Non-Gaussian diffusion metrics with whole-tumor histogram analysis for bladder cancer diagnosis: muscle invasion and histological grade.

PURPOSE: To investigate the performance of histogram features of non-Gaussian diffusion metrics for diagnosing muscle invasion and histological grade in bladder cancer (BCa). METHODS: Patients were prospectively allocated to MR scanner1 (training cohort) or MR2 (testing cohort) for conventional diffusion-weighted imaging (DWIconv) and multi-b-value DWI. Metrics of continuous time random walk (CTRW), diffusion kurtosis imaging (DKI), fractional-order calculus (FROC), intravoxel incoherent motion (IVIM), and stretched exponential model (SEM) were simultaneously calculated using multi-b-value DWI. Whole-tumor histogram features were extracted from DWIconv and non-Gaussian diffusion metrics for logistic regression analysis to develop diffusion models diagnosing muscle invasion and histological grade. The models' performances were quantified by area under the receiver operating characteristic curve (AUC). RESULTS: MR1 included 267 pathologically-confirmed BCa patients (median age, 67 years [IQR, 46-82], 222 men) and MR2 included 83 (median age, 65 years [IQR, 31-82], 73 men). For discriminating muscle invasion, CTRW achieved the highest testing AUC of 0.915, higher than DWIconv's 0.805 (p = 0.014), and similar to the combined diffusion model's AUC of 0.885 (p = 0.076). For differentiating histological grade of non-muscle-invasion bladder cancer, IVIM outperformed a testing AUC of 0.897, higher than DWIconv's 0.694 (p = 0.020), and similar to the combined diffusion model's AUC of 0.917 (p = 0.650). In both tasks, DKI, FROC, and SEM failed to show diagnostic superiority over DWIconv (p > 0.05). CONCLUSION: CTRW and IVIM are two potential non-Gaussian diffusion models to improve the MRI application in assessing muscle invasion and histological grade of BCa, respectively. CRITICAL RELEVANCE STATEMENT: Our study validates non-Gaussian diffusion imaging as a reliable, non-invasive technique for early assessment of muscle invasion and histological grade in BCa, enhancing accuracy in diagnosis and improving MRI application in BCa diagnostic procedures. KEY POINTS: Muscular invasion largely determines bladder salvageability in bladder cancer patients. Evaluated non-Gaussian diffusion metrics surpassed DWIconv in BCa muscle invasion and histological grade diagnosis. Non-Gaussian diffusion imaging improved MRI application in preoperative diagnosis of BCa.

Comparison of the monoexponential and biexponential models of diffusion-weighted magnetic imaging in grading clear-cell renal cell carcinoma: a case-control study.

Background: An accurate and noninvasive method to determine the preoperative clear-cell renal cell carcinoma (ccRCC) pathological grade is of great significance for surgical program selection and prognosis assessment. Previous studies have shown that diffusion-weighted imaging (DWI) has moderate value in grading ccRCC. But DWI cannot reflect the diffusion of tissue accurately because it is calculated using a monoexponential model. Intravoxel incoherent motion (IVIM) is the biexponential model of DWI. Only a few studies have examined the value of IVIM in grading ccRCC yet with inconsistent results. This study aimed to compare the value of DWI and IVIM in grading ccRCC. Methods: In this study, 96 patients with pathologically confirmed ccRCC were evaluated by DWI and IVIM on a 3-T scanner. According to the World Health Organization/International Society of Urological Pathology (WHO/ISUP) classification system, these patients were divided into two groups: low-grade (grade I and II) and high-grade (grade III and IV) ccRCC. The apparent diffusion coefficient (ADC), true diffusion coefficient (D), pseudodiffusion coefficient (D*), and perfusion fraction of pseudodiffusion (f) values were calculated. The Mann-Whitney test, receiver-operating characteristic (ROC) analysis, and the Delong test were used for statistical evaluations. Results: (I) According to the WHO/ISUP nuclear grading system, 96 patients were divided into low-grade (grade I and II, 45 patients) and high-grade (grade III and IV, 51 patients) groups. (II) Compared with patients of low-grade ccRCC, the ADC and D values of those with high-grade ccRCC decreased while the D* and f values increased (P<0.05). (III) The cutoff value of the ADC, D, D*, and f in distinguishing low-grade from high-grade ccRCC was 1.50×10-3 mm2/s, 1.12×10-3 mm2/s, and 33.19×10-3 mm2/s, 0.31, respectively; the area under the curve (AUC) for the ADC, D, D*, and f values was 0.871, 0.942, 0.621, and 0.894, respectively, with the AUC of the D value being the highest; the sensitivity for the ADC, D, D*, and f values was 94.12%, 92.16%, 47.06%, and 92.16%, respectively; and the specificity for the ADC, D, D*, and f values was 66.67%, 91.11%, 77.78%, and 73.33%, respectively. (IV) Based on the Delong test, AUCD was significantly higher than AUCADC (P=0.02) and AUCD* (P<0.001), but there was no significant difference between AUCD and AUC f (P=0.18). Conclusions: Compared with the monoexponential model DWI, the biexponential model IVIM was more accurate in grading ccRCC.

