Diffusion-weighted Imaging Models Research Articles

A framework for optimizing the acquisition protocol multishell diffusion-weighted imaging for multimodel assessment.

Complementary aspects of tissue microstructure can be studied with diffusion-weighted imaging (DWI). However, there is no consensus on how to design a diffusion acquisition protocol for multiple models within a clinically feasible time. The purpose of this study is to provide a flexible framework that is able to optimize the shell acquisition protocol given a set of DWI models. Eleven healthy subjects underwent an extensive DWI acquisition protocol, including 15 candidate shells, ranging from 10 to 3500 s/mm2. The proposed framework aims to determine the optimized acquisition scheme (OAS) with a data-driven procedure minimizing the squared error of model-estimated parameters. We tested the proposed method over five heterogeneous DWI models exploiting both low and high b-values (i.e., diffusion tensor imaging [DTI], free water, intra-voxel incoherent motion [IVIM], diffusion kurtosis imaging [DKI], and neurite orientation dispersion and density imaging [NODDI]). A voxel-level and region of interest (ROI)-level analysis was conducted over the white matter and in 48 fiber bundles, respectively. Results showed that acquiring data for the five abovementioned models via OAS requires 14 min, compared with 35 min for the joint recommended acquisition protocol. The parameters derived from the reference acquisition scheme and the OAS are comparable in terms of estimated values, noise, and tissue contrast. Furthermore, the power analysis showed that the OAS retains the potential sensitivity to group-level differences in the parameters of interest, with the exception of the free water model. Overall, there is a linear correspondence (R2= 0.91) between OAS and reference-derived parameters. In conclusion, the proposed framework optimizes the shell acquisition scheme for a given set of DWI models (i.e., DTI, free water, IVIM, DKI, and NODDI), combining low and high b-values while saving acquisition time.

Value of diffusion kurtosis MR imaging and conventional diffusion weighed imaging for evaluating response to first-line chemotherapy in unresectable pancreatic cancer

ObjectiveTo investigate the diagnostic value of diffusion kurtosis magnetic resonance imaging (DKI) and conventional diffusion-weighted imaging (DWI) for evaluating the response to first-line chemotherapy in unresectable pancreatic cancer.Materials and methodsWe retrospectively analyzed 21 patients with clinically and pathologically confirmed unresected pancreatic cancer who received palliative chemotherapy. Three-tesla MRI examinations containing DWI sequences with b values of 0, 100, 700, 1400, and 2100 s/mm2 were performed before and after chemotherapy. Parameters included the apparent diffusion coefficient (ADC), mean diffusion coefficient (MD), and mean diffusional kurtosis (MK). The performances of the DWI and DKI parameters in distinguishing the response to chemotherapy were evaluated by the area under the curve (AUC) of the receiver operating characteristic (ROC) curve. Overall survival (OS) was calculated from the date of first treatment to the date of death or the latest follow-up date.ResultsThe ADCchange and MDchange were significantly higher in the responding group (PR group) than in the nonresponding group (non-PR group) (ADCchange: 0.21 ± 0.05 vs. 0.11 ± 0.09, P = 0.02; MDchange: 0.37 ± 0.24 vs. 0.10 ± 0.12, P = 0.002). No statistical significance was shown when comparing ADCpre, ADCpost, MKpre, MKpost, MKchange, MDpre, and MDpost between the PR and non-PR groups. The ROC curve analysis indicated that MDchange (AUC = 0.898, cutoff value = 0.7143) performed better than ADCchange (AUC = 0.806, cutoff value = 0.1369) in predicting the response to chemotherapy.ConclusionThe ADCchange and MDchange demonstrated strong potential for evaluating the response to chemotherapy in unresectable pancreatic cancer. The MDchange showed higher specificity in the classification of PR and non-PR than the ADCchange. Other parameters, including ADCpre, ADCpost, MKpre, MKpost, MKchange, MDpre, and MDpost, are not suitable for response evaluation. The combined model SUMchange demonstrated superior performance compared to the individual DWI and DKI models. Further experiments are needed to evaluate the potential of DWI and DKI parameters in predicting the prognosis of patients with unresectable pancreatic cancer.

