3 Hurdles to Cross to Reach the Pinnacle of Radiomics

Three Key Challenges Faced with Respect to Radiomics.

Predible Health
Jul 10, 2017 · 4 min read

The conversion of digital medical images into mineable high-dimensional data is a process that is known as radiomics. It is motivated by the concept that biomedical images contain information that reflects underlying pathophysiology and that these relationships can be revealed via quantitative image analyses.

Radiomics is explicitly a process designed to extract a large number of quantitative features from digital images, place these data in shared databases, and subsequently mine the data for hypothesis generation, testing, or both.

While radiomics primarily grew out of basic research, lately it has also elicited interest from those in clinical research, as well as those in daily clinical practice. For a clinical radiologist, radiomics has the potential to help with the diagnosis of both common and rare tumors. Visualization of tumor heterogeneity may prove critical in the assessment of tumor aggressiveness and prognosis.

Radiomics begins with acquisition of high-quality images from which a region of interest (ROI) that contains either the whole tumor or its subregions can be identified. These are segmented with operator edits then rendered in three dimensions (3D), from which quantitative features are extracted to generate a report, which is placed in a database along with other clinical and genomic data. The data are then mined to develop diagnostic, predictive, or prognostic models for outcomes of interest.

But as in any young discipline, radiomics also has its own set of challenges that need to be cleared. Taking inputs from a study conducted by the Radiological Society of America (RSNA) [1], these challenges have been narrowed down to produce the “3 Key Challenges” faced with respect to radiomics.

The 3 Key Challenges

1. Reproducibility

While standardized tools for genomic profiling have been developed, they are not universally agreed upon or applied across medical centers, hampering efforts to share data and reproduce results.

Although radiomics offers immense potential to accelerate precision medicine, it is feared that it will undergo the same slow progress as experienced with most other molecular biology–based systemic diagnostic techniques and therapies. That slow progress can be attributed to a number of causes, including technical complexity, poor study design and overfitting of data, lack of standards for validating results, incomplete reporting of results, and unrecognized confounding variables in the databases used, particularly if data are derived retrospectively.

A clear solution to these challenges is to establish benchmarks for the conduct of radiomics studies and for their reporting in the literature.

2. Big Data

In the era of precision medicine, gigabytes of data are collected for each patient, and radiomics data can provide a significant component of this.

The exponential growth in the numbers of patients and the data elements being harvested from each is known colloquially as “big data”. Big data initiatives are aimed at drawing inferences from large data sets that are not derived from carefully controlled experiments. Although correlations among observations can be vast in number and easy to obtain, causality is much harder to assess and establish, partly because it is a vague and poorly specified construct for complex systems.

The key is to understand whether access to massive data is a crucial to understanding the fundamental questions of basic and applied science or if the vast increase in data confound analysis will produce computational bottlenecks, and decrease the ability to draw valid causal inferences.

3. Data Sharing

The biggest challenge to establishing radiomics-based models as biomarkers to use in decision support is the sharing of image data and metadata across multiple sites.

Multi-site trials are required to interrogate separate cohorts of patients and to create databases with sufficient size for statistical power. Data sharing is a common challenge in all biomedical research, and it must overcome cultural, administrative, regulatory, and personal issues. Data sharing in radiomics is especially daunting because shared data must include images and sharing must be in compliance with the Health Insurance Portability and Accountability Act, as a substantial amount of personal health information is needed to build models of sufficient complexity.

In Conclusion

Radiologists have central and critical roles to play in addressing the challenges faced with respect to radiomics, by identifying and curating data at the front end and in applying classifier models at the user end to improve diagnostic and prognostic accuracy.

But it will not be a lone effort of the radiologists, rather a multi-disciplinary effort involving information technologists, bio-informaticists, statisticians, and treating physicians for achievement of the ultimate vision for radiomics.

The vision for radiomics is optimistic and clear. In the foreseeable future, it is expected that data gleaned from radiologic examinations throughout the world will be converted into quantitative feature data and that these data will be interfaced with knowledge bases to eventually improve diagnostic accuracy and predictive power for decision support worldwide.

Predible Liver enables the radiologist to don the researchers hat in the confines of daily practice by creating a structured quantified dataset of lesion characteristics in a rapid manner. Sign up for Beta!

References

  1. Dr. Gillies, Robert; Dr. Kinahan,Paul ; Dr. Hricak, Hedvig (2016) Radiomics: Images Are More than Pictures, They Are Data. Radiology Journal(RSNA) https://doi.org/10.1148/radiol.2015151169

Predible Health

Written by

We are an AI startup, building delightful products for cancer radiologists. Looking for beta users for our first product in Liver Cancer!

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade