Apparent Diffusion Coefficient-Based Convolutional Neural Network Model Can Be Better Than Sole Diffusion-Weighted Magnetic Resonance Imaging to Improve the Differentiation of Invasive Breast Cancer From Breast Ductal Carcinoma In Situ

Background and PurposeBreast ductal carcinoma in situ (DCIS) has no metastatic potential, and has better clinical outcomes compared with invasive breast cancer (IBC). Convolutional neural networks (CNNs) can adaptively extract features and may achieve higher efficiency in apparent diffusion coefficient (ADC)-based tumor invasion assessment. This study aimed to determine the feasibility of constructing an ADC-based CNN model to discriminate DCIS from IBC.MethodsThe study retrospectively enrolled 700 patients with primary breast cancer between March 2006 and June 2019 from our hospital, and randomly selected 560 patients as the training and validation sets (ratio of 3 to 1), and 140 patients as the internal test set. An independent external test set of 102 patients during July 2019 and May 2021 from a different scanner of our hospital was selected as the primary cohort using the same criteria. In each set, the status of tumor invasion was confirmed by pathologic examination. The CNN model was constructed to discriminate DCIS from IBC using the training and validation sets. The CNN model was evaluated using the internal and external tests, and compared with the discriminating performance using the mean ADC. The area under the curve (AUC), sensitivity, specificity, and accuracy were calculated to evaluate the performance of the previous model.ResultsThe AUCs of the ADC-based CNN model using the internal and external test sets were larger than those of the mean ADC (AUC: 0.977 vs. 0.866, P = 0.001; and 0.926 vs. 0.845, P = 0.096, respectively). Regarding the internal test set and external test set, the ADC-based CNN model yielded sensitivities of 0.893 and 0.873, specificities of 0.929 and 0.894, and accuracies of 0.907 and 0.902, respectively. Regarding the two test sets, the mean ADC showed sensitivities of 0.845 and 0.818, specificities of 0.821 and 0.829, and accuracies of 0.836 and 0.824, respectively. Using the ADC-based CNN model, the prediction only takes approximately one second for a single lesion.ConclusionThe ADC-based CNN model can improve the differentiation of IBC from DCIS with higher accuracy and less time.

Machine learning to differentiate small round cell malignant tumors and non-small round cell malignant tumors of the nasal and paranasal sinuses using apparent diffusion coefficient values

Objective We used radiomics feature–based machine learning classifiers of apparent diffusion coefficient (ADC) maps to differentiate small round cell malignant tumors (SRCMTs) and non-SRCMTs of the nasal and paranasal sinuses. Materials A total of 267 features were extracted from each region of interest (ROI). Datasets were randomized into two sets, a training set (∼70%) and a test set (∼30%). We performed dimensional reductions using the Pearson correlation coefficient and feature selection analyses (analysis of variance [ANOVA], relief, recursive feature elimination [RFE]) and classifications using 10 machine learning classifiers. Results were evaluated with a leave-one-out cross-validation analysis. Results We compared the AUC for all the pipelines in the validation dataset using FeAture Explorer (FAE) software. The pipeline using RFE feature selection and Gaussian process classifier yielded the highest AUCs with ten features. When the “one-standard error” rule was used, FAE produced a simpler model with eight features, including Perc.01%, Perc.10%, Perc.90%, Perc.99%, S(1,0) SumAverg, S(5,5) AngScMom, S(5,5) Correlat, and WavEnLH_s-2. The AUCs of the training, validation, and test datasets achieved 0.995, 0.902, and 0.710, respectively. For ANOVA, the pipeline with the auto-encoder classifier yielded the highest AUC using only one feature, Perc.10% (training/validation/test datasets: 0.886/0.895/0.809, respectively). For the relief, the AUCs of the training, validation, and test datasets that used the LRLasso classifier using five features (Perc.01%, Perc.10%, S(4,4) Correlat, S(5,0) SumAverg, S(5,0) Contrast) were 0.892, 0.886, and 0.787, respectively. Compared with the RFE and relief, the results of all algorithms of ANOVA feature selection were more stable with the AUC values higher than 0.800. Conclusions We demonstrated the feasibility of combining artificial intelligence with the radiomics from ADC values in the differential diagnosis of SRCMTs and non-SRCMTs and the potential of this non-invasive approach for clinical applications. Key Points • The parameter with the best diagnostic performance in differentiating SRCMTs from non-SRCMTs was the Perc.10% ADC value. • Results of all the algorithms of ANOVA feature selection were more stable and the AUCs were higher than 0.800, as compared with RFE and relief. • The pipeline using RFE feature selection and Gaussian process classifier yielded the highest AUC.

