Peritumoral MRI Radiomics Features Increase the Evaluation Efficiency for Response to Chemotherapy in Patients With Epithelial Ovarian Cancer.

BACKGROUND: It remains unclear whether extracting peritumoral volume (PTV) radiomics features are useful tools for evaluating response to chemotherapy of epithelial ovarian cancer (EOC). PURPOSE: To evaluate MRI radiomics signatures (RS) capturing subtle changes of PTV and their added evaluation performance to whole tumor volume (WTV) for response to chemotherapy in patients with EOC. STUDY TYPE: Retrospective. POPULATION: 219 patients aged from 15 to 79 years were enrolled. FIELD STRENGTH/SEQUENCE: 3.0 or 1.5T, axial fat-suppressed T2-weighted imaging (FS-T2WI), diffusion-weighted imaging (DWI), and contrast enhanced T1-weighted imaging (CE-T1WI). ASSESSMENT: MRI features were extracted from the four axial sequences and six different volumes of interest (VOIs) (WTV and WTV + PTV (WPTV)) with different peritumor sizes (PS) ranging from 1 to 5 mm. Those features underwent preprocessing, and the most informative features were selected using minimum redundancy maximum relevance and least absolute shrinkage and selection operator to construct the RS. The optimal RS, with the highest area under the curve (AUC) of receiver operating characteristic was then integrated with independent clinical characteristics through multivariable logistic regression to construct the radiomics-clinical model (RCM). STATISTICAL TESTS: Mann-Whitney U test, chi-squared test, DeLong test, log-rank test. P < 0.05 indicated a significant difference. RESULTS: All the RSs constructed on WPTV exhibited higher AUCs (0.720-0.756) than WTV (0.671). Of which, RS with PS = 2 mm displayed a significantly better performance (AUC = 0.756). International Federation of Gynecology and Obstetrics (FIGO) stage was identified as the exclusive independent clinical evaluation characteristic, and the RCM demonstrated higher AUC (0.790) than the RS, but without statistical significance (P = 0.261). DATA CONCLUSION: The radiomics features extracted from PTV could increase the efficiency of WTV radiomics for evaluating the chemotherapy response of EOC. The cut-off of 2 mm PTV was a reasonable value to obtain effective evaluation efficiency. LEVEL OF EVIDENCE: 4 TECHNICAL EFFICACY: Stage 2.

Deep Learning Nomogram for the Identification of Deep Stromal Invasion in Patients With Early-Stage Cervical Adenocarcinoma and Adenosquamous Carcinoma: A Multicenter Study.

BACKGROUND: Deep stromal invasion (DSI) is one of the predominant risk factors that determined the types of radical hysterectomy (RH). Thus, the accurate assessment of DSI in cervical adenocarcinoma (AC)/adenosquamous carcinoma (ASC) can facilitate optimal therapy decision. PURPOSE: To develop a nomogram to identify DSI in cervical AC/ASC. STUDY TYPE: Retrospective. POPULATION: Six hundred and fifty patients (mean age of 48.2 years) were collected from center 1 (primary cohort, 536), centers 2 and 3 (external validation cohorts 1 and 2, 62 and 52). FIELD STRENGTH/SEQUENCE: 5-T, T2-weighted imaging (T2WI, SE/FSE), diffusion-weighted imaging (DWI, EPI), and contrast-enhanced T1-weighted imaging (CE-T1WI, VIBE/LAVA). ASSESSMENT: The DSI was defined as the outer 1/3 stromal invasion on pathology. The region of interest (ROI) contained the tumor and 3 mm peritumoral area. The ROIs of T2WI, DWI, and CE-T1WI were separately imported into Resnet18 to calculate the DL scores (TDS, DDS, and CDS). The clinical characteristics were retrieved from medical records or MRI data assessment. The clinical model and nomogram were constructed by integrating clinical independent risk factors only and further combining DL scores based on primary cohort and were validated in two external validation cohorts. STATISTICAL TESTS: Student's t-test, Mann-Whitney U test, or Chi-squared test were used to compare differences in continuous or categorical variables between DSI-positive and DSI-negative groups. DeLong test was used to compare AU-ROC values of DL scores, clinical model, and nomogram. RESULTS: The nomogram integrating menopause, disruption of cervical stromal ring (DCSRMR), DDS, and TDS achieved AU-ROCs of 0.933, 0.807, and 0.817 in evaluating DSI in primary and external validation cohorts. The nomogram had superior diagnostic ability to clinical model and DL scores in primary cohort (all P < 0.0125 [0.05/4]) and CDS (P = 0.009) in external validation cohort 2. DATA CONCLUSION: The nomogram achieved good performance for evaluating DSI in cervical AC/ASC. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY: Stage 2.

Intratumoral and peritumoral MRI radiomics nomogram for predicting parametrial invasion in patients with early-stage cervical adenocarcinoma and adenosquamous carcinoma.

