Purpose: Build predictive radiomic models for early relapse and BRCA mutation based on a multicentric database of high-grade serous ovarian cancer (HGSOC) and validate them in a test set coming from different institutions. Methods: Preoperative CTs of patients with HGSOC treated at four referral centers were retrospectively acquired and manually segmented. Hand-crafted features and deep radiomics features were extracted respectively by dedicated software (MODDICOM) and a dedicated convolutional neural network (CNN). Features were selected with and without prior harmonization (ComBat harmonization), and models were built using different machine learning algorithms, including clinical variables. Results: We included 218 patients. Radiomic models showed low performance in predicting both BRCA mutation (AUC in test set between 0.46 and 0.59) and 1-year relapse (AUC in test set between 0.46 and 0.56); deep learning models demonstrated similar results (AUC in the test of 0.48 for BRCA and 0.50 for relapse). The inclusion of clinical variables improved the performance of the radiomic models to predict BRCA mutation (AUC in the test set of 0.74). Conclusions: In our multicentric dataset, representative of a real-life clinical scenario, we could not find a good radiomic predicting model for PFS and BRCA mutational status, with both traditional radiomics and deep learning, but the combination of clinical and radiomic models improved model performance for the prediction of BRCA mutation. These findings highlight the need for standardization through the whole radiomic pipelines and robust multicentric external validations of results.

Uterine adenomyosis is a common benign condition defined by the presence of heterotopic endometrial glands and stroma within the myometrium. Adenomyosis is often related to infertility and other adverse pregnancy outcomes. Modern imaging techniques allow the non-invasive diagnosis of adenomyosis and, in this framework, Magnetic Resonance Imaging (MRI) has assumed a central role due to its high diagnostic accuracy in the detection of adenomyosis. Currently, there is still a lack of international consensus on adenomyosis diagnostic criteria and classification, despite the fact that an agreed reporting system would promote treatment outcomes and research. This review aims to emphasize the important contribution of MRI to the diagnosis of adenomyosis and to highlight how, thanks to the great tissue differentiation provided by MRI, it is possible to identify the main direct (cystic component) and indirect (junctional zone features) signs of adenomyosis and to distinguish its various subtypes according to different MRI-based classifications. We also explored the main MRI criteria to identify the most common pitfalls and differential diagnoses of adenomyosis, whose features should be considered to avoid misdiagnosis.

High- and low-risk endometrial carcinoma (EC) differ in whether or not a lymphadenectomy is performed. We aimed to develop MRI-based radio-genomic models able to preoperatively assess lymph-vascular space invasion (LVSI) and discriminate between low- and high-risk EC according to the ESMO-ESGO-ESTRO 2020 guidelines, which include molecular risk classification proposed by “ProMisE”. This is a retrospective, multicentric study that included 64 women with EC who underwent 3T-MRI before a hysterectomy. Radiomics features were extracted from T2WI images and apparent diffusion coefficient maps (ADC) after manual segmentation of the gross tumor volume. We constructed a multiple logistic regression approach from the most relevant radiomic features to distinguish between low- and high-risk classes under the ESMO-ESGO-ESTRO 2020 guidelines. A similar approach was taken to assess LVSI. Model diagnostic performance was assessed via ROC curves, accuracy, sensitivity and specificity on training and test sets. The LVSI predictive model used a single feature from ADC as a predictor; the risk class model used two features as predictors from both ADC and T2WI. The low-risk predictive model showed an AUC of 0.74 with an accuracy, sensitivity, and specificity of 0.74, 0.76, 0.94; the LVSI model showed an AUC of 0.59 with an accuracy, sensitivity, and specificity of 0.60, 0.50, 0.61. MRI-based radio-genomic models are useful for preoperative EC risk stratification and may facilitate therapeutic management.

