Role of artificial intelligence applied to ultrasound in endometrial cancer: a systematic review.

Background and Aim: Pathological variation and image overlapping due to several endometrial conditions could be challenging for radiologists. Diffused weighted magnetic resonance imaging (DWI) is a reliable and promising imaging technique for the diagnosis and characteristics of endometrial lesions. The present study aimed to assess the diagnostic accuracy of diffused weighted magnetic imaging resonance in differentiating between malignant and benign endometrial soft-tissue lesions. Methodology: This descriptive cross-sectional study was carried out on 50 suspected endometrial lesions in the department of radiology, Benazir Bhutto hospital, Rawalpindi from January 2021 to December 2021. Non-probability consecutive sampling technique was used for all the participants meeting the inclusion criteria. Patients were categorized into two groups; Group I and Group II comprised 25 suspected benign and malignant endometrial lesions respectively. All the study patients were subjected to ultrasound and MRI examination of the pelvis. DWI imaging was done and the ADC value was calculated at a high b value. Histopathological data was collected. Data were analyzed using SPSS version 23. Results: Of the total 50 endometrial lesions, histopathological results were divided into the malignant group (25 lesions, 50%) and benign group (25 lesions, 50%). Out of 50, 38 lesions (21/25 benign and 17/25 malignant lesions) were correctly diagnosed by the conventional magnetic resonance imaging technique. The sensitivity, specificity, predictive positive value (PPV), and negative-positive value (NPV) of conventional MRI were 76.82%, 79.41%, 74.12%, AND 81.5% respectively. However, combining the apparent diffusion coefficient (ADC) value at b=1000 with DWI, about 48 lesions (24/25 benign and 24/25 malignant lesions) were correctly diagnosed. The sensitivity, specificity, predictive positive value (PPV), and negative-positive value (NPV) of conventional MRI were 94.82%, 93.23%, 91.6%, and 97% respectively. Conclusion: Diffusion-weighted MRI can help in distinguishing uterine endometrial lesions as benign and malignant. The diagnostic accuracy of Combined DWI with ADC mapping is higher than conventional MRI when differentiating benign lesions from malignant lesions. Additionally, sensitivity, specificity, and accuracy of combined DWI with ADC mapping increased in pelvic MRI examination for differentiating endometrial focal lesions. Keywords: Pelvic ultrasound; MRI Pelvis; Benign and Malignant endometrial lesions, Validity.

ObjectivePreoperative differentiation of benign and malignant endometrial lesions, along with the identification of aggressive histological types of endometrial cancer (EC), is crucial for guiding treatment strategies. Time-dependent diffusion magnetic resonance imaging (TDD-MRI), which allows the characterization of tissue microstructure at the cellular level, is not currently applied for endometrial lesions. This study aimed to evaluate TDD-MRI-derived microstructural parameters for noninvasively distinguishing benign and malignant endometrial lesions and predicting aggressive histological types of EC.Materials and MethodsThis prospective study enrolled 177 patients with clinically suspected EC who underwent TDD-MRI between January 2024 and March 2025. The Imaging Microstructural Parameters Using Limited Spectrally Edited Diffusion method was used to extract microstructural parameters, including the cell diameter (d), intracellular volume fraction (vin), cellularity (number of cells per unit area), cellularity index (vin/d), and extracellular diffusivity (Dex), along with three apparent diffusion coefficient measurements. The area under the receiver operating characteristic curve (AUC) was used to assess diagnostic performance. The Pearson correlation coefficient between the microstructural parameters and histopathological measurements was calculated.ResultsA total of 130 women (mean ± standard deviation age: 56 ± 14 years) administered uterine curettage or surgery were included in the final analysis. All microstructural parameters showed significant differences between benign endometrial lesions and EC (P < 0.05), as well as between nonaggressive and aggressive EC (P < 0.05). Cellularity exhibited the highest AUC of 0.86 for distinguishing benign endometrial lesions from EC, whereas the cellularity index showed the highest AUC of 0.88 for distinguishing aggressive histological types. D0Hz was positively correlated with Dex (P < 0.05) and negatively correlated with diameter (P < 0.05), cellularity index (P < 0.01) and vin (P < 0.001) in patients with benign endometrial lesions. D0Hz was positively correlated with Dex (P < 0.001) and negatively correlated with vin (P < 0.001) in patients with EC. Microstructural parameters strongly correlated with corresponding pathological features (r = 0.77–0.83; P < 0.001).ConclusionTDD-MRI-derived microstructural parameters demonstrated high performance in differentiating benign from malignant endometrial diseases and identifying aggressive types of EC.

