Radiomics Approach for Cutaneous Melanoma Treatment Response Assessment in The Era of Precision Medicine
A Guerrisi1*, V Bruzzaniti2, M Russillo3 and FM Solivetti1
1Radiology and Diagnostic Imaging Unit, IRCCS San Gallicano Dermatological Institute, Italy
2Medical Physics and expert Systems Laboratory, IRCCS Regina Elena Cancer Institute, Italy
3Medical oncology unit 1, department of medical oncology IRCCS Regina Elena Cancer Institute, Italy
Submission: March 21, 2019; Published: March 28, 2019
*Corresponding Address: Antonino Guerrisi, MD, Radiology and Diagnostic Imaging Unit, IRCCS San Gallicano Dermatological Institute,via Bari, 13 – Roma- 00161, Italy
How to cite this article: A Guerrisi, V Bruzzaniti, M Russillo, FM Solivetti. Radiomics Approach for Cutaneous Melanoma Treatment Response Assessment
in The Era of Precision Medicine. Canc Therapy & Oncol Int J. 2019; 13(2): 555860. DOI:10.19080/CTOIJ.2019.13.555860
Novel target therapies as immunotherapy are revolutionizing oncology since they have been able to improve progression free and overall survival in many tumors. Although the enormous advantages demonstrated by these therapies in cutaneous melanoma patients there are still open challanges about the assessment of response due to the different imaging patterns could occur. Radiomics is an emerging field of medical imaging including those methodologies that extract additional quantitative data to support clinical decision. Radiomics is nowday an open field of research and a new multidisciplinary approach should be always considered when monitoring novel target therapies.
With the introduction of oncology target therapies, there is an urgent need to adopt a personalized approach in which a therapy is tailored for each patient, providing a customized healthcare . In particular, novel immunotherapies have revolutionized how clinicians take care of patients with cutaneous melanoma improving progression free and overall survival . Although immunotherapy is changing the landscape of oncology, some open issues merit consideration. In fact, nowadays treatment response is commonly evaluated according to RECIST 1.1. However, immunotherapy can generate atypical patterns of response due to what is terms pseudo progression, a condition that cannot be well evaluated with the above-mentioned criteria, not suitable .
Other criteria (i.e. irRC, irRECIST, iRecist) has been proposed, however no sufficient data for final validation for the latest iRecist has been collected and they are not adopted regularly in the clinical practice . Lack of validated response criteria for immunotherapy could cause delay to identify non responders patients. In fact, early prediction of treatments response can exclude or stop the administration of drugs to non-responder patients that severely affects the economic burden in charge to the National Healthcare System, also limiting potential unwanted side-effects that could occur in this patient. In the last years research efforts are focused on biomarkers (i.e. serological, molecular) validations for evaluation of treatment response . However, despite the use of biomarkers is widespread in oncology only a limited number of these guide clinical decisions.
In this contest, novel imaging biomarkers (IBs) could be used as clinical decision-making tools. The advantage of an imaging-based approach, respect to conventional approach (biopsy-derived biomarkers), is to provide multiple lesions analyses at multiple anatomy sites and at multiple time points by the use of non- invasive methods . Radiomics [7-9] is the recent field of research that analyze various tumor phenotypes by using a mathematical model and that allows to extrapolate a large amount of robust quantitative imaging-based parameters (features). The extracted features could be used as IBs to be associated to genetics and clinical outcomes. Nowadays immunotherapy is a primary option for cutaneous metastatic melanoma. These patients underwent several CT and PET-CT imaging for staging and monitoring therapy and MRI examination specially to evaluate brain metastases. Only a limited part of the informations present in the acquired images (i.e. CT, MRI, PET) are taken into consideration. Radiomics allows to extrapolate an increasingly amount of quantitative data present in the images . Texture analyses is an emerging area of “radiomics” that extracts, analyzes, and interprets quantitative imaging features
and it has already demonstrated it could be a useful tool in some
malignant tumors, in particular when applied to CT imaging,
however only few studies investigated it in melanoma patients
A major limitation of radiomics could be represent by the
reproducibility of the data since many variables are generated.
To overcome this drawback, machine learning models need to
be implemented and methodologies have to be validated on a
large cohort of patients . Obviously, this approach is time
consuming and it need advanced technological equipments.
Moreover, a multidisciplinary approach is mandatory since
specific medical, physics and informatics competencies must
converge. With recent technological developments in radiology
a road map has been drawn, however radiomics approach
will take time to be feasible in the routine clinical workflow.
The role of the medical physics acquire more importance and
the radiologists has to change their approach to interpret and
analyze the images . Interactions among physicians has to
be increased and informatics can help to support data analysis/
sharing and the entire clinical decision process.
Malignant tumors and in particular cutaneous melanoma are
biologically complex. Novel target therapies have revolutionized
the treatment options and patient management. In the era
of modern precision medicine a multidisciplinary approach
is mandatory to guide clinical decision and to choose best
treatment options. Radiomics has the potential to provide useful
information to provide robust data supporting clinical decision.
Features extracted by radiomics analysis could be associated
to the information obtained to the others “omics” sciences
(i.e.genomics) in order to strengthen them . On the other
hand, a novel approach need to be integrated in the clinical
workflow and new technology has to be always available to the
health care professionals. Educational and training programs
need to be constantly updated and they should be directed to
acquire new competencies by sharing among professionals.
Strategies directed to implement artificial intelligence, machine
learning and data analyses must be planned to overcome the
challenges that national healthcare systems has to face in the