Radiomics workflow definition & challenges - German priority program 2177 consensus statement on clinically applied radiomics.

OBJECTIVES: Achieving a consensus on a definition for different aspects of radiomics workflows to support their translation into clinical usage. Furthermore, to assess the perspective of experts on important challenges for a successful clinical workflow implementation. MATERIALS AND METHODS: The consensus was achieved by a multi-stage process. Stage 1 comprised a definition screening, a retrospective analysis with semantic mapping of terms found in 22 workflow definitions, and the compilation of an initial baseline definition. Stages 2 and 3 consisted of a Delphi process with over 45 experts hailing from sites participating in the German Research Foundation (DFG) Priority Program 2177. Stage 2 aimed to achieve a broad consensus for a definition proposal, while stage 3 identified the importance of translational challenges. RESULTS: Workflow definitions from 22 publications (published 2012-2020) were analyzed. Sixty-nine definition terms were extracted, mapped, and semantic ambiguities (e.g., homonymous and synonymous terms) were identified and resolved. The consensus definition was developed via a Delphi process. The final definition comprising seven phases and 37 aspects reached a high overall consensus (> 89% of experts "agree" or "strongly agree"). Two aspects reached no strong consensus. In addition, the Delphi process identified and characterized from the participating experts' perspective the ten most important challenges in radiomics workflows. CONCLUSION: To overcome semantic inconsistencies between existing definitions and offer a well-defined, broad, referenceable terminology, a consensus workflow definition for radiomics-based setups and a terms mapping to existing literature was compiled. Moreover, the most relevant challenges towards clinical application were characterized. CRITICAL RELEVANCE STATEMENT: Lack of standardization represents one major obstacle to successful clinical translation of radiomics. Here, we report a consensus workflow definition on different aspects of radiomics studies and highlight important challenges to advance the clinical adoption of radiomics. KEY POINTS: Published radiomics workflow terminologies are inconsistent, hindering standardization and translation. A consensus radiomics workflow definition proposal with high agreement was developed. Publicly available result resources for further exploitation by the scientific community.

Comparison of the accuracy of commercial two-point and multi-echo Dixon MRI for quantification of fat in liver, paravertebral muscles, and vertebral bone marrow.

PURPOSE: Excess fat accumulation contributes significantly to metabolic dysfunction and diseases. This study aims to systematically compare the accuracy of commercially available Dixon techniques for quantification of fat fraction in liver, skeletal musculature, and vertebral bone marrow (BM) of healthy individuals, investigating biases and sex-specific influences. METHOD: 100 healthy White individuals (50 women) underwent abdominal MRI using two-point and multi-echo Dixon sequences. Fat fraction (FF), proton density fat fraction (PDFF) and T2* values were calculated for liver, paravertebral muscles (PVM) and vertebral BM (Th8-L5). Agreement and systematic deviations were assessed using linear correlation and Bland-Altman plots. RESULTS: High correlations between FF and PDFF were observed in liver (r = 0.98 for women; r = 0.96 for men), PVM (r = 0.92 for women; r = 0.93 for men) and BM (r = 0.97 for women; r = 0.95 for men). Relative deviations between FF and PDFF in liver (18.92 % for women; 13.32 % for men) and PVM (1.96 % for women; 11.62 % for men) were not significant. Relative deviations in BM were significant (38.13 % for women; 27.62 % for men). Bias correction using linear models reduced discrepancies. T2* times were significantly shorter in BM (8.72 ms for women; 7.26 ms for men) compared to PVM (13.45 ms for women; 13.62 ms for men) and liver (29.47 ms for women; 26.35 ms for men). CONCLUSION: While no significant differences were observed for liver and PVM, systematic errors in BM FF estimation using two-point Dixon imaging were observed. These discrepancies - mainly resulting from organ-specific T2* times - have to be considered when applying two-point Dixon approaches for assessment of fat content. As suitable correction tools, linear models could provide added value in large-scale epidemiological cohort studies. Sex-specific differences in T2* should be considered.

Analysis of volume and topography of adipose tissue in the trunk: Results of MRI of 11,141 participants in the German National Cohort.