Diagnostic value of endometrial volume and flow parameters under 3D ultrasound acquisition in combination with serum CA125 in endometrial lesions

BackgroundDiffusion tensor imaging (DTI) can be beneficial to differentiate between endometrium and other uterine layers. It is believed that it can be used to differentiate between normal and abnormally thickened endometrium. The purpose of this study was to find out the diagnostic value of DTI as an extension of DWI in characterization of abnormally thickened endometrium and differentiate it from normal.ResultsThis study included 68 females, results of 3 of them were excluded (unable to complete the study), so the final number was 65 females subdivided into 2 groups; (A) control: 24 (13 premenopausal and 11 asymptomatic postmenopausal), (B) pathological thickened endometrium: 41 (11 premenopausal and 30 postmenopausal): benign (21 patients) and malignant (20 patients). The collected data was correlated to the histopathological results (as the gold standard) in cases of endometrial pathologies. The mean DW-ADC values for normal, benign, and malignant patients were 1.43 ± 0.13, 1.56 ± 0.17, and 0.86 ± 0.16 respectively and with significant statistical difference between normal and benign endometrial lesions (P value = 0.006), and between normal and malignant endometrial lesions, and between benign and malignant endometrial lesions (P value ˂ 0.001).The DTI-FA mean values for normal, benign, and malignant patients were 0.349 ± 0.08, 0.29 ± 0.09, and 0.299 ± 0.08 respectively and with significant statistical difference between normal and benign endometrial lesions (P value = 0.02), but there is no significant statistical difference regarding DTI-FA values between normal and malignant endometrial lesions or between benign and malignant endometrial lesions (P value ˃ 0.05). Also, there is a significant statistical difference regarding DTI-MD mean values between normal (1.59 ± 0.06) and benign (1.37 ± 0.09), normal and malignant (0.71 ± 0.25), and between benign and malignant endometrial lesions (P value ˂ 0.001). The DT-MD had a higher sensitivity, specificity, and accuracy than both DW-ADC and DT-FA in differentiating normal, benign, and malignant endometrial pathologies.ConclusionDTI (added to DWI) is a valuable non-invasive tool that can increase the accuracy in differentiating normal, benign, and malignant endometrial conditions, helping early management, and decrease the possibility of misdiagnosis.

Objective To explore the value of contrast-enhanced ultrasound (CEUS) and intraluminal contrast in the differential diagnosis of postmenopausal endometrial benign and malignant lesions. Methods The ultrasound data of 90 patients with postmenopausal endometrial lesions diagnosed in our hospital between March 2016 and March 2018 were retrospectively analyzed. According to pathological findings, they were divided into benign group (55 cases) and malignant group (35 cases). The endometrial thickness of endovascular contrast, rise time (RT), time to peak (TTP), base intensity (BI), and peak intensity (PI) of CEUS in two groups were compared. Receiver operating characteristic curves (ROC) were used to compare the efficacy of different ultrasound parameters in benign and malignant endometrial by using pathology diagnosis as gold standard. Results The endometrial thickness and PI were significantly higher in the malignant group than those in the benign group (P 0.05). The ROC curve showed that PI has the highest area under curve (AUC) in the differential diagnosis of benign and malignant endometrial lesions (AUC=0.983), followed by RT and TTP (AUC=0.889, 0.872), and intimal thickness (AUC=0.766). AUC of PI was significantly higher than RT, TTP and intimal thickness (P<0.05), and the best cut-off point for PI ≥20.23 dB. The sensitivity of PI, RT, and TTP in differentiating benign and malignant endometrial lesions was significantly higher than that in intimal thickness (P<0.05), whereas the specificity and positive likelihood ratio (+ LR) of PI were significantly higher than those of RT, TTP, and intimal thickness (P<0.05). Conclusions Compared with intracavitary ultrasound, CEUS has better diagnostic value in differentiating benign and malignant endometrial tumors. Among them, the diagnostic sensitivity and specificity of PI≥20.23 dB are higher. Key words: Endometrial neoplasms; Phlebography; Hysterosalpingography; Menopause