Evaluating the added value of synthetic magnetic resonance imaging in predicting sentinel lymph node status in breast cancer.

Background: The noninvasive prediction of sentinel lymph node (SLN) metastasis using quantitative magnetic resonance imaging (MRI), particularly with synthetic MRI (syMRI), is an emerging field. This study aimed to explore the potential added benefits of syMRI over conventional MRI and diffusion-weighted imaging (DWI) in predicting metastases in SLNs. Methods: This retrospective study consecutively enrolled 101 patients who were diagnosed with breast cancer (BC) and underwent SLN biopsy from December 2022 to October 2023 at the Affiliated Hospital of Jiangnan University. These patients underwent preoperative MRI including conventional MRI, DWI, and syMRI and were categorized into two groups according to the postoperative pathological results: those with and without metastatic SLNs. MRI morphological features, DWI, and syMRI-derived quantitative parameters of breast tumors were statistically compared between these two groups. Binary logistic regression was used to separately develop predictive models for determining the presence of SLN involvement, with variables that exhibited significant differences being incorporated. The performance of each model was evaluated through receiver operating characteristic (ROC) curve analysis, including the area under the curve (AUC), sensitivity, and specificity. Results: Compared to the group of 54 patients with BC but no metastatic SLNs, the group of 47 patients with BC and metastatic SLNs had a significantly larger maximum axis diameter [metastatic SLNs: median 2.40 cm, interquartile range (IQR) 1.50-3.00 cm; no metastatic SLNs: median 1.80 cm, IQR 1.37-2.50 cm; P=0.03], a higher proton density (PD) (78.44±11.92 vs. 69.20±10.63 pu; P<0.001), and a lower apparent diffusion coefficient (ADC) (metastatic SLNs: median 0.91×10-3 mm2/s, IQR 0.79-1.01 mm2/s; no metastatic SLNs: median 1.02×10-3 mm2/s, IQR 0.92-1.12 mm2/s; P=0.001). Moreover, the prediction model with maximum axis diameter and ADC yielded an AUC of 0.71 [95% confidence interval (CI): 0.618-0.802], with a sensitivity of 78.72% and a specificity of 51.85%; After addition of syMRI-derived PD to the prediction model, the AUC increased significantly to 0.86 (AUC: 0.86 vs. 0.71; 95% CI: 0.778-0.922; P=0.002), with a sensitivity of 80.85% and a specificity of 81.50%. Conclusions: Combined with conventional MRI and DWI, syMRI can offer additional value in enhancing the predictive performance of determining SLN status before surgery in patients with BC.

Noninvasive assessment of Ki-67 labeling index in glioma patients based on multi-parameters derived from advanced MR imaging.

Purpose: To investigate the predictive value of multi-parameters derived from advanced MR imaging for Ki-67 labeling index (LI) in glioma patients. Materials and Methods: One hundred and nine patients with histologically confirmed gliomas were evaluated retrospectively. These patients underwent advanced MR imaging, including dynamic susceptibility-weighted contrast enhanced MR imaging (DSC), MR spectroscopy imaging (MRS), diffusion-weighted imaging (DWI) and diffusion-tensor imaging (DTI), before treatment. Twenty-one parameters were extracted, including the maximum, minimum and mean values of relative cerebral blood flow (rCBF), relative cerebral blood volume (rCBV), relative mean transit time (rMTT), relative apparent diffusion coefficient (rADC), relative fractional anisotropy (rFA) and relative mean diffusivity (rMD) respectively, and ration of choline (Cho)/creatine (Cr), Cho/N-acetylaspartate (NAA) and NAA/Cr. Stepwise multivariate regression was performed to build multivariate models to predict Ki-67 LI. Pearson correlation analysis was used to investigate the correlation between imaging parameters and the grade of glioma. One-way analysis of variance (ANOVA) was used to explore the differences of the imaging parameters among the gliomas of grade II, III, and IV. Results: The multivariate regression showed that the model of five parameters, including rCBVmax (RC=0.282), rCBFmax (RC=0.151), rADCmin (RC= -0.14), rFAmax (RC=0.325) and Cho/Cr ratio (RC=0.157) predicted the Ki-67 LI with a root mean square (RMS) error of 0. 0679 (R2 = 0.8025).The regression check of this model showed that there were no multicollinearity problem (variance inflation factor: rCBVmax, 3.22; rCBFmax, 3.14; rADCmin, 1.96; rFAmax, 2.51; Cho/Cr ratio, 1.64), and the functional form of this model was appropriate (F test: p=0.682). The results of Pearson correlation analysis showed that the rCBVmax, rCBFmax, rFAmax, the ratio of Cho/Cr and Cho/NAA were positively correlated with Ki-67 LI and the grade of glioma, while the rADCmin and rMDmin were negatively correlated with Ki-67 LI and the grade of glioma. Conclusion: Combining multiple parameters derived from DSC, DTI, DWI and MRS can precisely predict the Ki-67 LI in glioma patients.

