Correlating imaging parameters with molecular data: An integrated approach to improve the management of breast cancer patients

Breast PET/MRI Hybrid Imaging and Targeted Tracers

The recent introduction of hybrid positron emission tomography/magnetic resonance imaging (PET/MRI) as a promising imaging modality for breast cancer assessment has prompted fervent research activity on its clinical applications. The current knowledge regarding the possible clinical applications of hybrid PET/MRI is constantly evolving, thanks to the development and clinical availability of hybrid scanners, the development of new PET tracers and the rise of artificial intelligence (AI) techniques. In this state-of-the-art review on the use of hybrid breast PET/MRI, the most promising advanced MRI techniques (diffusion-weighted imaging, dynamic contrast-enhanced MRI, magnetic resonance spectroscopy, and chemical exchange saturation transfer) are discussed. Current and experimental PET tracers (¹⁸ F-FDG, ¹⁸ F-NaF, choline, ¹⁸ F-FES, ¹⁸ F-FES, ⁸⁹ Zr-trastuzumab, choline derivatives, ¹⁸ F-FLT, and ⁶⁸ Ga-FAPI-46) are described in order to provide an overview on their molecular mechanisms of action and corresponding clinical applications. New perspectives represented by the use of radiomics and AI techniques are discussed. Furthermore, the current strengths and limitations of hybrid PET/MRI in the real world are highlighted. EVIDENCE LEVEL: 2 TECHNICAL EFFICACY: Stage 2.

ImaGene: a web-based software platform for tumor radiogenomic evaluation and reporting

Summary

Radiographic imaging techniques provide insight into the imaging features of tumor regions of interest, while immunohistochemistry and sequencing techniques performed on biopsy samples yield omics data. Relationships between tumor genotype and phenotype can be identified from these data through traditional correlation analyses and artificial intelligence (AI) models. However, the radiogenomics community lacks a unified software platform with which to conduct such analyses in a reproducible manner. To address this gap, we developed ImaGene, a web-based platform that takes tumor omics and imaging datasets as inputs, performs correlation analysis between them, and constructs AI models. ImaGene has several modifiable configuration parameters and produces a report displaying model diagnostics. To demonstrate the utility of ImaGene, we utilized data for invasive breast carcinoma (IBC) and head and neck squamous cell carcinoma (HNSCC) and identified potential associations between imaging features and nine genes (WT1, LGI3, SP7, DSG1, ORM1, CLDN10, CST1, SMTNL2, and SLC22A31) for IBC and eight genes (NR0B1, PLA2G2A, MAL, CLDN16, PRDM14, VRTN, LRRN1, and MECOM) for HNSCC. ImaGene has the potential to become a standard platform for radiogenomic tumor analyses due to its ease of use, flexibility, and reproducibility, playing a central role in the establishment of an emerging radiogenomic knowledge base.

Availability and implementation

www.ImaGene.pgxguide.org, https://github.com/skr1/Imagene.git.

Supplementary information

Supplementary data are available at https://github.com/skr1/Imagene.git.

Renal Cell Carcinoma: Predicting DNA Methylation Subtyping and Its Consequences on Overall Survival With Computed Tomography Imaging Characteristics

PURPOSE

The aim of the study was to investigate associations between computed tomography (CT) imaging characteristics, DNA methylation subtyping, and overall survival in renal cell carcinomas.

METHODS

Survival curves were calculated using the Kaplan-Meier analysis. The CT data from 212 patients generated with The Cancer Imaging Archive (TCIA) were reviewed. Identified were 70 (33.0%) M1 subtype, 17 (8.0%) M2 subtype, and 125 (59.0%) M3 subtype. Univariate and multivariate analyses were performed using the logistic regression model.

RESULTS

Patients with M1 subtype had the shortest median overall survival (P < 0.001). On univariate analysis, long axis of 70 mm, intratumoral calcifications, enhancement, long axis > median, short axis > median, and intratumoral vascularity were associated with a significantly higher incidence of M1 subtype (P < 0.05). Short axis ≤ median, absence of necrosis, absence of intratumoral vascularity, and nodular enhancement were associated with M2 subtype (P < 0.05). Short axis ≤ median, long axis ≤ median, long axis of less than 70 mm, and necrosis were associated with a significantly higher incidence of M3 subtype (P < 0.05). On multivariate logistic regression analysis, long axis of greater than 70 mm (odds ratio [OR] = 2.452, P = 0.004; 95% confidence interval [CI] = 1.332-4.514) and necrosis (OR = 4.758, P = 0.041, 95% CI = 1.065-21.250) were associated with M1 subtype (area under the curve [AUC] = 0. 664). Necrosis (OR = 0.047, P < 0.001, 95% CI = 0.012-0.178) and enhancement (OR = 0.083, P = 0.024, 95% CI = 0.010-0.716) were associated with M2 subtype (AUC = 0.909). Long axis > median (OR = 0.303, P < 0.001, 95% CI = 0.164-0.561) and necrosis (OR = 3.256, P = 0.003, 95% CI = 1.617-10.303) were associated with M3 subtype (AUC = 0. 664).

CONCLUSIONS

The shortest survival was observed in patients with M1 subtype. This preliminary radiogenomics analysis of renal cell carcinoma demonstrated associations between CT imaging characteristic and DNA methylation subtyping.