Brain Decoding Using fMRI Images for Multiple Subjects through Deep Learning.

Substantial information related to human cerebral conditions can be decoded through various noninvasive evaluating techniques like fMRI. Exploration of the neuronal activity of the human brain can divulge the thoughts of a person like what the subject is perceiving, thinking, or visualizing. Furthermore, deep learning techniques can be used to decode the multifaceted patterns of the brain in response to external stimuli. Existing techniques are capable of exploring and classifying the thoughts of the human subject acquired by the fMRI imaging data. fMRI images are the volumetric imaging scans which are highly dimensional as well as require a lot of time for training when fed as an input in the deep learning network. However, the hassle for more efficient learning of highly dimensional high-level features in less training time and accurate interpretation of the brain voxels with less misclassification error is needed. In this research, we propose an improved CNN technique where features will be functionally aligned. The optimal features will be selected after dimensionality reduction. The highly dimensional feature vector will be transformed into low dimensional space for dimensionality reduction through autoadjusted weights and combination of best activation functions. Furthermore, we solve the problem of increased training time by using Swish activation function, making it denser and increasing efficiency of the model in less training time. Finally, the experimental results are evaluated and compared with other classifiers which demonstrated the supremacy of the proposed model in terms of accuracy.

Edge Constraint and Location Mapping for Liver Tumor Segmentation from Nonenhanced Images.

As there is no contrast enhancement, the liver tumor area in nonenhanced MRI exists with blurred edges and low contrast, which greatly affects the speed and accuracy of liver tumor diagnosis. As a result, precise segmentation of liver tumor from nonenhanced MRI has become an urgent and challenging task. In this paper, we propose an edge constraint and localization mapping segmentation model (ECLMS) to accurately segment liver tumor from nonenhanced MRI. It consists of two parts: localization network and dual-branch segmentation network. We build the localization network, which generates prior coarse masks to provide position mapping for the segmentation network. This part enhances the ability of the model to localize liver tumor in nonenhanced images. We design a dual-branch segmentation network, where the main decoding branch focuses on the feature representation in the core region of the tumor and the edge decoding branch concentrates on capturing the edge information of the tumor. To improve the ability of the model for capturing detailed features, sSE blocks and dense upward connections are introduced into it. We design the bottleneck multiscale module to construct multiscale feature representations using kernels of different sizes while integrating the location mapping of tumor. The ECLMS model is evaluated on a private nonenhanced MRI dataset that comprises 215 different subjects. The model achieves the best Dice coefficient, precision, and accuracy of 90.23%, 92.25%, and 92.39%, correspondingly. The effectiveness of our model is demonstrated by experiment results, and our model reaches superior results in the segmentation task of nonenhanced liver tumor compared to existing segmentation methods.

Prognosis Evaluation of MRI Combined with Magnetic Resonance Myelography on Lumbar Disc Herniation after Transforaminal Endoscopic Discectomy.

OBJECTIVE: This study sets out to investigate the role of magnetic resonance imaging (MRI) combined with magnetic resonance myelography (MRM) in patients after percutaneous transforaminal endoscopic discectomy (PTED) and to evaluate its value in postoperative rehabilitation. METHODS: The clinical date of 96 patients with lumbar disc herniation (LDH) after PTED was retrospectively analyzed. The enrolled patients were divided into MRI group (n = 32) and MRI + MRM group (n = 64) according to whether MRM was performed. The nerve root sleeve (morphology, deformation) and dural indentation, intervertebral space height (ISH), intervertebral space angle (ISA), degree of pain (Visual Analogue Scale (VAS)), vertebral function (Japanese Orthopaedic Association (JOA)), and long-term recurrence were compared between the two groups. RESULTS: Compared with the MRI group, the MRI + MRM group better displayed nerve root morphology, sheath sleeve deformation, and dural indentation. Both MRI and MRI + MRM showed ISH and ISA changes well. Compared with the MRI group, the MRI + MRM group had a significantly lower VAS score for lumbar and leg pain, a significantly higher JOA score, and a significantly lower 2-year recurrence rate. CONCLUSION: MRM combined with MRI is more beneficial to improve the prognosis of LDH patients after PTED.

Machine Learning-Based MRI LAVA Dynamic Enhanced Scanning for the Diagnosis of Hilar Lesions.

OBJECTIVE: To explore the value of machine learning-based magnetic resonance imaging (MRI) liver acceleration volume acquisition (LAVA) dynamic enhanced scanning for diagnosing hilar lesions. METHODS: A total of 90 patients with hilar lesions and 130 patients without hilar lesions who underwent multiphase dynamic enhanced MRI LAVA were retrospectively selected as the study subjects. The 10-fold crossover method was used to establish the data set, 7/10 (154 cases) data were used to establish the training set, and 3/10 (66 cases) data were used to establish the validation set to verify the model. The region of interest was extracted from MRI images using radiomics, and the hilar lesion model was constructed based on a convolutional neural network. RESULTS: There were significant differences in respiration and pulse frequency between patients with hilar lesions and without hilar lesions (P <0.05). The subjective scores of the images in the first three phases of dynamic enhanced scanning in the training set were higher than those in the validation set (P < 0.05). There was no significant difference between the training and validation set in the last three phases of dynamic enhanced scanning. CONCLUSION: Machine learn-based MRI LAVA dynamic enhanced scanning for diagnosing hilar lesions has high diagnostic efficiency and can be used as an auxiliary diagnostic method.

Interpretable Model Based on Pyramid Scene Parsing Features for Brain Tumor MRI Image Segmentation.

Due to the black box model nature of convolutional neural networks, computer-aided diagnosis methods based on depth learning are usually poorly interpretable. Therefore, the diagnosis results obtained by these unexplained methods are difficult to gain the trust of patients and doctors, which limits their application in the medical field. To solve this problem, an interpretable depth learning image segmentation framework is proposed in this paper for processing brain tumor magnetic resonance images. A gradient-based class activation mapping method is introduced into the segmentation model based on pyramid structure to visually explain it. The pyramid structure constructs global context information with features after multiple pooling layers to improve image segmentation performance. Therefore, class activation mapping is used to visualize the features concerned by each layer of pyramid structure and realize the interpretation of PSPNet. After training and testing the model on the public dataset BraTS2018, several sets of visualization results were obtained. By analyzing these visualization results, the effectiveness of pyramid structure in brain tumor segmentation task is proved, and some improvements are made to the structure of pyramid model based on the shortcomings of the model shown in the visualization results. In summary, the interpretable brain tumor image segmentation method proposed in this paper can well explain the role of pyramid structure in brain tumor image segmentation, which provides a certain idea for the application of interpretable method in brain tumor segmentation and has certain practical value for the evaluation and optimization of brain tumor segmentation model.

Artificial Intelligence Algorithm-Based MRI in Evaluating the Treatment Effect of Acute Cerebral Infarction.

The study is aimed at exploring the application of artificial intelligence algorithm-based magnetic resonance imaging (MRI) in the diagnosis of acute cerebral infarction, expected to provide a reference for diagnosis and effect evaluation of acute cerebral infarction. In this study, 80 patients diagnosed with suspected acute cerebral infarction per Diagnostic Criteria for Cerebral Infarction were selected as the research subjects. MRI images were reconstructed by deep dictionary learning to improve their recognition ability. At the same time, the same diagnostic operation was performed by Computed Tomography (CT) images to compare with MRI. The results of the interalgorithm comparison showed the image reconstruction effect of the deep dictionary learning model is significantly better than SAE reconstruction, single-layer dictionary reconstruction model, and KAVD reconstruction. After comparison, the results of MRI based on artificial intelligence algorithm and CT evaluation were statistically significant (P < 0.05). In the lesion image, the diameter of MRI lesions (3.81 ± 0.77 cm) based on artificial intelligence algorithm and the diameter of lesions in CT (3.66 ± 1.65 cm) also had significant statistical significance (P < 0.05). The results showed that MRI based on deep learning was more sensitive than CT imaging for diagnosis and evaluation of patients with acute cerebral infarction, with only 1 case misdiagnosed. The rate of disease detection and lesion image quality had a higher improvement. The results can provide effective support for the clinical application of MRI based on artificial intelligence algorithm in the diagnosis of acute cerebral infarction.

Establishment and Verification of Logistic Regression Model for Qualitative Diagnosis of Ovarian Cancer Based on MRI and Ultrasound Signs.