Mean Apparent Propagator MRI: Quantitative Assessment of Tumor-Stroma Ratio in Invasive Ductal Breast Carcinoma.

Purpose To determine whether metrics from mean apparent propagator (MAP) MRI perform better than apparent diffusion coefficient (ADC) value in assessing the tumor-stroma ratio (TSR) status in breast carcinoma. Materials and Methods From August 2021 to October 2022, 271 participants were prospectively enrolled (ClinicalTrials.gov identifier: NCT05159323) and underwent breast diffusion spectral imaging and diffusion-weighted imaging. MAP MRI metrics and ADC were derived from the diffusion MRI data. All participants were divided into high-TSR (stromal component < 50%) and low-TSR (stromal component ≥ 50%) groups based on pathologic examination. Clinicopathologic characteristics were collected, and MRI findings were assessed. Logistic regression was used to determine the independent variables for distinguishing TSR status. The area under the receiver operating characteristic curve (AUC) and sensitivity, specificity, and accuracy were compared between the MAP MRI metrics, either alone or combined with clinicopathologic characteristics, and ADC, using the DeLong and McNemar test. Results A total of 181 female participants (mean age, 49 years ± 10 [SD]) were included. All diffusion MRI metrics differed between the high-TSR and low-TSR groups (P < .001 to P = .01). Radial non-Gaussianity from MAP MRI and lymphovascular invasion were significant independent variables for discriminating the two groups, with a higher AUC (0.81 [95% CI: 0.74, 0.87] vs 0.61 [95% CI: 0.53, 0.68], P < .001) and accuracy (138 of 181 [76%] vs 106 of 181 [59%], P < .001) than that of the ADC. Conclusion MAP MRI may serve as a better approach than conventional diffusion-weighted imaging in evaluating the TSR of breast carcinoma. Keywords: MR Diffusion-weighted Imaging, MR Imaging, Breast, Oncology ClinicalTrials.gov Identifier: NCT05159323 Supplemental material is available for this article. © RSNA, 2024.

The Role of Optic Nerve Diffusion Restriction on Visual Prognosis in Methanol Poisoning.

The aim of this study was to investigate the role of optic nerve diffusion status on cranio-orbital magnetic resonance imaging (MRI) in predicting visual prognosis in cases of methanol intoxication. Diffusion-weighted imaging (DWI) from 16 eyes of eight patients who were admitted to our clinic due to methanol intoxication was analysed retrospectively. The relationship between clinical and laboratory findings, treatment regimen, visual prognosis, and imaging findings was investigated. Diffusion restriction (DR) of the optic nerve on DWI was observed in seven (43%) eyes. Regardless of the clinical and laboratory characteristics and treatment regimen, visual acuity (VA) improved in eyes in which restricted diffusion regressed over the follow-up period. DWI of the optic nerve during the acute phase of methanol poisoning may provide prognostically important data. Improvement of DR during follow-up may be an indicator of an increase in VA.

Short fiber bundle filtering and test-retest reproducibility of the Superficial White Matter.

