Challenges

Radiomics is a young field and enthusiasm for its promise has frequently outpaced the available evidence base. Much work needs to be done to validate and standardize radiomic methodologies. The majority of published research has been retrospective pilot studies and case series, rather than rigorous, randomized, prospective trials.

Scant methodological standardization in this field, and some researchers’ failures to disclose data and computer code used in their radiomics studies, have complicated reproducibility and validation.2,9 These issues and open questions about radiomic specificity and sensitivity (the risk of false positive and false negative findings) have slowed translation of research findings into clinical practice.2,9 Machine learning for fully automated image segmentation remains an area of investigation and validation.2,6


Continue Reading

“Due to the retrospective nature of radiomic studies, imaging protocols, including acquisition, and reconstruction settings, are often not controlled or standardized,” cautioned authors of a 2020 review of the field.2

For the field to mature and advance, validation studies and well-designed, controlled clinical studies will be required.2,6,9,10

A May 2022 search of the ClinicalTrials.gov database of US government-registered studies identified only 12 radiomics oncology studies, 9 of which were preclinical. Three National Institutes of Health (NIH)-funded clinical trials were identified: an early phase 1 study of radiomics in the detection of primary and metastatic brain tumors (NCT04752267); a phase 2 study of atezolizumab and eribulin mesylate treatment regimen outcomes in patients with recurrent, advanced, or metastatic urothelial cancers (NCT03237780); and a phase 3 trial of outcomes following adjuvant and neoadjuvant chemotherapy regimens for pancreatic cancer surgery (NCT04340141).

Eventually, the hope is radiomics workflows will become reliably automated and integrated into other radiological workflows in the clinic.2,6

References

  1. Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology. 2016;278(2):563-577. doi:10.1148/radiol.2015151169
  2. van Timmeren JE, Cester D, Tanadini-Lang S, Alkadhi H, Baessler B. Radiomics in medical imaging — ”how-to” guide and critical reflection. Insights Imaging. 2020;11(1):91. doi:10.1186/s13244-020-00887-2
  3. Richardson ML, Amini B, Kinahan PE. Bone and soft tissue tumors: horizons in radiomics and artificial intelligence. Radiol Clin North Am. 2022;60(2):339-358. doi:10.1016/j.rcl.2021.11.011
  4. Kang CY, Duarte SE, Kim HS, et al. Artificial intelligence-based radiomics in the era of immuno-oncology. Oncologist. Published online March 28, 2022. doi:10.1093/oncolo/oyac036
  5. Leithner D, Horvat JV, Marino MA, et al. Radiomic signatures with contrast-enhanced magnetic resonance imaging for the assessment of breast cancer receptor status and molecular subtypes: initial results. Breast Cancer Res. 2019;21(1):106. doi:10.1186/s13058-019-1187-z
  6. Reginelli A, Nardone V, Giacobbe G, et al. Radiomics as a new frontier of imaging for cancer prognosis: a narrative review. Diagnostics (Basel). 2021;11(10):1796. doi:10.3390/diagnostics11101796
  7. Gillies RJ, Schabath MB. Radiomics improves cancer screening and early detection. Cancer Epidemiol Biomarkers Prev. 2020;29(12):2556-2567. doi:10.1158/1055-9965
  8. Lucia F, Bourbonne V, Visvikis D, et al. Radiomics analysis of 3D dose distributions to predict toxicity of radiotherapy for cervical cancer. J Pers Med. 2021;11(5):398. doi:10.3390/jpm11050398
  9. Liu Z, Wang S, Dong D, et al. The applications of radiomics in precision diagnosis and treatment of oncology: opportunities and challenges. Theranostics. 2019;9(5):1303-3122. doi:10.7150/thno.30309
  10. Papanikolaou N, Matos C, Koh DM. How to develop a meaningful radiomic signature for clinical use in oncologic patients. Cancer Imaging. 2020;20(1):33. doi:10.1186/s40644-020-00311-4

This article originally appeared on Oncology Nurse Advisor