The Assessment of Prostate Cancer Aggressiveness Using a Combination of Quantitative Diffusion-Weighted Imaging and Dynamic Contrast-Enhanced Magnetic Resonance Imaging

Diagnostic Performance Evaluation of Multiparametric Magnetic Resonance Imaging in the Detection of Prostate Cancer with Supervised Machine Learning Methods

Prostate cancer is the second leading cause of cancer-related death in men. Its early and correct diagnosis is of particular importance to controlling and preventing the disease from spreading to other tissues. Artificial intelligence and machine learning have effectively detected and graded several cancers, in particular prostate cancer. The purpose of this review is to show the diagnostic performance (accuracy and area under the curve) of supervised machine learning algorithms in detecting prostate cancer using multiparametric MRI. A comparison was made between the performances of different supervised machine-learning methods. This review study was performed on the recent literature sourced from scientific citation websites such as Google Scholar, PubMed, Scopus, and Web of Science up to the end of January 2023. The findings of this review reveal that supervised machine learning techniques have good performance with high accuracy and area under the curve for prostate cancer diagnosis and prediction using multiparametric MR imaging. Among supervised machine learning methods, deep learning, random forest, and logistic regression algorithms appear to have the best performance.

Synthetic MRI, multiplexed sensitivity encoding, and BI-RADS for benign and malignant breast cancer discrimination

Objective

To assess the diagnostic value of predictive models based on synthetic magnetic resonance imaging (syMRI), multiplexed sensitivity encoding (MUSE) sequences, and Breast Imaging Reporting and Data System (BI-RADS) in the differentiation of benign and malignant breast lesions.

Methods

Clinical and MRI data of 158 patients with breast lesions who underwent dynamic contrast-enhanced MRI (DCE-MRI), syMRI, and MUSE sequences between September 2019 and December 2020 were retrospectively collected. The apparent diffusion coefficient (ADC) values of MUSE and quantitative relaxation parameters (longitudinal and transverse relaxation times [T1, T2], and proton density [PD] values) of syMRI were measured, and the parameter variation values and change in their ratios were calculated. The patients were randomly divided into training (n = 111) and validation (n = 47) groups at a ratio of 7:3. A nomogram was built based on univariate and multivariate logistic regression analyses in the training group and was verified in the validation group. The discriminatory and predictive capacities of the nomogram were assessed by the receiver operating characteristic curve and area under the curve (AUC). The AUC was compared by DeLong test.

Results

In the training group, univariate analysis showed that age, lesion diameter, menopausal status, ADC, T2_pre, PD_pre, PD_Gd, T2_Delta, and T2_ratio were significantly different between benign and malignant breast lesions (P < 0.05). Multivariate logistic regression analysis showed that ADC and T2_pre were significant variables (all P < 0.05) in breast cancer diagnosis. The quantitative model (model A: ADC, T2_pre), BI-RADS model (model B), and multi-parameter model (model C: ADC, T2_pre, BI-RADS) were established by combining the above independent variables, among which model C had the highest diagnostic performance, with AUC of 0.965 and 0.986 in the training and validation groups, respectively.

Conclusions

The prediction model established based on syMRI, MUSE sequence, and BI-RADS is helpful for clinical differentiation of breast tumors and provides more accurate information for individualized diagnosis.

CCKAR is a biomarker for prognosis and asynchronous brain metastasis of non-small cell lung cancer

Background

Non-small cell lung cancer (NSCLC) is the most common histological type of lung cancer, and brain metastasis (BM) is the most lethal complication of NSCLC. The predictive biomarkers and risk factors of asynchronous BM are still unknown.

Materials and methods

A total of 203 patients with NSCLC were enrolled into our cohort and followed up. The clinicopathological factors such as tumor size, T stage, lymphatic invasion, metastasis and asynchronous BM were investigated. CCKAR expression in NSCLC and resected BM was assessed by IHC, and CCKAR mRNAs in NSCLC and para-tumor tissues were estimated by qRT-PCR. The correlations between CCKAR expression, BM and other clinicopathological factors were assessed by chi-square test, and prognostic significance of CCKAR was estimated by univariate and multivariate analyses.

Results

CCKAR was highly expressed in NSCLC tissues compared with para-tumor tissues. CCKAR expression in NSCLC was significantly associated with asynchronous BM. The BM percentages for NSCLC patients with low and high CCKAR were surprisingly 5.2% and 66.6%, respectively. CCKAR expression and BM were unfavorable factors predicting unfavorable outcome of NSCLC. Moreover, CCKAR expression in NSCLC was an independent risk factor of asynchronous BM.

Conclusions

CCKAR is a prognostic biomarker of NSCLC. CCKAR expression in NSCLC is positively associated with asynchronous BM, and is a risk factor of asynchronous BM from NSCLC.

Multiparametric Magnetic Resonance Imaging for Assessing Thymic Epithelial Tumors: Correlation With Pathological Subtypes and Clinical Stages

BACKGROUND

World Health Organization classification and Masaoka-Koga stage are widely used for thymic epithelial tumors (TETs). Reduced field-of-view (rFOV) diffusion-weighed imaging (DWI) proved to improve the image quality. Dynamic contrast-enhanced (DCE) MRI was commonly used in evaluating tumors.

PURPOSE

To investigate the value of multiparametric MRI in evaluating TETs.

STUDY TYPE

Retrospective.