Multisequence MRI-based radiomics signature as potential biomarkers for differentiating KRAS mutations in non-small cell lung cancer with brain metastases

BackgroundKirsten rat sarcoma virus (KRAS) has evolved from a genotype with predictive value to a therapeutic target recently. The study aimed to establish non-invasive radiomics models based on MRI to discriminate KRAS from epidermal growth factor receptor (EGFR) or anaplastic lymphoma kinase (ALK) mutations in lung cancer patients with brain metastases (BM), then further explore the optimal sequence for prediction. MethodsThis retrospective study involved 317 patients (218 patients in training cohort and 99 patients in testing cohort) who had confirmed of KRAS, EGFR or ALK mutations. Radiomics features were separately extracted from T2WI, T2 fluid-attenuated inversion recovery (T2-FLAIR), diffusion weighted imaging (DWI) and contrast-enhanced T1-weighted imaging (T1-CE) sequences. The maximal information coefficient and recursive feature elimination method were used to select informative features. Then we built four radiomics models for differentiating KRAS from EGFR or ALK using random forest classifier. ROC curves were used to validate the capability of the models. ResultsThe four radiomics models for discriminating KRAS from EGFR all worked well, especially DWI and T2WI models (AUCs: 0.942, 0.942 in training cohort, 0.949, 0.954 in testing cohort). When KRAS compared to ALK, DWI and T2-FLAIR models showed excellent performance in two cohorts (AUCs: 0.947, 0.917 in training cohort, 0.850, 0.824 in testing cohort). ConclusionsRadiomics classifiers integrating MRI have potential to discriminate KRAS from EGFR or ALK, which are helpful to guide treatment and facilitate the discovery of new approaches capable of achieving this long-sought goal of cure in lung cancer patients with KRAS.

Insights and improvements in correspondence between axonal volume fraction measured with diffusion-weighted MRI and electron microscopy.

Biophysical diffusion-weighted imaging (DWI) models are increasingly used in neuroscience to estimate the axonal water fraction ( ), which in turn is key for noninvasive estimation of the axonal volume fraction ( ). These models require thorough validation by comparison with a reference method, for example, electron microscopy (EM). While EM studies often neglect the unmyelinated axons and solely report the fraction of myelinated axons, in DWI both myelinated and unmyelinated axons contribute to the DWI signal. However, DWI models often include simplifications, for example, the neglect of differences in the compartmental relaxation times or fixed diffusivities, which in turn might affect the estimation of . We investigate whether linear calibration parameters (scaling and offset) can improve the comparability between EM- and DWI-based metrics of . To this end, we (a) used six DWI models based on the so-called standard model of white matter (WM), including two models with fixed compartmental diffusivities (e.g., neurite orientation dispersion and density imaging, NODDI) and four models that fitted the compartmental diffusivities (e.g., white matter tract integrity, WMTI), and (b) used a multimodal data set including ex vivo diffusion DWI and EM data in mice with a broad dynamic range of fibre volume metrics. We demonstrated that the offset is associated with the volume fraction of unmyelinated axons and the scaling factor is associated with different compartmental and can substantially enhance the comparability between EM- and DWI-based metrics of . We found that DWI models that fitted compartmental diffusivities provided the most accurate estimates of the EM-based . Finally, we introduced a more efficient hybrid calibration approach, where only the offset is estimated but the scaling is fixed to a theoretically predicted value. Using this approach, a similar one-to-one correspondence to EM was achieved for WMTI. The method presented can pave the way for use of validated DWI-based models in clinical research and neuroscience.

Preoperative Noninvasive Evaluation of Tumor Budding in Rectal Cancer Using Multiparameter MRI Radiomics

To assess the value of a multiparametric magnetic resonance imaging (MRI)-based model integrating radiomics features with clinical and MRI semantic features for preoperative evaluation of tumor budding (TB) in rectal cancer. A total of 120 patients with pathologically confirmed rectal cancer were retrospectively analyzed. The patients were randomized into training and validation cohorts in a 6:4 ratio. Radiomics features were extracted and selected from preoperative T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and contrast-enhanced T1-weighted imaging (T1CE) sequences, after which the corresponding radiomics score (RS) was calculated, and the radiomics models (T2WI model, DWI model, and T1CE model) were constructed. Logistic regression analysis was selected to develop a combined model integrated RST2WI, RSDWI, RST1CE, and clinical and MRI semantic features. The efficacy of each model in diagnosing TB grade was observed by the receiver operating characteristic (ROC) curve. Decision curve analysis (DCA) was used to assess the clinical benefits of the models. Seven features were extracted and selected from each T2WI, DWI, and T1CE sequence to calculate the corresponding RS and construct the corresponding radiomics model. MRI reported N stagewas an independent risk factor for TB. The area under the ROC curveof the combined model was 0.961 and 0.891 in the training and validation cohorts, respectively. The combined model showed better performance than the other models. DCA showed that the net benefit of the combined model was better than that of the other models in the vast majority of threshold probabilities. A combined model integrating radiomics features and MRI semantic features allows for noninvasive preoperative evaluation of TB grading in patients with rectal cancer.