OBJECTIVE: To explore the establishment and verification of logistic regression model for qualitative diagnosis of ovarian cancer based on MRI and ultrasonic signs. METHOD: 207 patients with ovarian tumors in our hospital from April 2018 to April 2021 were selected, of which 138 were used as the training group for model creation and 69 as the validation group for model evaluation. The differences of MRI and ultrasound signs in patients with ovarian cancer and benign ovarian tumor in the training group were analyzed. The risk factors were screened by multifactor unconditional logistic regression analysis, and the regression equation was established. The self-verification was carried out by subject working characteristics (ROC), and the external verification was carried out by K-fold cross verification. RESULT: There was no significant difference in age, body mass index, menstruation, dysmenorrhea, times of pregnancy, cumulative menstrual years, and marital status between the two groups (P > 0.05). After logistic regression analysis, the diagnostic model of ovarian cancer was established: logit (P) = -1.153 + [MRI signs : morphology × 1.459 + boundary × 1.549 + reinforcement × 1.492 + tumor components × 1.553] + [ultrasonic signs : morphology × 1.594 + mainly real × 1.417 + separated form × 1.294 + large nipple × 1.271 + blood supply × 1.364]; self-verification: AUC of the model is 0.883, diagnostic sensitivity is 93.94%, and specificity is 80.95%; K-fold cross validation: the training accuracy was 0.904 ± 0.009 and the prediction accuracy was 0.881 ± 0.049. CONCLUSION: Irregular shape, unclear boundary, obvious enhancement in MRI signs, cystic or solid tumor components and irregular shape, solid-dominated shape, thick septate shape, large nipple, and abundant blood supply in ultrasound signs are independent risk factors for ovarian cancer. After verification, the diagnostic model has good accuracy and stability, which provides basis for clinical decision-making.

Functional Magnetic Resonance Imaging Study of Electroacupuncture Stimulating Uterine Acupoints.

OBJECTIVE: Based on resting-state functional magnetic resonance imaging (rs-fMRI), to observe the changes of brain function of bilateral uterine points stimulated by electroacupuncture, so as to provide imaging basis for acupuncture in the treatment of gynecological and reproductive diseases. METHODS: 20 healthy female subjects were selected to stimulate bilateral uterine points (EX-CA1) by electroacupuncture. FMRI data before and after acupuncture were collected. The ReHo values before and after acupuncture were compared by using the analysis method of regional homogeneity (ReHo) of the whole brain, so as to explore the regulatory effect of acupuncture intervention on brain functional activities of healthy subjects. RESULTS: Compared with before acupuncture, the ReHo values of the left precuneus lobe, left central posterior gyrus, calcarine, left lingual gyrus, and cerebellum decreased significantly after acupuncture. CONCLUSION: Electroacupuncture at bilateral uterine points can induce functional activities in brain areas such as the precuneus, cerebellum, posterior central gyrus, talform sulcus, and lingual gyrus. The neural activities in these brain areas may be related to reproductive hormone level, emotional changes, somatic sensation, and visual information. It can clarify the neural mechanism of acupuncture at uterine points in the treatment of reproductive and gynecological diseases to a certain extent.

Intelligent Segmentation Medical Assistance System for MRI Images of Osteosarcoma in Developing Countries.

Osteosarcoma is the most common primary malignant bone tumor in children and adolescents. It has a high degree of malignancy and a poor prognosis in developing countries. The doctor manually explained that magnetic resonance imaging (MRI) suffers from subjectivity and fatigue limitations. In addition, the structure, shape, and position of osteosarcoma are complicated, and there is a lot of noise in MRI images. Directly inputting the original data set into the automatic segmentation system will bring noise and cause the model's segmentation accuracy to decrease. Therefore, this paper proposes an osteosarcoma MRI image segmentation system based on a deep convolution neural network, which solves the overfitting problem caused by noisy data and improves the generalization performance of the model. Firstly, we use Mean Teacher to optimize the data set. The noise data is put into the second round of training of the model to improve the robustness of the model. Then, we segment the image using a deep separable U-shaped network (SepUNet) and conditional random field (CRF). SepUnet can segment lesion regions of different sizes at multiple scales; CRF further optimizes the boundary. Finally, this article calculates the area of the tumor area, which provides a more intuitive reference for assisting doctors in diagnosis. More than 80000 MRI images of osteosarcoma from three hospitals in China were tested. The results show that the proposed method guarantees the balance of speed, accuracy, and cost under the premise of improving accuracy.

Functional Dysconnectivity in Ventral Striatocortical Systems in 22q11.2 Deletion Syndrome.

