Search

Background: Treatment response in High-grade Glioma (HGG) patients changes based on their genetic and biological characteristics. MiRNAs, as important regulators of drug and radiation resistance, and the Apparent Diffusion Coefficients (ADC) value of tumor can be used as a prognostic predictor for glioma.Objective: This study aimed to identify some of the pre-treatment individual patient features for predicting the treatment response in HGG patients.Material and Methods: In this prospective study, 18 HGG patients, who were candidated for chemo-radiation treatment, participated after informed consent of the patients. The investigated features were the expression level of miR-222 and miR-205 in plasma, the ADC value of tumor, Body Mass Index (BMI), and age. Treatment response was assessed, and Least Absolute Shrinkage and Selection Operator (LASSO) regression was used to obtain a model to predict the treatment response. Mann-Whitney U test was also applied to select the variables with a significant relationship with patients’ treatment response.Results: The LASSO coefficients for miR-205, miR-222, tumor’s mean ADC value, BMI, and age were 3.611, -1.683, 2.468, -0.184, and -0.024, respectively. Mann-Whitney U test results showed miR-205 and tumor’s mean ADC significantly related to treatment response (P-value˂0.05). Conclusion: The miR-205 expression level of the patient in plasma and tumor’s mean ADC value has the potential for prognostic predictors in HGG.

Background: Treatment response in High-grade Glioma (HGG) patients changes based on their genetic and biological characteristics. MiRNAs, as important regulators of drug and radiation resistance, and the Apparent Diffusion Coefficients (ADC) value of tumor can be used as a prognostic predictor for glioma. Objective: This study aimed to identify some of the pre-treatment individual patient features for predicting the treatment response in HGG patients. Material and Methods: In this prospective study, 18 HGG patients, who were candidated for chemo-radiation treatment, participated after informed consent of the patients. The investigated features were the expression level of miR-222 and miR-205 in plasma, the ADC value of tumor, Body Mass Index (BMI), and age. Treatment response was assessed, and Least Absolute Shrinkage and Selection Operator (LASSO) regression was used to obtain a model to predict the treatment response. Mann-Whitney U test was also applied to select the variables with a significant relationship with patients' treatment response. Results: The LASSO coefficients for miR-205, miR-222, tumor's mean ADC value, BMI, and age were 3.611, -1.683, 2.468, -0.184, and -0.024, respectively. Mann- Whitney U test results showed miR-205 and tumor's mean ADC significantly related to treatment response (P-value<0.05). Conclusion: The miR-205 expression level of the patient in plasma and tumor's mean ADC value has the potential for prognostic predictors in HGG. [ABSTRACT FROM AUTHOR]

(1) Background: Colorectal cancer is the third most common type of cancer with a high mortality rate and poor prognosis. The accurate prediction of key genetic mutations, such as the KRAS status, tumor staging, and extramural venous invasion (EMVI), is crucial for guiding personalized treatment decisions and improving patients' outcomes. MRI radiomics was assessed to predict the KRAS status and tumor staging in colorectal cancer patients across different imaging platforms to improve the personalized treatment decisions and outcomes. (2) Methods: Sixty colorectal cancer patients (35M/25F; avg. age 56.3 ± 12.9 years) were treated at an oncology unit. The MRI scans included T2-weighted (T2W) and diffusion-weighted imaging (DWI) or the apparent diffusion coefficient (ADC). The manual segmentation of colorectal cancer was conducted on the T2W and DWI/ADC images. The cohort was split into training and validation sets, and machine learning was used to build predictive models. (3) Results: The neural network (NN) model achieved 73% accuracy and an AUC of 0.71 during training for predicting the KRAS mutation status, while during testing, it achieved 62.5% accuracy and an AUC of 0.68. In the case of tumor grading, the support vector machine (SVM) model excelled with a training accuracy of 72.93% and an AUC of 0.7, and during testing, it reached an accuracy of 72% and an AUC of 0.69. (4) Conclusions: ML models using radiomics from ADC maps and T2-weighted images are effective for distinguishing KRAS genes, tumor grading, and EMVI in colorectal cancer. Standardized protocols are essential to improve MRI radiomics' reliability in clinical practice. [ABSTRACT FROM AUTHOR]