Diffusion kurtosis imaging and standard diffusion imaging in the magnetic resonance imaging assessment of prostate cancer.

In recent years, magnetic resonance imaging (MRI) has shown excellent results in the study of the prostate gland. MRI has indeed shown to be advantageous in the prostate cancer (PCa) detection, as in guiding targeting biopsy, improving its diagnostic yield. Although current acquisition protocols provide for multiparametric acquisition, recent evidence has shown that biparametric protocols can be non-inferior in PCa detection. Diffusion-weighted imaging (DWI) sequence, in particular, plays a key role, particularly in the peripheral zone which accounts for the larger part of the prostate. High b-values are generally recommended, although with the possibility of obtaining non-Gaussian diffusion effects, which requires a more sophisticated model for the analysis, namely through the diffusion kurtosis imaging (DKI). Purpose of this narrative review was to analyze the current applications and clinical evidence regarding the use of DKI with a main focus on PCa detection, also in comparison with DWI. This narrative review synthesized the findings of literature retrieved from main researches, narrative and systematic reviews, and meta-analyses obtained from PubMed. DKI analyses the non-Gaussian water diffusivity and describe the effect of signal intensity decay related to high b-value through two main metrics (Dapp and Kapp). Differently from DWI-apparent diffusion coefficient (DWI-ADC) which reflects only water restriction outside of cells, DKI metrics are supposed to represent also the direct interaction of water molecules with cell membranes and intracellular compounds. This review describes current evidence on ADC and DKI metrics in clinical imaging, and finally collect the results derived from the main articles focused on DWI and DKI models in detecting PCa. DKI advantages, compared to conventional ADC analysis, still remain controversial. Wider application and greater technical knowledge of DKI, however, may help in proving its intrinsic validity in the field of oncology and therefore in the study of clinically significant PCa. Finally, a deep understanding of DKI is important for radiologists to better understand what Kapp and Dapp mean in the context of different cancer and how these metrics may vary specifically in PCa imaging.

Characterization of parotid gland tumors: Whole-tumor histogram analysis of diffusion weighted imaging, diffusion kurtosis imaging, and intravoxel incoherent motion – A pilot study

PurposeTo investigate the diagnostic performance of histogram features of diffusion parameters in characterizating parotid gland tumors. MethodFrom December 2018 to January 2023, patients who underwent diffusion weighted imaging (DWI), diffusion kurtosis imaging (DKI), and intravoxel incoherent motion (IVIM) were consecutively enrolled in this retrospective study. The histogram features of diffusion parameters, including apparent diffusion coefficient (ADC), diffusion coefficient (Dk), diffusion kurtosis (K), pure diffusion coefficient (D), pseudo-diffusion coefficient (DP), and perfusion fraction (FP) were analyzed. The Mann-Whitney U test was used for comparison between benign parotid gland tumors (BPGTs) and malignant parotid gland tumors (MPGTs). Receiver operating characteristic curve and logistic regression analysis were used to identify the differential diagnostic performance. The Spearman’s correlation coefficient was used to analyze the correlation between diffusion parameters and Ki-67 labeling index. ResultsFor diffusion MRI, twenty-three histogram features of diffusion parameters showed significant differences between BPGTs and MPGTs (all P < 0.05). Compared with the DWI model, the IVIM model and combined model had better diagnostic specificity (58 %, 94 %, and 88 %, respectively; both corrected P < 0.001) and accuracy (64 %, 89 %, and 86 %, respectively; both corrected P = 0.006). The combined model was superior to the single DWI model with improved IDI (IDI improvement 0.25). Significant correlations were found between Ki-67 and ADCmean, Dkmean, Kmean, and Dmean (r = -0.57 to 0.53; all P < 0.05). ConclusionsWhole-tumor histogram analysis of IVIM and combined diffusion model could further improve the diagnostic performance for differentiating BPGTs from MPGTs.

MRI-based automatic identification and segmentation of extrahepatic cholangiocarcinoma using deep learning network