22q11.2 deletion syndrome (22q11.2DS) is a genetic neurodevelopmental disorder that represents one of the greatest known risk factors for psychosis. Previous studies in psychotic subjects without the deletion have identified a dopaminergic dysfunction in striatal regions, and dysconnectivity of striatocortical systems, as an important mechanism in the emergence of psychosis. Here, we used resting-state functional MRI to examine striatocortical functional connectivity in 22q11.2DS patients. We used a 2 × 2 factorial design including 125 subjects (55 healthy controls, 28 22q11.2DS patients without a history of psychosis, 10 22q11.2DS patients with a history of psychosis, and 32 subjects with a history of psychosis without the deletion), allowing us to identify network effects related to the deletion and to the presence of psychosis. In line with previous results from psychotic patients without 22q11.2DS, we found that there was a dorsal to ventral gradient of hypo- to hyperstriatocortical connectivity related to psychosis across both patient groups. The 22q11.2DS was additionally associated with abnormal functional connectivity in ventral striatocortical networks, with no significant differences identified in the dorsal system. Abnormalities in the ventral striatocortical system observed in these individuals with high genetic risk to psychosis may thus reflect a marker of illness risk.

Neuroradiological Mimics of Periventricular Leukomalacia.

AIM: Periventricular leukomalacia (PVL) is a term reserved to describe white matter injury in the premature brain. In this review article, the authors highlight the common and rare pathologies mimicking the chronic stage of PVL and propose practical clinico-radiological criteria that would aid in diagnosis and management. METHODS AND RESULTS: The authors first describe the typical brain MRI (magnetic resonance imaging) features of PVL. Based on their clinical presentation, pathologic entities and their neuroimaging findings were clustered into distinct categories. Three clinical subgroups were identified: healthy children, children with stable/nonprogressive neurological disorder, and those with progressive neurological disorder. The neuroradiological discriminators are described in each subgroup with relevant differential diagnoses. The mimics were broadly classified into normal variants, acquired, and inherited disorders. CONCLUSIONS: The term "PVL" should be used appropriately as it reflects its pathomechanism. The phrase "white matter injury of prematurity" or "brain injury of prematurity" is more specific. Discrepancies in imaging and clinical presentation must be tread with caution and warrant further investigations to exclude other possibilities.

Imaging and pathologic features of non-calcified ductal carcinoma in situ: can sonography predict upgrade?

OBJECTIVE: The purpose of this study was to evaluate the imaging and pathologic features and upgrade rate of non-calcified ductal carcinoma in situ (NCDCIS). The study tested the hypothesis that lesions with sonographic findings have higher upgrade rate compared to lesions seen on mammography or MRI only. METHODS: This retrospective study included patients with ductal carcinoma in situ (DCIS) diagnosed by image-guided core breast biopsy from December 2009 to April 2018. Patients with microcalcifications on mammography or concurrent ipsilateral cancer on core biopsy were excluded. An upgrade was defined as surgical pathology showing microinvasive or invasive cancer. RESULTS: A total of 71 lesions constituted the study cohort. 62% of cases (44/71) had a mammographic finding, and 38% (27/71) of mammographically occult lesions had findings on either ultrasound, MRI, or both. Of the 67 cases that underwent sonography, a mass was noted in 56/67 (83.6%) cases and no sonographic correlate was identified in 11/67 (16.4%) cases. 21% (15/71) of lesions were upgraded on final surgical pathology. The upgrade rate of patients with sonographic correlate was 27% (15/56) vs with mammographic findings only was 0% (0/11). CONCLUSION: DCIS should be considered in the differential diagnosis of architectural distortion, asymmetries, focal asymmetries, and masses, even in the absence of microcalcifications. NCDCIS diagnosed by ultrasound may be an independent risk factor for upgrade. ADVANCES IN KNOWLEDGE: Radiologists must be aware of imaging features of DCIS and consider increased upgrade rate when NCDCIS is diagnosed by ultrasound.

Preoperative MRI PI-RADS scores are associated with prostate cancer upstaging on surgical pathology.

