Warning: Undefined array key "https://lungcancersymptomsx.com/diagnosing-lung-cancer.html" in /home/atozdwxp/lungcancersymptomsx.com/wp-content/plugins/wpa-seo-auto-linker/wpa-seo-auto-linker.php on line 192
Warning: Undefined array key "https://lungcancersymptomsx.com/the-lung-cancer.html" in /home/atozdwxp/lungcancersymptomsx.com/wp-content/plugins/wpa-seo-auto-linker/wpa-seo-auto-linker.php on line 192
Lung Cancer is one of the deadliest cancers worldwide. It results in 1.7Mn deaths globally every year, according to World Health Organization. Alphabet’s Google team has reported a new research that utilizes artificial intelligence (AI) to predict risks of lung cancer. Google AI researchers in collaboration with Northwestern Medicine created an AI model to detect lung cancer from screening tests better than human radiologists having an average of eight years of experience. The detailed in research was published in Nature Medicine.
According to US study, artificial intelligence is better than specialist doctors for diagnosing lung cancer. “The AI system uses 3D volumetric deep learning to analyze the full anatomy on chest CT scans, as well as patches based on object detection techniques that identify regions with malignant lesions,” Google technical lead Shravya Shetty and product manager Daniel Tse said in a blog post today.
The model used more than 42000 chest CT screening images taken from nearly 150000 patients of whom 578 developed cancer within a year. The results were then validated with data sets from Northwestern Medicine. The new AI was able to detect lung cancers as great as a trained radiologist and achieved more than 94% accurate results.
The new model will be able to generate 3D volume scans and account for past scans of the lung cancer patients. With this new AI model, Google can generate overall lung cancer malignancy prediction and identify subtle malignant tissue which are often difficult to see. The AI also helps to reveal the growth rate of suspicious tissue.
The new model needs additional clinical research before it can be deployed. According to Google, the initial results are encouraging. Google hopes that this AI model might make early detection more accessible.
The information shared in this blog is for educational purposes only.