scholarly journals Discriminating Benign from Malignant Testicular Masses Using Machine-Learning Based Radiomics Signature of Appearance Diffusion Coefficient Maps: Comparing with Conventional Mean and Minimum ADC Values

2022 ◽  
pp. 110158
Author(s):  
Chanyuan Fan ◽  
Kailun Sun ◽  
Xiangde Min ◽  
Wei Cai ◽  
Wenzhi Lv ◽  
...  
Keyword(s):  
Machine Learning ◽  
Diffusion Coefficient ◽  
Adc Values ◽  
Radiomics Signature

scholarly journals Apparent diffusion coefficient cannot discriminate metastatic and non-metastatic lymph nodes in rectal cancer: a meta-analysis

2021 ◽  
Author(s):  
Alexey Surov ◽  
Hans-Jonas Meyer ◽  
Maciej Pech ◽  
Maciej Powerski ◽  
Jasan Omari ◽  
...  
Keyword(s):  
Rectal Cancer ◽  
Diffusion Coefficient ◽  
Apparent Diffusion Coefficient ◽  
Lymph Nodes ◽  
Meta Analysis ◽  
Adc Value ◽  
Metastatic Lymph Nodes ◽  
Metastatic Lymph ◽  
Apparent Diffusion ◽  
Adc Values

Abstract Background Our aim was to provide data regarding use of diffusion-weighted imaging (DWI) for distinguishing metastatic and non-metastatic lymph nodes (LN) in rectal cancer. Methods MEDLINE library, EMBASE, and SCOPUS database were screened for associations between DWI and metastatic and non-metastatic LN in rectal cancer up to February 2021. Overall, 9 studies were included into the analysis. Number, mean value, and standard deviation of DWI parameters including apparent diffusion coefficient (ADC) values of metastatic and non-metastatic LN were extracted from the literature. The methodological quality of the studies was investigated according to the QUADAS-2 assessment. The meta-analysis was undertaken by using RevMan 5.3 software. DerSimonian, and Laird random-effects models with inverse-variance weights were used to account the heterogeneity between the studies. Mean DWI values including 95% confidence intervals were calculated for metastatic and non-metastatic LN. Results ADC values were reported for 1376 LN, 623 (45.3%) metastatic LN, and 754 (54.7%) non-metastatic LN. The calculated mean ADC value (× 10−3 mm2/s) of metastatic LN was 1.05, 95%CI (0.94, 1.15). The calculated mean ADC value of the non-metastatic LN was 1.17, 95%CI (1.01, 1.33). The calculated sensitivity and specificity were 0.81, 95%CI (0.74, 0.89) and 0.67, 95%CI (0.54, 0.79). Conclusion No reliable ADC threshold can be recommended for distinguishing of metastatic and non-metastatic LN in rectal cancer.

scholarly journals Apparent Diffusion Coefficient in Invasive Ductal Breast Carcinoma: Correlation with Detailed Histologic Features and the Enhancement Ratio on Dynamic Contrast-Enhanced MR Images

2010 ◽  
Vol 2010 ◽  
pp. 1-6 ◽  
Author(s):  
Roka Namoto Matsubayashi ◽  
Teruhiko Fujii ◽  
Kotaro Yasumori ◽  
Toru Muranaka ◽  
Seiya Momosaki
Keyword(s):  
Diffusion Coefficient ◽  
Growth Patterns ◽  
Breast Carcinomas ◽  
Mr Images ◽  
Cellular Density ◽  
Dynamic Contrast Enhanced ◽  
Diffusion Weighted Images ◽  
Architectural Features ◽  
Contrast Enhanced ◽  
Adc Values

Purpose. To investigate the correlation of Apperent Diffusion Coefficient (ADC) values in invasive ductal breast carcinomas with detailed histologic features and enhancement ratios on dynamic contrast-enhanced MRI.Methods and Materials. Dynamic MR images and diffusion-weighted images (DWIs) of invasive ductal breast carcinomas were reviewed in 25 (26 lesions) women. In each patient, DWI, T2WI, T1WI, and dynamic images were obtained. The ADC values of the 26 carcinomas were calculated with b-factors of 0 and 1000 s/ using echoplanar DWI. Correlations of the ADC values were examined on dynamic MRI with enhancement ratios (early to delayed phase: E/D ratio) and detailed histologic findings for each lesion, including cellular density, the size of cancer nests, and architectural features of the stroma (broad, narrow, and delicate) between cancer nests.Results. The mean ADC was  /sec. Cellular density was significantly correlated with ADC values () and E/D ratios (). The ADC values were also significantly correlated to features of the stroma (broad to narrow, ).Conclusion. The findings suggest that DWIs reflect the growth patterns of carcinomas, including cellular density and architectural features of the stroma, and E/D ratios may also be closely correlated to cellular density.

