Abstract

A key objective of modern medicine is precision medicine, whose purpose is to personalize the treatment based on the specific characteristics of the patients and their illness. To guide treatment decisions, it is generally necessary to have a sample of the neoplastic tissue, which is obtained only with biopsies or similar invasive surgical procedures. As tumors are heterogeneous in their volume and change over time, a dynamic analysis of diagnostic medical images can provide a better understanding of the entire tumor, both in the screening and follow-up phase. In this work, the authors proposed the use of a radiomics pipeline which is able to characterize the possible response of the oncological patients to the anti- programmed death-ligand protein 1 (PD-L1) immunotherapeutic treatment. The immunotherapeutic treatment consists of a modern therapeutic approach in which the physicians try to reactivate the patient's immune system so that it recognizes and destroys cancer cells. The oncological biomarkers capable of characterizing patients who can benefit from immunotherapy from those who would not, are being studied. One of them is related to the expression of the PD-L1 inhibitor in the surface of neoplastic cells which are analyzed in this paper, considering that the analyzed immunotherapeutic treatment is of the anti-PD-L1 type. In this context, the authors propose a pipeline for an immunotherapy response prediction based on the analysis of only CT-scan images of patients with metastatic bladder cancer. Using a framework based on the use of deep Autoeconder network, CT-scan images were analyzed to extract the features capable of discriminating the patient's response to anti-PD-L1 immunotherapy treatment from those who are not. The preliminary results obtained (accuracy of approximately 86% with a sensitivity of approximately 80% against a specificity of approximately 89%) on the analyzed patient dataset, allows the confirmation of the feasibility of the proposed method. Although validated in a dataset containing patients with only one tumor histology (bladder cancer), the proposed method shows how modern radiomics techniques can contribute significantly in the implementation of non-invasive predictive systems that support the physician in the therapeutic choice. The idea of the authors is to create a form of oncological point of care on an embedded platform that allows physicians to always have a support tool in choosing the best therapy to suggest to the patient.

Highlights

  • In order to validate the discriminatory performance of the proposed pipeline, the authors used a dataset of selected patients suffering from metastatic bladder cancer already treated on the front line with a chemotherapy treatment that did not produce total regression of the disease

  • In order to highlight the advantages obtainable from the application of the proposed pipeline as a non-invasive, predictive method of a response to immunotherapy treatment, this study reports in Table 5 the overall response rate (ORR) of a dataset of patients suffering from bladder cancer and treated in first line with chemotherapy, which were treated with immunotherapy

  • The proposed pipeline offers a non-invasive decision support tool to the oncologist who can have an estimation of the level of response to immunotherapeutic treatment in the absence of a biopsy of the primary tumor that reports a quantification of the inhibitor’s expression programmed cell death ligand-1 (PD-L1)

Read more

Summary

Introduction

Radiomics and radiogenomics are two terms that are increasingly used in the language of thoseRadiomics are two terms that are nuclear increasingly used inand themedical language of those working in the and fieldradiogenomics of diagnostic imaging: radiologists, physicians physicists.working in the field of diagnostic imaging: radiologists, nuclear physicians and medical physicists.To understand the meaning of the term radiomics, the start must be from a fundamental premise, To understand the meaning of the term radiomics, the startthan must be from a fundamental even if not so obvious: radiological images are much more simple anatomical figures.premise, The new even if not so obvious: radiological images are much more than simple anatomical figures.The new diagnostic technologies, produce in addition to the classic images familiar even to diagnostic technologies, produce in addition to the classic images familiar even to many many not employed to the works, an enormous wealth of numerical data that simple visual not employedthe to the works,qualitative an enormous wealth of to numerical simple visual observation, so-called analysis, fails elaboratedata [1]. thatIf these images areobservation, analyzed in the so-called qualitative analysis, fails to elaborate [1].If these images are analyzed in detail by detail by powerful computers through complex mathematical algorithms, it is possible powerful to obtain computers through complex mathematical algorithms, it is possible obtain objective quantitative objective quantitative data, capable of providing information on thetounderlying pathophysiological data, capable of providing information on the underlying pathophysiological phenomena, inaccessible phenomena, inaccessible to simple visual analysis [2]. Radiomics are two terms that are nuclear increasingly used inand themedical language of those working in the and fieldradiogenomics of diagnostic imaging: radiologists, physicians physicists. If these images areobservation, analyzed in the so-called qualitative analysis, fails to elaborate [1]. If these images are analyzed in detail by detail by powerful computers through complex mathematical algorithms, it is possible powerful to obtain computers through complex mathematical algorithms, it is possible obtain objective quantitative objective quantitative data, capable of providing information on thetounderlying pathophysiological data, capable of providing information on the underlying pathophysiological phenomena, inaccessible phenomena, inaccessible to simple visual analysis [2]. The use of modern machine and deep learning methodologies for methodologies for high-tech quantitative analysis, relating to medical images [1,2].

Methods
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.