Abstract Background SUV Max is a glycolytic index obtained from PET imaging, relates to tumour cell proliferation. FDG uptake (i.e. SUV max) is found to be high in aggressive tumours and is used to identify malignant from benign pathologies. Meningiomas are intracranial tumours which display varying grades of FDG avidity based on its biological aggressiveness. Benign grade I meningiomas are FDG non-avid, while the rest of the typical and atypical meningiomas show varying degrees of FDG avidity. Uptake of FDG can be high in certain infectious and inflammatory brain etiologies and pose a diagnostic challenge in differentiating benign brain lesions from neoplasms. MRI is the preferred modality for accurately identifying meningiomas, providing superior contrast differentiation and its ability to differentiate extra-axial from intra-axial brain lesions. CT is said to be superior in specific types of meningioma where there is calcification and adjacent changes in calvarium. Although typical meningiomas have characteristic MRI features, care must be taken to avoid misleading diagnosis between brain tumours and atypical meningiomas. Case presentation We are presenting a recently diagnosed case of invasive breast carcinoma (Ca) referred for staging by PET/MR imaging. Based on atypical DWI and ADC map findings, MRI falsely reported an atypical meningioma as a brain metastasis. Abnormal intense FDG uptake was noted in a well-defined homogeneously enhancing mass lesion in posterior fossa in left paramedian aspect and broad base to left transverse sinus protruding into left cerebellar hemisphere. Atypical meningioma Grade III, i.e. papillary meningioma was later histologically proven. Conclusions We wish to highlight the inconsistency of DWI and ADC map MR findings in papillary meningioma masquerading as solitary brain metastases in a Ca breast patient on 18F FDG PET/MR imaging. From an imaging standpoint, it is important to recognize the variable and pleomorphic features exhibited by meningiomas in MR based on atypical location, histological subtypes, and biologic behaviours. Further FDG PET was incremental in displaying a high SUV max indicating biologic aggressiveness of lesion and correlating with the CT diagnosis of papillary meningioma.

Purpose: In order to evaluate the neuroprotective effect of low-intensity pulsed ultrasound (LIPUS) for acute traumatic brain injury (TBI), we studied the potential of apparent diffusion coefficient (ADC) values and ADC-derived first-order features regarding this problem. Methods: Forty-five male Sprague Dawley rats (sham group: 15, TBI group: 15, LIPUS treated: 15) were enrolled and underwent magnetic resonance imaging. Scanning layers were acquired using a multi-shot readout segmentation of long variable echo trains (RESOLVE) to decrease distortion. The ultrasound transducer was applied to the designated region in the injured cortical areas using a conical collimator and was filled with an ultrasound coupling gel. Regions of interest were manually delineated in the center of the damaged cortex on the diffusion weighted images (b = 800 s/mm2) layer by layer for the TBI and LIPUS treated groups using the open-source software ITK-SNAP. Before analysis and modeling, the features were normalized using a z-score method, and a logistic regression model with a backward filtering method was employed to perform the modeling. The entire process was completed using the R language. Results: During the observation time, the ADC values ipsilateral to the trauma in the TBI and LIPUS groups increased rapidly up to 24 h. After statistical analysis, the 10th percentile, 90th percentile, mean, skewness, and uniformity demonstrated a significant difference among three groups. The receiver operating characteristic curve (ROC) analysis shows that the combined LR model exhibited the highest area under the curve value (AUC: 0.96). Conclusion: The combined LR model of first-order features based on the ADC map can acquire a higher diagnostic performance than each feature only in evaluating the neuroprotective effect of LIPUS for TBI. Models based on first-order features may have potential value in predicting the therapeutic effect of LIPUS in clinical practice in the future. [ABSTRACT FROM AUTHOR]

