Deep Learning Prostate MRI Segmentation Accuracy and Robustness: A Systematic Review

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Purpose To investigate the accuracy and robustness of prostate segmentation using deep learning across various training data sizes, MRI vendors, prostate zones, and testing methods relative to fellowship-trained diagnostic radiologists. Materials and methods In this systematic review, EMBASE, PubMed, Scopus and Web of Science databases were queried for English-language articles using keywords and related terms for prostate MRI segmentation and deep learning algorithms dated to July 31, 2022. A total of 691 articles from the search query were collected, and subsequently filtered to 48 based on predefined inclusion and exclusion criteria. Multiple characteristics were extracted from selected studies, such as deep learning algorithm performance, MRI vendor, and training dataset features. The primary outcome was comparison of mean Dice similarity coefficient (DSC) for prostate segmentation for deep learning algorithms versus diagnostic radiologists. Results Forty-eight studies were included. The vast majority of published deep learning algorithms for whole prostate gland segmentation (39/42 or 93%) had a DSC at or above expert level (DSC ≥ 0.86). The mean DSC was 0.79 ± 0.06 for peripheral zone, 0.87 ± 0.05 for transition zone, and 0.90 ± 0.04 for whole prostate gland segmentation. For selected studies using one major MRI vendor, the mean DSCs of each were as follows: GE (3/48 studies) 0.92 ± 0.03, Philips (4/48 studies) 0.92 ± 0.02, and Siemens (6/48 studies) 0.91 ± 0.03. Conclusion Deep learning algorithms for prostate MRI segmentation demonstrated comparable accuracy to expert radiologists despite varying parameters, therefore future research should shift toward evaluating segmentation robustness and patient outcomes across diverse clinical settings. ©RSNA, 2024.

Demonstrating the Value of Interventional Radiology

While national healthcare expenditures per capita in the United States exceed those in all other Organisation for Economic Co-operation and Development (OECD) countries, measures of health outcomes in the United States lag behind those in peer nations. This combination of high healthcare spending and relatively poor health has led to attempts to identify high- and low-value healthcare services and to develop mechanisms to reimburse health care providers based on the value of the care delivered. This article investigates the meaning of value in healthcare and identifies specific services delivered by interventional radiologists that have accrued evidence that they meet criteria for high-value services. Recognizing the shift in reimbursement to high-value care, it is imperative that interventional radiology (IR) develop the evidence needed to articulate to all relevant stakeholders how IR contributes value to the system.

Network inference performance complexity: a consequence of topological, experimental and algorithmic determinants

MOTIVATION

Network inference algorithms aim to uncover key regulatory interactions governing cellular decision-making, disease progression and therapeutic interventions. Having an accurate blueprint of this regulation is essential for understanding and controlling cell behavior. However, the utility and impact of these approaches are limited because the ways in which various factors shape inference outcomes remain largely unknown.

RESULTS

We identify and systematically evaluate determinants of performance-including network properties, experimental design choices and data processing-by developing new metrics that quantify confidence across algorithms in comparable terms. We conducted a multifactorial analysis that demonstrates how stimulus target, regulatory kinetics, induction and resolution dynamics, and noise differentially impact widely used algorithms in significant and previously unrecognized ways. The results show how even if high-quality data are paired with high-performing algorithms, inferred models are sometimes susceptible to giving misleading conclusions. Lastly, we validate these findings and the utility of the confidence metrics using realistic in silico gene regulatory networks. This new characterization approach provides a way to more rigorously interpret how algorithms infer regulation from biological datasets.

AVAILABILITY AND IMPLEMENTATION

Code is available at http://github.com/bagherilab/networkinference/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.