Radiomics for Identification and Prediction in Metastatic Prostate Cancer: A Review of Studies

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.

Artificial Intelligence in Bone Metastases: An MRI and CT Imaging Review

“…The average recorded RQS was 22.6% (0-38.8%). This low score confirms what has been reported in other reviews in the field of radiomics, representing a relatively low quality of research methodology [25][26][27][28][29][30]. None of the reviewed studies were prospective in design, no external validation on a dataset from another institution was performed, no cost-effectiveness of the clinical application of the radiomic models was reported, and no datasets were made publicly available (although four authors allowed access to the datasets upon request).…”

Overcoming Immune Resistance With Radiation Therapy in Prostate Cancer

“…Furthermore, adapting standard imaging methods to accurately capture the immune response is required to assess response to treatment. Radiomics analysis of multiple standard imaging modalities, magnetic resonance imaging (MRI), computed tomography (CT) and positron-emission tomography (PET), incorporated with machine learning and artificial intelligence, is emerging as a promising field ( 164 ).…”

Radiomics and artificial intelligence in prostate cancer: new tools for molecular hybrid imaging and theragnostics

“…Automatic segmentation could overcome the major problem of interobserver and intra-observer variability of manual segmentation, which is also time-consuming. This might increase the homogeneity and reproducibility of data, also for radiomics assessment [ 43 , 44 ].…”