Diagnostic value of apparent diffusion coefficient in differentiating between high-grade gliomas and brain metastases

2017 ◽  
Vol 59 (5) ◽  
pp. 599-605 ◽  
Author(s):  
Ionut Caravan ◽  
Cristiana Augusta Ciortea ◽  
Alexandra Contis ◽  
Andrei Lebovici
Keyword(s):  
Diffusion Coefficient ◽  
Brain Metastases ◽  
Apparent Diffusion Coefficient ◽  
Curve Analysis ◽  
High Grade ◽  
Peritumoral Edema ◽  
Roc Curve Analysis ◽  
Apparent Diffusion ◽  
Adc Values ◽  
The Mean

Background High-grade gliomas (HGGs) and brain metastases (BMs) can display similar imaging characteristics on conventional MRI. In HGGs, the peritumoral edema may be infiltrated by the malignant cells, which was not observed in BMs. Purpose To determine whether the apparent diffusion coefficient values could differentiate HGGs from BMs. Material and Methods Fifty-seven patients underwent conventional magnetic resonance imaging (MRI) and diffusion-weighted imaging (DWI) before treatment. The minimum and mean ADC in the enhancing tumor (ADCmin, ADCmean) and the minimum ADC in the peritumoral region (ADCedema) were measured from ADC maps. To determine whether there was a statistical difference between groups, ADC values were compared. A receiver operating characteristic (ROC) curve analysis was used to determine the cutoff ADC value for distinguishing between HGGs and BMs. Results The mean ADCmin values in the intratumoral regions of HGGs were significantly higher than those in BMs. No differences were observed between groups regarding ADCmean values. The mean ADCmin values in the peritumoral edema of HGGs were significantly lower than those in BMs. According to ROC curve analysis, a cutoff value of 1.332 × 10−3 mm2/s for the ADCedema generated the best combination of sensitivity (95%) and specificity (84%) for distinguishing between HGGs and BMs. The same value showed a sensitivity of 95.6% and a specificity of 100% for distinguishing between GBMs and BMs. Conclusion ADC values from DWI were found to distinguish between HGGs and solitary BMs. The peritumoral ADC values are better than the intratumoral ADC values in predicting the tumor type.

scholarly journals A Clinical-Radiomics Nomogram Based on Computed Tomography for Predicting Risk of Local Recurrence After Radiotherapy in Nasopharyngeal Carcinoma

2021 ◽  
Vol 11 ◽  
Author(s):  
Chaohua Zhu ◽  
Huixian Huang ◽  
Xu Liu ◽  
Hao Chen ◽  
Hailan Jiang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Computed Tomography ◽  
Nasopharyngeal Carcinoma ◽  
Local Recurrence ◽  
Stochastic Gradient Descent ◽  
Support Vector ◽  
Stable Model ◽  
Clinical Factors ◽  
Specificity And Sensitivity ◽  
Radiomics Signature

Purpose: We aimed to establish a nomogram model based on computed tomography (CT) imaging radiomic signature and clinical factors to predict the risk of local recurrence in nasopharyngeal carcinoma (NPC) after intensity-modulated radiotherapy (IMRT).Methods: This was a retrospective study consisting of 156 NPC patients treated with IMRT. Radiomics features were extracted from the gross tumor volume for nasopharynx (GTVnx) in pretreatment CT images for patients with or without local recurrence. Discriminative radiomics features were selected after t-test and the least absolute shrinkage and selection operator (LASSO) analysis. The most stable model was obtained to generate radiomics signature (Rad_Score) by using machine learning models including Logistic Regression, K-Nearest neighbor, Naive Bayes, Decision Tree, Stochastic Gradient Descent, Gradient Booting Tree and Linear Support Vector Classification. A nomogram for local recurrence was established based on Rad_Score and clinical factors. The predictive performance of nomogram was evaluated by discrimination ability and calibration ability. Decision Curve Analysis (DCA) was used to evaluate the clinical benefits of the multi-factor nomogram in predicting local recurrence after IMRT.Results: Local recurrence occurred in 42 patients. A total of 1,452 radiomics features were initially extracted and seven stable features finally selected after LASSO analysis were used for machine learning algorithm modeling to generate Rad_Score. The nomogram showed that the greater Rad_Score was associated with the higher risk of local recurrence. The concordance index, specificity and sensitivity in the training cohort were 0.931 (95%CI:0.8765–0.9856), 91.2 and 82.8%, respectively; whereas, in the validation cohort, they were 0.799 (95%CI: 0.6458–0.9515), 79.4, and 69.2%, respectively.Conclusion: The nomogram based on radiomics signature and clinical factors can predict the risk of local recurrence after IMRT in patients with NPC and provide evidence for early clinical intervention.

