparing the model's results with real-world data from various hospitals.
Next, the research team identified four measurable biomarkers in tissue samples that could more accurately predict disease progression and patient lifespan. Additionally, to advance global lung cancer research, the team publicly shared three large datasets, facilitating the development of new algorithms.
The research team believes this platform will become a useful tool in accurately diagnosing diseases, predicting disease progression, and even supporting future treatment decisions. To confirm the platform's feasibility, the team is collaborating with five leading pathology research institutes in Germany, Austria, and Japan to conduct large-scale validation studies.
In addition to automating tasks in healthcare and medical image analysis, AI is gradually penetrating patients' lives. AI tools like ChatGPT are increasingly being used by people to search for health information, and even for self-diagnosis.
Studies have shown that ChatGPT has the potential to provide useful medical information, support mental health assessments, counseling, medication management, and patient education. However, the effectiveness of ChatGPT still has limitations, particularly in diagnosing health conditions in children, with accuracy rates as low as 17% according to some studies.
Although large language models such as Llama-2-chat, Vicuna, Medllama2, Bard/Gemini, Claude, ChatGPT-3.5, and ChatGPT-4 have made significant progress, their application to the diagnosis of genetic diseases remains limited. The complexity of genetic diseases demands more specialized diagnostic tools.
