HospiMedica

Download Mobile App
Recent News AI Critical Care Surgical Techniques Patient Care Health IT Point of Care Business Focus

AI Tool Identifies Cancer Type and Changes in Lung Tumor

By HospiMedica International staff writers
Posted on 01 Oct 2018
Print article
Image: An AI tool analyzes a slice of cancerous tissue to create a map that tells apart two lung cancer types, with squamous cell carcinoma in red, lung squamous cell carcinoma in blue, and normal lung tissue in gray (Photo courtesy of Cision).
Image: An AI tool analyzes a slice of cancerous tissue to create a map that tells apart two lung cancer types, with squamous cell carcinoma in red, lung squamous cell carcinoma in blue, and normal lung tissue in gray (Photo courtesy of Cision).
Researchers from the NYU School of Medicine (New York City, NY, USA) have developed a new computer program that can analyze the images of patients' lung tumors, specify cancer types, and even identify altered genes driving abnormal cell growth. In their study, the researchers found that the artificial intelligence (AI), or "machine learning," program could distinguish -- with 97% accuracy -- between adenocarcinoma and squamous cell carcinoma, two lung cancer types that experienced pathologists at times struggle to parse without confirmatory tests. Additionally, the study found that the AI was also able to determine from analyzing the images whether the abnormal versions of six genes linked to lung cancer – including EGFR, KRAS and TP53 – were present in cells, with an accuracy ranging from 73% to 86%, depending upon the gene.

For their study, the researchers designed statistical techniques that gave their program the ability to "learn" how to get better at a task, but without being told exactly how. Such programs build rules and mathematical models that enable decision-making based on data examples fed into them, with the program becoming "smarter" as the amount of training data grows.

Newer AI approaches, inspired by nerve cell networks in the brain, use increasingly complex circuits to process information in layers, with each step feeding information into the next, and assigning more or less importance to each piece of information along the way. The researchers trained a deep convolutional neural network, Google's Inception v3, to analyze slide images obtained from The Cancer Genome Atlas, a database of images where cancer diagnoses had already been determined. This allowed the researchers to measure how well their program could be trained to accurately and automatically classify normal versus diseased tissue.

The study found that about half of the small percentage of tumor images misclassified by the study AI program was also misclassified by the pathologists, highlighting the difficulty in distinguishing between the two lung cancer types. On the other hand, 45 out of 54 of the images misclassified by at least one of the pathologists in the study were assigned to the correct cancer type by the machine-learning program, suggesting that AI could offer a useful second opinion.

The researchers now plan to continue training their AI program with data until it can determine which genes are mutated in a given cancer with more than 90% accuracy, after which they will begin seeking government approval to use the technology clinically, and in the diagnosis of several cancer types.

"Delaying the start of cancer treatment is never good," said senior study author Aristotelis Tsirigos, PhD, associate professor in the Department of Pathology at NYU School of Medicine and NYU Langone Health's Perlmutter Cancer Center. "Our study provides strong evidence that an AI approach will be able to instantly determine cancer subtype and mutational profile to get patients started on targeted therapies sooner."

"In our study, we were excited to improve on pathologist-level accuracies, and to show that AI can discover previously unknown patterns in the visible features of cancer cells and the tissues around them," said the study’s co-corresponding author Narges Razavian, PhD, assistant professor in the departments of Radiology and Population Health. "The synergy between data and computational power is creating unprecedented opportunities to improve both the practice and the science of medicine."

Related Links:
NYU School of Medicine

Gold Member
SARS‑CoV‑2/Flu A/Flu B/RSV Sample-To-Answer Test
SARS‑CoV‑2/Flu A/Flu B/RSV Cartridge (CE-IVD)
Gold Member
POC Blood Gas Analyzer
Stat Profile Prime Plus
Silver Member
Compact 14-Day Uninterrupted Holter ECG
NR-314P
New
Surgical Table
STERIS 5085 SRT

Print article

Channels

Critical Care

view channel
Image: The new risk assessment tool determines patient-specific risks of developing unfavorable outcomes with heart failure (Photo courtesy of 123RF)

Powerful AI Risk Assessment Tool Predicts Outcomes in Heart Failure Patients

Heart failure is a serious condition where the heart cannot pump sufficient blood to meet the body's needs, leading to symptoms like fatigue, weakness, and swelling in the legs and feet, and it can ultimately... Read more

Surgical Techniques

view channel
Image: The multi-sensing device can be implanted into blood vessels to help physicians deliver timely treatment (Photo courtesy of IIT)

Miniaturized Implantable Multi-Sensors Device to Monitor Vessels Health

Researchers have embarked on a project to develop a multi-sensing device that can be implanted into blood vessels like peripheral veins or arteries to monitor a range of bodily parameters and overall health status.... Read more

Patient Care

view channel
Image: The portable, handheld BeamClean technology inactivates pathogens on commonly touched surfaces in seconds (Photo courtesy of Freestyle Partners)

First-Of-Its-Kind Portable Germicidal Light Technology Disinfects High-Touch Clinical Surfaces in Seconds

Reducing healthcare-acquired infections (HAIs) remains a pressing issue within global healthcare systems. In the United States alone, 1.7 million patients contract HAIs annually, leading to approximately... Read more

Health IT

view channel
Image: First ever institution-specific model provides significant performance advantage over current population-derived models (Photo courtesy of Mount Sinai)

Machine Learning Model Improves Mortality Risk Prediction for Cardiac Surgery Patients

Machine learning algorithms have been deployed to create predictive models in various medical fields, with some demonstrating improved outcomes compared to their standard-of-care counterparts.... Read more

Point of Care

view channel
Image: The Quantra Hemostasis System has received US FDA special 510(k) clearance for use with its Quantra QStat Cartridge (Photo courtesy of HemoSonics)

Critical Bleeding Management System to Help Hospitals Further Standardize Viscoelastic Testing

Surgical procedures are often accompanied by significant blood loss and the subsequent high likelihood of the need for allogeneic blood transfusions. These transfusions, while critical, are linked to various... Read more