OBJECTIVE: To develop a comprehensive nomogram based on MRI intra- and peritumoral radiomics signatures and independent risk factors for predicting parametrial invasion (PMI) in patients with early-stage cervical adenocarcinoma (AC) and adenosquamous carcinoma (ASC). METHODS: A total of 460 patients with IB to IIB cervical AC and ASC who underwent preoperative MRI examination and radical trachelectomy/hysterectomy were retrospectively enrolled and divided into primary, internal validation, and external validation cohorts. The original (Ori) and wavelet (Wav)-transform features were extracted from the volumetric region of interest of the tumour (ROI-T) and 3mm- and 5mm-peritumoral rings (ROI-3 and ROI-5), respectively. Then the Ori and Ori-Wav feature-based radiomics signatures from the tumour (RST) and 3 mm- and 5 mm-peritumoral regions (RS3 and RS5) were independently built and their diagnostic performances were compared to select the optimal ones. Finally, the nomogram was developed by integrating optimal intra- and peritumoral signatures and clinical independent risk factors based on multivariable logistic regression analysis. RESULTS: FIGO stage, disruption of the cervical stromal ring on MRI (DCSRMR), parametrial invasion on MRI (PMIMR), and serum CA-125 were identified as independent risk factors. The nomogram constructed by integrating independent risk factors, Ori-Wav feature-based RST, and RS5 yielded AUCs of 0.874 (0.810-0.922), 0.885 (0.834-0.924), and 0.966 (0.887-0.995) for predicting PMI in the primary, internal and external validation cohorts, respectively. Furthermore, the nomogram was superior to radiomics signatures and clinical model for predicting PMI in three cohorts. CONCLUSION: The nomogram can preoperatively, accurately, and noninvasively predict PMI in patients with early-stage cervical AC and ASC. CLINICAL RELEVANCE STATEMENT: The nomogram can preoperatively, accurately, and noninvasively predict PMI and facilitate precise treatment decisions regarding chemoradiotherapy or radical hysterectomy in patients with early-stage cervical AC and ASC. KEY POINTS: The accurate preoperative prediction of PMI in early-stage cervical AC and ASC can facilitate precise treatment decisions regarding chemoradiotherapy or radical hysterectomy. The nomogram integrating independent risk factors, Ori-Wav feature-based RST, and RS5 can preoperatively, accurately, and noninvasively predict PMI in early-stage cervical AC and ASC. The nomogram was superior to radiomics signatures and clinical model for predicting PMI in early-stage cervical AC and ASC.

In vivo detection of dysregulated choline metabolism in paclitaxel-resistant ovarian cancers with proton magnetic resonance spectroscopy.

BACKGROUND: Chemoresistance gradually develops during treatment of epithelial ovarian cancer (EOC). Metabolic alterations, especially in vivo easily detectable metabolites in paclitaxel (PTX)-resistant EOC remain unclear. METHODS: Xenograft models of the PTX-sensitive and PTX-resistant EOCs were built. Using a combination of in vivo proton-magnetic resonance spectroscopy (1H-MRS), metabolomics and proteomics, we investigated the in vivo metabolites and dysregulated metabolic pathways in the PTX-resistant EOC. Furthermore, we analyzed the RNA expression to validate the key enzymes in the dysregulated metabolic pathway. RESULTS: On in vivo 1H-MRS, the ratio of (glycerophosphocholine + phosphocholine) to (creatine + phosphocreatine) ((GPC + PC) to (Cr + PCr))(i.e. Cho/Cr) in the PTX-resistant tumors (1.64 [0.69, 4.18]) was significantly higher than that in the PTX-sensitive tumors (0.33 [0.10, 1.13]) (P = 0.04). Forty-five ex vivo metabolites were identified to be significantly different between the PTX-sensitive and PTX-resistant tumors, with the majority involved of lipids and lipid-like molecules. Spearman's correlation coefficient analysis indicated in vivo and ex vivo metabolic characteristics were highly consistent, exhibiting the highest positive correlation between in vivo GPC + PC and ex vivo GPC (r = 0.885, P < 0.001). These metabolic data suggested that abnormal choline concentrations were the results from the dysregulated glycerophospholipid metabolism, especially choline metabolism. The proteomics data indicated that the expressions of key enzymes glycerophosphocholine phosphodiesterase 1 (GPCPD1) and glycerophosphodiester phosphodiesterase 1 (GDE1) were significantly lower in the PTX-resistant tumors compared to the PTX-sensitive tumors (both P < 0.01). Decreased expressions of GPCPD1 and GDE1 in choline metabolism led to an increased GPC levels in the PTX-resistant EOCs, which was observed as an elevated total choline (tCho) on in vivo 1H-MRS. CONCLUSIONS: These findings suggested that dysregulated choline metabolism was associated with PTX-resistance in EOCs and the elevated tCho on in vivo 1H-MRS could be as an indicator for the PTX-resistance in EOCs.

MRI-Based Multiple Instance Convolutional Neural Network for Increased Accuracy in the Differentiation of Borderline and Malignant Epithelial Ovarian Tumors.

