A recent report shows that Artificial Intelligence (AI) can help physicians identify cancer risk in lung nodules that are visible on CT.
According to Anil Vachani, MD, Study Senior Author and Director, Clinical Research, Interventional Pulmonology and Thoracic Oncology, Perelman School of Medicine, University of Pennsylvania, "Chest CT is such a sensitive test, you'll see a small nodule in upwards of a third to a half of cases. We've gone from a problem that was relatively uncommon to one that affects 1.6 million people in the US every year," he said.
Dr. Vachani and his team tested an AI-based computer-aided diagnosis system that is developed by Oxford, England-based Optellum Ltd. The test is to help doctors analyze lung nodules on chest CT more accurately and further.
"AI can go through very large datasets to come up with unique patterns that can't be seen through the naked eye and end up being predictive of malignancy," Dr. Vachani added.
Also Read: AI in Healthcare: The Key To The Success In The Medical Industry
The Test
There were six pulmonologists and six radiologists who used CT imaging data alone to determine the possibility of malignancy for nodules in the research. The study consisted of 300 chest CT scans of indeterminate lung nodules with a diameter of 5 to 30 mm.
The test showed that AI helped enhance the nodule malignancy assessment on chest CT and increased reader agreement on risk categorization and management recommendations.
It also showed that the model operates well on diagnostic and low-dose screening CT. However, there still needs to be additional research before the AI tool can be used inside a clinic.
Taking the First Step & What's Next?
Dr. Vachani and his team took the first step in testing the AI tool in radiology and pulmonology practice. Now, the next step is to take the tool into trials where physicians can use it in a real-world setting. Currently, Dr. Vachani and his team are designing these trials.
AI demonstrates its value specifically in this medical field because of its high potential to ease the workload of physicians while increasing the speed and accuracy of diagnosis.
Along with AI being used in the detection of the malignancy of lung nodules, there are also ongoing studies in Non-Small Cell Lung Cancer (NSCLC) that used radiomics to predict distant metastasis in lung adenocarcinoma and tumor histological subtypes and disease recurrence, somatic mutations, gene-expression profiles, and overall survival.
Also in 2019, researchers developed and tested a deep-learning-based algorithm for classifying results of chest radiographs from patients with pulmonary malignant neoplasm, active tuberculosis, pneumonia, and pneumothorax.
This article is owned by TechTimes
Written by April Fowell