BackgroundAccurate identification of extrahepatic cholangiocarcinoma (ECC) from an image is challenging because of the small size and complex background structure. Therefore, considering the limitation of manual delineation, it’s necessary to develop automated identification and segmentation methods for ECC. The aim of this study was to develop a deep learning approach for automatic identification and segmentation of ECC using MRI.MethodsWe recruited 137 ECC patients from our hospital as the main dataset (C1) and an additional 40 patients from other hospitals as the external validation set (C2). All patients underwent axial T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), and diffusion-weighted imaging (DWI). Manual delineations were performed and served as the ground truth. Next, we used 3D VB-Net to establish single-mode automatic identification and segmentation models based on T1WI (model 1), T2WI (model 2), and DWI (model 3) in the training cohort (80% of C1), and compared them with the combined model (model 4). Subsequently, the generalization capability of the best models was evaluated using the testing set (20% of C1) and the external validation set (C2). Finally, the performance of the developed models was further evaluated.ResultsModel 3 showed the best identification performance in the training, testing, and external validation cohorts with success rates of 0.980, 0.786, and 0.725, respectively. Furthermore, model 3 yielded an average Dice similarity coefficient (DSC) of 0.922, 0.495, and 0.466 to segment ECC automatically in the training, testing, and external validation cohorts, respectively.ConclusionThe DWI-based model performed better in automatically identifying and segmenting ECC compared to T1WI and T2WI, which may guide clinical decisions and help determine prognosis.

Preoperative Grading of Rectal Cancer with Multiple DWI Models, DWI-Derived Biological Markers, and Machine Learning Classifiers.

Background: this study aimed to utilize various diffusion-weighted imaging (DWI) techniques, including mono-exponential DWI, intravoxel incoherent motion (IVIM), and diffusion kurtosis imaging (DKI), for the preoperative grading of rectal cancer. Methods: 85 patients with rectal cancer were enrolled in this study. Mann-Whitney U tests or independent Student's t-tests were conducted to identify DWI-derived parameters that exhibited significant differences. Spearman or Pearson correlation tests were performed to assess the relationships among different DWI-derived biological markers. Subsequently, four machine learning classifier-based models were trained using various DWI-derived parameters as input features. Finally, diagnostic performance was evaluated using ROC analysis with 5-fold cross-validation. Results: With the exception of the pseudo-diffusion coefficient (Dp), IVIM-derived and DKI-derived parameters all demonstrated significant differences between low-grade and high-grade rectal cancer. The logistic regression-based machine learning classifier yielded the most favorable diagnostic efficacy (AUC: 0.902, 95% Confidence Interval: 0.754-1.000; Specificity: 0.856; Sensitivity: 0.925; Youden Index: 0.781). Conclusions: utilizing multiple DWI-derived biological markers in conjunction with a strategy employing multiple machine learning classifiers proves valuable for the noninvasive grading of rectal cancer.

Value of radiomics models based on MRI diffusion weighted imaging and apparent diffusion coefficient in differentiating benign and malignant thyroid nodules

Objective: To investigate the value of radiomics models based on magnetic resonance imaging (MRI) diffusion weighted imaging (DWI) and apparent diffusion coefficient (ADC) maps in distinguishing benign and malignant thyroid nodules. Methods: A cross-sectional study. Clinical data of 148 thyroid nodules (50 benign, 98 malignant) from 140 patients who underwent thyroid MRI examination in Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences between January 2019 and December 2022 were retrospectively analyzed. The nodules were used as the study units, and a leave-one-out method was used to randomly divide the nodules into a training set and a test set at a 7∶3 ratio. Region of interest was segmented and radiomics features were extracted from the DWI and ADC images. In the training set, feature selection was performed using inter-observer agreement analysis, U-test, least absolute shrinkage and selection operator algorithm, and correlation analysis. Four classifiers, including support vector machine (SVM), random forest (RF), k-nearest neighbors (KNN) and logistic regression (LR) were used to build models with the selected features, including the DWI models, ADC models, and combined models. The models were independently tested in the test set. The performance of the radiomics models in distinguishing benign and malignant thyroid nodules was evaluated using the receiver operating characteristic (ROC) curve, with pathological results as the gold standard. Results: Of the 140 patients, there were 40 males and 100 females, with a mean age of (38.4±12.2) years. After feature selection, 11 DWI features and 11 ADC features were used to build the models. In the training set, the AUC values of the combined models were higher than those of the corresponding DWI and ADC models. In the test set, the SVM combined model showed the best predictive performance, with an AUC of 0.873 (95%CI:0.740-0.954), accuracy of 75.6%, sensitivity of 46.7%, specificity of 90.0%, positive predictive value (PPV) of 70.0% and negative predictive value (NPV) of 77.1%, while the RF combined model had an AUC of 0.836 (95%CI:0.695-0.929), accuracy of 77.8%, sensitivity of 40.0%, specificity of 96.7%, PPV of 85.7% and NPV of 76.3%, the KNN combined model had an AUC of 0.832 (95%CI:0.691-0.927), accuracy of 77.8%, sensitivity of 33.3%, specificity of 100%, PPV of 100% and NPV of 75.0%, the LR combined model had an AUC of 0.813 (95%CI:0.669-0.914), accuracy of 77.8%, sensitivity of 60.0%, specificity of 86.7%, PPV of 69.2% and NPV of 81.3%. Conclusions: Radiomics models based on DWI and ADC image features can effectively distinguish benign and malignant thyroid nodules. The SVM combined model had the best prediction performance.