BACKGROUND: Preoperative differentiation of borderline from malignant epithelial ovarian tumors (BEOT vs. MEOT) is challenging and can significantly impact surgical management. PURPOSE: To develop a multiple instance convolutional neural network (MICNN) that can differentiate BEOT from MEOT, and to compare its diagnostic performance with that of radiologists. STUDY TYPE: Retrospective study of eight clinical centers. SUBJECTS: Between January 2010 and June 2018, a total of 501 women (mean age, 48.93 ± 14.05 years) with histopathologically confirmed BEOT (N = 165) or MEOT (N = 336) were divided into the training (N = 342) and validation cohorts (N = 159). FIELD STRENGTH/SEQUENCE: Three axial sequences from 1.5 or 3 T scanner were used: fast spin echo T2-weighted imaging with fat saturation (T2WI FS), echo planar diffusion-weighted imaging, and 2D volumetric interpolated breath-hold examination of contrast-enhanced T1-weighted imaging (CE-T1WI) with FS. ASSESSMENT: Three monoparametric MICNN models were built based on T2WI FS, apparent diffusion coefficient map, and CE-T1WI. Based on these monoparametric models, we constructed an early multiparametric (EMP) model and a late multiparametric (LMP) model using early and late information fusion methods, respectively. The diagnostic performance of the models was evaluated using the receiver operating characteristic (ROC) curve and compared to the performance of six radiologists with varying levels of experience. STATISTICAL TESTS: We used DeLong test, chi-square test, Mann-Whitney U-test, and t-test, with significance level of 0.05. RESULTS: Both EMP and LMP models differentiated BEOT from MEOT, with an area under the ROC curve (AUC) of 0.855 (95% CI, 0.795-0.915) and 0.884 (95% CI, 0.831-0.938), respectively. The AUC of the LMP model was significantly higher than the radiologists' pooled AUC (0.884 vs. 0.797). DATA CONCLUSION: The developed MICNN models can effectively differentiate BEOT from MEOT and the diagnostic performances (AUCs) were more superior than that of the radiologists' assessments. LEVEL OF EVIDENCE: 3 TECHNICAL EFFICACY STAGE: 2.

Noninvasive prediction of residual disease for advanced high-grade serous ovarian carcinoma by MRI-based radiomic-clinical nomogram.

OBJECTIVES: To develop a preoperative MRI-based radiomic-clinical nomogram for prediction of residual disease (RD) in patients with advanced high-grade serous ovarian carcinoma (HGSOC). METHODS: In total, 217 patients with advanced HGSOC were enrolled from January 2014 to June 2019 and randomly divided into a training set (n = 160) and a validation set (n = 57). Finally, 841 radiomic features were extracted from each tumor on T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted imaging (CE-T1WI) sequence, respectively. We used two fusion methods, the maximal volume of interest (MV) and the maximal feature value (MF), to fuse the radiomic features of bilateral tumors, so that patients with bilateral tumors have the same kind of radiomic features as patients with unilateral tumors. The radiomic signatures were constructed by using mRMR method and LASSO classifier. Multivariable logistic regression analysis was used to develop a radiomic-clinical nomogram incorporating radiomic signature and conventional clinico-radiological features. The performance of the nomogram was evaluated on the validation set. RESULTS: In total, 342 tumors from 217 patients were analyzed in this study. The MF-based radiomic signature showed significantly better prediction performance than the MV-based radiomic signature (AUC = 0.744 vs. 0.650, p = 0.047). By incorporating clinico-radiological features and MF-based radiomic signature, radiomic-clinical nomogram showed favorable prediction ability with an AUC of 0.803 in the validation set, which was significantly higher than that of clinico-radiological signature and MF-based radiomic signature (AUC = 0.623, 0.744, respectively). CONCLUSIONS: The proposed MRI-based radiomic-clinical nomogram provides a promising way to noninvasively predict the RD status. KEY POINTS: • MRI-based radiomic-clinical nomogram is feasible to noninvasively predict residual disease in patients with advanced HGSOC. • The radiomic signature based on MF showed significantly better prediction performance than that based on MV. • The radiomic-clinical nomogram showed a favorable prediction ability with an AUC of 0.803.

MR image-based radiomics to differentiate type Ι and type ΙΙ epithelial ovarian cancers.

OBJECTIVES: Epithelial ovarian cancers (EOC) can be divided into type I and type II according to etiology and prognosis. Accurate subtype differentiation can substantially impact patient management. In this study, we aimed to construct an MR image-based radiomics model to differentiate between type I and type II EOC. METHODS: In this multicenter retrospective study, a total of 294 EOC patients from January 2010 to February 2019 were enrolled. Quantitative MR imaging features were extracted from the following axial sequences: T2WI FS, DWI, ADC, and CE-T1WI. A combined model was constructed based on the combination of these four MR sequences. The diagnostic performance was evaluated by ROC-AUC. In addition, an occlusion test was carried out to identify the most critical region for EOC differentiation. RESULTS: The combined radiomics model exhibited superior diagnostic capability over all four single-parametric radiomics models, both in internal and external validation cohorts (AUC of 0.806 and 0.847, respectively). The occlusion test revealed that the most critical region for differential diagnosis was the border zone between the solid and cystic components, or the less compact areas of solid component on direct visual inspection. CONCLUSIONS: MR image-based radiomics modeling can differentiate between type I and type II EOC and identify the most critical region for differential diagnosis. KEY POINTS: • Combined radiomics models exhibited superior diagnostic capability over all four single-parametric radiomics models, both in internal and external validation cohorts (AUC of 0.834 and 0.847, respectively). • The occlusion test revealed that the most crucial region for differentiating type Ι and type ΙΙ EOC was the border zone between the solid and cystic components, or the less compact areas of solid component on direct visual inspection on T2WI FS. • The light-combined model (constructed by T2WI FS, DWI, and ADC sequences) can be used for patients who are not suitable for contrast agent use.

