Advances in genomics have in recent years accelerated the personalization of medicine, but that is just the beginning. As researchers have mapped the human genome, clinicians have gained understanding of the effects that even minor abnormalities in the genetic structure can have on patients' conditions.
These insights have enabled providers to make more informed decisions about which treatment options to select over others, even in instances when two patients share similar characteristics, such as age, gender, weight, ethnicity, and lifestyle.
Nonetheless, even with this wealth of new genomic data, it has remained a challenge for clinicians to understand how effective treatment plans are overall, as well as gather real-time insights into how a treatment plan is affecting a patient at any given moment -- for cancer patients, in particular.
The reason is that, despite genetic similarities between different patients and their tumors or lesions, patients often react differently to the same therapy. As a result, clinicians in many instances do not definitively understand the effectiveness of a course of treatment until it is well underway or completed.
As a result of advances in radiomics, or advanced imaging analytics, clinicians now have the opportunity to gain these insights earlier in the cancer treatment process. The phenotypic data generated by radiomics, when combined with artificial intelligence (AI), provides data concerning the biology of tumors and lesions.
As a result, researchers and clinicians can accurately predict how a specific tumor or lesion will react to various treatment options, therefore helping to guide the treatment-planning decision process.
The critical value radiomics delivers is the ability to enable clinicians to see below the surface of a lesion or tumor. Generally, most radiological images are limited to two dimensions: length and width, also known as the long and short. With these images, radiologists can determine whether a lesion is growing, shrinking, or unchanged as a result of the course of treatment, but it is difficult for them to gather deeper insights.
In contrast, radiomics leverages AI-driven analytics to extract meaningful, previously unobtainable data from traditional imaging modalities such as CT, MRI, or PET scans. Radiomics software then curates this quantitative data to present clinicians with a plethora of data that cannot be gathered from an image via traditional optical analysis.
Through radiomics, providers acquire new insights pertaining to a lesion or tumor's depth, volume, density, doubling size, textures, and other features, as well as gain the advantage of comparing that data to AI-enabled models that are based on a library of healthy organ images.
Consequently, clinicians obtain new knowledge of lesion and tumor progression previously only available through invasive procedures such as biopsies -- in addition to detailed data that was not previously obtainable through any means. Furthermore, deep-learning capabilities enable radiomics software to increase accuracy and effectiveness as more images are analyzed and outcomes confirmed.
Insights into treatment efficacy
Here's what that means for the personalization of cancer treatment planning: When providers discover a lesion, they can combine the patient's genetic information with phenotypic data derived from radiomics to match the patient to others with similar profiles. With this data, clinicians can then review previous patient outcomes to determine which treatment plans delivered the best results. These results then become the starting point for treatment.
Radiomics offers further benefit to treatment planning by enabling clinicians to measure and monitor the effects of treatment across thousands of new data points that characterize tumor and lesion biology.
So, for example, if clinicians observe that a treatment has not achieved expected results at a particular checkpoint, they can adjust the treatment plan immediately as opposed to waiting until treatment has been completed. Throughout the process, providers can continue to leverage radiomic data to monitor and adjust their approaches to ensure each patient is receiving the best treatment based on each individual patient's response to the treatment plan.
Although the healthcare industry has made great strides in the personalization of medicine in recent years, more work remains to be done, in part because patients' genomic data only reveals part of the story. Radiomics complements genomic data with detailed information about tumor and lesion biology, enabling clinicians to deliver more personalization during all phases of cancer treatment.
Rose Higgins serves as chief executive officer of HealthMyne, a company specializing in applied radiomics -- the field of extracting novel data and biomarkers from medical images.
Dr. Mimi Huizinga is a physician executive who serves on the HealthMyne board of directors. She is also vice president and head of U.S. Oncology Medical at Novartis.
The comments and observations expressed are those of the author and do not necessarily reflect the opinions of AuntMinnie.com.