In recent years, there has been a growing interest in studying the Superficial White Matter (SWM). The SWM consists of short association fibers connecting near giry of the cortex, with a complex organization due to their close relationship with the cortical folding patterns. Therefore, their segmentation from dMRI tractography datasets requires dedicated methodologies to identify the main fiber bundle shape and deal with spurious fibers. This paper presents an enhanced short fiber bundle segmentation based on a SWM bundle atlas and the filtering of noisy fibers. The method was tuned and evaluated over HCP test-retest probabilistic tractography datasets (44 subjects). We propose four fiber bundle filters to remove spurious fibers. Furthermore, we include the identification of the main fiber fascicle to obtain well-defined fiber bundles. First, we identified four main bundle shapes in the SWM atlas, and performed a filter tuning in a subset of 28 subjects. The filter based on the Convex Hull provided the highest similarity between corresponding test-retest fiber bundles. Subsequently, we applied the best filter in the 16 remaining subjects for all atlas bundles, showing that filtered fiber bundles significantly improve test-retest reproducibility indices when removing between ten and twenty percent of the fibers. Additionally, we applied the bundle segmentation with and without filtering to the ABIDE-II database. The fiber bundle filtering allowed us to obtain a higher number of bundles with significant differences in fractional anisotropy, mean diffusivity, and radial diffusivity of Autism Spectrum Disorder patients relative to controls.

Radiological insights into rheumatoid meningitis - a rare central nervous system manifestation of rheumatoid arthritis: a retrospective review of six cases.

BACKGROUND: The objective is to analyze and review the clinical, laboratory, and neuroimaging characteristics of rheumatoid meningitis (RM) in six patients with known rheumatoid arthritis (RA). METHODS: We performed a retrospective review of patients diagnosed with RM from August 2012 to June 2023. To identify the cases, we used medical term search engines and the hospital´s radiology case database. Clinical information and laboratory findings were gathered from the medical records. A neuroradiologist with five years of experience reviewed and analyzed the RM to determine the characteristics findings of RM. RESULTS: Six patients with RM are included. Seizures along with headaches were among the clinical signs that were documented. All the patients had high levels of rheumatoid factor (RF) and anti-cyclic citrullinated peptides (ACPA) in the peripheral blood. Biopsy in two cases confirmed typical rheumatoid nodules. Leptomeningeal enhancement was found bilaterally in all cases and was predominantly found in the frontoparietal region. "Mismatch DWI/FLAIR" was found in five patients. Bilateral subdural collections could be found in two patients. Brain PET scan revealed increased metabolism in two cases. CONCLUSION: Rheumatoid meningitis is a rare complication of rheumatoid arthritis (RA) with challenging clinical diagnosis due to non-specific symptoms. This study highlights the importance of MR in detecting characteristic neuroimaging patterns, including "mismatch DWI/FLAIR", to aid in early diagnosis. Increased awareness of this condition may facilitate timely intervention and improve prognosis. These results still need to be verified by large studies.

Diagnostic performance of multishot echo-planar imaging (RESOLVE) and non-echo-planar imaging (HASTE) diffusion-weighted imaging in cholesteatoma with an emphasis on signal intensity ratio measurement.

PURPOSE: To evaluate the diagnostic efficacy of multishot echo-planar imaging (EPI) [RESOLVE (RS)] and non-EPI (HASTE) diffusion-weighted imaging (DWI) in detecting cholesteatoma (CHO), and to explore the role of signal intensity (SI) ratio measurements in addressing diagnostic challenges. METHODS: We analyzed RS-EPI and non-EPI DWI images from 154 patients who had undergone microscopic middle ear surgery, with pathological confirmation of their diagnoses. Two radiologists, referred to as Reader A and Reader B, independently reviewed the images without prior knowledge of the outcomes. Their evaluation focused on lesion location, T1-weighted (T1W) signal characteristics, and contrast enhancement in temporal bone magnetic resonance imaging. Key parameters included lesion hyperintensity, size, SI, SI ratio, and susceptibility artifact scores across both imaging modalities. RESULTS: Of the patients, 62.3% (96/154) were diagnosed with CHO, whereas 37.7% (58/154) were found to have non-CHO conditions. In RS-EPI DWI, Reader A achieved 89.6% sensitivity, 79.3% specificity, 87.8% positive predictive value (PPV), and 82.1% negative predictive value (NPV). Non-EPI DWI presented similar results with sensitivities of 89.6%, specificities of 86.2%, PPVs of 91.5%, and NPVs of 83.3%. Reader B's results for RS-EPI DWI were 82.3% sensitivity, 84.5% specificity, 89.8% PPV, and 74.2% NPV, whereas, for non-EPI DWI, they were 86.5% sensitivity, 89.7% specificity, 93.3% PPV, and 80% NPV. The interobserver agreement was excellent (RS-EPI, κ: 0.84; non-EPI, κ: 0.91). The SI ratio measurements were consistently higher in non-EPI DWI (Reader A: 2.51, Reader B: 2.46) for the CHO group compared with RS-EPI. The SI ratio cut-off (>1.98) effectively differentiated hyperintense lesions between CHO and non-CHO groups, demonstrating 82.9% sensitivity and 100% specificity, with an area under the curve of 0.901 (95% confidence interval: 0.815-0.956; P < 0.001). Susceptibility artifact scores averaged 1.18 ± 0.7 (Reader A) and 1.04 ± 0.41 (Reader B) in RS-EPI, with non-EPI DWI recording a mean score of 0. CONCLUSION: Both RS-EPI and non-EPI DWI exhibited high diagnostic accuracy for CHO. While RS-EPI DWI cannot replace non-EPI DWI, their combined use improves sensitivity. SI ratio measurement in non-EPI DWI was particularly beneficial in complex diagnostic scenarios. CLINICAL SIGNIFICANCE: This study refines CHO diagnostic protocols by showcasing the diagnostic capabilities of both RS-EPI and non-EPI DWI and highlighting the utility of SI measurements as a diagnostic tool. These findings may reduce false positives and aid in more accurate treatment planning, offering substantial insights for clinicians in managing CHO.