This research addresses the assessment of adipose tissue (AT) and spatial distribution of visceral (VAT) and subcutaneous fat (SAT) in the trunk from standardized magnetic resonance imaging at 3 T, thereby demonstrating the feasibility of deep learning (DL)-based image segmentation in a large population-based cohort in Germany (five sites). Volume and distribution of AT play an essential role in the pathogenesis of insulin resistance, a risk factor of developing metabolic/cardiovascular diseases. Cross-validated training of the DL-segmentation model led to a mean Dice similarity coefficient of >0.94, corresponding to a mean absolute volume deviation of about 22 ml. SAT is significantly increased in women compared to men, whereas VAT is increased in males. Spatial distribution shows age- and body mass index-related displacements. DL-based image segmentation provides robust and fast quantification of AT (≈15 s per dataset versus 3 to 4 hours for manual processing) and assessment of its spatial distribution from magnetic resonance images in large cohort studies.

Automated shape-independent assessment of the spatial distribution of proton density fat fraction in vertebral bone marrow.

This work proposes a method for automatic standardized assessment of bone marrow volume and spatial distribution of the proton density fat fraction (PDFF) in vertebral bodies. Intra- and interindividual variability in size and shape of vertebral bodies is a challenge for comparable interindividual evaluation and monitoring of changes in the composition and distribution of bone marrow due to aging and/or intervention. Based on deep learning image segmentation, bone marrow PDFF of single vertebral bodies is mapped to a cylindrical template and corrected for the inclination with respect to the horizontal plane. The proposed technique was applied and tested in a cohort of 60 healthy (30 males, 30 females) individuals. Obtained bone marrow volumes and mean PDFF values are comparable to former manual and (semi-)automatic approaches. Moreover, the proposed method allows shape-independent characterization of the spatial PDFF distribution inside vertebral bodies.

A Comparative Study on the Potential of Unsupervised Deep Learning-based Feature Selection in Radiomics.

In Radiomics, deep learning-based systems for medical image analysis play an increasing role. However, due to the better explainability, feature-based systems are still preferred, especially by physicians. Often, high-dimensional data and low sample size pose different challenges (e.g. increased risk of overfitting) to machine learning systems. By removing irrelevant and redundant features from the data, feature selection is an effective way of pre-processing. The research in this study is focused on unsupervised deep learning-based methods for feature selection. Five recently proposed algorithms are compared regarding their applicability and efficiency on seven data sets in three different sample applications. It was found that deep learning-based feature selection leads to improved classification results compared to conventional methods, especially for small feature subsets. Clinical Relevance - The exploration of distinctive features and the ability to rank their importance without the need for outcome information is a potential field of application for unsupervised feature selection methods. Especially in multiparametric radiology, the number of features is increasing. The identification of new potential biomarkers is important both for treatment and prevention.

Fat Distribution Patterns and Future Type 2 Diabetes.

Fat accumulation in the liver, pancreas, skeletal muscle, and visceral bed relates to type 2 diabetes (T2D). However, the distribution of fat among these compartments is heterogenous and whether specific distribution patterns indicate high T2D risk is unclear. We therefore investigated fat distribution patterns and their link to future T2D. From 2,168 individuals without diabetes who underwent computed tomography in Japan, this case-cohort study included 658 randomly selected individuals and 146 incident cases of T2D over 6 years of follow-up. Using data-driven analysis (k-means) based on fat content in the liver, pancreas, muscle, and visceral bed, we identified four fat distribution clusters: hepatic steatosis, pancreatic steatosis, trunk myosteatosis, and steatopenia. In comparisons with the steatopenia cluster, the adjusted hazard ratios for incident T2D were 4.02 (95% CI 2.27-7.12) for the hepatic steatosis cluster, 3.38 (1.65-6.91) for the pancreatic steatosis cluster, and 1.95 (1.07-3.54) for the trunk myosteatosis cluster. The clusters were replicated in 319 German individuals without diabetes who underwent MRI and metabolic phenotyping. The distribution of the glucose area under the curve across the four clusters found in Germany was similar to the distribution of T2D risk across the four clusters in Japan. Insulin sensitivity and insulin secretion differed across the four clusters. Thus, we identified patterns of fat distribution with different T2D risks presumably due to differences in insulin sensitivity and insulin secretion.