Perfusion-based functional magnetic resonance imaging for differentiating serous borderline ovarian tumors from early serous ovarian cancers in a rat model.

BACKGROUND: Differentiation of borderline tumors from early ovarian cancer has recently received increasing attention, since borderline tumors often affect young women of childbearing age who desire to preserve fertility. However, previous studies have demonstrated that non-enhanced magnetic resonance imaging (MRI) sequences cannot sufficiently differentiate these tumors. PURPOSE: To investigate the value of dynamic contrast-enhanced MRI (DCE-MRI) and intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) in differentiating serous borderline ovarian tumors (SBOT) from early serous ovarian cancers (eSOCA). MATERIAL AND METHODS: Twenty SBOT and 20 eSOCA rat models were performed with DCE-MRI and IVIM-DWI at 3.0-T MR scanner. Qualitative and quantitative parameters of DCE-MRI were acquired and compared between two groups and correlated with the microvessel density (MVD). The receiver operating characteristic (ROC) curve analyses were conducted to determine their differentiating performances. RESULTS: SBOTs presented significantly lower values of the initial area under the enhancement curve (iAUC), volume transfer constant (Ktrans), and extracellular extravascular volume fraction (ve) (P < 0.05) and a significantly higher value of true diffusion (D) (P = 0.001) compared with eSOCAs. The diagnostic effectiveness of ve combined with D was significantly better than that of ve or Ktrans alone (P ≤ 0.039). CONCLUSION: DCE-MRI may represent a promising tool for differentiating SBOTs from eSOCAs and may not be replaced by IVIM-DWI. Combining DCE-MRI with DWI may improve the diagnostic performance of ovarian tumors.

MRI-Based Machine Learning for Differentiating Borderline From Malignant Epithelial Ovarian Tumors: A Multicenter Study.

BACKGROUND: Preoperative differentiation of borderline from malignant epithelial ovarian tumors (BEOT from MEOT) can impact surgical management. MRI has improved this assessment but subjective interpretation by radiologists may lead to inconsistent results. PURPOSE: To develop and validate an objective MRI-based machine-learning (ML) assessment model for differentiating BEOT from MEOT, and compare the performance against radiologists' interpretation. STUDY TYPE: Retrospective study of eight clinical centers. POPULATION: In all, 501 women with histopathologically-confirmed BEOT (n = 165) or MEOT (n = 336) from 2010 to 2018 were enrolled. Three cohorts were constructed: a training cohort (n = 250), an internal validation cohort (n = 92), and an external validation cohort (n = 159). FIELD STRENGTH/SEQUENCE: Preoperative MRI within 2 weeks of surgery. Single- and multiparameter (MP) machine-learning assessment models were built utilizing the following four MRI sequences: T2 -weighted imaging (T2 WI), fat saturation (FS), diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC), and contrast-enhanced (CE)-T1 WI. ASSESSMENT: Diagnostic performance of the models was assessed for both whole tumor (WT) and solid tumor (ST) components. Assessment of the performance of the model in discriminating BEOT vs. early-stage MEOT was made. Six radiologists of varying experience also interpreted the MR images. STATISTICAL TESTS: Mann-Whitney U-test: significance of the clinical characteristics; chi-square test: difference of label; DeLong test: difference of receiver operating characteristic (ROC). RESULTS: The MP-ST model performed better than the MP-WT model for both the internal validation cohort (area under the curve [AUC] = 0.932 vs. 0.917) and external validation cohort (AUC = 0.902 vs. 0.767). The model showed capability in discriminating BEOT vs. early-stage MEOT, with AUCs of 0.909 and 0.920, respectively. Radiologist performance was considerably poorer than both the internal (mean AUC = 0.792; range, 0.679-0.924) and external (mean AUC = 0.797; range, 0.744-0.867) validation cohorts. DATA CONCLUSION: Performance of the MRI-based ML model was robust and superior to subjective assessment of radiologists. If our approach can be implemented in clinical practice, improved preoperative prediction could potentially lead to preserved ovarian function and fertility for some women. LEVEL OF EVIDENCE: Level 4. TECHNICAL EFFICACY: Stage 2. J. Magn. Reson. Imaging 2020;52:897-904.

Role of proton MR spectroscopy in the differentiation of borderline from malignant epithelial ovarian tumors: A preliminary study.