Uterine endometrial cancer is the most common gynecologic malignancy, and benign endometrial hyperplasia or polyps should be differentiated from endometrial cancer. In evaluating endometrial cancer on magnetic resonance imaging (MRI), the assessment of the depth of myometrial invasion is important because it closely correlates with the patient's prognosis. To verify the feasibility of diffusion-weighted magnetic resonance imaging (DWI) to distinguish benign and malignant endometrial lesions, and to evaluate myometrial invasion of endometrial cancer. Sixty-seven endometrial lesions including 45 cancers and 22 benign lesions (hyperplasia and polyps) were evaluated by DWI with apparent diffusion coefficient (ADC) measurement. The staging accuracies of DWI and gadolinium-enhanced T1-weighted images in the assessment of myometrial invasion were evaluated in 33 patients with endometrial cancer. The ADC values (x10(-3) mm(2)/s) in cancer and benign lesions were 0.84+/-0.19 and 1.58+/-0.36, respectively (P<0.01). The staging accuracy (superficial or deep myometrial invasion) was 94% for DWI and 88% for gadolinium-enhanced T1-weighted images. Coexisting adenomyosis and infiltrative myometrial invasion caused staging errors on gadolinium-enhanced T1-weighted images, whereas DWI could demonstrate the tumor extent correctly. DWI provides helpful information in evaluating benign and malignant endometrial lesions.

PurposeThe objective of this study was to evaluate the diagnostic value of transvaginal contrast-enhanced ultrasound (CEUS) in differentiating benign from malignant endometrial lesions and assessing the extent of myometrial invasion.MethodsA total of 70 patients who underwent surgery for endometrial lesions at the authors’ hospital were selected. Transvaginal ultrasound examination and CEUS were performed for quantitative and qualitative analysis. Based on the CEUS results, an International Federation of Gynecology and Obstetrics (FIGO) disease grade was assigned and compared with pathological findings.ResultsPostmenopausal vaginal bleeding is a key clinical manifestation of endometrial carcinoma. Among the patients with endometrial carcinoma, compared with normal myometrium, the lesion areas exhibited a greater rate of rise (defined as enhanced intensity divided by enhancement time) and a shorter half-clearance time (P<0.05). These findings suggest that in endometrial carcinoma, the contrast agent displays a "fast-in/fast-out/hyperenhancement" perfusion pattern. In contrast, the characteristic perfusion pattern for benign endometrial lesions is low enhancement (P<0.05). The diagnostic accuracy of CEUS in detecting myometrial invasion was 88% (22 of 25 cases).ConclusionTransvaginal CEUS is a practical and effective diagnostic imaging method for distinguishing between benign and malignant endometrial lesions. It can also be used to evaluate the depth of myometrial invasion in patients with early-stage endometrial carcinoma.

Distinguishing benign and malignant endometrial lesions on the basis of endometrial thickness (ET) may lead to a missed diagnosis of endometrial carcinoma (EC) in women with postmenopausal bleeding (PMB) or increased invasive examination and pain in women with benign endometrial lesions. Our research aims to establish an ultrasonic prediction model for differentiating between benign endometrial lesions and EC in women with PMB. PMB women with ET ≥ 5 mm (n = 412) or ET < 5 mm who presented with recurrent vaginal bleeding (n = 57) were enrolled in this prospective observational study. According to the pathological examination results of the endometrium, women with PMB were divided into endometrial atrophy (EA) (n = 231), endometrial polyp (EP) (n = 98), endometrial hyperplasia (EH) (n = 58) and EC (n = 82) groups. Ultrasonic parameters were compared among the four groups. The predictive value of different parameters for differentiation between benign endometrial lesions and EC in women with PMB was determined via receiver operating characteristic (ROC) curves. The best cut-off of ultrasonic parameters analyzed by ROC curves was used to establish prediction model. Women with EC had significantly thicker endometrium and higher endometrial volume (EV), vascularization index (VI), flow index (FI) and vascularization-flow index (VFI) than women with other pathological types of endometrium (P < 0.05). The endometrial VI, FI and VFI of women with EH were significantly higher compared with those in women with EA and EP (P < 0.05). For patients with ET ≥ 5 mm, the best parameter for distinguishing between benign lesions and EC was the FI, with an area under the curve (AUC) of 0.86, a sensitivity of 86.7% and a specificity of 81.4%. In addition, for patients with ET < 5 mm, the best parameter for distinguishing between benign lesions and EC was the VI, with an AUC of 0.92, a sensitivity of 92.1% and a specificity of 72.9%. The ultrasonic prediction model based on the FI and VI had better predictive value for EC in both patients with ET ≥ 5 mm and patients with ET < 5 mm. The ultrasonic parameters differed among the different pathological types of the endometrium in women with PMB. The ultrasonic prediction model based on the endometrial FI and VI was clinically useful for differentiating between benign endometrial lesions and EC, especially in postmenopausal patients with recurrent vaginal bleeding presenting with ET of less than 5 mm.

