1
|
Kendrick J, Francis R, Hassan GM, Rowshanfarzad P, Jeraj R, Kasisi C, Rusanov B, Ebert M. Radiomics for Identification and Prediction in Metastatic Prostate Cancer: A Review of Studies. Front Oncol 2021; 11:771787. [PMID: 34790581 PMCID: PMC8591174 DOI: 10.3389/fonc.2021.771787] [Citation(s) in RCA: 21] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2021] [Accepted: 10/11/2021] [Indexed: 12/21/2022] Open
Abstract
Metastatic Prostate Cancer (mPCa) is associated with a poor patient prognosis. mPCa spreads throughout the body, often to bones, with spatial and temporal variations that make the clinical management of the disease difficult. The evolution of the disease leads to spatial heterogeneity that is extremely difficult to characterise with solid biopsies. Imaging provides the opportunity to quantify disease spread. Advanced image analytics methods, including radiomics, offer the opportunity to characterise heterogeneity beyond what can be achieved with simple assessment. Radiomics analysis has the potential to yield useful quantitative imaging biomarkers that can improve the early detection of mPCa, predict disease progression, assess response, and potentially inform the choice of treatment procedures. Traditional radiomics analysis involves modelling with hand-crafted features designed using significant domain knowledge. On the other hand, artificial intelligence techniques such as deep learning can facilitate end-to-end automated feature extraction and model generation with minimal human intervention. Radiomics models have the potential to become vital pieces in the oncology workflow, however, the current limitations of the field, such as limited reproducibility, are impeding their translation into clinical practice. This review provides an overview of the radiomics methodology, detailing critical aspects affecting the reproducibility of features, and providing examples of how artificial intelligence techniques can be incorporated into the workflow. The current landscape of publications utilising radiomics methods in the assessment and treatment of mPCa are surveyed and reviewed. Associated studies have incorporated information from multiple imaging modalities, including bone scintigraphy, CT, PET with varying tracers, multiparametric MRI together with clinical covariates, spanning the prediction of progression through to overall survival in varying cohorts. The methodological quality of each study is quantified using the radiomics quality score. Multiple deficits were identified, with the lack of prospective design and external validation highlighted as major impediments to clinical translation. These results inform some recommendations for future directions of the field.
Collapse
Affiliation(s)
- Jake Kendrick
- School of Physics, Mathematics and Computing, University of Western Australia, Perth, WA, Australia
| | - Roslyn Francis
- Medical School, University of Western Australia, Crawley, WA, Australia
- Department of Nuclear Medicine, Sir Charles Gairdner Hospital, Perth, WA, Australia
| | - Ghulam Mubashar Hassan
- School of Physics, Mathematics and Computing, University of Western Australia, Perth, WA, Australia
| | - Pejman Rowshanfarzad
- School of Physics, Mathematics and Computing, University of Western Australia, Perth, WA, Australia
| | - Robert Jeraj
- Department of Medical Physics, University of Wisconsin, Madison, WI, United States
- Faculty of Mathematics and Physics, University of Ljubljana, Ljubljana, Slovenia
| | - Collin Kasisi
- Department of Nuclear Medicine, Sir Charles Gairdner Hospital, Perth, WA, Australia
| | - Branimir Rusanov
- School of Physics, Mathematics and Computing, University of Western Australia, Perth, WA, Australia
| | - Martin Ebert
- School of Physics, Mathematics and Computing, University of Western Australia, Perth, WA, Australia
- Department of Radiation Oncology, Sir Charles Gairdner Hospital, Perth, WA, Australia
- 5D Clinics, Claremont, WA, Australia
| |
Collapse
|
2
|
Reese DE, Henderson MC, Silver M, Mulpuri R, Letsios E, Tran Q, Wolf JK. Breast density does not impact the ability of Videssa® Breast to detect breast cancer in women under age 50. PLoS One 2017; 12:e0186198. [PMID: 29069101 PMCID: PMC5656317 DOI: 10.1371/journal.pone.0186198] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/26/2017] [Accepted: 09/18/2017] [Indexed: 01/23/2023] Open
Abstract
Breast density is associated with reduced imaging resolution in the detection of breast cancer. A biochemical approach that is not affected by density would provide an important tool to healthcare professionals who are managing women with dense breasts and suspicious imaging findings. Videssa® Breast is a combinatorial proteomic biomarker assay (CPBA), comprised of Serum Protein Biomarkers (SPB) and Tumor Associated Autoantibodies (TAAb) integrated with patient-specific clinical data to produce a diagnostic score that reliably detects breast cancer (BC) as an adjunctive tool to imaging. The performance of Videssa® Breast was evaluated in the dense (a and b) and non-dense (c and d) groups in a population of n = 545 women under age 50. The sensitivity and specificity in the dense breast group were calculated to be 88.9% and 81.2%, respectively, and 92.3% and 86.6%, respectively, for the non-dense group. No significant differences were observed in the sensitivity (p = 1.0) or specificity (p = 0.18) between these groups. The NPV was 99.3% and 99.1% in non-dense and dense groups, respectively. Unlike imaging, Videssa® Breast does not appear to be impacted by breast density; it can effectively detect breast cancer in women with dense and non-dense breasts alike. Thus, Videssa® Breast provides a powerful tool for healthcare providers when women with dense breasts present with challenging imaging findings. In addition, Videssa® Breast provides assurance to women with dense breasts that they do not have breast cancer, reducing further anxiety in this higher risk patient population.
Collapse
Affiliation(s)
- David E. Reese
- Provista Diagnostics, New York, NY, United States of America
| | | | - Michael Silver
- Provista Diagnostics, New York, NY, United States of America
| | - Rao Mulpuri
- Provista Diagnostics, New York, NY, United States of America
| | - Elias Letsios
- Provista Diagnostics, New York, NY, United States of America
| | - Quynh Tran
- Provista Diagnostics, New York, NY, United States of America
| | - Judith K. Wolf
- Provista Diagnostics, New York, NY, United States of America
- * E-mail:
| |
Collapse
|