BACKGROUND: Due to the overlapping imaging appearances between borderline and malignant epithelial ovarian tumors (EOTs), borderline EOTs often represent a diagnostic challenge on conventional MRI. Proton magnetic resonance spectroscopy (1 H-MRS) might have potential to differentiate borderline from malignant tumors. PURPOSE: To investigate the ability of 1 H-MRS to differentiate borderline from malignant EOTs. STUDY TYPE: Prospective. POPULATION: In all, 278 patients with adnexal masses. FIELD STRENGTH/SEQUENCE: 1.5 T Siemens Avanto MRI system and 1 H-MRS using a point-resolved spectroscopy sequence (PRESS). ASSESSMENT: Resonance peak integrals of the most common metabolites were analyzed and compared between the two groups. STATISTICAL TESTS: The ratios of metabolites between borderline and malignant EOTs were compared with the Mann-Whitney U-test. A receiver operating characteristic (ROC) curve was used to determine their differential diagnosis performances. RESULTS: In the solid components of borderline and malignant EOTs, the mean Cho/Cr, NAA/Cr, and NAA/Cho ratios were 4.4 ± 1.1 and 9.9 ± 2.8; 10.4 ± 3.0 and 2.2 ± 1.0; and 2.4 ± 0.7 and 0.3 ± 0.1, respectively (all P < 0.001). The sensitivity, specificity, and area under the curve (AUC) were 91%, 100%, and 0.98 for the Cho/Cr ratio; 100%, 98%, and 0.99 for the NAA/Cr ratio; and 100%, 100%, and 1.00 for the NAA/Cho ratio, respectively. In the cystic components, the mean Cho/Cr, NAA/Cr, and NAA/Cho ratios were 3.2 ± 0.8 and 5.1 ± 1.2; 9.1 ± 3.4 and 2.3 ± 1.4; and 2.9 ± 1.2 and 0.5 ± 0.4, respectively (all P < 0.001). The sensitivity, specificity, and AUC were 84%, 82%, and 0.89 for the Cho/Cr ratio; 94%, 97%, and 0.99 for the NAA/Cr ratio; and 94%, 97%, and 0.99 for the NAA/Cho ratio, respectively. DATA CONCLUSION: The NAA/Cho ratio is a reliable biomarker for differentiating borderline from malignant EOTs. LEVEL OF EVIDENCE: 2 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2019;49:1684-1693.

Diffusion kurtosis imaging for differentiating borderline from malignant epithelial ovarian tumors: A correlation with Ki-67 expression.

PURPOSE: To investigate the use of diffusion kurtosis imaging (DKI) in differentiating borderline from malignant epithelial ovarian tumors (MEOTs) and to correlate DKI parameters with Ki-67 expression. MATERIALS AND METHODS: Fifty-two consecutive patients with epithelial ovarian tumors (17 borderline epithelial ovarian tumors, BEOTs; 35 MEOTs) were prospectively evaluated using DKI with b values of 0, 500, 1000, 1500, 2000, and 2500 s/mm2 and standard diffusion-weighted imaging (DWI) with b values of 0 and 1000 s/mm2 using a 1.5T magnetic resonance imaging (MRI) unit. The kurtosis (K) and diffusion coefficient (D) from DKI and apparent diffusion coefficient (ADC) from standard DWI were measured, compared, and correlated with Ki-67 expression between the two groups. Statistical analyses were performed using the Mann-Whitney U-test, receiver operating characteristic (ROC) curves, and Spearman's correlation. RESULTS: The K value was significantly lower in BEOTs than in MEOTs (0.55 ± 0.09 vs. 0.9 ± 0.2), while the D and ADC values were significantly higher in BEOTs than in MEOTs (2.27 ± 0.35 vs. 1.39 ± 0.37 and 1.72 ± 0.36 vs. 1.1 ± 0.25, respectively) (P < 0.001). For differentiating between BEOTs and MEOTs, the sensitivity, specificity, and accuracy were 88.2%, 94.3%, and 92.3% for K value; 88.2%, 91.4%, and 90.4% for D value; and 88.2%, 88.6%, and 88.5% for ADC value, respectively. However, there were no differences in the diagnostic performances among the three parameters above (K vs. ADC, P = 0.203; D vs. ADC, P = 0.148; K vs. D, P = 0.904). The K value was positively correlated with Ki-67 expression (r = 0.699), while the D and ADC values were negatively correlated with Ki-67 expression (r = -0.680, -0.665, respectively). CONCLUSION: Preliminary findings demonstrate that DKI is an alternative tool for differentiating BEOTs from MEOTs, and is correlated with Ki-67 expression. However, no added value is found for DKI compared with standard DWI. LEVEL OF EVIDENCE: 1 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2017;46:1499-1506.

Multiparametric MRI-based radiomics nomogram for differentiation of primary mucinous ovarian cancer from metastatic ovarian cancer.

OBJECTIVE: To develop a multiparametric magnetic resonance imaging (mpMRI)-based radiomics nomogram and evaluate its performance in differentiating primary mucinous ovarian cancer (PMOC) from metastatic ovarian cancer (MOC). METHODS: A total of 194 patients with PMOC (n = 72) and MOC (n = 122) confirmed by histology were randomly divided into the primary cohort (n = 137) and validation cohort (n = 57). Radiomics features were extracted from axial fat-saturated T2-weighted imaging (FS-T2WI), diffusion-weighted imaging (DWI), and contrast-enhanced T1-weighted imaging (CE-T1WI) sequences of each lesion. The effective features were selected by minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) regression to develop a radiomics model. Combined with clinical features, multivariate logistic regression analysis was employed to develop a radiomics nomogram. The efficiency of nomogram was evaluated using the receiver operating characteristic (ROC) curve analysis and compared using DeLong test. Finally, the goodness of fit and clinical benefit of nomogram were assessed by calibration curves and decision curve analysis, respectively. RESULTS: The radiomics nomogram, by combining the mpMRI radiomics features with clinical features, yielded area under the curve (AUC) values of 0.931 and 0.934 in the primary and validation cohorts, respectively. The predictive performance of the radiomics nomogram was significantly superior to the radiomics model (0.931 vs. 0.870, P = 0.004; 0.934 vs. 0.844, P = 0.032), the clinical model (0.931 vs. 0.858, P = 0.005; 0.934 vs. 0.847, P = 0.030), and radiologists (all P < 0.05) in the primary and validation cohorts, respectively. The decision curve analysis revealed that the nomogram could provide higher net benefit to patients. CONCLUSION: The mpMRI-based radiomics nomogram exhibited notable predictive performance in differentiating PMOC from MOC, emerging as a non-invasive preoperative imaging approach.

