Towards developing a robust radiomics signature in diffuse diseases of the pancreas: Accuracy and stability of features derived from T1-weighted magnetic resonance imaging

Impact of Preprocessing Parameters in Medical Imaging-Based Radiomic Studies: A Systematic Review

BACKGROUND

Lately, radiomic studies featuring the development of a signature to use in prediction models in diagnosis or prognosis outcomes have been increasingly published. While the results are shown to be promising, these studies still have many pitfalls and limitations. One of the main issues of these studies is that radiomic features depend on how the images are preprocessed before their computation. Since, in widely known and used software for radiomic features calculation, it is possible to set these preprocessing parameters before the calculation of the radiomic feature, there are ongoing studies assessing the stability and repeatability of radiomic features to find the most suitable preprocessing parameters for every used imaging modality.

MATERIALS AND METHODS

We performed a comprehensive literature search using four electronic databases: PubMed, Cochrane Library, Embase, and Scopus. Mesh terms and free text were modeled in search strategies for databases. The inclusion criteria were studies where preprocessing parameters' influence on feature values and model predictions was addressed. Records lacking information on image acquisition parameters were excluded, and any eligible studies with full-text versions were included in the review process, while conference proceedings and monographs were disregarded. We used the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies 2) tool to investigate the risk of bias. We synthesized our data in a table divided by the imaging modalities subgroups.

RESULTS

After applying the inclusion and exclusion criteria, we selected 43 works. This review examines the impact of preprocessing parameters on the reproducibility and reliability of radiomic features extracted from multimodality imaging (CT, MRI, CBCT, and PET/CT). Standardized preprocessing is crucial for consistent radiomic feature extraction. Key preprocessing steps include voxel resampling, normalization, and discretization, which influence feature robustness and reproducibility. In total, 44% of the included works studied the effects of an isotropic voxel resampling, and most studies opted to employ a discretization strategy. From 2021, several studies started selecting the best set of preprocessing parameters based on models' best performance. As for comparison metrics, ICC was the most used in MRI studies in 58% of the screened works.

CONCLUSIONS

From our work, we highlighted the need to harmonize the use of preprocessing parameters and their values, especially in light of future studies of prospective studies, which are still lacking in the current literature.

CT histogram analysis to distinguish between acute intracerebral hemorrhage and cavernous hemangioma

OBJECTIVE

Acute intracerebral hemorrhage (AICH) and cerebral cavernous hemangioma (CCM) are two common cerebral hemorrhage diseases with partially overlapping CT findings and clinical symptoms, making it hard to distinguish between them. The current study used histogram analysis based on CT images to differentiate between CCM and AICH and test its diagnosis performance.

METHODS

This retrospective study included 158 patients with CCM and 137 patients with AICH. The histograms of brain CT plain scan images of both groups were extracted using Python code and included 18 histogram parameters of the lesions. The most effective parameters were selected by univariate logistic regression analysis and Spearman correlation analysis and included in the final multivariate logistic regression model. The sample was randomly divided into the training set and the validation set by 7:3. The ROC curve was constructed to evaluate the discriminant efficiency of the final logistic regression model in distinguishing between AICH and CCM.

RESULTS

The univariate analysis identified seven significant histogram parameters with the following final logistic regression model: F = 3.731 + 2.6411 × 10-9 × Energy-1.192 × Kurtosis-0.003 × Minimum-1.449 × Skewness + 2.5002 × 10-10 × Total Energy-1.103 × Uniformity+0.009 × Variance. The model showed good diagnostic performance in distinguishing between AICH and CCM, with an AUC of 0.876, sensitivity of 70.8%, and specificity of 91.9% in the training set, and an AUC of 0.870, sensitivity of 82.9%, and specificity of 85.1% in the validation set.

CONCLUSIONS

The histogram analysis of brain CT images can be used as an auxiliary method to distinguish between AICH and CCM effectively.