SUBJECTS

Eighty-seven participants including 38 low risk (52.08 ± 14.19 years), 30 high risk (52.40 ± 11.35 years), and 19 thymic carcinoma patients (59.76 ± 10.78 years).

FIELD STRENGTH/SEQUENCE

A 3 T, turbo spin echo imaging, echo planar imaging, volumetric interpolated breath-hold examination with radial acquisition trajectory.

ASSESSMENT

DCE-MRI and apparent diffusion coefficient (ADC) variables were compared. Diagnostic performances of single significant factor and combined model were compared.

STATISTICAL TESTS

Parameters were compared using one-way ANOVA or independent-samples t test. Logistic regression was employed to investigate the combined model. Receiver operating curves (ROC) and DeLong's test were used to compare the diagnostic efficiency.

RESULTS

ADC, K^trans , and k_ep values were significantly different among low-risk, high-risk and carcinoma group (ADC, 1.279 ± 0.345 × 10^-3  mm² /sec, 0.978 ± 0.260 × 10^-3  mm² /sec, 0.661 ± 0.134 × 10^-3  mm² /sec; K^trans 0.167 ± 0.071 min^-1 , 0.254 ± 0.136 min^-1 , 0.393 ± 0.110 min^-1 ; k_ep 0.345 ± 0.113 min^-1 , 0.560 ± 0.269 min^-1 , 0.872 ± 0.149 min^-1 ). They were significantly different for early stage and advanced stage (ADC, 1.270 ± 0.356 × 10^-3  mm² /sec vs. 0.845 ± 0.251 × 10^-3  mm² /sec; K^trans 0.179 ± 0.092 min^-1 vs. 0.304 ± 0.142 min^-1 ; k_ep 0.370 ± 0.181 min^-1 vs. 0.674 ± 0.362 min^-1 ). The combination of them had highest diagnostic efficiency for WHO classification (AUC, 0.925; sensitivity, 83.7%; specificity, 89.5%), clinical stage (AUC, 0.879; sensitivity, 80.9%; specificity, 82.5%).

DATA CONCLUSION

Multiparametric MRI model may be useful for discriminating WHO classification and clinical stage of TETs.

EVIDENCE LEVEL

4 TECHNICAL EFFICIENCY: Stage 2.

Artificial Intelligence Algorithm-Based MRI for Differentiation Diagnosis of Prostate Cancer

The rapid increase in prostate cancer (PCa) patients is similar to that of benign prostatic hyperplasia (BPH) patients, but the treatments are quite different. In this research, magnetic resonance imaging (MRI) images under the weighted low-rank matrix restoration algorithm (RLRE) were utilized to differentiate PCa from BPH. The diagnostic effects of different sequences of MRI images were evaluated to provide a more effective examination method for the clinical differential diagnosis of PCa and BPH. 150 patients with suspected PCa were taken as the research objects. Pathological examination revealed that 137 patients had PCa and 13 patients had BPH. The pathological results were the gold standard and were compared with the MRI results of different sequences. Therefore, the accuracy of the MRI results was evaluated. The results showed that with the rise of Gaussian noise, the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) of all three algorithms gradually decreased, but the PSNR and SSIM of the RLRE algorithm were always higher than those of the RL and BM3D algorithms (P < 0.05). The sensitivity (97.08%), specificity (92.31%), accuracy (96.67%), and consistency (0.678) of the dynamic contrast enhancement (DCE) sequence were higher than those of the plain scan (86.13%, 69.23%, 84.67%, and 0.469, respectively). In conclusion, the RLRE algorithm could promote the resolution of MRI images and improve the display effect. DCE could better differentiate PCa from BPH, had great clinical application value, and was worthy of clinical promotion.

Analysis of Apparent Diffusion Coefficient Value and Dynamic Contrast-Enhanced Magnetic Resonance Imaging Parameters of Prostate Cancer Patients after Diagnosis and Treatment with Magnetic Resonance Imaging

This research was aimed at exploring the changes in the apparent diffusion coefficient (ADC) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) parameters of prostate cancer (PCa) patients. Sixty PCa patients from the hospital were recruited as the research object, and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) scans were performed to determine the shape, scope, and enhancement characteristics of prostate lesions and their relationship with surrounding tissues. The quantitative parameters of ADC and DCE-MRI were measured. There were 4 patients (6.67%) with a Gleason score of 6 and 15 patients (25%) with a 4 + 3 score. The ADC with Gleason = 6 is 0.81 ± 0.08 × 10⁻³ s/mm², the ADC with Gleason = 3 + 4 is 0.74 ± 0.07 × 10⁻³ s/mm², the ADC with Gleason = 4 + 3 is 0.73 ± 0.05 × 10⁻³ s/mm², the ADC with Gleason = 9 is 0.65 ± 0.06 × 10⁻³ s/mm², and the ADC with Gleason = 10 is 0.59 ± 0.07 × 10⁻³ s/mm². As the Gleason score increased, the ADC decreased and the permeation parameter transfer constant increased. When the ADC was combined with the permeability parameter transfer constant, the AUC of Gleason = 6 points and Gleason = 7 points was greatly different (P < 0.05). The 95% CI of the ADC combined permeability parameter transport constant when Gleason = 6 points and Gleason = 7 points was 0.898-0.934, the sensitivity was 75.4%, and the specificity was 86.2%. The ADC value was negatively correlated with Gleason score. The ADC value combined with VTC value has good diagnostic performance in evaluating the invasion of PCa, which is very important for making treatment plan and evaluating prognosis.