Pretreatment synthetic magnetic resonance imaging predicts disease progression in nonmetastatic nasopharyngeal carcinoma after intensity modulation radiation therapy

BackgroundTo investigate the potential of synthetic MRI (SyMRI) in the prognostic assessment of patients with nonmetastatic nasopharyngeal carcinoma (NPC), and the predictive value when combined with diffusion-weighted imaging (DWI) as well as clinical factors.MethodsFifty-three NPC patients who underwent SyMRI were prospectively included. 10th Percentile, Mean, Kurtosis, and Skewness of T1, T2, and PD maps and ADC value were obtained from the primary tumor. Cox regression analysis was used for analyzing the association between SyMRI and DWI parameters and progression-free survival (PFS), and then age, sex, staging, and treatment as confounding factors were also included. C-index was obtained by bootstrap. Moreover, significant parameters were used to construct models in predicting 3-year disease progression. ROC curves and leave-one-out cross-validation were used to evaluate the performance and stability.ResultsDisease progression occurred in 16 (30.2%) patients at a follow-up of 39.6 (3.5, 48.2) months. T1_Kurtosis, T1_Skewness, T2_10th, PD_Mean, and ADC were correlated with PFS, and T1_Kurtosis (HR: 1.093) and ADC (HR: 1.009) were independent predictors of PFS. The C-index of SyMRI and SyMRI + DWI + Clinic models was 0.687 and 0.779. Moreover, the SyMRI + DWI + Clinic model predicted 3-year disease progression better than DWI or Clinic model (p ≤ 0.008). Interestingly, there was no significant difference between the SyMRI model (AUC: 0.748) and SyMRI + DWI + Clinic model (AUC: 0.846, p = 0.092).ConclusionSyMRI combined with histogram analysis could predict disease progression in NPC patients, and SyMRI + DWI + Clinic model further improved the predictive performance.

Whole-tumor histogram analysis of diffusion and perfusion metrics for noninvasive pediatric glioma grading

An accurate assessment of the World Health Organization grade is vital for patients with pediatric gliomas to direct treatment planning. We aim to evaluate the diagnostic performance of whole-tumor histogram analysis of diffusion-weighted imaging (DWI) and dynamic susceptibility contrast-enhanced perfusion-weighted imaging (DSC-PWI) for differentiating pediatric high-grade gliomas from pediatric low-grade gliomas. Sixty-eight pediatric patients (mean age, 10.47 ± 4.37years; 42 boys) with histologically confirmed gliomas underwent preoperative MR examination. The conventional MRI features and whole-tumor histogram features extracted from apparent diffusion coefficient (ADC) and cerebral blood volume (CBV) maps were analyzed, respectively. Receiver operating characteristic curves and the binary logistic regression analysis were performed to determine the diagnostic performance of parameters. For conventional MRI features, location, hemorrhage and tumor margin showed significant difference between pediatric high- and low-grade gliomas (all, P < .05). For advanced MRI parameters, ten histogram features of ADC and CBV showed significant differences between pediatric high- and low-grade gliomas (all, P < .05). The diagnostic performance of the combination of DSC-PWI and DWI (AUC = 0.976, sensitivity = 100%, NPV = 100%) is superior to conventional MRI or DWI model, respectively (AUCcMRI = 0.700, AUCDWI = 0.830; both, P < .05). The whole-tumor histogram analysis of DWI and DSC-PWI is a promising method for grading pediatric gliomas.

Clinical features and FLAIR radiomics nomogram for predicting functional outcomes after thrombolysis in ischaemic stroke.