This meta-analysis aimed to identify the accuracy of shear wave elastography (SWE) in the diagnosis of endometrial cancer (EC). We searched the PubMed, Cochrane Library, and chinese biomedical literature database from inception to September 30, 2022. Meta-analysis was conducted using STATA version 14.0 and Meta-Disc version 1.4 software. We calculated summary statistics for sensitivity (Sen), specificity (Spe), positive and negative likelihood ratio (LR+/LR-), diagnostic odds ratio (DOR), and receiver operating characteristic (SROC) curves. Eight studies that met all the inclusion criteria were included in this meta-analysis. A total of 432 patients with EC and 548 with benign endometrial lesions were assessed. All endometrial lesions were histologically confirmed by SWE. The pooled Sen was 0.91 (95% confidence interval [CI] = 0.83-0.95); the pooled Spe was 0.90 (95% CI = 0.86-0.93); the pooled LR+ was 9.10 (95% CI = 6.20-13.35); the pooled negative LR- was 0.10 (95% CI = 0.05-0.20); the pooled DOR of SWE in the diagnosis of EC was 90.73 (95% CI = 36.62-804.5). The area under the SROC curve was 0.95 (95% CI = 0.93-0.97). No evidence of publication bias was found (t = 0.98, P = .37). Our meta-analysis indicates that SWE may have high diagnostic accuracy in the differential diagnosis of benign and malignant endometrial lesions. Thus, SWE may be a useful tool for the diagnosis of EC.

Objective To investigate the diagnostic value of conventional and dynamic gadolinium-enhanced T1-weighted (T1W) MRI in benign and malignant endometrial polypoid lesions. The pathologic basis of MRI features was also evaluated. Methods The conventional and dynamic contrast enhanced MRI features in 48 cases with clinicopathologically-proved endometrial polypoid lesions were retrospectively analyzed, including 26 cases with malignant tumors (23 eases with endometrial carcinoma and 3 cases with endometrial sarcoma) and 22 cases with benign polypoid lesions (12 cases with endothehal polyps and 10 cases with submucons leiomyomas). The occurrence probability of central fibrous core, intratumoral cysts and intact junctional zone were evaluated by Fisher's exact test. Results Benign and malignant endometrial polypoid lesions had specific characteristics on MRL Endometrial carcinomas usually appeared as homogeneous intermediate or slightly high signal-intensity masses on T2-weighted images, and relatively homogeneous hypedense masses on contrast-enhanced images with myometrial invasion (P < 0.05). An irregular central fthrous core and small non-enhanced intratumoral cysts were seen more frequently in endometrial polyps (P < 0.05) than others. All 3 cases with uterine sarcomas showed obviously inhomageneous intensity on T2WI and demonstrated areas of early and persistent marked enhancement.Submucous leiomyomas demonstrated isodense or slightly low-density masses with defined outline on T2 WI and the endomerium was displaced. The diagnostic sensitivity, specificity and accuracy of malignant polypoid masses were 92.3% (24/26), 83.3% (20/24) and 95.8% (46/48) respectively. Conclusion Conventional and dynamic contrast-enhanced MRI are valuable in characterizing the benign and malignant endometrial polypoid lesions. Key words: Endometrial neoplasms; Leiomyoma; Magnetic resonance imaging

