The performance of intravoxel-incoherent motion diffusion-weighted imaging derived hypoxia for the risk stratification of prostate cancer in peripheral zone

Noninvasive grading of renal interstitial fibrosis and prediction of annual renal function loss in chronic kidney disease: the optimal solution of seven MR diffusion models

OBJECTIVES

To explore the optimal choice of seven diffusion models (DWI, IVIM, DKI, CTRW, FROC, SEM, and sADC) to assess renal interstitial fibrosis (IF) and annual renal function loss in chronic kidney disease (CKD).

METHODS

One hundred thirty-three CKD patients and 30 controls underwent multi-b diffusion sequence scans. Patients were divided into the training, testing, and temporal external validation sets. Least absolute shrinkage and selection operator regression and logistic regression were used to select the optimal metrics for distinguishing the mild from moderate-to-severe IF. The performances of imaging, clinical, and combined models were compared. A linear mixed-effects model calculated estimated glomerular filtration rate (eGFR) slope, and multiple linear regression assessed the association between metrics and 1-3-year eGFR slopes.

RESULTS

The training, testing, and temporal external validation sets had 75, 30, and 28 patients, respectively. The combined model incorporating cortical fIVIM, MKDKI and eGFR was superior to the clinical model combining the eGFR and 24-hour urinary protein in all sets (net reclassification index [NRI] > 0, p < 0.05). Decision curve analysis showed the combined model provided greater net clinical benefit across most thresholds. Fifty-two, 35, and 16 patients completed 1-, 2-, and 3-year follow-ups. After adjusting for covariates, cortical fIVIM correlated with the 1-year eGFR slope (β = 30.600, p = 0.001), and cortical αSEM correlated with the 2- and 3-year eGFR slopes (β = 44.859, p = 0.002; β = 95.631, p = 0.019).

CONCLUSIONS

A combined model of cortical fIVIM, MKDKI and eGFR provides a useful comprehensive tool for grading IF, with cortical fIVIM and αSEM as potential biomarkers for CKD progression.

Precise Prostate Cancer Assessment Using IVIM-Based Parametric Estimation of Blood Diffusion from DW-MRI

Prostate cancer is a significant health concern with high mortality rates and substantial economic impact. Early detection plays a crucial role in improving patient outcomes. This study introduces a non-invasive computer-aided diagnosis (CAD) system that leverages intravoxel incoherent motion (IVIM) parameters for the detection and diagnosis of prostate cancer (PCa). IVIM imaging enables the differentiation of water molecule diffusion within capillaries and outside vessels, offering valuable insights into tumor characteristics. The proposed approach utilizes a two-step segmentation approach through the use of three U-Net architectures for extracting tumor-containing regions of interest (ROIs) from the segmented images. The performance of the CAD system is thoroughly evaluated, considering the optimal classifier and IVIM parameters for differentiation and comparing the diagnostic value of IVIM parameters with the commonly used apparent diffusion coefficient (ADC). The results demonstrate that the combination of central zone (CZ) and peripheral zone (PZ) features with the Random Forest Classifier (RFC) yields the best performance. The CAD system achieves an accuracy of 84.08% and a balanced accuracy of 82.60%. This combination showcases high sensitivity (93.24%) and reasonable specificity (71.96%), along with good precision (81.48%) and F1 score (86.96%). These findings highlight the effectiveness of the proposed CAD system in accurately segmenting and diagnosing PCa. This study represents a significant advancement in non-invasive methods for early detection and diagnosis of PCa, showcasing the potential of IVIM parameters in combination with machine learning techniques. This developed solution has the potential to revolutionize PCa diagnosis, leading to improved patient outcomes and reduced healthcare costs.

Differential diagnosis of prostate cancer and benign prostatic hyperplasia based on DCE-MRI using bi-directional CLSTM deep learning and radiomics

Dynamic contrast-enhanced MRI (DCE-MRI) is routinely included in the prostate MRI protocol for a long time; its role has been questioned. It provides rich spatial and temporal information. However, the contained information cannot be fully extracted in radiologists' visual evaluation. More sophisticated computer algorithms are needed to extract the higher-order information. The purpose of this study was to apply a new deep learning algorithm, the bi-directional convolutional long short-term memory (CLSTM) network, and the radiomics analysis for differential diagnosis of PCa and benign prostatic hyperplasia (BPH). To systematically investigate the optimal amount of peritumoral tissue for improving diagnosis, a total of 9 ROIs were delineated by using 3 different methods. The results showed that bi-directional CLSTM with ± 20% region growing peritumoral ROI achieved the mean AUC of 0.89, better than the mean AUC of 0.84 by using the tumor alone without any peritumoral tissue (p = 0.25, not significant). For all 9 ROIs, deep learning had higher AUC than radiomics, but only reaching the significant difference for ± 20% region growing peritumoral ROI (0.89 vs. 0.79, p = 0.04). In conclusion, the kinetic information extracted from DCE-MRI using bi-directional CLSTM may provide helpful supplementary information for diagnosis of PCa.

