Computer Tomography in the Diagnosis of Ovarian Cysts: The Role of Fluid Attenuation Values

Radiomics in the CT diagnosis of ovarian cystic malignancies - a pilot study

Background and aims

The conventional computed tomography (CT) appearance of ovarian cystic masses is often insufficient to adequately differentiate between benign and malignant entities. This study aims to investigate whether texture analysis of the fluid component can augment the CT diagnosis of ovarian cystic tumors.

Methods

Eighty-four patients with adnexal cystic lesions who underwent CT examinations were retrospectively included. All patients had a final diagnosis that was established by histological analysis in forty four cases. The texture features of the lesions content were extracted using dedicated software and further used for comparing benign and malignant lesions, primary tumors and metastases, malignant and borderline lesions, and benign and borderline lesions. Texture features' discriminatory ability was evaluated through univariate and receiver operating characteristics analysis and also by the use of the k-nearest-neighbor classifier.

Results

The univariate analysis showed statistically significant results when comparing benign and malignant lesions (the Difference Variance parameter, p=0.0074) and malignant and borderline tumors (the Correlation parameter, p=0.488). The highest accuracy (83.33%) was achieved by the classifier when discriminating primary tumors from ovarian metastases.

Conclusion

Texture parameters were able to successfully discriminate between different types of ovarian cystic lesions based on their content, but it is not entirely clear whether these differences are a result of the physical properties of the fluids or their appartenance to a particular histopathological group. If further validated, radiomics can offer a rapid and non-invasive alternative in the diagnosis of ovarian cystic tumors.

CT-Based Radiomic Analysis May Predict Bacteriological Features of Infected Intraperitoneal Fluid Collections after Gastric Cancer Surgery

The ability of texture analysis (TA) features to discriminate between different types of infected fluid collections, as seen on computed tomography (CT) images, has never been investigated. The study comprised forty patients who had pathological post-operative fluid collections following gastric cancer surgery and underwent CT scans. Patients were separated into six groups based on advanced microbiological analysis of the fluid: mono bacterial (n = 16)/multiple-bacterial (n = 24)/fungal (n = 14)/non-fungal (n = 26) infection and drug susceptibility tests into: multiple drug-resistance bacteria (n = 23) and non-resistant bacteria (n = 17). Dedicated software was used to extract the collections’ TA parameters. The parameters obtained were used to compare fungal and non-fungal infections, mono-bacterial and multiple-bacterial infections, and multiresistant and non-resistant infections. Univariate and receiver operating characteristic analyses and the calculation of sensitivity (Se) and specificity (Sp) were used to identify the best-suited parameters for distinguishing between the selected groups. TA parameters were able to differentiate between fungal and non-fungal collections (ATeta3, p = 0.02; 55% Se, 100% Sp), mono and multiple-bacterial (CN2D6AngScMom, p = 0.03); 80% Se, 64.29% Sp) and between multiresistant and non-multiresistant collections (CN2D6Contrast, p = 0.04; 100% Se, 50% Sp). CT-based TA can statistically differentiate between different types of infected fluid collections. However, it is unclear which of the fluids’ micro or macroscopic features are reflected by the texture parameters. In addition, this cohort is used as a training cohort for the imaging algorithm, with further validation cohorts being required to confirm the changes detected by the algorithm.

Quantitative MRI of Pancreatic Cystic Lesions: A New Diagnostic Approach

The commonly used magnetic resonance (MRI) criteria can be insufficient for discriminating mucinous from non-mucinous pancreatic cystic lesions (PCLs). The histological differences between PCLs’ fluid composition may be reflected in MRI images, but cannot be assessed by visual evaluation alone. We investigate whether additional MRI quantitative parameters such as signal intensity measurements (SIMs) and radiomics texture analysis (TA) can aid the differentiation between mucinous and non-mucinous PCLs. Fifty-nine PCLs (mucinous, n = 24; non-mucinous, n = 35) are retrospectively included. The SIMs were performed by two radiologists on T2 and diffusion-weighted images (T2WI and DWI) and apparent diffusion coefficient (ADC) maps. A total of 550 radiomic features were extracted from the T2WI and ADC maps of every lesion. The SIMs and TA features were compared between entities using univariate, receiver-operating, and multivariate analysis. The SIM analysis showed no statistically significant differences between the two groups (p = 0.69, 0.21–0.43, and 0.98 for T2, DWI, and ADC, respectively). Mucinous and non-mucinous PLCs were successfully discriminated by both T2-based (83.2–100% sensitivity and 69.3–96.2% specificity) and ADC-based (40–85% sensitivity and 60–96.67% specificity) radiomic features. SIMs cannot reliably discriminate between PCLs. Radiomics have the potential to augment the common MRI diagnosis of PLCs by providing quantitative and reproducible imaging features, but validation is required by further studies.

Ultrasonography in the Diagnosis of Adnexal Lesions: The Role of Texture Analysis

The classic ultrasonographic differentiation between benign and malignant adnexal masses encounters several limitations. Ultrasonography-based texture analysis (USTA) offers a new perspective, but its role has been incompletely evaluated. This study aimed to further investigate USTA’s capacity in differentiating benign from malignant adnexal tumors, as well as comparing the workflow and the results with previously-published research. A total of 123 adnexal lesions (benign, 88; malignant, 35) were retrospectively included. The USTA was performed on dedicated software. By applying three reduction techniques, 23 features with the highest discriminatory potential were selected. The features’ ability to identify ovarian malignancies was evaluated through univariate, multivariate, and receiver operating characteristics analyses, and also by the use of the k-nearest neighbor (KNN) classifier. Three parameters were independent predictors for ovarian neoplasms (sum variance, and two variations of the sum of squares). Benign and malignant lesions were differentiated with 90.48% sensitivity and 93.1% specificity by the prediction model (which included the three independent predictors), and with 71.43–80% sensitivity and 87.5–89.77% specificity by the KNN classifier. The USTA shows statistically significant differences between the textures of the two groups, but it is unclear whether the parameters can reflect the true histopathological characteristics of adnexal lesions.