Comparison of MRI features among squamous cell carcinoma, adenocarcinoma and adenosquamous carcinoma, usual-type endocervical adenocarcinoma and gastric adenocarcinoma of cervix.

OBJECTIVE: To compare and explore the characteristics of squamous cell carcinoma (SCC), adenocarcinoma (AC) and adenosquamous carcinoma (ASC), usual-type endocervical adenocarcinoma (UEA) and gastric adenocarcinoma (GAC) of cervix. MATERIALS AND METHODS: A total of 728 cervical cancers (254 cases of AC, 252 cases of ASC, and 222 cases of SCC) confirmed by histopathology were retrospectively reviewed. Among AC, 119 UEA and 47 GAC were included. Clinical baseline data and tumor morphological features on MRI (including tumor location, shape, diameter and volume, margin, growth pattern, presence of fluid component or cyst, heterogenous and peritumoral enhancement) of all cases were collected and analyzed. The signal intensity (SI) of tumor and gluteus maximus muscle were measured and their ratios (SIR) were calculated based on T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC) and contrast-enhanced T1WI at arterial and delay phases (A/DCE-T1WI). These clinical and MRI features were compared between SCC, AC and ASC, UEA and GAC, and the specific ones of each subtype were identified. RESULTS: There was a significant difference in SCC-Ag, CA-199, CEA, ADC value, SIR-DWI, presence of intratumor cyst and peritumoral enhancement between AC and ASC; in patient age, menopausal status, International Federation of Gynecology and Obstetrics (FIGO) stage, SCC-Ag, CA-125, CA-199, CEA, tumor shape, growth pattern, margin, presence of intratumor fluid component and cyst, tumor diameter and volume, ADC value, SIR-T1WI, SIR-T2WI, and SIR-DWI between SCC and AC, as well as SCC and ASC. Also, there was a significant difference in deep stromal invasion (DSI), peritumoral and heterogenous enhancement between SCC and AC, and in SIR-ACE-T1WI between SCC and ASC. There was a significant difference in reproductive history, menopausal status, FIGO stage, CA-199, DSI, lymph node metastasis (LNM), parametrial invasion (PMI), tumor location, shape, margin, growth pattern, presence of fluid component and cyst, tumor diameter and volume, SIR-T1WI, SIR-DWI, and heterogenous enhancement between GAC and UEA. CONCLUSION: The clinical and MRI features with significant differences among SCC, AC and ASC, and between UEA and GAC, can help to identify each subtype of cervical cancer.

Whole-tumor ADC histogram analysis for differentiating endometriosis-related tumors: seromucinous borderline tumor, clear cell carcinoma and endometrioid carcinoma.

PURPOSE: To investigate the feasibility of whole-tumor apparent diffusion coefficient (ADC) histogram analysis for improving the differentiation of endometriosis-related tumors: seromucinous borderline tumor (SMBT), clear cell carcinoma (CCC) and endometrioid carcinoma (EC). METHODS: Clinical features, solid component ADC (ADCSC) and whole-tumor ADC histogram-derived parameters (volume, the ADCmean, 10th, 50th and 90th percentile ADCs, inhomogeneity, skewness, kurtosis and entropy) were compared among 22 SMBTs, 42 CCCs and 21 ECs. Statistical analyses were performed using chi-square test, one-way ANOVA or Kruskal-Wallis test, and receiver operating characteristic curves. RESULTS: A significantly higher ADCSC and smaller volume were associated with SMBT than with CCC/EC. The ADCmean was significantly higher in CCC than in EC. The 10th percentile ADC was significantly lower in EC than in SMBT/CCC. The 50th and 90th percentile ADCs were significantly higher in CCC than in SMBT/EC. For differentiating SMBT from CCC, AUCs of the ADCSC, volume, and 50th and 90th percentile ADCs were 0.97, 0.86, 0.72 and 0.81, respectively. For differentiating SMBT from EC, AUCs of the ADCSC, volume and 10th percentile ADC were 0.97, 0.71 and 0.72, respectively. For differentiating CCC from EC, AUCs of the ADCmean and 10th, 50th and 90th percentile ADCs were 0.79, 0.72, 0.81 and 0.85, respectively. CONCLUSION: Whole-tumor ADC histogram analysis was valuable for differentiating endometriosis-related tumors, and the 90th percentile ADC was optimal in differentiating CCC from EC.

Magnetic Resonance Imaging and Diffusion Weighted Imaging-Based Histogram in Predicting Mesenchymal Transition High-Grade Serous Ovarian Cancer.