Accurate differentiation between benign and malignant endometrial lesions holds substantial clinical importance. This study aimed to evaluate the efficacy of various diffusion models in the preoperative diagnosis of early-stage endometrial carcinoma (EC). A total of 72 consecutive patients with benign or malignant endometrial lesions from the First People's Hospital of Yunnan Province were prospectively enrolled between April 2021 and July 2023. Fourteen diffusion parameters derived from monoexponential diffusion-weighted imaging (DWI), diffusion kurtosis imaging (DKI), intravoxel incoherent motion (IVIM), stretched exponential model (SEM), continuous-time random walk (CTRW), and fractional order calculus (FROC) models were calculated and compared. Independent predictors of early-stage EC were identified using logistic regression analysis. The performance of the diffusion parameters, both individually and in combination with effective clinical indicators, for differentiating benign and malignant endometrial lesions was evaluated. This study consisted of 17 patients with benign endometrial lesions and 55 patients with EC. Significant differences in age and menopausal status were observed between the benign and malignant endometrial groups (P=0.015 and P=0.011, respectively). With the exception of the pseudodiffusion coefficient (D*) and perfusion fraction (f), all other parameters exhibited significant differences between the benign and malignant groups (P<0.05). Mean kurtosis (MK), true diffusion coefficient (D), and temporal diffusion heterogeneity index (αCTRW) were identified as independent predictors of early-stage EC, achieving an area under the curve (AUC) of 0.903 [95% confidence interval (CI): 0.824-0.982], surpassing that of any individual diffusion parameter. The combination of these independent predictors with menopausal status yielded the highest AUC (0.922, 95% CI: 0.845-0.999), accuracy (93.1%), and sensitivity (100.0%). MK, D, and αCTRW have the potential to serve as independent predictors in predicting early-stage EC, and the performance can be enhanced when combined with menopausal status.

Endometrial cancer is the cancer of the inner lining of the uterus. Histopathology is considered a gold standard invasive diagnostic test for it. However, Magnetic Resonance Imaging (MRI) based Diffusion-Weighted Imaging (DWI) and apparent diffusion coefficients (ADC) values are non-invasive tests that can differentiate malignant endometrial lesions from benign conditions. Objective: To assess the diagnostic accuracy of MR DWI in differentiating benign from malignant endometrial lesions taking histopathology as a gold standard. Methods: This cross sectional study was carried out at Radiology Ward Lahore General Hospital Lahore for six months. A total of 132 women between 25-55 years of age, with abnormal vaginal bleeding were included. In all patients, diffusion-weighted MRI (DE-MRI) of the pelvis was done followed by histopathology. DW-MRI and histopathology findings were compared. Data were analyzed on SPSS 20.0. The Sensitivity, Specificity, Positive Predictive Value (PPV), Negative Predictive Value (NPV) and diagnostic accuracy were measured using 2×2 contingency table. P-value of &lt;0.001 was taken as significant. Results: DW-MRI diagnosed endometrial cancer in 75 patients while 57 patients didn’t show any malignant lesion. Histopathology confirmed endometrial cancer in 79 cases and benign lesion in 53. Out of 75 positive DW-MRI patients, 72 were True Positive (TP). Out of 57 negative DW-MRI patients, 07 were True negative (TN). Sensitivity, Specificity, PPV, NPV and diagnostic accuracy were 91.14%, 94.34%, 96.0%, 97.72% and 92.42% respectively. Conclusions: DWI based apparent diffusion coefficients (ADC) can more accurately diagnose endometrial cancers than benign lesions. Hence it can be useful adjunct for diagnosis of endometrial lesions.

AimTo investigate the association of the blood flow parameters measured by transvaginal three-dimensional power Doppler ultrasound and the angiogenesis of endometrial cancer.Material and MethodsThe expressions of vascular endothelial growth factor (VEGF) and CD31 in benign and malignant endometrial lesions, and in malignant lesions with different clinical and pathological features were analyzed. The correlations of the blood flow parameters (vascularization index [VI], blood flow index [FI], and vascularization-blood flow index [VFI]) of transvaginal 3D power Doppler ultrasound, and VEGF expressions, microvessel density (MVD) were also evaluated.ResultsThe VEGF-positive rates and the MVD values in benign and malignant endometrial lesions were significantly different (both P<0.001). The differences of VEGF-positive rates (P < 0.001) and MVD values (P = 0.021) between type I and type II lesions of endometrial cancer were statistically significant. There was no significant difference in the VEGF-positive rate and MVD value between stage IA and IB (P=0.443, P=0.311). The difference of VEGF expression and MVD in stage IA, stage IB and stage II and above was statistically significant (P=0.003, P=0.017). The VEGF-positive rate and MVD value were not significantly different in IAG1 and IAG2 lesions of endometrioid adenocarcinoma (P=0.709, P=0.792). There was no significant correlation between VI, FI, VFI and VEGF expression and MVD in endometrial cancer.ConclusionThe VEGF-positive rates and MVD values were relatively high in malignant endometrial lesions, type II and stage II and above lesions of type I endometrial cancer, indicating that the angiogenesis of endometrial cancer tissues might play a crucial role in the tumor classification, and pelvic metastasis.

