Comparative performance of fully-automated and semi-automated artificial intelligence methods for the detection of clinically significant prostate cancer on MRI: a systematic review

Abstract

Objectives We systematically reviewed the current literature evaluating the ability of fully-automated deep learning (DL) and semi-automated traditional machine learning (TML) MRI-based artificial intelligence (AI) methods to differentiate clinically significant prostate cancer (csPCa) from indolent PCa (iPCa) and benign conditions. Methods We performed a computerised bibliographic search of studies indexed in MEDLINE/PubMed, arXiv, medRxiv, and bioRxiv between 1 January 2016 and 31 July 2021. Two reviewers performed the title/abstract and full-text screening. The remaining papers were screened by four reviewers using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) for DL studies and Radiomics Quality Score (RQS) for TML studies. Papers that fulfilled the pre-defined screening requirements underwent full CLAIM/RQS evaluation alongside the risk of bias assessment using QUADAS-2, both conducted by the same four reviewers. Standard measures of discrimination were extracted for the developed predictive models. Results 17/28 papers (five DL and twelve TML) passed the quality screening and were subject to a full CLAIM/RQS/QUADAS-2 assessment, which revealed a substantial study heterogeneity that precluded us from performing quantitative analysis as part of this review. The mean RQS of TML papers was 11/36, and a total of five papers had a high risk of bias. AUCs of DL and TML papers with low risk of bias ranged between 0.80–0.89 and 0.75–0.88, respectively. Conclusion We observed comparable performance of the two classes of AI methods and identified a number of common methodological limitations and biases that future studies will need to address to ensure the generalisability of the developed models.

Prediction of upgrade to clinically significant prostate cancer in patients under active surveillance: Performance of a fully automated AI‐algorithm for lesion detection and classification

“…Moreover, PCa detected by established predictors of tumor progression such as PSA level elevation alone often results in higher false-positive rates, thus causing excess costs and potential risks related to unnecessary biopsies. 39 Recent studies do not only suggest that AI-based algorithms derived from mpMRI are able to differentiate between ncsPCa, csPCa, and benign prostatic alterations 40 and are capable of detecting tumors on histopathological level comparable to expert pathologists 41 but could already show advances in false positive reduction 25 which gains importance rapidly with 25% PCa per PSA elevation (>4 ng/mL 42 ) and a total of estimated 1.4 million diagnoses worldwide in 2020. 43 The use of AS has increased drastically over the last decades, for example, from 14.5% in 2010 to 42.1% in 2015 in the US population.…”

Assessing the impact of MRI based diagnostics on pre-treatment disease classification and prognostic model performance in men diagnosed with new prostate cancer from an unscreened population

“…MRI quality and radiologist experience are variable and may have a direct impact on outcomes, in the future computer-aided diagnosis (CAD) systems may help reduce this variability, initial studies have shown promise in this area. However, these have demonstrated methodological limitations and biases which future studies will need to address to ensure generalisability [44]. Finally, all the risk models we tested were developed prior to the era of pre-biopsy MRI and we have assumed a similar proportion of deaths for the new simulated risk groups which may therefore be under or over estimates.…”

AI-powered radiomics: revolutionizing detection of urologic malignancies

“…Analyzing subtle changes in prostate, kidney, and bladder images can enhance early detection of urologic cancers, identification of the extent and stage of malignant tissues, and even predict tumor aggressiveness and responsiveness to treatment. The quantitative nature of radiomics allows for more consistency in radiographic assessment, minimizing inter-observer variability and enhancing diagnostic capabilities [3][4][5]. This review provides an overview of the most recent advancements in the domain of AI-powered radiomics applied to the field of urologic oncology, focusing on prostate, kidney, and bladder malignancies.…”