Structured reporting systems for endometriotic disease are gaining a central role in diagnostic imaging: our aim is to evaluate applicability and the feasibility of the recent ENZIAN score (2020) assessed by MRI. A total of 60 patients with suspected tubo–ovarian/deep endometriosis were retrospectively included in our study according to the following criteria: availability of MR examination; histopathological results from laparoscopic or surgical treatment; patients were not assuming estro-progestin or progestin therapy. Three different readers (radiologists with 2-, 5-, and 20-years of experience in pelvic imaging) have separately assigned a score according to the ENZIAN score (revised 2020) for all lesions detected by magnetic resonance imaging (MRI). Our study showed a high interobserver agreement and feasibility of the recent ENZIAN score applied to MRI; on the other hand, our experience highlighted some limitations mainly due to MRI’s inability to assess tubal patency and mobility, as required by the recent score (2020). In view of the limitations which arose from our study, we propose a modified MRI-ENZIAN score that provides a complete structured reporting system, more suitable for MRI. The high interobserver agreement of the recent ENZIAN score applied to MRI confirms its validity as a complete staging system for endometriosis, offering a shared language between radiologists and surgeons.

Purpose: Introduce DWI and quantitative ADC evaluation in O-RADS MRI system and observe how diagnostic performance changes. Assess its validity and reproducibility between readers with different experience in female pelvic imaging. Finally, evaluate any correlation between ADC value and histotype in malignant lesions. Materials and Methods: In total, 173 patients with 213 indeterminate adnexal masses (AMs) on ultrasound were subjected to MRI examination, from which 140 patients with 172 AMs were included in the final analysis. Standardised MRI sequences were used, including DWI and DCE sequences. Two readers, blinded to histopathological data, retrospectively classified AMs according to the O-RADS MRI scoring system. A quantitative analysis method was applied by placing a ROI on the ADC maps obtained from single-exponential DWI sequences. AMs considered benign (O-RADS MRI score 2) were excluded from the ADC analysis. Results: Excellent inter-reader agreement was found in the classification of lesions according to the O-RADS MRI score (K = 0.936; 95% CI). Two ROC curves were created to determine the optimal cut-off value for the ADC variable between O-RADS MRI categories 3–4 and 4–5, respectively, 1.411 × 10^–3 mm²/sec and 0.849 × 10^–3 mm²/sec. Based on these ADC values, 3/45 and 22/62 AMs were upgraded, respectively, to score 4 and 5, while 4/62 AMs were downgraded to score 3. ADC values correlated significantly with the ovarian carcinoma histotype (p value < 0.001). Conclusion: Our study demonstrates the prognostic potential of DWI and ADC values in the O-RADS MRI classification for better radiological standardisation and characterisation of AMs.

The aim of this study was to determine whether quantitative parameters obtained from intravoxel incoherent motion (IVIM) model at baseline magnetic resonance imaging (MRI) correlate with histological parameters and response to neoadjuvant chemotherapy in patients with locally advanced cervical cancer (LACC). Methods: Twenty patients with biopsy-proven cervical cancer, staged as LACC on baseline MRI and addressed for neoadjuvant chemotherapy were enrolled. At treatment completion, tumor response was assessed with a follow-up MRI evaluated using the revised response evaluation criteria in solid tumors (RECIST; version 1.1), and patients were considered good responders (GR) if they had complete response or partial remission, and poor responders/non-responders (PR/NR) if they had stable or progressive disease. MRI protocol included conventional diffusion-weighted imaging (DWI; b = 0 and 1000 s/mm²) and IVIM acquisition using eight b-values (range: 0–1500 s/mm²). MR-images were analyzed using a dedicated software to obtain quantitative parameters: diffusion (D), pseudo-diffusion (D*), and perfusion fraction (fp) from the IVIM model; apparent diffusion coefficient (ADC) from conventional DWI. Histologic subtype, grading, and tumor-infiltrating lymphocytes (TILs) were assessed in each LACC. Results: D showed significantly higher values in GR patients (p = 0.001) and in moderate/high TILs (p = 0.018). Fp showed significantly higher values in squamous cell tumors (p = 0.006). Conclusions: D extracted from the IVIM model could represent a promising tool to identify tumor aggressiveness and predict response to therapy.