The Potential Role of Peritumoral Apparent Diffusion Coefficient Evaluation in Differentiating Glioblastoma and Solitary Metastatic Lesions of the Brain

2021 ◽  
Vol 17 ◽  
Author(s):  
Murat Tepe ◽  
Suzan Saylisoy ◽  
Ugur Toprak ◽  
Ibrahim Inan
Keyword(s):  
Diffusion Coefficient ◽  
White Matter ◽  
Apparent Diffusion Coefficient ◽  
Sensitivity And Specificity ◽  
Brain Mri ◽  
Solitary Metastasis ◽  
Metastatic Lesions ◽  
Institutional Review ◽  
Apparent Diffusion ◽  
Adc Values

Objective: Differentiating glioblastoma (GBM) and solitary metastasis is not always possible using conventional magnetic resonance imaging (MRI) techniques. In conventional brain MRI, GBM and brain metastases are lesions with mostly similar imaging findings. In this study, we investigated whether apparent diffusion coefficient (ADC) ratios, ADC gradients, and minimum ADC values in the peritumoral edema tissue can be used to discriminate between these two tumors. Methods: This retrospective study was approved by the local institutional review board with a waiver of written informed consent. Prior to surgical and medical treatment, conventional brain MRI and diffusion-weighted MRI (b = 0 and b = 1000) images were taken from 43 patients (12 GBM and 31 solitary metastasis cases). Quantitative ADC measurements were performed on the peritumoral tissue from the nearest segment to the tumor (ADC1), the middle segment (ADC2), and the most distant segment (ADC3). The ratios of these three values were determined proportionally to calculate the peritumoral ADC ratios. In addition, these three values were subtracted from each other to obtain the peritumoral ADC gradients. Lastly, the minimum peritumoral and tumoral ADC values, and the quantitative ADC values from the normal appearing ipsilateral white matter, contralateral white matter and ADC values from cerebrospinal fluid (CSF) were recorded. Results: For the differentiation of GBM and solitary metastasis, ADC3 / ADC1 was the most powerful parameter with a sensitivity of 91.7% and specificity of 87.1% at the cut-off value of 1.105 (p < 0.001), followed by ADC3 / ADC2 with a cut-off value of 1.025 (p = 0.001), sensitivity of 91.7%, and specificity of 74.2%. The cut-off, sensitivity and specificity of ADC2 / ADC1 were 1.055 (p = 0.002), 83.3%, and 67.7%, respectively. For ADC3 – ADC1, the cut-off value, sensitivity and specificity were calculated as 150 (p < 0.001), 91.7% and 83.9%, respectively. ADC3 – ADC2 had a cut-off value of 55 (p = 0.001), sensitivity of 91.7%, and specificity of 77.4 whereas ADC2 – ADC1 had a cut-off value of 75 (p = 0.003), sensitivity of 91.7%, and specificity of 61.3%. Among the remaining parameters, only the ADC3 value successfully differentiated between GBM and metastasis (GBM 1802.50 ± 189.74 vs. metastasis 1634.52 ± 212.65, p = 0.022). Conclusion: The integration of the evaluation of peritumoral ADC ratio and ADC gradient into conventional MR imaging may provide valuable information for differentiating GBM from solitary metastatic lesions.

scholarly journals Machine Learning Based on a Multiparametric and Multiregional Radiomics Signature Predicts Radiotherapeutic Response in Patients with Glioblastoma

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Zi-Qi Pan ◽  
Shu-Jun Zhang ◽  
Xiang-Lian Wang ◽  
Yu-Xin Jiao ◽  
Jian-Jian Qiu
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Cox Regression ◽  
Clinical Risk Factors ◽  
Cox Regression Analysis ◽  
Clinical Risk ◽  
Independent Test ◽  
Independent Test Dataset ◽  
Multiple Regions ◽  
Radiomics Signature