Interobserver Agreement in Automatic Segmentation Annotation of Prostate Magnetic Resonance Imaging

We aimed to compare the performance and interobserver agreement of radiologists manually segmenting images or those assisted by automatic segmentation. We further aimed to reduce interobserver variability and improve the consistency of radiomics features. This retrospective study included 327 patients diagnosed with prostate cancer from September 2016 to June 2018; images from 228 patients were used for automatic segmentation construction, and images from the remaining 99 were used for testing. First, four radiologists with varying experience levels retrospectively segmented 99 axial prostate images manually using T2-weighted fat-suppressed magnetic resonance imaging. Automatic segmentation was performed after 2 weeks. The Pyradiomics software package v3.1.0 was used to extract the texture features. The Dice coefficient and intraclass correlation coefficient (ICC) were used to evaluate segmentation performance and the interobserver consistency of prostate radiomics. The Wilcoxon rank sum test was used to compare the paired samples, with the significance level set at p < 0.05. The Dice coefficient was used to accurately measure the spatial overlap of manually delineated images. In all the 99 prostate segmentation result columns, the manual and automatic segmentation results of the senior group were significantly better than those of the junior group (p < 0.05). Automatic segmentation was more consistent than manual segmentation (p < 0.05), and the average ICC reached >0.85. The automatic segmentation annotation performance of junior radiologists was similar to that of senior radiologists performing manual segmentation. The ICC of radiomics features increased to excellent consistency (0.925 [0.888~0.950]). Automatic segmentation annotation provided better results than manual segmentation by radiologists. Our findings indicate that automatic segmentation annotation helps reduce variability in the perception and interpretation between radiologists with different experience levels and ensures the stability of radiomics features.

Relationship of Serum Bile Acids with Fat Deposition in the Pancreas, Liver, and Skeletal Muscle

Introduction

Ectopic fat deposition is well appreciated as a key contributor to digestive and liver diseases. Bile acids have emerged as pleiotropic signalling molecules involved in numerous metabolic pathways. The aim was to study the associations of bile acids with ectopic fat deposition and lipid panel.

Methods

A single 3.0 Tesla magnetic resonance imaging scanner was employed to measure fat deposition in the pancreas, liver, and skeletal muscle in 76 adults. Blood samples were drawn to determine total bile acids and lipid panel. Linear regression analyses were run, taking into account age, sex, body mass index, and other covariates.

Results

The studied ectopic fat depots were not significantly associated with levels of total bile acids in serum. Total bile acids were significantly associated high-density lipoprotein cholesterol - consistently in both the unadjusted (p = 0.018) and all adjusted models (p = 0.012 in the most adjusted model). Low-density lipoprotein cholesterol, total cholesterol, and triglycerides were not significantly associated with total bile acids in both the unadjusted and all adjusted models.

Conclusion

Fat deposition in the pancreas, liver, and skeletal muscle is not associated with circulating levels of total bile acids. High-density lipoprotein cholesterol is the only component of lipid panel that is associated with total bile acids.

Effect of Gray Value Discretization and Image Filtration on Texture Features of the Pancreas Derived from Magnetic Resonance Imaging at 3T

Radiomics of pancreas magnetic resonance (MR) images is positioned well to play an important role in the management of diseases characterized by diffuse involvement of the pancreas. The effect of image pre-processing configurations on these images has been sparsely investigated. Fifteen individuals with definite chronic pancreatitis (an exemplar diffuse disease of the pancreas) and 15 healthy individuals were included in this age- and sex-matched case-control study. MR images of the pancreas were acquired using a single 3T scanner. A total of 93 first-order and second-order texture features of the pancreas were compared between the study groups, by subjecting MR images of the pancreas to 7 image pre-processing configurations related to gray level discretization and image filtration. The studied parameters of intensity discretization did not vary in terms of their effect on the number of significant first-order texture features. The number of statistically significant first-order texture features varied after filtering (7 with the use of logarithm filter and 3 with the use of Laplacian of Gaussian filter with 5 mm σ). Intensity discretization generally affected the number of significant second-order texture features more markedly than filtering. The use of fixed bin number of 16 yielded 42 significant second-order texture features, fixed bin number of 128–38 features, fixed bin width of 6–24 features, and fixed bin width of 42–26 features. The specific parameters of filtration and intensity discretization had differing effects on radiomics signature of the pancreas. Relative discretization with fixed bin number of 16 and use of logarithm filter hold promise as pre-processing configurations of choice in future radiomics studies in diffuse diseases of the pancreas.