Exploratory Analysis of Radiomics and Pathomics in Uterine Corpus Endometrial Carcinoma

Abstract

Uterine corpus endometrial carcinoma (EC) is one of the most common malignancies in the female reproductive system, characterized by tumor heterogeneity at both radiological and pathological scales. Both radiomics and pathomics have the potential to assess this heterogeneity and support EC diagnosis. This study examines the correlation between radiomics features from Apparent Diffusion Coefficient (ADC) maps and post-contrast T1 (T1C) images with pathomic features from pathology images in 32 patients from the CPTAC-UCEC database. 91 radiomics features were extracted from ADC maps and T1C images, and 566 pathomic features from cell detections and cell density maps at four different resolutions. Spearman's correlation and Bayes Factor analysis were used to evaluate radio-pathomic correlations. Significant cross-scale correlations were found, with strengths ranging from 0.57 to 0.89 in absolute value (9.47 × 10⁴ < BF < 4.77 × 10¹⁴) for the ADC task, and from 0.64 and 0.70 (1.80 × 10⁴ < BF < 5.69 × 10⁵) for the T1C task. Most significant and high cross-scale associations were observed between ADC textural features and features from cell density maps. Correlations involving morphometric features and ADC and T1C first-order features were also observed, reflecting variations in tumor aggressiveness and tissue composition. These findings suggest that correlating radiomic features from ADC and T1C features with histopathological features can enhance understanding of EC intratumoral heterogeneity.

Keywords: Digital pathology; Endometrial carcinoma; MRI; Pathomics; Radiomics; Uterine corpus.

Fig. 1

Example of Endometrial Carcinoma (EC) located in anterior endometrium. (A) In the delayed phase of DCE (dynamic contrast enhanced) Magnetic Resonance images, the EC (red arrow) was low in signal compared to the enhancing myometrium; (B) the lesion on the axial ADC (apparent diffusion coefficient) map showed a hypointense signal (red arrow). (C) histological slide of G2 (grade) EC in FFPE (formalin-fixed paraffin-embedded) (percent tumor nuclei: 90; percent total cellularity: 90; percent necrosis: 0).

Fig. 2

Radiopathomic workflow implemented in the study. Abbreviations: ADC = Apparent Diffusion Coefficient; T1C = post-contrast T1 images.

Fig. 3

Radiopathomic analysis between ADC radiomic features and pathomic features (part 1). Correlation matrix filtered from nonsignificant correlations (rows and columns with non-significant values were deleted, while non-significant values surviving were set to zero).

Fig. 4

Radiopathomic analysis between ADC radiomic features and pathomic features (part 2). Correlation matrix filtered from nonsignificant correlations (rows and columns with non-significant values were deleted, while non-significant values surviving were set to zero).

Fig. 5

Radiopathomic analysis between ADC radiomic features and pathomic features (part 2). Correlation matrix filtered from nonsignificant correlations (rows and columns with non-significant values were deleted, while non-significant values surviving were set to zero).