We explored whether radiomics features extracted from diffusion-weighted imaging (DWI) and fluid-attenuated inversion recovery (FLAIR) images can predict the clinical outcome of patients with acute ischaemic stroke. This study was conducted to investigate and validate a radiomics nomogram for predicting acute ischaemic stroke prognosis. A total of 257 patients with acute ischaemic stroke from three clinical centres were retrospectively assessed from February 2019 to July 2022. According to the modified Rankin scale (mRS) at 3 months, the patients were divided into a favourable outcome group (mRS of 0-2) and an unfavourable outcome group (mRS of 3-6). The high-throughput features from the regions of interest (ROIs) within the radiologist-drawn contour by AK software were extracted. We used two feature selection methods, minimum redundancy and maximum (mRMR) and the least absolute shrinkage and selection operator algorithm (LASSO), to select the features. Three radiomics models (DWI, FLAIR, and DWI-FLAIR) were established. A radiomics nomogram with patient characteristics and radiomics signature was built using a multivariate logistic regression model. The performance of the nomogram was evaluated in the test and validation sets. Ultimately, decision curve analysis was implemented to assess the clinical value of the nomogram. The FLAIR, DWI, and DWI-FLAIR radiomics model exhibited good prediction performance, with area under the curve (AUCs) of 0.922 (95% CI: 0.876-0.968), 0.875 (95% CI: 0.815-0.935), and 0.895 (95% CI: 0.840-0.950). The radiomics nomogram with clinical characteristics including the overall cerebral small vessel disease (CSVD) burden score, hemorrhagic transformation (HT) and admission National Institutes of Health Stroke Scale score (NIHSS) score and the FLAIR Radscore presented good discriminatory potential in the training set (AUC = 0.94; 95% CI: 0.90-0.98) and test set (AUC = 0.94; 95% CI: 0.87-1), which was validated in the validation set 1 (AUC = 0.95; 95% CI: 0.88-1) and validation set 2 (AUC = 0.90; 95% CI: 0.768-1). In addition, it demonstrated good calibration, and decision curve analysis confirmed the clinical value of this nomogram. This non-invasive clinical-FLIAR radiomics nomogram shows good performance in predicting ischaemic stroke prognosis after thrombolysis.

Biparametric magnetic resonance imaging-based radiomics features for prediction of lymphovascular invasion in rectal cancer

BackgroundPreoperative assessment of lymphovascular invasion(LVI) of rectal cancer has very important clinical significance. However, accurate preoperative imaging evaluation of LVI is highly challenging because the resolution of MRI is still limited. Relatively few studies have focused on prediction of LVI of rectal cancer with the tool of radiomics, especially in patients with negative statue of MRI-based extramural vascular invasion (mrEMVI).The purpose of this study was to explore the preoperative predictive value of biparametric MRI-based radiomics features for LVI of rectal cancer in patients with the negative statue of mrEMVI.MethodsThe data of 146 cases of rectal adenocarcinoma confirmed by postoperative pathology were retrospectively collected. In the cases, 38 had positive status of LVI. All patients were examined by MRI before the operation. The biparametric MRI protocols included T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI). We used whole-volume three-dimensional method and two feature selection methods, minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO), to extract and select the features. Logistics regression was used to construct models. The area under the receiver operating characteristic curve (AUC) and DeLong’s test were used to evaluate the diagnostic performance of the radiomics based on T2WI and DWI and the combined models.ResultsRadiomics models based on T2WI and DWI had good predictive performance for LVI of rectal cancer in both the training cohort and the validation cohort. The AUCs of the T2WI model were 0.87 and 0.87, and the AUCs of the DWI model were 0.94 and 0.92. The combined model was better than the T2WI model, with AUCs of 0.97 and 0.95. The predictive performance of the DWI model was comparable to that of the combined model.ConclusionsThe radiomics model based on biparametric MRI, especially DWI, had good predictive value for LVI of rectal cancer. This model has the potential to facilitate the clinical recognition of LVI in rectal cancer preoperatively.

Predicting EGFR T790M Mutation in Brain Metastases Using Multisequence MRI-Based Radiomics Signature

Timely identifying T790M mutation for non-small cell lung cancer (NSCLC) patients with brain metastases (BM) is essential to adjust targeted treatment strategies. To develop and validate radiomics models based on multisequence MRI for differentiating patients with T790M resistance from no T790M mutation in BM and explore the optimal sequence for prediction. This retrospective study enrolled 233 patients with proven of BM in NSCLC which included 95 with T790M and 138 without T790M from two hospitals as the training cohort and testing cohort separately. Radiomics features extracted from T2WI, T2 fluid-attenuated inversion recovery (T2-FLAIR), diffusion weighted imaging (DWI) and contrast-enhanced T1-weighted imaging (T1-CE) sequence respectively. The most predictable features were selected based on the maximal information coefficient and Boruta method. Then four radiomics models were built to characterize T790M mutation by random forest classifier. ROC curves, F1 score and DCA curves were constructed to validate the capability and verify the performance of four models. The DWI model showed best performance with AUC and F1 score of 0.886 and 0.789 in the training cohort, 0.850 and 0.743 in the testing cohort. DCA curves also showed higher overall net benefit from the DWI model than from the remaining three models in the testing cohort. Other three models also had some classification power whether in the training or testing cohort, especially T2-FLAIR model. Multisequence MRI-based radiomics has potential to predict the emergence of EGFR T790M resistance mutations especially the radiomics signature based on DWI sequence.

