AI Could Help With Lung Cancer Diagnosis

According to a study led by experts from The Royal Marsden NHS Foundation Trust in partnership with The Institute of Cancer Research, London, and Imperial College London, artificial intelligence (AI) could help clinicians with lung cancer diagnosis early.
The LIBRA project created an AI algorithm using data from CT images of roughly 500 individuals with big lung nodules. The AI model was then put through its paces to see if it could correctly identify malignant nodules.

Lung nodules are benign abnormal growths that are prevalent. However, some lung nodules are cancerous, and large ones (e.g., 15-30mm in size) are the most dangerous.

Researchers anticipate that this technique will eventually be able to speed up the detection of lung cancer by assisting in the rapid treatment of high-risk patients and by expediting the processing of patient scans.

The AUC (“Area under the curve”) was used by the authors to determine how good the new model was at predicting cancer. An AUC of 1 suggests a flawless model, whereas an AUC of 0.5 would be predicted if the model was guessing at random. The findings, published in ebiomedicine, show that the AI model was able to predict the probability of cancer in each nodule with an AUC of 0.87. The Brock score, a test commonly utilized in clinics, was improved from 0.672 to 0.672.

The new model also outperformed the Herder score, another commonly used test in clinic, with an AUC of 0.83. However, because the artificial intelligence model relies on only two variables, as opposed to seven for the Herder score and nine for the Brock score, it has the potential to streamline and accelerate nodule risk calculation in the future.

The new approach may also assist clinicians in making decisions about patients who do not currently have a clear referral channel. Patients are classified as low risk if their Herder score is less than 10%, and high risk and requiring intervention if their score is greater than 70%. A wide range of testing or treatment options could be investigated for people in the intermediate risk group (10-70%).

The researchers employed radionics to evaluate the CT scan data, which may extract information about the patient’s ailment from medical images that are difficult to view with the naked eye.

Lung cancer is the largest cause of cancer mortality worldwide, accounting for slightly more than a fifth (21%) of cancer fatalities in the UK. Patients with early-stage disease can be treated far more effectively, but current data suggest that more than 60% of lung cancers in England are detected at stage three or four, therefore steps to improve diagnosis are urgently needed.

Dr. Benjamin Hunter, Clinical Oncology Registrar at The Royal Marsden NHS Foundation Trust, said, “According to these initial results, our model appears to identify cancerous large lung nodules accurately. In the future, we hope it will improve early detection and potentially make cancer treatment more successful by highlighting high-risk patients and fast-tracking them to earlier intervention. Next, we plan to test the technology on patients with large lung nodules in the clinic to see if it can accurately predict their risk of lung cancer.”

Chief investigator for the LIBRA study, Dr. Richard Lee, Consultant Physician in Respiratory Medicine and Early Diagnosis at The Royal Marsden NHS Foundation Trust said, “While at an early stage, this study is an example of the vital scientific clinical research we’re undertaking in the Early Diagnosis and Detection Centre at The Royal Marsden and the ICR. Through this work, we hope to push boundaries to speed up the detection of the disease using innovative technologies such as AI.”

“People diagnosed with lung cancer at the earliest stage are much more likely to survive for five years when compared with those whose cancer is caught late. This means it is a priority we find ways to speed up the detection of the disease, and this study—which is the first to develop a radionics model specifically focused on large lung nodules—could one-day support clinicians in identifying high-risk patients.”

Keith Hewett, 64 from Watford, was diagnosed with lung cancer in 2018 and treated with surgery at his local hospital. He was then referred to Dr. Richard Lee at The Royal Marsden for follow-up care. Last year, a CT scan revealed nodules in Keith’s lung, and, after further investigation, he was diagnosed with cancer again. Keith, whose medical history is similar to patients used in this study, said,

“After my first diagnosis, I had a CT scan at The Royal Marsden every three months and, just as they were about to become every six months, Dr. Lee noticed a change in the scans. They weren’t sure what it was but agreed it needed further investigation. As I have arthritis, I can get lumps on my body which added more cloudiness to what was happening.”

“It turned out that there were three nodules in my lungs which were cancerous, and I was treated with surgery at The Royal Brompton. My care at The Royal Marsden has been excellent as their attention to detail is great and I felt safe in their care.”

“Any new technology that helps gives more clarity over whether something on a CT scan is or isn’t cancer would be great. As a patient, you want to know whether you have the disease as soon as possible because the earlier the treatment, the better the outcome.”

Source Link