INTRODUCTION: Prostate Imaging Reporting and Data System (PI-RADS) scores can help identify clinically significant prostate cancer and improve patient selection for prostate biopsies. However, the role of PI-RADS scores in patients already diagnosed with prostate cancer remains unclear. The purpose of this study was to evaluate the association of PI-RADS scores with prostate cancer upstaging. Upstaging on final pathology harbors a higher risk for biochemical recurrence with important implications for additional treatments, morbidity, and mortality. METHODS: All patients from a single high-volume institution who underwent a prostate multiparametric magnetic resonance imaging and radical prostatectomy between 2016 and 2020 were included in this retrospective analysis. Univariable and multivariable analyses were conducted to investigate potential associations with upstaging events, defined by pT3, pT4, or N1 on final pathology. A logistic regression model was constructed for the prediction of upstaging events based on PI-RADS score, prostate-specific antigen density (PSA-D), and biopsy Gleason grade groups. We built receiver operative characteristic (ROC) curves to measure the area under the curve of different predictive models. RESULTS: Two hundred and ninety-four patients were included in the final analysis. Upstaging events occurred in 137 (46.5%) of patients. On univariable analysis, patients who were upstaged on final pathology had significantly higher PI-RADS scores (odds ratio [OR] 2.34 95% confidence interval [CI] 1.64-3.40, p < 0.001) but similar PSA-D (OR 2.70 95% 0.94-8.43, p = 0.188) compared with patients who remained pT1 or pT2 on final pathology. On multivariable analysis, PI-RADS remained independently significantly associated with upstaging, suggesting it is an independent risk predictor for upstaging. Lymph node metastasis only occurred in patients with PI-RADS 4 or 5 lesions (n = 15). Our model using PSA-D, biopsy Gleason grade, and PI-RADS had a predictive AUC of 0.69 for upstaging events, an improvement from 0.59 using biopsy Gleason grade alone. CONCLUSION: PI-RADS scores are independent predictors for upstaging events and may play an important role in forecasting biochemical recurrence and lymph node metastasis. Modern nomograms should be updated to include PI-RADS to predict lymph node metastases and the likelihood of biochemical recurrence more accurately.

The Impact of the COVID-19 Pandemic on the Workload, Case Mix and hospital Resources at a Tertiary Vascular Unit.

BACKGROUND: The aim of this study was to examine the COVID-19 pandemic and its associated impact on the provision of vascular services, and the pattern of presentation and practice in a tertiary referral vascular unit. METHODS: This is a retrospective observational study from a prospectively maintained data-base comparing two time frames, Period 1(15th March-30th May 2019-P1) and Period 2(15th March-30th May 2020-P2)All the patients who presented for a vascular review in the 2 timeframes were included. Metrics of service and patient care episodes were collected and compared including, the number of emergency referrals, patient encounters, consultations, emergency admissions and interventions. Impact on key hospital resources such as critical care and imaging facilities during the two time periods were also examined. RESULTS: There was an absolute reduction of 44% in the number of patients who required urgent or emergency treatment from P1 to P2 (141 vs 79). We noted a non-significant trend towards an increase in the proportion of patients presenting with Chronic Limb Threatening Ischaemia (CLTI) Rutherford 5&6 (P=0.09) as well as a reduction in the proportion of admissions related to Aortic Aneurysm (P=0.21). There was a significant absolute reduction of 77% in all vascular interventions from P1 to P2 with the greatest reductions noted in Carotid (P=0.02), Deep Venous (P=0.003) and Aortic interventions (P=0.016). The number of lower limb interventions also decreased though there was a significant increase as a relative proportion of all vascular interventions in P2 (P=0.001). There was an absolute reduction in the number of scans performed for vascular pathology; Duplex scans reduced by 86%(P<0.002), CT scans by 68%(P<0.003) and MRIs by 74%(P<0.009). CONCLUSION: We report a decrease in urgent and emergency vascular presentations, admissions and interventions. The reduction in patients presenting with lower limb pathology was not as significant as other vascular conditions, resulting in a significant rise in interventions for CLTI and DFI as a proportion of all vascular interventions. These observations will help guide the provision of vascular services during future pandemics.

Morphometric Analysis of Structural MRI Using Schizophrenia Meta-analytic Priors Distinguish Patients from Controls in Two Independent Samples and in a Sample of Individuals With High Polygenic Risk.

