Study Finds Computers Surpass Pathologists in Predicting Lung Cancer Type, Severity
Computers can be trained to be more accurate than pathologists in assessing slides of lung cancer tissues, according to a new study by researchers at the Stanford University School of Medicine. The researchers found that a machine-learning approach to identifying critical disease-related features accurately differentiated between two types of lung cancers and predicted patient survival times better than the standard approach of pathologists classifying tumors by grade and stage. Their findings were published by Yu et al in Nature Communications.
“Pathology as it is practiced now is very subjective,” said Michael Snyder, PhD, Professor and Chair of Genetics at Stanford. “Two highly skilled pathologists assessing the same slide will agree only about 60% of the time. This approach replaces this subjectivity with sophisticated, quantitative measurements that we feel are likely to improve patient outcomes.”
Although the current study focused on lung cancer, the researchers believe that a similar approach could be used for many other types of cancer.
“Ultimately, this technique will give us insight into the molecular mechanisms of cancer by connecting important pathologic features with outcome data,” said Dr. Snyder.
Lung Cancer Focus
Often, a cancer's grade and stage can be used to predict how the patient will fare. They also can help clinicians decide how—and how aggressively—to treat the disease. This classification system doesn’t always work well for lung cancer, however.
In particular, the lung cancer subtypes of adenocarcinoma and squamous cell carcinoma can be difficult to tell apart when examining tissue culture slides. Furthermore, the stage and grade of a patient’s cancer doesn’t always correlate with their prognosis, which can vary widely. Fifty percent of stage I adenocarcinoma patients, for example, die within 5 years of their diagnosis, whereas about 15% survive for more than 10 years.
The researchers used 2,186 images from The Cancer Genome Atlas obtained from patients with either adenocarcinoma or squamous cell carcinoma. The database also contained information about the grade and stage assigned to each cancer and how long each patient lived after diagnosis.
The researchers then used the images to train a computer software program to identify many more cancer-specific characteristics than can be detected by the human eye—nearly 10,000 individual traits vs the several hundred usually assessed by pathologists. These characteristics included not just cell size and shape, but also the shape and texture of the cells’ nuclei and the spatial relations among neighboring tumor cells.
“We began the study without any preconceived ideas, and we let the software determine which characteristics are important,” said Dr. Snyder, who is also the Stanford W. Ascherman, MD, FACS, Professor in Genetics. “In hindsight, everything makes sense. And the computers can assess even tiny differences across thousands of samples many times more accurately and rapidly than a human.”
Connecting Imaging and ‘Omics’
The researchers homed in on a subset of cellular characteristics identified by the software that could best be used to differentiate tumor cells from the surrounding noncancerous tissue, identify the cancer subtype, and predict how long each patient would survive after diagnosis. They then validated the ability of the software to accurately distinguish short-term survivors from those who lived significantly longer on another dataset of 294 lung cancer patients from the Stanford Tissue Microarray Database.
Identifying previously unknown physical characteristics that can predict cancer severity and survival times is also likely to lead to greater understanding of the molecular processes of cancer initiation and progression. In particular, Dr. Snyder anticipates that the machine-learning system described in this study will be able to complement the emerging fields of cancer genomics, transcriptomics, and proteomics.
“We launched this study because we wanted to begin marrying imaging to our ‘omics’ studies to better understand cancer processes at a molecular level,” Dr. Snyder said. “This brings cancer pathology into the 21st century.”
The content in this post has not been reviewed by the American Society of Clinical Oncology, Inc. (ASCO®) and does not necessarily reflect the ideas and opinions of ASCO®.