Objective To evaluate the efficacy of three-dimensional power Doppler (3DPD) and 3D multislice view in distinguishing between benign and malignant endometrial lesions in women with postmenopausal bleeding (PMB) and endometrial thickness of 5 mm or more. Study design This was a diagnostic accuracy study. Patients and methods Women with PMB and an endometrial thickness of 5 mm or more on two-dimensional transvaginal sonography were evaluated by 3DPD before endometrial sampling to make a definitive histological diagnosis of endometrial lesions. Endometrial volume (EV), vascularization index (VI), flow index (FI), and vascularization–flow index (VFI) were calculated using Virtual Organ Computer-aided AnaLysis (VOCAL) software. 3D multislice view was used to increase the diagnostic accuracy of the above parameters (EV, VI, FI, and VFI) in the diagnosis of different endometrial lesions. The women included were divided into two groups: group 1 included 28 patients who had a histological diagnosis of endometrial carcinoma and group 2 included 32 patients who had a histological diagnosis of benign endometrial disorders. Results Sixty women with PMB were finally analyzed; 32 (53.3%) women had benign endometrial lesions and 28 (46.7%) had endometrial malignancy. Women in group 1 tended to have significantly thicker endometrium (11.11±3.61 vs. 5.78±0.94 mm; P=0.0001), larger EV (4.89±3.53 vs. 2.22±1.60; P=0.001), and higher 3DPD flow indices (P=0.0001) than those with benign endometrial lesions. There was a statistically significant difference between 3DPD and 3D multislice view, with increased vasculature in different planes in malignant cases than in benign cases (P=0.0001). The best logistic regression models for predicting malignancy [i.e. the models with the largest area under the curve (AUC)] included endometrial thickness and VFI (AUC 0.984 and 0.884). Conclusion Even though histopathological examination of the endometrium is the gold standard for the final diagnosis or exclusion of endometrial malignancy, EV, 3DPD indices, and 3D multislice view are good diagnostic tools in predicting endometrial malignancy in women with PMB.

Endometrial pathologies represent a diagnostic challenge for radiologist and gynecologist due to dynamic changes of the endometrium, wide variability in imaging appearance and overlap between benign and malignant causes of endometrial abnormalities. Although tissue analysis via dilatation and curettage, endometrial biopsy or hysteroscopy is the backbone in the diagnosis, these tests are invasive, not without complications and may be difficult to perform in certain circumstances, hence the need for noninvasive imaging methods to aid in the diagnosis and triaging the patient for subsequent invasive procedures as well as contribution in treatment planning. This study aimed to evaluate the role of diffusion weighted imaging (DWI) with apparent diffusion coefficient (ADC) value measurement in differentiating benign from malignant uterine endometrial lesions. The study included 47 patients with endometrial lesions divided into two groups according to the result of histopathological analysis; the malignant group consisting from 18 cases and the benign group consisting from 29 cases, the latter was further subdivided into: polyp, hyperplasia and other benign entities. Pelvic magnetic resonance imaging with DWI performed for each patient with visual evaluation of signal intensity on diffusion and ADC value measurement. Subsequently mean ADC values for each group were calculated and compared, and validity measures for the optimal cut-off values for differentiating benign from malignant lesions were determined. The mean±standard deviation for ADC value (x10-3mm2/sec) for malignant group was 0.71±0.12, and for benign group was 1.52±0.42, with a significant difference between the two groups (P value <0.01), there was no significant difference in ADC value between the subdivision of benign group. At ADC cut-off value of 0.976x10-3mm2/sec, the sensitivity, specificity, positive predictive value and negative predictive value and accuracy of DWI in detecting endometrial carcinoma were 100%, 89.6%, 85.71%, 100% and 93.62% respectively. In conclusion, DWI with ADC value measurement is a valuable non-invasive diagnostic test, aiding in the differentiation of benign from malignant uterine endometrial cavity lesions. Key words: diffusion weighted imaging, apparent diffusion coefficient map, benign endometrial lesions, malignant endometrial lesions.