Kinetic control concept for the diffusion processes of paracetamol active molecules across affinity polymer membranes from acidic solutions

Background Paracetamol compound remains the most used pharmaceutical as an analgesic and antipyretic for pain and fever, often identified in aquatic environments. The elimination of this compound from wastewater is one of the critical operations carried out by advanced industries. Our work objective was to assess studies based on membrane processes by using two membranes, polymer inclusion membrane and grafted polymer membrane containing gluconic acid as an extractive agent for extracting and recovering paracetamol compound from aqueous solutions. Result The elaborated membrane characterizations were assessed using Fourier-transform infrared spectroscopy (FTIR) and scanning electron microscopy (SEM). Kinetic and thermodynamic models have been applied to determine the values of macroscopic (P and J0), microscopic (D* and Kass), activation and thermodynamic parameters (Ea, ΔH#, ΔS#, ΔH#diss, and ΔH#th). All results showed that the PVA–GA was more performant than its counterpart GPM–GA, with apparent diffusion coefficient values (107D*) of 41.807 and 31.211 cm2 s−1 respectively, at T = 308 K. In addition, the extraction process for these membranes was more efficient at pH = 1. The relatively low values of activation energy (Ea), activation association enthalpy (ΔH≠ass), and activation dissociation enthalpy (ΔH≠diss) have indicated a kinetic control for the oriented processes studied across the adopted membranes much more than the energetic counterpart. Conclusion The results presented for the quantification of oriented membrane process ensured clean, sustainable, and environmentally friendly methods for the extraction and recovery of paracetamol molecule as a high-value substance.

Diffusion Weighted and Dynamic Contrast Enhanced Magnetic Resonance Imaging in Carcinoma of Cervix: Role of Apparent Diffusion Coefficient Value and Time Intensity Curve Pattern in Chemoradiotherapeutic Response Evaluation

Introduction: Magnetic resonance imaging (MRI) is a widely used imaging modality in the imaging evaluation of carcinoma of cervix. The aim of our study was to evaluate the response in carcinoma cervix patients following chemoradiotherapy by Diffusion weighted (DW-MRI) and Dynamic contrast enhanced-MRI (DCE-MRI). Methods: 21 inoperable biopsy proven patients (mean age 48.43 years) of carcinoma cervix were included in the study. All patients underwent MRI (conventional, DW and DCE) of the pelvis thrice. Baseline MRI, Post chemotherapy MRI after neoadjuvant chemotherapy and Post chemoradiotherapy MRI after completion of concurrent chemoradiotherapy. Post treatment apparent diffusion coefficient(ADC) values and Time intensity curve(TIC) pattern were compared with baseline values. Results: Baseline meanADC value of all patients was 0.82 x10-3 mm2/s. After completion of treatment, 18 patients showed complete resolution of tumor and showed 0.50 x10-3 mm2/s increase in meanADC value from baseline MRI which was significantly higher than remaining 3 patients with residual tumor (0.50 x10-3 mm2/s v/s 0.17 x10-3 mm2/s). ADC threshold value of 1.15 x10-3 mm2/s was defined, differentiating the residual tumor from the healthy cervical tissue after chemoradiation. On post treatment MRI, 17 out of 18 patients with complete resolution of tumor showed increasing trend of enhancement on TIC and only one patient showed plateau pattern. 2 of the 3 patients with residual tumor showed washout pattern and one patient showed plateau pattern. Conclusion: ADC values and TIC pattern differ in patients with complete response to chemoradiotherapy from patients with residual tumor, so helps in differentiating residual tumor from cancer free cervix. Keywords: Carcinoma of cervix; Chemoradiotherapy; Diffusion weighted MRI; Dynamic contrast enhanced MRI; Time intensity curve.

MRI findings of epithelial–myoepithelial carcinoma of the parotid gland with radiologic–pathologic correlation

Purpose This study aimed to describe the MRI findings of epithelial-myoepithelial carcinoma (EMC) of the parotid gland. Materials and methods Seven patients (four males and three females) aged 40–86 years (mean age, 64 years) with histologically proven EMC of the parotid gland who underwent surgical resection after preoperative MRI were enrolled. MRI images were retrospectively reviewed and contrasted with pathological findings. Results Five patients (71%) had predominantly solid lesions, and two (29%) had predominantly cystic lesions. All seven lesions had well-demarcated margins and capsules without the invasion of adjacent structures. The capsules were incomplete in five lesions (71%) and complete in two (29%). Four lesions (57%) exhibited a multinodular structure with internal septa. Cystic components were observed in three lesions (43%). On T1-weighted images, the solid components were frequently homogeneous (5/7, 71%), and demonstrated isointensity in five lesions (71%) and hypointensity in two (29%) relative to the spinal cord. On T2-weighted images, the solid components were usually heterogeneous (6/7, 86%), and demonstrated hyperintensity in five lesions (71%) and isointensity in two (29%) relative to the spinal cord. The mean apparent diffusion coefficient value of the solid components was 0.967 × 10−3 mm2/s. Conclusion Parotid gland EMCs usually appeared as predominantly solid lesions with well-demarcated margins and capsules. A multinodular structure with internal septa was characteristics of EMCs.