Schizophrenia (SCZ) is associated with structural brain changes, with considerable variation in the extent to which these cortical regions are influenced. We present a novel metric that summarises individual structural variation across the brain, while considering prior effect sizes, established via meta-analysis. We determine individual participant deviation from a within-sample-norm across structural MRI regions of interest (ROIs). For each participant, we weight the normalised deviation of each ROI by the effect size (Cohen's d) of the difference between SCZ/control for the corresponding ROI from the SCZ Enhancing Neuroimaging Genomics through Meta-Analysis working group. We generate a morphometric risk score (MRS) representing the average of these weighted deviations. We investigate if SCZ-MRS is elevated in a SCZ case/control sample (NCASE = 50; NCONTROL = 125), a replication sample (NCASE = 23; NCONTROL = 20) and a sample of asymptomatic young adults with extreme SCZ polygenic risk (NHIGH-SCZ-PRS = 95; NLOW-SCZ-PRS = 94). SCZ cases had higher SCZ-MRS than healthy controls in both samples (Study 1: ß = 0.62, P < 0.001; Study 2: ß = 0.81, P = 0.018). The high liability SCZ-PRS group also had a higher SCZ-MRS (Study 3: ß = 0.29, P = 0.044). Furthermore, the SCZ-MRS was uniquely associated with SCZ status, but not attention-deficit hyperactivity disorder (ADHD), whereas an ADHD-MRS was linked to ADHD status, but not SCZ. This approach provides a promising solution when considering individual heterogeneity in SCZ-related brain alterations by identifying individual's patterns of structural brain-wide alterations.

3 T: the good, the bad and the ugly.

It is around 20 years since the first commercial 3 T MRI systems became available. The theoretical promise of twice the signal-to-noise ratio of a 1.5 T system together with a greater sensitivity to magnetic susceptibility-related contrast mechanisms, such as the blood oxygen level dependent effect that is the basis for functional MRI, drove the initial market in neuroradiology. However, the limitations of the increased field strength soon became apparent, including the increased radiofrequency power deposition, tissue-dependent changes in relaxation times, increased artifacts, and greater safety concerns. Many of these issues are dependent upon MR physics and workarounds have had to be developed to try and mitigate their effects. This article reviews the underlying principles of the good, the bad and the ugly aspects of 3 T, discusses some of the methods used to improve image quality and explains the remaining challenges and concerns.

Superior sensitivity of 18F-fluorocholine: PET localization in primary hyperparathyroidism.

BACKGROUND: Preoperative parathyroid imaging guides surgeons during parathyroidectomy. This study evaluates the clinical impact of 18F-fluorocholine positron emission tomography for preoperative parathyroid localization on patients with primary hyperparathyroidism. METHODS: Patients with primary hyperparathyroidism and indications for parathyroidectomy had simultaneous 18F-fluorocholine positron emission tomography imaging/magnetic resonance imaging. In patients who underwent subsequent parathyroidectomy, cure was based on lab values at least 6 months after surgery. Location-based sensitivity and specificity of 18F-fluorocholine positron emission tomography imaging was assessed using 3 anatomic locations (left neck, right neck, and mediastinum), with surgery as the gold standard. RESULTS: In 101 patients, 18F-fluorocholine positron emission tomography localized at least 1 candidate lesion in 93% of patients overall and in 91% of patients with previously negative imaging, leading to a change in preoperative strategy in 60% of patients. Of 76 patients who underwent parathyroidectomy, 58 (77%) had laboratory data at least 6 months postoperatively, with 55/58 patients (95%) demonstrating cure. 18F-fluorocholine positron emission tomography successfully guided curative surgery in 48/58 (83%) patients, compared with 20/57 (35%) based on ultrasound and 13/55 (24%) based on sestamibi. In a location-based analysis, sensitivity of 18F-fluorocholine positron emission tomography (88.9%) outperformed both ultrasound (37.1%) and sestamibi (27.5%), as well as ultrasound and sestamibi combined (47.8%). CONCLUSION: Long-term results in the first cohort in the United States to use 18F-fluorocholine positron emission tomography for parathyroid localization confirm its utility in a challenging cohort, with better sensitivity than ultrasound or sestamibi.

Preoperative staging of ovarian cancer: comparison between ultrasound, CT and whole-body diffusion-weighted MRI (ISAAC study).