PurposeIn order to evaluate the neuroprotective effect of low-intensity pulsed ultrasound (LIPUS) for acute traumatic brain injury (TBI), we studied the potential of apparent diffusion coefficient (ADC) values and ADC-derived first-order features regarding this problem.MethodsForty-five male Sprague Dawley rats (sham group: 15, TBI group: 15, LIPUS treated: 15) were enrolled and underwent magnetic resonance imaging. Scanning layers were acquired using a multi-shot readout segmentation of long variable echo trains (RESOLVE) to decrease distortion. The ultrasound transducer was applied to the designated region in the injured cortical areas using a conical collimator and was filled with an ultrasound coupling gel. Regions of interest were manually delineated in the center of the damaged cortex on the diffusion weighted images (b = 800 s/mm2) layer by layer for the TBI and LIPUS treated groups using the open-source software ITK-SNAP. Before analysis and modeling, the features were normalized using a z-score method, and a logistic regression model with a backward filtering method was employed to perform the modeling. The entire process was completed using the R language.ResultsDuring the observation time, the ADC values ipsilateral to the trauma in the TBI and LIPUS groups increased rapidly up to 24 h. After statistical analysis, the 10th percentile, 90th percentile, mean, skewness, and uniformity demonstrated a significant difference among three groups. The receiver operating characteristic curve (ROC) analysis shows that the combined LR model exhibited the highest area under the curve value (AUC: 0.96).ConclusionThe combined LR model of first-order features based on the ADC map can acquire a higher diagnostic performance than each feature only in evaluating the neuroprotective effect of LIPUS for TBI. Models based on first-order features may have potential value in predicting the therapeutic effect of LIPUS in clinical practice in the future.

Background: SUV Max is a glycolytic index obtained from PET imaging, relates to tumour cell proliferation. FDG uptake (i.e. SUV max) is found to be high in aggressive tumours and is used to identify malignant from benign pathologies. Meningiomas are intracranial tumours which display varying grades of FDG avidity based on its biological aggressiveness. Benign grade I meningiomas are FDG non-avid, while the rest of the typical and atypical meningiomas show varying degrees of FDG avidity. Uptake of FDG can be high in certain infectious and inflammatory brain etiologies and pose a diagnostic challenge in differentiating benign brain lesions from neoplasms. MRI is the preferred modality for accurately identifying meningiomas, providing superior contrast differentiation and its ability to differentiate extra-axial from intra-axial brain lesions. CT is said to be superior in specific types of meningioma where there is calcification and adjacent changes in calvarium. Although typical meningiomas have characteristic MRI features, care must be taken to avoid misleading diagnosis between brain tumours and atypical meningiomas. Case presentation: We are presenting a recently diagnosed case of invasive breast carcinoma (Ca) referred for staging by PET/MR imaging. Based on atypical DWI and ADC map findings, MRI falsely reported an atypical meningioma as a brain metastasis. Abnormal intense FDG uptake was noted in a well-defined homogeneously enhancing mass lesion in posterior fossa in left paramedian aspect and broad base to left transverse sinus protruding into left cerebellar hemisphere. Atypical meningioma Grade III, i.e. papillary meningioma was later histologically proven. Conclusions: We wish to highlight the inconsistency of DWI and ADC map MR findings in papillary meningioma masquerading as solitary brain metastases in a Ca breast patient on 18F FDG PET/MR imaging. From an imaging standpoint, it is important to recognize the variable and pleomorphic features exhibited by meningiomas in MR based on atypical location, histological subtypes, and biologic behaviours. Further FDG PET was incremental in displaying a high SUV max indicating biologic aggressiveness of lesion and correlating with the CT diagnosis of papillary meningioma. [ABSTRACT FROM AUTHOR]

