Continue in 2 seconds

Algorithm identifies lung cancer patients who should have chemotherapy

  • March 12 2018, 7:23am EDT

Case Western Reserve University and the Cleveland Clinic are developing a computerized tissue imaging capability that uses predictive analytics to potentially help identify which lung cancer patients are likely to experience an earlier recurrence of the disease.

The National Cancer Institute (NCI) recently awarded Anant Madabhushi, founding director of the Center for Computational Imaging and Personalized Diagnostics at the Case School of Engineering, and his colleagues a $3.2 million grant to more accurately determine which early-stage lung cancer patients would most benefit from chemotherapy following surgery, and which would not.

“Oncologists don’t really have any tools at their disposal to address this particular question,” says Madabhushi, who is principal investigator along with co-principal investigator Vamsidhar Velcheti, MD, a thoracic oncologist at Cleveland Clinic. “Right now, virtually all early-stage lung cancer patients get surgery. The problem is oncologists don’t currently have sufficient information to know which of these patients will also receive added benefit from chemotherapy.”

Using computer analysis of digitized tissue biopsy images, researchers are attempting to identify patients who could get additional therapeutic help from chemo, while avoiding the adverse side effects of the therapy for other patients who do not need such an intervention.

Also See: Penn Medicine using predictive model to anticipate ER visits by lung cancer patients

“What we hope with this computerized tissue analysis is that we can generate a risk score to then inform the oncologists about the need for chemotherapy,” according to Madabhushi, who adds that the algorithm utilized has been internally developed at Case Western’s Center for Computational Imaging and Personalized Diagnostics.

In October 2017, Madabhushi, Velcheti and six collaborators from the center published a paper in the journal Scientific Reports showing that the combination of nuclear shape, texture, and architectural features in the tissue biopsies were predictive of recurrence in early stage lung cancer, independent of clinical parameters such as gender, cancer stages and histologic subtype.

“Our results appear to suggest that the image classifier is able to predict disease outcome independent of the spatial location of where in the tumor block the tissue punch came from and independent of different nuclei segmentation methods as well,” wrote the authors. “Continuous risk scores computed via the Cox proportional hazard model allowed for assigning individual patients into more specific risk groups based on computed individual hazard ratios.”

Going forward, Madabhushi believes that the five-year NCI grant will result in the first validated predictive tool for identifying which early-stage lung cancer patients will benefit from chemotherapy after surgery.

“If this can tell us that only 10 percent of patients have a chance of the cancer returning, that means the other 90 percent won’t have to go through chemotherapy,” said Velcheti.

“Not only is it potentially a big deal for the patients, but it’s also a big deal for the healthcare system overall because we can reduce unnecessary expenditures with therapies like this,” concluded Madabhushi, who noted that chemotherapy can often cost as much as $35,000 for a single patient.

Tampa, Fla.-based Inspirata, which provides a cancer diagnostics solution that digitizes and automates the pathology workflow, is an industry partner for the NCI grant and “will work on translating the tools that we develop into a deployable test,” adds Madabhushi.

Register or login for access to this item and much more

All Information Management content is archived after seven days.

Community members receive:
  • All recent and archived articles
  • Conference offers and updates
  • A full menu of enewsletter options
  • Web seminars, white papers, ebooks

Don't have an account? Register for Free Unlimited Access