Assessing the radiofrequency shielding effect of titanium mesh on diffusion-weighted imaging: a comparative study of the twice-refocused spin-echo and Stejskal-Tanner sequences.

This study compared twice-refocused spin-echo sequence (TRSE) and Stejskal-Tanner sequence (ST) to evaluate their respective effects on the image quality of magnetic resonance (MR) diffusion-weighted imaging in the presence of radiofrequency (RF) shielding effect of titanium mesh in cranioplasty. A 1.5-T MR scanner with a Head/Neck coil 20 channels and a phantom simulating the T2 and apparent diffusion coefficient (ADC) value of the human brain were used. Imaging was performed with and without titanium mesh placed on the phantom in TRSE and ST, and normalized absolute average deviation (NAAD), Dice similarity coefficient (DSC), and ADC values were calculated. The NAAD values were significantly lower for TRSE than for ST in the area below the titanium mesh, and the drop rates due to titanium mesh were 14.1% for TRSE and 9.8% for ST. The DSC values were significantly lower for TRSE than for ST. The ADC values were significantly higher for TRSE than for ST without titanium mesh. The ADC values showed no significant difference between TRSE and ST with titanium mesh. The ST had a lower RF shielding effect of titanium mesh than the TRSE.

Diffusion-Weighted MRI in Perianal Abscess: Role and Comparison With Contrast-Enhanced MRI.

BACKGROUND: Perianal abscess is a clinical infective and/or inflammatory collection in the perianal region, one entity of a large group of anal and perianal disorders. Perianal abscesses are often seen as a complication of grade 2 and grade 4 perianal fistulas from St. James's University Hospital classification. Several imaging modalities have been tried in the past for adequate assessment of perianal abscess with contrast-enhanced magnetic resonance imaging (CE-MRI) providing the most accurate results. Diffusion-weighted imaging (DWI) is an emerging sequence that can provide comparable results to CE-MRI in diagnosing and characterizing perianal abscess. The main objective of this study is to assess the role of DWI in adequate identification and assessment of perianal abscess and compare the final results with contrast-enhanced images. METHODS: Twenty patients with complicated perianal fistula with clinically suspected perianal abscess were evaluated with DWI and CE-MRI. This study was a comparative cross-sectional study conducted in the Department of Radiodiagnosis and Imaging, All India Institute of Medical Sciences, Bhopal, India. Chi-square test was done to find the association between categorical variables. Kappa test was used to find the agreement between two different tests. Receiver operating characteristics (ROC) analysis was done to estimate the area under the curve in predicting the outcome. Sensitivity, specificity, positive predictive value, negative predictive value and accuracy were used to measure the validity of the tests. RESULTS: DWI is a very sensitive MRI sequence and is equivalent to CE-MRI to detect the location and analyzing the loco-regional extent of abscess in complicated perianal fistula cases. DWI is also very sensitive and superior to T2 short tau inversion recovery (STIR) in differentiating perianal abscess from perianal inflammation without abscess. CONCLUSION: DWI can be used as an alternative to post-contrast fat-suppressed MRI in precisely defining the location and extent of anal and perianal abscesses and disease activity in complicated fistula cases.