Objectives: To validate prospectively the ADNEX magnetic resonance (MR) scoring system to assess adnexal masses and to evaluate a new, modified ADNEX MR scoring system that incorporates diffusion-weighted imaging (DWI) with apparent diffusion coefficient (ADC) mapping.Methods: Between January 2015 and September 2018, 323 consecutive women with adnexal masses diagnosed on transvaginal ultrasound (TVS) underwent standardized MR imaging (MRI) including diffusion and dynamic contrast-enhanced sequences. Of these, 131 underwent subsequent surgery. For interpretation of the MRI examinations, we applied the five-category ADNEX MR scoring system, along with a modified scoring system including DWI with ADC mapping. For both scoring systems, a score was given for all adnexal masses. Histological diagnosis was considered as the gold standard and lesions were classified as benign or malignant. The difference between the predictive values for diagnosing malignancy of the classical and modified scoring systems was assessed on the basis of the areas under the receiver-operating-characteristics (AUC) curves. The sensitivity and specificity for diagnosing malignancy of each score were also calculated.Results: Among the 131 women with adnexal mass(es) diagnosed on TVS who underwent MRI and subsequent surgery, the surgery revealed 161 adnexal masses in 126 women; five women had no mass. Histological examination confirmed 161 adnexal masses, of which all had been detected on MRI: 32 malignant tumors, 15 borderline tumors, which were classified as part of the malignant group (n = 47), and 114 benign lesions. The AUC for prediction of a malignant lesion was 0.938 (95% CI, 0.902-0.975) using the classical ADNEX MR scoring system and 0.974 (95% CI, 0.953-0.996) using the modified scoring system. Pairwise comparison of these AUCs revealed a significant difference (P = 0.0032). The sensitivity and specificity for diagnosing malignancy with an ADNEX MR score of 4 or more were 95.5% and 86.6%, respectively, using the classic scoring system, and 95.7% and 93.3%, respectively, using the modified scoring system.Conclusion: DWI with ADC mapping could be integrated into the ADNEX MR scoring system to improve specificity, thereby potentially optimizing clinical management by avoiding unnecessary surgery. © 2020 International Society of Ultrasound in Obstetrics and Gynecology. [ABSTRACT FROM AUTHOR]

The purpose of this study was to determine diffusion coefficient (ADC) in plaque, peri-plaque and normal-appearing white matter (NAWM) in multiple sclerosis (MS), compare them with the control and correlate findings with cognitive state. Subjects and methods: Sixty-five participants were included and categorized into MS patients with normal cognition (n = 25); MS with mild cognitive impairment (n = 20) and control group (no MS and normal cognition; n = 20). The Montreal Cognitive Assessment was used to determine cognitive state. Mean ADC was measured in plaque, peri-plaques and NAWM, compared with ADC from corresponding white matter in control and correlated with cognitive scores. Chi Square and Pearson correlation coefficient were used. Results: The mean ADC of peri-plaque and NAWM in MS group with cognitive impairment was significantly higher than MS group with normal cognition (p

Introduction: Leukoaraiosis is a common cerebral white matter disease identified radiologically as discrete focal or diffuse patchy bilateral hypodense on computed tomography and hyperintense on T2 weighted Resonance Imaging. Underlying pathogenesis and clinical essence of this radiological finding is yet to be defined clearly. Some patients present with impairment of cognition and dementia. Aim: To assess the usefulness of ADC values in grading the leukoaraiosis and defining its complete extent, identification of the normal appearing white matter with early demyelination changes which is not detectable on conventional MRI and to evaluate the association of leukoaraiosis with impaired cognition. Materials and Methods: This prospective study was done at MRI unit of Department of Radiodiagnosis, C.S.M. Medical University, Lucknow, India during a period of one year from August 2007 to July 2008. Study comprised of Group 1 (cases, n-60) with leukoaraiosis and Group 2 (controls, n-20), healthy subjects with no leukoaraiosis both above 50 years of age. All subjects were studied with 1.5T MRI machine, ADCav values of leukoaraiosis lesions and normal white matter (WM) were estimated. Results: The ADCav values of the leukoaraiotic regions were higher than the normal white matter and the values proportionately increased with the grade of the lesions (p-value ≤ 0.001). The ADCav values of normal white matter were higher in cases than controls and the values increased with grade of leukoaraiosis (p-value < 0.001). Significant association found between reduced Mini Mental Status Examination (MMSE) and presence of leukoaraiosis (p-value ≤ 0.001) and proportional reduction of MMSE score with increasing grade of leukoaraiosis (p-value ≤ 0.001). Conclusions: Increasing ADC values of leukoaraiosis lesions with increasing grade could be used as a grading scale of leukoaraiosis. Higher ADCav values of normal white matter in patients with leukoaraiosis which were increasing with higher grades of leukoaraiosis, is probably representing those areas that are prone to develop leukoaraiosis over time and hence help in assessment of complete extent of the lesion. The significant association of leukoaraiosis with impaired cognition, proposes leukoaraiosis as one of the cause for cognitive function.