OBJECTIVES: To compare the performance of transvaginal and transabdominal ultrasound with that of the first-line staging method (contrast-enhanced computed tomography (CT)) and a novel technique, whole-body magnetic resonance imaging with diffusion-weighted sequence (WB-DWI/MRI), in the assessment of peritoneal involvement (carcinomatosis), lymph-node staging and prediction of non-resectability in patients with suspected ovarian cancer. METHODS: Between March 2016 and October 2017, all consecutive patients with suspicion of ovarian cancer and surgery planned at a gynecological oncology center underwent preoperative staging and prediction of non-resectability with ultrasound, CT and WB-DWI/MRI. The evaluation followed a single, predefined protocol, assessing peritoneal spread at 19 sites and lymph-node metastasis at eight sites. The prediction of non-resectability was based on abdominal markers. Findings were compared to the reference standard (surgical findings and outcome and histopathological evaluation). RESULTS: Sixty-seven patients with confirmed ovarian cancer were analyzed. Among them, 51 (76%) had advanced-stage and 16 (24%) had early-stage ovarian cancer. Diagnostic laparoscopy only was performed in 16% (11/67) of the cases and laparotomy in 84% (56/67), with no residual disease at the end of surgery in 68% (38/56), residual disease ≤ 1 cm in 16% (9/56) and residual disease > 1 cm in 16% (9/56). Ultrasound and WB-DWI/MRI performed better than did CT in the assessment of overall peritoneal carcinomatosis (area under the receiver-operating-characteristics curve (AUC), 0.87, 0.86 and 0.77, respectively). Ultrasound was not inferior to CT (P = 0.002). For assessment of retroperitoneal lymph-node staging (AUC, 0.72-0.76) and prediction of non-resectability in the abdomen (AUC, 0.74-0.80), all three methods performed similarly. In general, ultrasound had higher or identical specificity to WB-DWI/MRI and CT at each of the 19 peritoneal sites evaluated, but lower or equal sensitivity in the abdomen. Compared with WB-DWI/MRI and CT, transvaginal ultrasound had higher accuracy (94% vs 91% and 85%, respectively) and sensitivity (94% vs 91% and 89%, respectively) in the detection of carcinomatosis in the pelvis. Better accuracy and sensitivity of ultrasound (93% and 100%) than WB-DWI/MRI (83% and 75%) and CT (84% and 88%) in the evaluation of deep rectosigmoid wall infiltration, in particular, supports the potential role of ultrasound in planning rectosigmoid resection. In contrast, for the bowel serosal and mesenterial assessment, abdominal ultrasound had the lowest accuracy (70%, 78% and 79%, respectively) and sensitivity (42%, 65% and 65%, respectively). CONCLUSIONS: This is the first prospective study to document that, in experienced hands, ultrasound may be an alternative to WB-DWI/MRI and CT in ovarian cancer staging, including peritoneal and lymph-node evaluation and prediction of non-resectability based on abdominal markers of non-resectability. © 2021 International Society of Ultrasound in Obstetrics and Gynecology.

The accuracy of three-dimensional ultrasonography in the diagnosis of Müllerian duct anomalies and its concordance with magnetic resonance imaging.

This retrospective study was performed to comparatively evaluate the diagnostic accuracies of three-dimensional ultrasonography (3D-US) and magnetic resonance imaging (MRI) for identification of Müllerian duct anomalies (MDAs). A total of 27 women with suspected MDAs underwent gynaecological examination, 2D-US, 3D-US and MRI, respectively. The MDAs were classified with respect to the European Society of Human Reproduction and Embryology-European Society for Gynaecological Endoscopy (ESHRE/ESGE) and American Society of Reproductive Medicine (ASRM) systems. Based on the ESHRE/ESGE classification, there was a discrepancy for only one patient between US and MRI. Thus, the concordance between US and MRI was 26/27 (96.3%). With respect to ASRM classification, there was a disagreement between MRI and 3D-US in three patients, thus the concordance between MRI and 3D-US was 24/27 (88.9%). To conclude, the 3D-US has a good level of agreement with MRI for recognition of MDAs.Impact StatementWhat is already known on this subject? Müllerian duct anomalies (MDAs) are relatively common malformations of the female genital tract and they may adversely affect the reproductive potential. The establishment of accurate and timely diagnosis of these malformations is critical to overcome clinical consequences of MDAs.What the results of this study add? The concordance between US and MRI for diagnosis of MDAs based on ESHRE-ESGE classification and ASRM were 96.3% and 88.9%, respectively. These results indicate that 3D US has a satisfactory level of diagnostic accuracy for MDAs and it can be used in conjunction with MRI. Minimisation of diagnostic errors is important to improve reproductive outcome and to avoid unnecessary surgical interventions.What the implications are of these findings for clinical practice and/or further research? Efforts must be spent to eliminate the discrepancies between the clinical and radiological diagnosis of MDAs. Further trials should be implemented for establishment and standardisation of radiological images for identification and classification of MDAs.