Background and Objective. Although radiotherapy has become one of the main treatment methods for cancer, there is no noninvasive method to predict the radiotherapeutic response of individual glioblastoma (GBM) patients before surgery. The purpose of this study is to develop and validate a machine learning-based radiomics signature to predict the radiotherapeutic response of GBM patients. Methods. The MRI images, genetic data, and clinical data of 152 patients with GBM were analyzed. 122 patients from the TCIA dataset (training set: n = 82 ; validation set: n = 40 ) and 30 patients from local hospitals were used as an independent test dataset. Radiomics features were extracted from multiple regions of multiparameter MRI. Kaplan-Meier survival analysis was used to verify the ability of the imaging signature to predict the response of GBM patients to radiotherapy before an operation. Multivariate Cox regression including radiomics signature and preoperative clinical risk factors was used to further improve the ability to predict the overall survival (OS) of individual GBM patients, which was presented in the form of a nomogram. Results. The radiomics signature was built by eight selected features. The C -index of the radiomics signature in the TCIA and independent test cohorts was 0.703 ( P < 0.001 ) and 0.757 ( P = 0.001 ), respectively. Multivariate Cox regression analysis confirmed that the radiomics signature (HR: 0.290, P < 0.001 ), age (HR: 1.023, P = 0.01 ), and KPS (HR: 0.968, P < 0.001 ) were independent risk factors for OS in GBM patients before surgery. When the radiomics signature and preoperative clinical risk factors were combined, the radiomics nomogram further improved the performance of OS prediction in individual patients ( C ‐ index = 0.764 and 0.758 in the TCIA and test cohorts, respectively). Conclusion. This study developed a radiomics signature that can predict the response of individual GBM patients to radiotherapy and may be a new supplement for precise GBM radiotherapy.

Can the apparent diffusion coefficient differentiate the grade of endometrioid adenocarcinoma and the histological subtype of endometrial cancer?

2017 ◽  
Vol 59 (3) ◽  
pp. 363-370 ◽  
Author(s):  
Bin Yan ◽  
Tingting Zhao ◽  
Xiufen Liang ◽  
Chen Niu ◽  
Caixia Ding
Keyword(s):  
Diffusion Coefficient ◽  
Endometrial Cancer ◽  
Apparent Diffusion Coefficient ◽  
Low Grade ◽  
Endometrioid Adenocarcinoma ◽  
High Grade ◽  
Squamous Differentiation ◽  
Apparent Diffusion ◽  
Adc Values ◽  
Endometrial Cancers

Background Diffusion-weighted imaging (DWI) provides useful information for the identification of benign and malignant uterine lesions. However, the use of the apparent diffusion coefficient (ADC) for histopathological grading of endometrial cancer is controversial. Purpose To explore the use of ADC values in differentiating the preoperative tumor grading of endometrioid adenocarcinomas and investigate the relationship between the ADC values of endometrial cancer and the histological tumor subtype. Material and Methods We retrospectively evaluated 98 patients with endometrial cancers, including both endometrioid adenocarcinomas (n = 80) and non-endometrioid adenocarcinomas (n = 18). All patients underwent DWI procedures and ADC values were calculated. The Kruskal–Wallis test and the independent samples Mann–Whitney U test were used to compare differences in the ADC values between different tumor grades and different histological subtypes. Results The mean ADC values (ADCmean) for high-grade endometrioid adenocarcinomas were significantly lower than the values for low-grade tumors (0.800 versus 0.962 × 10–3 mm2/s) ( P = 0.002). However, no significant differences in ADCmean and minimum ADC values (ADCmin) were found between tumor grades (G1, G2, and G3) of endometrial cancer. Compared with endometrioid adenocarcinomas, the adenocarcinoma with squamous differentiation showed lower ADC values (mean/minimum = 0.863/0.636 versus 0.962/0.689 × 10–3 mm2/s), but the differences were not significant ( Pmean = 0.074, Pmin = 0.441). Moreover, ADCmean for carcinosarcomas was significantly higher than the value for G3 non-carcinosarcoma endometrial cancers (1.047 versus 0.823 × 10–3 mm2/s) ( P = 0.001). Conclusion The ADCmean was useful for identifying high-grade and low-grade endometrioid adenocarcinomas. Additionally, squamous differentiation may decrease ADCmean and ADCmin of endometrioid adenocarcinoma, and carcinosarcomas showed relatively high ADCmean.

Sign in / Sign up

Export Citation Format

Share Document