RATIONALE AND OBJECTIVES: To investigate the value of magnetic resonance imaging (MRI) including diffusion-weighted imaging (DWI) findings in predicting mesenchymal transition (MT) high-grade serous ovarian cancer (HGSOC). MATERIALS AND METHODS: Patients with HGSOC were enrolled from May 2017 to December 2020, who underwent pelvic MRI including DWI (b = 0,1000 s/mm2) before surgery, and were assigned to the MT HGSOC or non-MT HGSOC group according to histopathology results. Clinical characteristics and MRI features including DWI-based histogram metrics were assessed and compared between the two groups. Univariate and multivariate analyses were performed to identify the significant variables associated with MT HGSOC - these variables were then incorporated into a predictive nomogram, and ROC curve analysis was subsequently carried out to evaluate diagnostic performance. RESULTS: A total of 81 consecutive patients were recruited for pelvic MRI before surgery, including 37 (45.7%) MT patients and 44 (54.3%) non-MT patients. At univariate analysis, the features significantly related to MT HGSOC were identified as absence of discrete primary ovarian mass, pouch of Douglas implants, ovarian mass size, tumor volume, mean, SD, median, and 95th percentile apparent diffusion coefficient (ADC) values (all p < 0.05). At multivariate analysis, the absence of discrete primary ovarian mass {odds ratio (OR): 46.477; p = 0.025}, mean ADC value ≤ 1.105 (OR: 1.023; p = 0.009), and median ADC value ≤ 1.038 (OR: 0.982; p = 0.034) were found to be independent risk factors associated with MT HGSOC. The combination of all independent criteria yielded the largest AUC of 0.82 with a sensitivity of 83.87% and specificity of 66.67%, superior to any of the single predictor alone (p ≤ 0.012). The predictive C-index nomogram performance of the combination was 0.82. CONCLUSION: The combination of absence of discrete primary ovarian mass, lower mean ADC value, and median ADC value may be helpful for preoperatively predicting MT HGSOC.

Multiple instance convolutional neural network with modality-based attention and contextual multi-instance learning pooling layer for effective differentiation between borderline and malignant epithelial ovarian tumors.

Malignant epithelial ovarian tumors (MEOTs) are the most lethal gynecologic malignancies, accounting for 90% of ovarian cancer cases. By contrast, borderline epithelial ovarian tumors (BEOTs) have low malignant potential and are generally associated with a good prognosis. Accurate preoperative differentiation between BEOTs and MEOTs is crucial for determining the appropriate surgical strategies and improving the postoperative quality of life. Multimodal magnetic resonance imaging (MRI) is an essential diagnostic tool. Although state-of-the-art artificial intelligence technologies such as convolutional neural networks can be used for automated diagnoses, their application have been limited owing to their high demand for graphics processing unit memory and hardware resources when dealing with large 3D volumetric data. In this study, we used multimodal MRI with a multiple instance learning (MIL) method to differentiate between BEOT and MEOT. We proposed the use of MAC-Net, a multiple instance convolutional neural network (MICNN) with modality-based attention (MA) and contextual MIL pooling layer (C-MPL). The MA module can learn from the decision-making patterns of clinicians to automatically perceive the importance of different MRI modalities and achieve multimodal MRI feature fusion based on their importance. The C-MPL module uses strong prior knowledge of tumor distribution as an important reference and assesses contextual information between adjacent images, thus achieving a more accurate prediction. The performance of MAC-Net is superior, with an area under the receiver operating characteristic curve of 0.878, surpassing that of several known MICNN approaches. Therefore, it can be used to assist clinical differentiation between BEOTs and MEOTs.

Predicting Disease-Free Survival With Multiparametric MRI-Derived Radiomic Signature in Cervical Cancer Patients Underwent CCRT.

Prognostic biomarkers that can reliably predict the disease-free survival (DFS) of locally advanced cervical cancer (LACC) are needed for identifying those patients at high risk for progression, who may benefit from a more aggressive treatment. In the present study, we aimed to construct a multiparametric MRI-derived radiomic signature for predicting DFS of LACC patients who underwent concurrent chemoradiotherapy (CCRT). METHODS: This multicenter retrospective study recruited 263 patients with International Federation of Gynecology and Obetrics (FIGO) stage IB-IVA treated with CCRT for whom pretreatment MRI scans were performed. They were randomly divided into two groups: primary cohort (n = 178) and validation cohort (n = 85). The LASSO regression and Cox proportional hazard regression were conducted to construct the radiomic signature (RS). According to the cutoff of the RS value, patients were dichotomized into low- and high-risk groups. Pearson's correlation and Kaplan-Meier analysis were conducted to evaluate the association between the RS and DFS. The RS, the clinical model incorporating FIGO stage and lymph node metastasis by the multivariate Cox proportional hazard model, and a combined model incorporating RS and clinical model were constructed to estimate DFS individually. RESULTS: The final radiomic signature consisted of four radiomic features: T2W_wavelet-LH_ glszm_Size Zone NonUniformity, ADC_wavelet-HL-first order_ Median, ADC_wavelet-HH-glrlm_Long Run Low Gray Level Emphasis, and ADC_wavelet _LL_gldm_Large Dependence High Gray Emphasis. Higher RS was significantly associated with worse DFS in the primary and validation cohorts (both p<0.001). The RS demonstrated better prognostic performance in predicting DFS than the clinical model in both cohorts (C-index, 0.736-0.758 for RS, and 0.603-0.649 for clinical model). However, the combined model showed no significant improvement (C-index, 0.648, 95% CI, 0.571-0.685). CONCLUSIONS: The present study indicated that the multiparametric MRI-derived radiomic signature could be used as a non-invasive prognostic tool for predicting DFS in LACC patients.

