AI And Diagnosis Of Lung Cancer

In recent years, AI has gradually entered the medical field. Artificial intelligence continues to break through the sensitivity and specificity of machine-assisted diagnosis at the 'digital' level, and exerts its value in multiple scenarios. However, many products are still far from large-scale clinical applications, and it is not easy to obtain the approval of clinicians. For the big names in the medical profession, whether the ability of AI really reflects the value clinically is the key point.

From February 21 to 24, 2019, the 27th Asian Thoracic and Cardiovascular Surgery Annual Conference (ASCVTS) was held in Chennai, India. Thoracic and Cardiovascular Surgery scholars from all over the world participated The event, in-depth exchanges and discussions on the latest progress, clinical experience and basic research in the field of thoracic and cardiovascular surgery. Among them, the value of artificial intelligence in clinical diagnosis has also become one of the important issues. The discussion also affirmed the value of artificial intelligence diagnostic system in the early diagnosis of pulmonary nodules.

Lung cancer is the most common malignant tumor in the world, with morbidity and mortality ranking first in malignant tumors, and has become a recognized killer of human health. The prognosis of lung cancer is closely related to the clinical stage. Due to the late appearance of symptoms and signs, most patients have metastasized at the first visit, and the 5-year survival rate is only 16% due to the missed optimal surgery time. The 5-year survival rate of stage patients can reach more than 70-90%. If it can be found early in the onset, it can effectively improve the prognosis of lung cancer patients.

Therefore, the establishment of a reasonable and effective screening program and simple and effective screening of high-risk groups are the focus of clinical work. Clinical staff are constantly looking for newer and more sensitive imaging techniques suitable for lung cancer screening.

In August 2002, the United States Lung Cancer Screening Trial Group (NLST) led the launch of a randomized controlled clinical trial comparing lung cancer screening with low-dose spiral CT (LDCT) and ordinary chest X-rays, which is by far the most authoritative in the world , The lung cancer screening study with the highest level of evidence.

However, the NLST study also found that only 0.6-2.7% of patients with lung nodules found through the clinical screening practice of low-dose spiral CT were eventually diagnosed with lung cancer. This also means that how to improve the early diagnosis rate of lung cancer in lung nodules under the circumstances that CT nodules are found to be feasible at the early stage of CT screening is the primary proposition facing clinicians today.

Save your time!
We can take care of your essay

• Proper editing and formatting
• Free revision, title page, and bibliography
• Flexible prices and money-back guarantee

Place Order

In the traditional method of early diagnosis of pulmonary nodules, simple imaging data requires long-term radiological follow-up of the patient to observe the imaging morphological changes, resulting in potential radiation damage; invasive diagnostic operations, even direct surgical treatment, give patients Cause physical and psychological damage. However, the rapid development of novel liquid biopsy and artificial intelligence diagnosis has brought revolutionary dawn to the early diagnosis of pulmonary nodules.

'Biomarker + AI' diagnostic mode is the key

It has realized the use of AI medical image analysis to assist doctors in screening for esophageal cancer, lung nodules, diabetic retinopathy, colorectal tumors, breast cancer and other diseases, and the use of AI assisted diagnosis engine to assist doctors in identifying and predicting the risk of more than 700 diseases . In the identification of lung nodules, we can use computer vision and deep learning technology to assist doctors in reading through artificial intelligence medical image analysis capabilities, can accurately locate tiny lung nodules more than 3mm, and determine the sensitivity of their benign and malignant It reaches 85%, and the specificity is as high as 90%.

How to further assist in improving the diagnostic efficiency of artificial intelligence? Today's liquid biopsy technology can detect trace biological markers released into the blood by early tumors, such as microRNA, circulating tumor DNA, circulating tumor cells, etc. Professor Zhang Lanjun believes that the combination of liquid biomarker biopsy and artificial intelligence technology will inevitably improve the accuracy of early lung nodule diagnosis. As expected, in the ABC model of compound clinical features (Clinic), biomarkers (Biomarkers) and artificial intelligence results (AI), the area under the curve value (a statistical method for evaluating the effectiveness of diagnostic tools, the closer the value is to 1, indicating the diagnosis The higher the efficiency) up to 0.955. In the subsequent verification group, the ABC model also showed higher area value and sensitivity under the curve than other models, which means that the diagnostic model of biological marker + AI can be more accurate.

Today, biomedical imaging (Biomedical imaging) technology is not yet mature, the construction of a multi-modal 'biological markers + AI' mathematical model, is the ideal mode of artificial intelligence for clinical pulmonary nodule diagnosis at this stage.

Artificial intelligence diagnostic technology must have a qualitative leap

Artificial intelligence is a huge change to the classification and management of traditional imaging data. It can process tens of thousands of image information quickly and simultaneously, which will greatly save the physical and mental effort of high-quality professional imaging doctors; based on the latest deep convolutional neural network The algorithm's Tencent search can directly convert or use machine deep learning in different levels of hospitals, reducing the sample size required for different hospitals to convert machine deep learning; with the development of biological imaging technology, artificial intelligence diagnostic technology will certainly occur Great progress.

The Asian Society of Thoracic and Cardiovascular Surgery was established in 1993. It is the largest academic group of cardiovascular and thoracic surgery in Asia. It is the same as the American Society of Thoracic Surgeons and the European Society of Thoracic Surgeons, together forming the world's three major thoracic surgery academic events. The invitation of Prof. Zhang Lanjun ’s team to attend the conference and make a speech at the conference also means that this forward-looking research conclusion on artificial intelligence diagnostic systems has been recognized by international peers, which not only helps promote the development of disciplines and foreign exchanges, but also Promote the application of artificial intelligence new technologies in clinical practice.

AI medicine is a brand-new 'medical-industry integration' field. Driven by big data, artificial intelligence, cloud computing and other technologies, the growth of the 'AI medical assistant' has made the medical community full of expectations. The cross-border integration of medical and technology is also continuously promoting the application of artificial intelligence medical imaging, effectively connecting the three parts of AI, application scenarios and value, and ultimately serving clinical and benefiting the people....