Introduction: With widespread use of imaging modalities including USG, triple Phase CT-scan and MRI, there is increase in rate of detecting focal liver lesions in otherwise asymptomatic patient. This poses a diagnostic challenge in an Oncology patient as their accurate diagnosis is must for proper staging in a patient with known oncological disease. The accurate diagnosis of these focal liver lesions requires either FNAC or biopsies. Even though all these modalities help in characterizing liver lesions, MRI is most accurate modality in characterizing these lesions, especially DWI sequence, which provides information at the molecular level of the tissue giving structural and functional information and also helps in assessing the treatment response in tumor cells. Aim: To study the role of DWI/ADC in detecting focal liver lesions and its further characterization. Also, assessing its role in differentiating benign from malignant lesions using DWI/ADC map and providing a quantitative cut off ADC to differentiate benign from malignant lesions. Materials and Methods: Total 50 patients with 71 liver lesions were evaluated with diffusion-weighted MR imaging for over a period of 2 years. All these lesions were assessed by experienced radiologist in the field of Onco-imaging. Necessary clinical history and laboratory data were considered and all lesions either biopsied or underwent FNAC for final Diagnosis. All cases underwent DWI at two different b values of b 600 and b 1000 and corresponding ADC were calculated for each lesion. Results: For the current study total of 50 patients (71 liver lesions) were investigated, majority of patients were in age group of 41-60 years (48%). Out of 71 liver lesions, 40(56.3%) were malignant lesions and 31(43.7%) were benign lesions, with most common diagnosis being metastases 17 (34%) followed by HCC 12(24%) and simple cyst 10(20%). Conclusion: Based on qualitative and quantitative assessment of liver lesions on DWI and ADC map, we could characterize liver lesions and differentiate malignant and benign lesions. DWI is a useful diagnostic tool in patients where contrast is contraindicated like in patients with renal impairment.

The purpose of this study was to determine diffusion coefficient (ADC) in plaque, peri-plaque and normal-appearing white matter (NAWM) in multiple sclerosis (MS), compare them with the control and correlate findings with cognitive state. Subjects and methods Sixty-five participants were included and categorized into MS patients with normal cognition ( n = 25); MS with mild cognitive impairment ( n = 20) and control group (no MS and normal cognition; n = 20). The Montreal Cognitive Assessment was used to determine cognitive state. Mean ADC was measured in plaque, peri-plaques and NAWM, compared with ADC from corresponding white matter in control and correlated with cognitive scores. Chi Square and Pearson correlation coefficient were used. Results The mean ADC of peri-plaque and NAWM in MS group with cognitive impairment was significantly higher than MS group with normal cognition ( p < 0.001) and control group ( p < 0.05) respectively. In MS patients with impaired cognition, the mean ADC in peri-plaque and NAWM demonstrated inverse correlations with cognitive state ( r = −0.64, p < 0.001) and ( r = −0.56, p = 0.01) respectively. Conclusions ADC values in peri-plaque and NAWM have an inverse correlation with cognition in MS. The ADC is useful for detecting subtle abnormalities in white matter and can be used as a predictor of cognitive state. [ABSTRACT FROM AUTHOR]

Aims – The aim of this study was i) to evaluate the potential of the DWI sequence in the characterization of malignant breast lesions; ii) to verify if this sequence should incorporate the breast MRI protocol and iii) to correlate the apparent diffusion coefficients (ADC) values and histological results. Methodology – The sample includes 18 female patients between the ages of 38 and 71 years, who presented with malignant breast lesion confirmed by histology. The DWI sequence was added to the MRI standard protocol to calculate the ADC values. Results – In the results obtained we observed that the range of the ADC values calculated in the center of the malignant lesions, showed a mean and standard deviation of 0.89 ± 0.14 x10-3 mm2 / s. This method of using the ADC values for the detection of malignant lesions showed a sensitivity of 100%. Conclusion – The DWI technique proved to be a useful method in the characterization of malignant breast lesions, as it showed a sensitivity of 100%, so we suggest its inclusion in the Breast MR standard protocol. [ABSTRACT FROM AUTHOR]