Prediction of Platinum-based Chemotherapy Response in Advanced High-grade Serous Ovarian Cancer: ADC Histogram Analysis of Primary Tumors.

RATIONALE AND OBJECTIVES: To investigate the feasibility of apparent diffusion coefficient (ADC) histogram analysis of primary advanced high-grade serous ovarian cancer (HGSOC) to predict patient response to platinum-based chemotherapy. MATERIALS AND METHODS: A total of 70 patients with 102 advanced stage HGSOCs (International Federation of Gynecology and Obstetrics (FIGO) stages III-IV) who received standard treatment of primary debulking surgery followed by the first line of platinum-based chemotherapy were retrospectively enrolled. Patients were grouped as platinum-resistant and platinum-sensitive according to whether relapse occurred within 6 months. Clinical characteristics, including age, pretherapy CA125 level, International Federation of Gynecology and Obstetrics stage, residual tumor, and histogram parameters derived from whole tumor and solid component such as ADCmean; 10th, 20th, 25th, 30th, 40th, 50th, 60th, 70th, 75th, 80th, 90th percentiles; skewness and kurtosis, were compared between platinum-resistant and platinum-sensitive groups. RESULTS: No significantly different clinical characteristics were observed between platinum-sensitive and platinum-resistant patients. There were no significant differences in any whole-tumor histogram-derived parameters between the two groups. Significantly higher ADCmean and percentiles and significantly lower skewness and kurtosis from the solid-component histogram parameters were observed in the platinum-sensitive group when compared with the platinum-resistant group. ADCmean, skewness and kurtosis showed moderate prediction performances, with areas under the curve of 0.667, 0.733 and 0.616, respectively. Skewness was an independent risk factor for platinum resistance. CONCLUSION: Pretreatment ADC histogram analysis of primary tumors has the potential to allow prediction of response to platinum-based chemotherapy in patients with advanced HGSOC.

A rat model of serous borderline ovarian tumors induced by 7,12-dimethylbenz[a]anthracene.

Serous borderline ovarian tumors (SBOTs) behave between benign cystadenomas and carcinomas, and the effective detection and clinical management of SBOTs remain clinical challenges. Because it is difficult to isolate and enrich borderline tumor cells, a borderline animal model is in need. 7,12-dimethylbenz[a]anthracene (DMBA) is capable of inducing the initiation, promotion, and progression of serous ovarian tumors. This study aims to investigate the proper dosage and induction time of DMBA for rat models of SBOTs, and explore their morphological features demonstrated by magnetic resonance (MR) imaging and molecular genetic characteristics. Rats were randomly divided into six groups (1 mg/70 D, 2 mg/70 D, 3 mg/70 D, 2 mg/50 D, 2 mg/90 D, and 2 mg/110 D). The 3 mg/70 D group induced the most SBOTs (50.0%, 12/24). The micropapillary projections were shown on MR imaging, which was the characteristic of SBOTs. The Cyclin D1 characterizing an early pathogenetic event strongly expressed in induced serous benign tumors (SBTs). The immunoreactivity staining scores of P53 expression significantly increased from SBTs, SBOTs to serous ovarian carcinomas (SCAs), which elucidate that P53 might be a promising biomarker to grade serous ovarian tumors. Based on morphological and molecular genetic similarities, this rodent SBOT model was suitable for investigating the pathogenesis of serous ovarian tumors and developing an early detection strategy.

MRI features and score for differentiating borderline from malignant epithelial ovarian tumors.

PURPOSE: To identify the MRI features of borderline epithelial ovarian tumors (BEOTs) and to differentiate BEOTs from malignant epithelial ovarian tumors (MEOTs). MATERIALS AND METHODS: The clinical and MRI data of 89 patients with a BEOT and 109 patients with a MEOT proven by surgery and histopathology were retrospectively reviewed. MRI features, including bilaterality, size, shape, margin, cystic-solid interface, configuration, papillae or nodules, signal intensity, enhancement, presence of an ipsilateral ovary, peritoneal implants and ascites were analyzed and compared. Based on the odds ratio (OR) values, the significant risk features for BEOTs were scored as 3 (OR≈∞), 2 (5≤OR<∞) or 1 (OR<5). RESULTS: There were 89 BEOT patients with 113 tumors [mean size of (13±6.7)cm], with bilateral ovary involvement in 24 cases. There were 109 MEOT patients with 142 tumors [(9.3±4.2)cm] with bilateral ovary involvement in 33 cases. There were eight significant risk factors for BEOTs, including round or oval shape (OR=2.714), well-defined margins (OR=3.318), clear cystic-solid interfaces (OR=5.593), purely cystic (OR=15.206), predominantly cystic with papillae or nodules (OR=2.579), exophytic papillae or nodules (OR=5.351), branching papilla (OR≈∞) and the presence of an ipsilateral ovary (OR≈∞). Based on the scoring of the eight risk factors, a cut-off score of 3.5 yielded a differential sensitivity, specificity, and accuracy of 82%, 85% and 84%, respectively. CONCLUSION: In contrast to MEOTs, BEOTs frequently had the following features on MRI: round or oval, with well-defined margins and clear cystic-solid interfaces, purely cystic or predominantly cystic with papillae or nodules, branching or exophytic papillae, with the presence of an ipsilateral ovary. MRI can reveal the distinct morphological features of BEOTs and MEOTs and facilitate their discrimination.