Incorporating multiple magnetic resonance diffusion models to differentiate low- and high-grade adult gliomas: a machine learning approach.

Accurate grading of gliomas is a challenge in imaging diagnosis. This study aimed to evaluate the performance of a machine learning (ML) approach based on multiparametric diffusion-weighted imaging (DWI) in differentiating low- and high-grade adult gliomas. A model was developed from an initial cohort containing 74 patients with pathology-confirmed gliomas, who underwent 3 tesla (3T) diffusion magnetic resonance imaging (MRI) with 21 b values. In all, 112 histogram features were extracted from 16 parameters derived from seven diffusion models [monoexponential, intravoxel incoherent motion (IVIM), diffusion kurtosis imaging (DKI), fractional order calculus (FROC), continuous-time random walk (CTRW), stretched-exponential, and statistical]. Feature selection and model training were performed using five randomly permuted five-fold cross-validations. An internal test set (15 cases of the primary dataset) and an external cohort (n=55) imaged on a different scanner were used to validate the model. The diagnostic performance of the model was compared with that of a single DWI model and DWI radiomics using accuracy, sensitivity, specificity, and the area under the curve (AUC). Seven significant multiparametric DWI features (two from the stretched-exponential and FROC models, and three from the CTRW model) were selected to construct the model. The multiparametric DWI model achieved the highest AUC (0.84, versus 0.71 for the single DWI model, P<0.05), an accuracy of 0.80 in the internal test, and both AUC and accuracy of 0.76 in the external test. Our multiparametric DWI model differentiated low- (LGG) from high-grade glioma (HGG) with better generalization performance than the established single DWI model. This result suggests that the application of an ML approach with multiple DWI models is feasible for the preoperative grading of gliomas.

Development and external validation of a multiparametric MRI-based radiomics model for preoperative prediction of microsatellite instability status in rectal cancer: a retrospective multicenter study.

To establish and validate a radiomics model based on multiparametric magnetic resonance imaging (MRI), and to predict microsatellite instability (MSI) status in rectal cancer patients. A total of 199 patients with pathologically confirmed rectal cancer were included. The MSI status was confirmed by immunohistochemistry (IHC) staining. Clinical factors and laboratory data associated with MSI status were analyzed. The imaging data of 100 patients from one of the hospitals were used as the training set. The remaining 99 patients from the other two hospitals were used as the external validation set. The regions of interest (ROIs) were delineated from T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and contrast-enhanced T1WI (CE-T1WI) sequence to extract the radiomics features. The Tree-based approach was used for feature selection. The models were constructed based on the four single sequences and a combination of the four sequences using the random forest (RF) algorithm. The external validation set was used to verify the generalization ability of each model. The receiver operating characteristic (ROC) curves and the area under the curve (AUC) were plotted to evaluate and compare the predictive performance of each model. In the four single-series models, the CE-T1WI model performed the best. The AUCs of the T1WI, T2WI, DWI, and CE-T1WI prediction models in the training set were 0.74, 0.71, 0.71, and 0.78, respectively, while in the external validation set, the corresponding AUCs were 0.67, 0.66, 0.70, and 0.77. The prediction and generalization performance of the combined model of multi-sequences was comparable to that of the CE-T1WI model and it was better than that of the remaining three single-series models, with AUC values of 0.78 and 0.78 in the training and validation sets, respectively. The established radiomics models based on CE-T1WI or multiparametric MRI have similar predictive performance. They have the potential to predict MSI status in rectal cancer patients. • A radiomics model for the prediction of MSI status in patients with rectal cancer was established and validated using external validation. • The models based on CE-T1WI or multiparametric MRI have better predictive performance than those based on single unenhanced sequence images. • The radiomics model has the potential to suggest MSI status in rectal cancer patients; however, it is not yet a substitute for histological confirmation.

Combining machine learning with radiomics features in predicting outcomes after mechanical thrombectomy in patients with acute ischemic stroke

Background and ObjectiveSome patients with mechanical thrombectomy will have a poor prognosis. This study establishes a model for predicting the prognosis after mechanical thrombectomy in acute stroke based on diffusion-weighted imaging (DWI) omics characteristics. MethodsA total of 260 stroke patients receiving mechanical thrombectomy in our hospital were randomly divided into a training set (n = 182) and a test set (n = 78) in a 7:3 ratio. The regions of interest (ROI) of the imaging features of the DWI infarct area were extracted, and the minimum absolute contraction and selection operator regression model were used to screen the best radiomics features. A support vector machine classifier established the prediction model of the prognosis after mechanical thrombectomy of acute stroke based on the selected features. The prediction efficiency of the model was evaluated by the receiver operating characteristic (ROC) curve. ResultsA total of 1936 radiomic features were extracted, and six features highly correlated with prognosis were screened after dimensionality reduction. Based on the DWI model, the ROC analysis showed that the area under the curve (AUC) for correct prediction in the training and test sets was 0.945 and 0.920, respectively. ConclusionThe model based on the characteristics of radiomics and machine learning has high predictive efficiency for the prognosis of acute stroke after mechanical thrombectomy, which can be used to guide personalized clinical treatment.