Evaluation of split renal dysfunction using radiomics based on magnetic resonance diffusion-weighted imaging.

BACKGROUND: Accurate and noninvasive assessment of split renal dysfunction is crucial, while there is lack of corresponding method clinically. PURPOSE: To investigate the feasibility of using diffusion-weighted imaging (DWI)-based radiomics models to evaluate split renal dysfunction. METHODS: We enrolled patients with impaired and normal renal function undergoing renal DWI examination. Glomerular filtration rate (GFR, mL/min) was measured using 99mTc-DTPA scintigraphy, which is reference standard of GFR measurement. The kidneys were classified into normal (GFR ≥40), mildly impaired (20≤ GFR < 40), moderately impaired (10≤ GFR < 20), and severely impaired (GFR < 10) renal function groups. Optimized subsets of radiomics features were selected from renal DWI images and radiomics scores (Rad-score) calculated to discriminate groups with different renal function. The radiomics model (Rad-score based) was developed in a training cohort and validated in a test cohort. Evaluations were conducted on the discrimination, calibration, and clinical application of the method. RESULTS: The final analysis included 330 kidneys. Logistic regression was used to develop three radiomics models, model A, B, and C, which were used to distinguish normal from impaired, mild from moderate, and moderate from severe renal function, respectively. The area under the curve of the three models were 0.822, 0.704, and 0.887 in the training cohort and 0.843, 0.717, and 0.897 in the test cohort, respectively, indicating efficient discrimination performance. CONCLUSIONS: DWI-based radiomics models have potential for evaluating split renal dysfunction and discriminating between normal and impaired renal function groups and their subgroups.

Structural and microstructural predictors of cognitive decline in deep brain stimulation of subthalamic nucleus in Parkinson's disease.

BACKGROUND AND OBJECTIVES: The intricate relationship between deep brain stimulation (DBS) in Parkinson's disease (PD) and cognitive impairment has lately garnered substantial attention. The presented study evaluated pre-DBS structural and microstructural cerebral patterns as possible predictors of future cognitive decline in PD DBS patients. METHODS: Pre-DBS MRI data in 72 PD patients were combined with neuropsychological examinations and follow-up for an average of 2.3 years after DBS implantation procedure using a screening cognitive test validated for diagnosis of mild cognitive impairment in PD in a Czech population - Dementia Rating Scale 2. RESULTS: PD patients who would exhibit post-DBS cognitive decline were found to have, already at the pre-DBS stage, significantly lower cortical thickness and lower microstructural complexity than cognitively stable PD patients. Differences in the regions directly related to cognition as bilateral parietal, insular and cingulate cortices, but also occipital and sensorimotor cortex were detected. Furthermore, hippocampi, putamina, cerebellum and upper brainstem were implicated as well, all despite the absence of pre-DBS differences in cognitive performance and in the position of DBS leads or stimulation parameters between the two groups. CONCLUSIONS: Our findings indicate that the cognitive decline in the presented PD cohort was not attributable primarily to DBS of the subthalamic nucleus but was associated with a clinically silent structural and microstructural predisposition to future cognitive deterioration present already before the DBS system implantation.

Sample strategies for the assessment of the apparent diffusion coefficient in single large intracranial space-occupying lesions of dogs and cats.

Diffusion-weighted imaging is increasingly available for brain investigation. Image interpretation of intracranial space-occupying lesions often includes the derived apparent diffusion coefficient (ADC) analysis. In human medicine, ADC can help discriminate between benign and malignant lesions in intracranial tumors. This study investigates the difference in ADC values depending on the sample strategies of image analysis. MRI examination, including diffusion-weighted images of canine and feline patients presented between 2015 and 2020, were reviewed retrospectively. Patients with single, large intracranial space-occupying lesions were included. Lesions homogeneity was subjectively scored. ADC values were calculated using six different methods of sampling (M1-M6) on the ADC map. M1 included as much as possible of the lesion on a maximum of five consecutive slices; M2 included five central and five peripheral ROIs; M3 included a single ROI on the solid part of the lesion; M4 included three central ROIs on one slice; M5 included three central ROIs on different slices; and M6 included one large ROI on the entire lesion. A total of 201 animals of various breeds, genders, and ages were analyzed. ADC values differed significantly between M5 against M2 (peripheral) (p < 0.001), M5 against M6 (p = 0.009), and M4 against M2 (peripheral) (p = 0.005). When lesions scored as homogeneous in all sequences were excluded, an additional significant difference in three further sampling methods was present (p < 0.005). ADC of single, large, intracranial space-occupying lesions differed significantly in half of the tested methods of sampling. Excluding homogeneous lesions, additional significant differences among the sampling methods were present. The obtained results should increase awareness of the variability of the ADC, depending on the sample strategies used.