Objective: To investigate the role of diffusion-weighted magnetic resonance imaging (DW-MRI) in the diagnosis of gastric tumors and discuss the diagnostic importance and potential use of apparent diffusion coefficient (ADC) measurements. Materials and Methods: Beginning in March 2009, DW-MRI was added to the routine abdominal and pelvic MR examination for all patients imaged at our institution. A total of 21 patients (12 men and 9 women; mean age 55±6.3SD, range: 39-74 years) with known gastric malignancy were referred to our MR unit. All MRI examinations were performed using a 1.5-T MRI scanner (Magnetom Avanto, Siemens Healthcare). The evaluation of the DW-MRI examinations was made by radiologists' consensus. Changes in the signal intensity of the lesions were determined by their appearance in images at b=50, 400, and 800 s/mm2 and in ADC maps. Results were compared with histopathological findings. Results: All of the gastric tumors in this study showed high signal intensity in DW-MRI and low signal intensity in ADC maps. Mean ADC values for gastric tumor and normal gastric wall were 0.892±0.23 SD mm2/s and 1.453±0.35 SD mm2/s respectively. The mean ADC values of gastric tumors were significantly lower than that of the normal gastric wall. Conclusion: DW-MRI and ADC values together can successfully differentiate gastric tumors from normal gastric wall. [ABSTRACT FROM AUTHOR]

We present the magnetic resonance imaging findings of an eight-year-old boy with Epstein–Barr virus (EBV) encephalitis, with special attention to lesion neuroanatomic distribution, diffusion-weighted images, and proton magnetic resonance spectroscopy (MRS). T2 and FLAIR-weighted images showed bilateral and symmetric basal nuclei lesions, with diffusion facilitation. MRS of the lesions demonstrated elevated lactate/lipid and excitatory neurotransmitters. The purpose of this report is to alert to this imagiologic pattern of EBV infection, and in particular to the fact that facilitated diffusion does occur on EBV encephalitis. [ABSTRACT FROM AUTHOR]

Background: Early neurological deterioration is encountered in up to a third of patients with isolated pontine infarcts. A limited number of clinical and imaging features have been suggested as predictors of neurological progression in this setting. In this study, we assessed whether quantitative apparent diffusion coefficient (ADC) measurements within the ischemic pontine region could be used as a radiomic feature to forecast clinical deterioration., Methods: We calculated the mean ADC value of ischemic voxels within the ischemic region and normalized them to the contralateral non-ischemic tissue (relative ADC, rADC) in patients with isolated pontine infarcts. This imaging signature was then compared among patients with neurological progression (n = 21) and a propensity matched cohort of non-progressors (n = 42), together with other clinical and imaging features in bivariate and multivariate statistical models., Results: The rADC mean was significantly lower among patients with progression ( p = 0.008). Female gender and extension of the ischemic lesion to the ventral pontine surface were other features significantly associated with progression. The association between rADC mean and progression persisted in multivariate models with an odds ratio of 13.7 (95% CI 2.6-72.8; p = 0.002) for progression among patients with rADC mean ≤ 0.67 in their ischemic tissue. The probability for worsening was 80% among patients who had an ischemic lesion extending to the ventral pontine surface with a mean rADC ≤ 0.67., Conclusion: The mean rADC value within the ischemic lesion is closely related with early neurological deterioration in patients with isolated pontine infarcts., Competing Interests: Declaration of Conflicting Interests: The author(s) declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article., (© European Stroke Organisation 2022.)