Predicting Grade of Esophageal Squamous Carcinoma: Can Stretched Exponential Model-Based DWI Perform Better Than Bi-Exponential and Mono-Exponential Model?

BackgroundTo evaluate and compare the potential performance of various diffusion parameters obtained from mono-exponential model (MEM)-, bi-exponential model (BEM)-, and stretched exponential model (SEM)-based diffusion-weighted imaging (DWI) in grading of esophageal squamous carcinoma (ESC).MethodsEighty-two patients with pathologically confirmed ESC without treatment underwent multi-b-value DWI scan with 13 b values (0~12,00 s/mm2). The apparent diffusion coefficient (ADC) deriving from the MEM; the pure molecular diffusion (ADCslow), pseudo-diffusion coefficient (ADCfast), perfusion, and fraction (f) deriving from the BEM; and the distributed diffusion coefficient (DDC) and water molecular diffusion heterogeneity index (α) deriving from the SEM were calculated and compared between poorly differentiated and well/moderately differentiated ESC, respectively. The prediction parameters and diagnostic efficiency were compared by drawing receiver operating characteristic (ROC) curves.ResultsThe ADC, ADCslow, ADCfast, and DDC in poorly ESC were significantly lower than those in well/moderately differentiated ones. By using only one parameter, ADCslow, DDC had the moderate diagnostic efficiency and the areas under the curve (AUC) were 0.758 and 0.813 in differentiating ESC. The DDC had the maximum AUC with sensitivity (88.00%) and specificity (68.42%). Combining ADC with ADCfast, ADCslow, and DDC and combining ADCslow with ADCfast can provide a higher diagnostic accuracy with AUC ranging from 0.756, 0.771, 0.816, and 0.793, respectively.ConclusionVarious parameters derived from different DWI models including MEM, BEM, and SEM were potentially helpful in grading ESC. DDC obtained from SEM was the most promising diffusion parameter for predicting the grade of ESC.

Combining multiparametric MRI features-based transfer learning and clinical parameters: application of machine learning for the differentiation of uterine sarcomas from atypical leiomyomas.

To explore the feasibility and effectiveness of machine learning (ML) based on multiparametric magnetic resonance imaging (mp-MRI) features extracted from transfer learning combined with clinical parameters to differentiate uterine sarcomas from atypical leiomyomas (ALMs). The data of 86 uterine sarcomas between July 2011 and December 2019 and 86 ALMs between June 2013 and June 2017 were retrospectively reviewed. We extracted deep-learning features and radiomics features from T2-weighted imaging (T2WI) and diffusion weighted imaging (DWI). The two feature extraction methods, transfer learning and radiomics, were compared. Random forest was adopted as the classifier. T2WI features, DWI features, combined T2WI and DWI (mp-MRI) features, and combined clinical parameters and mp-MRI features were applied to establish T2, DWI, T2-DWI, and complex multiparameter (mp) models, respectively. Predictive performance was assessed with the area under the receiver operating characteristic curve (AUC). In the test set, the T2, DWI, T2-DWI and complex mp models based on transfer learning (AUCs range from 0.76 to 0.81, 0.80 to 0.88, 0.85 to 0.92, and 0.94 to 0.96, respectively) outperformed the models based on radiomics (AUCs of 0.73, 0.76, 0.79, and 0.92, respectively). Moreover, the complex mp model showed the best prediction performance, with the Resnet50-complex mp model achieving the highest AUC (0.96) and accuracy (0.87). Transfer learning is feasible and superior to radiomics in the differential diagnosis of uterine sarcomas and ALMs in our dataset. ML models based on deep learning features of nonenhanced mp-MRI and clinical parameters can achieve good diagnostic efficacy. • The ML model combining nonenhanced mp-MRI features and clinical parameters can distinguish uterine sarcomas from ALMs. • Transfer learning can be applied to differentiate uterine sarcomas from ALMs and outperform radiomics. • The most accurate prediction model was Resnet50-based transfer learning, built with the deep-learning features of mp-MRI and clinical parameters.