Super-resolution of diffusion-weighted images using space-customized learning model.

BACKGROUND: Diffusion-weighted imaging (DWI) is a noninvasive method used for investigating the microstructural properties of the brain. However, a tradeoff exists between resolution and scanning time in clinical practice. Super-resolution has been employed to enhance spatial resolution in natural images, but its application on high-dimensional and non-Euclidean DWI remains challenging. OBJECTIVE: This study aimed to develop an end-to-end deep learning network for enhancing the spatial resolution of DWI through post-processing. METHODS: We proposed a space-customized deep learning approach that leveraged convolutional neural networks (CNNs) for the grid structural domain (x-space) and graph CNNs (GCNNs) for the diffusion gradient domain (q-space). Moreover, we represented the output of CNN as a graph using correlations defined by a Gaussian kernel in q-space to bridge the gap between CNN and GCNN feature formats. RESULTS: Our model was evaluated on the Human Connectome Project, demonstrating the effective improvement of DWI quality using our proposed method. Extended experiments also highlighted its advantages in downstream tasks. CONCLUSION: The hybrid convolutional neural network exhibited distinct advantages in enhancing the spatial resolution of DWI scans for the feature learning of heterogeneous spatial data.

Investigating the discrimination ability of 3D convolutional neural networks applied to altered brain MRI parametric maps.

Convolutional neural networks (CNNs) are gradually being recognized in the neuroimaging community as a powerful tool for image analysis. Despite their outstanding performances, some aspects of CNN functioning are still not fully understood by human operators. We postulated that the interpretability of CNNs applied to neuroimaging data could be improved by investigating their behavior when they are fed data with known characteristics. We analyzed the ability of 3D CNNs to discriminate between original and altered whole-brain parametric maps derived from diffusion-weighted magnetic resonance imaging. The alteration consisted in linearly changing the voxel intensity of either one (monoregion) or two (biregion) anatomical regions in each brain volume, but without mimicking any neuropathology. Performing ten-fold cross-validation and using a hold-out set for testing, we assessed the CNNs' discrimination ability according to the intensity of the altered regions, comparing the latter's size and relative position. Monoregion CNNs showed that the larger the modified region, the smaller the intensity increase needed to achieve good performances. Biregion CNNs systematically outperformed monoregion CNNs, but could only detect one of the two target regions when tested on the corresponding monoregion images. Exploiting prior information on training data allowed for a better understanding of CNN behavior, especially when altered regions were combined. This can inform about the complexity of CNN pattern retrieval and elucidate misclassified examples, particularly relevant for pathological data. The proposed analytical approach may serve to gain insights into CNN behavior and guide the design of enhanced detection systems exploiting our prior knowledge.

Prediction of cervix cancer stage and grade from diffusion weighted imaging using EfficientNet.

Purpose. This study aims to introduce an innovative noninvasive method that leverages a single image for both grading and staging prediction. The grade and the stage of cervix cancer (CC) are determined from diffusion-weighted imaging (DWI) in particular apparent diffusion coefficient (ADC) maps using deep convolutional neural networks (DCNN).Methods. datasets composed of 85 patients having annotated tumor stage (I, II, III, and IV), out of this, 66 were with grade (II and III) and the remaining patients with no reported grade were retrospectively collected. The study was IRB approved. For each patient, sagittal and axial slices containing the gross tumor volume (GTV) were extracted from ADC maps. These were computed using the mono exponential model from diffusion weighted images (b-values = 0, 100, 1000) that were acquired prior to radiotherapy treatment. Balanced training sets were created using the Synthetic Minority Oversampling Technique (SMOTE) and fed to the DCNN. EfficientNetB0 and EfficientNetB3 were transferred from the ImageNet application to binary and four-class classification tasks. Five-fold stratified cross validation was performed for the assessment of the networks. Multiple evaluation metrics were computed including the area under the receiver operating characteristic curve (AUC). Comparisons with Resnet50, Xception, and radiomic analysis were performed.Results. for grade prediction, EfficientNetB3 gave the best performance with AUC = 0.924. For stage prediction, EfficientNetB0 was the best with AUC = 0.931. The difference between both models was, however, small and not statistically significant EfficientNetB0-B3 outperformed ResNet50 (AUC = 0.71) and Xception (AUC = 0.89) in stage prediction, and demonstrated comparable results in grade classification, where AUCs of 0.89 and 0.90 were achieved by ResNet50 and Xception, respectively. DCNN outperformed radiomic analysis that gave AUC = 0.67 (grade) and AUC = 0.66 (stage).Conclusion.the prediction of CC grade and stage from ADC maps is feasible by adapting EfficientNet approaches to the medical context.