Simple Summary: Artificial Intelligence methods using machine learning and radiomics is an emerging area of research for radiological and oncological applications for patient management. Recent evidence from breast cancer suggests that different breast cancer subtypes may respond differently to adjuvant therapies. The use of a 21-gene array assay called OncotypeDX can predict potential recurrence of cancer in patients with estrogen positive breast cancer after treatment, however, there are potential cost disadvantages that hamper its widespread use. Multiparametric magnetic resonance imaging can simultaneously identify key functional parameters and provide unique imaging phenotypes of breast cancer, which is used in radiomic analysis. Radiomics provide quantitative information of different tissue types. We have developed a new machine learning radiomic informatics tool that integrates clinical and imaging variables, single, and multiparametric radiomics to compare with the OncotypeDX test to stratify patients into three risk groups: low, medium, and high risk of breast cancer recurrence. Optimal use of multiparametric magnetic resonance imaging (mpMRI) can identify key MRI parameters and provide unique tissue signatures defining phenotypes of breast cancer. We have developed and implemented a new machine-learning informatic system, termed Informatics Radiomics Integration System (IRIS) that integrates clinical variables, derived from imaging and electronic medical health records (EHR) with multiparametric radiomics (mpRad) for identifying potential risk of local or systemic recurrence in breast cancer patients. We tested the model in patients (n = 80) who had Estrogen Receptor positive disease and underwent OncotypeDX gene testing, radiomic analysis, and breast mpMRI. The IRIS method was trained using the mpMRI, clinical, pathologic, and radiomic descriptors for prediction of the OncotypeDX risk score. The trained mpRad IRIS model had a 95% and specificity was 83% with an Area Under the Curve (AUC) of 0.89 for classifying low risk patients from the intermediate and high-risk groups. The lesion size was larger for the high-risk group (2.9 ± 1.7 mm) and lower for both low risk (1.9 ± 1.3 mm) and intermediate risk (1.7 ± 1.4 mm) groups. The lesion apparent diffusion coefficient (ADC) map values for high- and intermediate-risk groups were significantly (p < 0.05) lower than the low-risk group (1.14 vs. 1.49 × 10−3 mm2/s). These initial studies provide deeper insight into the clinical, pathological, quantitative imaging, and radiomic features, and provide the foundation to relate these features to the assessment of treatment response for improved personalized medicine. [ABSTRACT FROM AUTHOR]

Background and Purpose: Apparent diffusion coefficient (ADC) reflects micro-enviromental changes and therefore might be useful in predicting recurrence prior to brachytherapy. The purpose of this study is to evaluate change in ADC of the primary tumour and pathologic lymph nodes during treatment and to correlate this with clinical outcome., Material and Methods: Twenty patients were included who received chemoradiation for locally advanced cervical cancer between July 2016 and November 2017. All patients underwent magnetic resonance imaging (MRI) prior to treatment, and three MRIs in weeks 1/2, 3 and 4 of treatment, including T2 and diffusion weighted imaging ( b- values 0, 200, 800 s/mm 2 ) for determining an ADC-map. Primary tumour was delineated on T2 and ADC-map and pathologic lymph nodes were delineated only on ADC-map., Results: At time of analysis median follow-up was 15 (range 7-22) months. From MRI one to four, primary tumour on ADC-map showed a significant signal increase of 0.94 (range 0.74-1.46) × 10 -3  mm 2 /s to 1.13 (0.98-1.49) × 10 -3  mm 2 /s (p < 0.001). When tumour was delineated on T2, ADC-value signal increase (in tumour according to T2) was similar. All 46 delineated pathologic lymph nodes showed an ADC-value increase on average from 0.79 (range 0.33-1.12) × 10 -3  mm 2 /s to 1.14 (0.59-1.75) × 10 -3  mm 2 /s (p < 0.001). The mean tumour/suspected lymph node volumes decreased respectively 51/40%. Four patients developed relapse (one local and three nodal), without clear relation with ΔADC. However, the median volume decrease of the primary tumour was substantially lower in the failing patients compared to the group without relapse (19 vs. 57%)., Conclusions: ADC values can be acquired using T2-based tumour delineations unless there are substantial shifts between ADC-mapping and T2 acquisition. It remains plausible that ΔADC is a predictor for response to EBRT. However, the correlation in this study was not statistically significant., (© 2019 The Authors.)