Predictive Value of the Prognostic Nutritional Index in Neoadjuvant Chemoradiotherapy for Rectal Cancer

Background/Aim: Prognostic nutritional index (PNI) and neutrophil-to-lymphocyte ratio (NLR) indicate nutritional status and host immunity. We used immunohistochemistry and apparent diffusion coefficient (ADC) values calculated using diffusion-weighted imaging (DWI) to investigate relationships of these factors with pathological and radiological characteristics in rectal cancer treated with neoadjuvant chemoradiotherapy (nCRT). Patients and Methods: We evaluated expression levels of VEGFA, CD8, CD33, and ADC values in tumors pre/post nCRT; and analyzed the relationships between those factors and PNI, NLR in 32 patients. Results: Pretreatment PNI negatively correlated with change in tumor stromal CD8+ T cells and positively correlated with ADC values. Pretreatment NLR and PNI change correlated with recurrence-free survival (RFS). Conclusion: Patients with higher pretreatment PNI had greater changes in ADC values and stromal CD8+ T-cell counts, and those with greater PNI reduction from nCRT had a worse prognosis. Proper nutritional management during nCRT benefits patients and may lead to better prognosis in rectal cancer.

An Application of Machine Learning That Uses the Magnetic Resonance Imaging Metric, Mean Apparent Diffusion Coefficient, to Differentiate between the Histological Types of Ovarian Cancer

This retrospective single-center study included patients diagnosed with epithelial ovarian cancer (EOC) using preoperative pelvic magnetic resonance imaging (MRI). The apparent diffusion coefficient (ADC) of the axial MRI maps that included the largest solid portion of the ovarian mass was analysed. The mean ADC values (ADCmean) were derived from the regions of interest (ROIs) of each largest solid portion. Logistic regression and three types of machine learning (ML) applications were used to analyse the ADCs and clinical factors. Of the 200 patients, 103 had high-grade serous ovarian cancer (HGSOC), and 97 had non-HGSOC (endometrioid carcinoma, clear cell carcinoma, mucinous carcinoma, and low-grade serous ovarian cancer). The median ADCmean of patients with HGSOC was significantly lower than that of patients without HGSOCs. Low ADCmean and CA 19-9 levels were independent predictors for HGSOC over non-HGSOC. Compared to stage I disease, stage III disease was associated with HGSOC. Gradient boosting machine and extreme gradient boosting machine showed the highest accuracy in distinguishing between the histological findings of HGSOC versus non-HGSOC and between the five histological types of EOC. In conclusion, ADCmean, disease stage at diagnosis, and CA 19-9 level were significant factors for differentiating between EOC histological types.

Diagnostic performance of apparent diffusion coefficient values for the differentiation of intrahepatic cholangiocarcinoma from gastrointestinal adenocarcinoma liver metastases

Background We aimed to investigate whether there is a difference between intrahepatic cholangiocarcinoma (IHCC) and liver metastases of gastrointestinal system (GIS) adenocarcinoma in terms of apparent diffusion coefficient (ADC) values. Patients and methods From January 2018 to January 2020, we retrospectively examined 64 consecutive patients with liver metastases due to gastrointestinal system adenocarcinomas and 13 consecutive IHCC in our hospital’s medical records. After exclusions, fifty-three patients with 53 liver metastases and 10 IHCC were included in our study. We divided the patients into two groups as IHCC and liver metastases of GIS adenocarcinoma. For mean apparent diffusion coefficient (ADCmean) values, the region of interests (ROI) was placed in solid portions of the lesions. ADCmean values of groups were compared. Results The mean age of IHCC group was 62.50 ± 13.49 and mean age of metastases group was 61.15 ± 9.18. ADCmean values were significantly higher in the IHCC group compared to the metastatic group (p < 0.001). ROC curves method showed high diagnostic accuracy (AUC = 0.879) with cut-off value of < 1178 x 10-6 mm2/s for ADCmean (Sensitivity = 90.57, Specificity = 70.0, positive predictive value [PPV] = 94.1, negative predictive value [NPV] = 58.3) in differentiating adenocarcinoma metastases from IHCC. Conclusions The present study results suggest that ADC values have a potential role for differentiation between IHCC and GIS adenocarcinoma liver metastases which may be valuable for patient management.