Non-arteritic anterior ischemic optic neuropathy secondary to idiopathic intracranial hypertension.

Purpose: Patients with increased intracranial pressure and underlying hypertensive emergency may present with optic disc edema. Papilledema in this setting may be a predisposing risk factor for superimposed non-arteritic anterior ischemic optic neuropathy (NAION). We highlight the role of neuroimaging including diffusion-weighted imaging in magnetic resonance imaging that can help to differentiate visual loss from NAION versus papilledema in fulminant IIH with and without hypertension. Observations: A 46-year-old female presented with acute vision loss in the right eye and transient right hemiparesis. Neuro-ophthalmic examination revealed optic disc edema in both eyes. Magnetic resonance imaging (MRI) of the brain with diffusion-weighted imaging (DWI) sequences showed restricted diffusion in the optic nerve head of the affected eye. Lumbar puncture revealed an elevated opening pressure of 34.8 cm H2O confirming increased intracranial pressure. Additionally, literature searches were conducted in the PubMed, Google Scholar and Embase databases to uncover previous cases of patients with ischemic optic neuropathy and restricted diffusion on MRI. Conclusions and importance: We highlight the shared pathophysiology between optic disc edema related visual loss in NAION and papilledema in IIH. We review the overlapping clinical and radiographic findings in these two conditions which may occur simultaneously. The presence of restricted diffusion in the optic nerve head versus in the optic nerve parenchyma may support a diagnosis of superimposed NAION and might influence the decision to perform surgery in cases of IIH with fulminant visual loss. Although restricted diffusion on MRI DWI sequences is often used to define cytotoxic edema related to ischemic infarction in the brain, this radiographic finding alone should not be used to determine the indication for surgery for papilledema related visual loss in fulminant IIH.

A Rare and Challenging Presentation of Acute Hemorrhagic Leukoencephalitis With Tumefactive Demyelinating Lesions in a 41-Year-Old Male.

Acute hemorrhagic leukoencephalitis (AHLE) is a rare and severe inflammatory condition of the central nervous system (CNS), characterized by hemorrhagic lesions in the brain's white matter. Here, we present a case of AHLE with concurrent tumefactive demyelinating disease, highlighting the diagnostic and management challenges associated with this complex presentation. Tumefactive multiple sclerosis (MS) is a rare variant of MS characterized by large, space-occupying lesions in the CNS. Concurrently, hemorrhagic leukoencephalitis (HLE) represents a severe inflammatory disorder characterized by hemorrhagic lesions within the CNS white matter. The diagnosis of tumefactive MS with associated HLE posed significant diagnostic challenges due to overlapping clinical and radiological features. Management involved high-dose corticosteroid therapy and supportive care measures, with longitudinal follow-up to assess treatment response and prevent complications. The patient exhibited a favorable clinical response to treatment, with gradual improvement in symptoms and resolution of radiological abnormalities. The coexistence of tumefactive MS with HLE is exceptionally rare and presents diagnostic and therapeutic challenges. We report a 41-year-old male presenting with acute neurological symptoms, including severe headache, confusion, left-sided body weakness, slurred speech, and blurred vision. Neurological examination revealed dysarthric speech, right homonymous hemianopia, left upper motor neuron facial palsy, and motor deficits. MRI demonstrated multifocal areas of T2 hyperintensity with associated hemorrhage, suggestive of tumefactive MS with associated HLE. Diagnostic workup included neurological examination, MRI imaging, cerebrospinal fluid analysis, and serological testing. Management involved high-dose corticosteroid therapy and supportive care measures. The patient exhibited a favorable clinical response to treatment, with gradual improvement in symptoms and resolution of radiological abnormalities. Longitudinal follow-up confirmed sustained improvement. In conclusion, the coexistence of tumefactive MS with HLE poses diagnostic challenges due to overlapping features. This case underscores the importance of considering rare and atypical presentations of CNS demyelinating disease and the potential complications, including associated HLE. Comprehensive evaluation, multidisciplinary collaboration, and individualized management are essential for optimizing outcomes in patients with complex CNS inflammatory disorders.