Integrated MRI-guided radiotherapy - opportunities and challenges

MRI can help to categorize tissues as malignant or non-malignant both anatomically and functionally, with a high level of spatial and temporal resolution. This non-invasive imaging modality has been integrated with radiotherapy in devices that can differentially target the most aggressive and resistant regions of tumours. The past decade has seen the clinical deployment of treatment devices that combine imaging with targeted irradiation, making the aspiration of integrated MRI-guided radiotherapy (MRIgRT) a reality. The two main clinical drivers for the adoption of MRIgRT are the ability to image anatomical changes that occur before and during treatment in order to adapt the treatment approach, and to image and target the biological features of each tumour. Using motion management and biological targeting, the radiation dose delivered to the tumour can be adjusted during treatment to improve the probability of tumour control, while simultaneously reducing the radiation delivered to non-malignant tissues, thereby reducing the risk of treatment-related toxicities. The benefits of this approach are expected to increase survival and quality of life. In this Review, we describe the current state of MRIgRT, and the opportunities and challenges of this new radiotherapy approach.

Quantification of Tumor Hypoxia through Unsupervised Modelling of Consumption and Supply Hypoxia MR Imaging in Breast Cancer

Simple Summary

Hypoxia in solid tumors is common in most solid cancers and is associated with treatment resistance to both chemo- and radiation-therapy. There is also reason to believe that hypoxia is an important determinant of metastic disease. Identifying hypoxia in solid tumors is important in treatment planning and decision making. In 2018 Hompland et al. proposed a method, based on quantifying consumption and supply of oxygen from diffusion weighted magnetic resonance imaging, to estimate the hypoxic fraction of a solid tumor. The method was based on training model parameters on a known hypoxia state in prostate cancer. In the present study we verified the validity of the consumption and supply concept in breast cancer. Furthermore, we developed and validated a new approach to the concept that does not require a ground truth to train the parameters.

Abstract

The purpose of the present study is to investigate if consumption and supply hypoxia (CSH) MR-imaging can depict breast cancer hypoxia, using the CSH-method initially developed for prostate cancer. Furthermore, to develop a generalized pan-cancer application of the CSH-method that doesn’t require a hypoxia reference standard for training the CSH-parameters. In a cohort of 69 breast cancer patients, we generated, based on the principles of intravoxel incoherent motion modelling, images reflecting cellular density (apparent diffusion coefficient; ADC) and vascular density (perfusion fraction; fp). Combinations of the information in these images were compared to a molecular hypoxia score made from gene expression data, aiming to identify a way to apply the CSH-methodology in breast cancer. Attempts to adapt previously proposed models for prostate cancer included direct transfers and model parameter rescaling. A novel approach, based on rescaling ADC and fp data to give more nuanced response in the relevant physiologic range, was also introduced. The new CSH-method was validated in a prostate cancer cohort with known hypoxia status. The proposed CSH-method gave estimates of hypoxia that was strongly correlated to the molecular hypoxia score in breast cancer, and hypoxia as measured in pathology slices stained with pimonidazole in prostate cancer. The generalized approach to CSH-imaging depicted hypoxia in both breast and prostate cancers and requires no model training. It is easy to implement using readily available technology and encourages further investigation of CSH-imaging in other cancer entities and in other settings, with the goal being to overcome hypoxia-induced resistance to treatment.

Stratification of prostate cancer patients into low- and high-grade groups using multiparametric magnetic resonance radiomics with dynamic contrast-enhanced image joint histograms

PURPOSE

This study aimed to investigate the potential of stratification of prostate cancer patients into low- and high-grade groups (GGs) using multiparametric magnetic resonance (mpMR) radiomics in conjunction with two-dimensional (2D) joint histograms computed with dynamic contrast-enhanced (DCE) images.

METHODS

A total of 101 prostate cancer regions extracted from the MR images of 44 patients were identified and divided into training (n = 31 with 72 cancer regions) and test datasets (n = 13 with 29 cancer regions). Each dataset included low-grade tumors (International Society of Urological Pathology [ISUP] GG ≤ 2) and high-grade tumors (ISUP GG ≥ 3). A total of 137,970 features consisted of mpMR image (16 types of images in four sequences)-based and joint histogram (DCE images at 10 phases)-based features for each cancer region. Joint histogram features can visualize temporally changing perfusion patterns in prostate cancer based on the joint histograms between different phases or subtraction phases of DCE images. Nine signatures (a set of significant features related to GGs) were determined using the best combinations of features selected using the least absolute shrinkage and selection operator. Further, support vector machine models with the nine signatures were built based on a leave-one-out cross-validation for the training dataset and evaluated with receiver operating characteristic (ROC) curve analysis.

RESULTS

The signature showing the best performance was constructed using six features derived from the joint histograms, DCE original images, and apparent diffusion coefficient maps. The areas under the ROC curves for the training and test datasets were 1.00 and 0.985, respectively.

CONCLUSION

This study suggests that the proposed approach with mpMR radiomics in conjunction with 2D joint histogram computed with DCE images could have the potential to stratify prostate cancer patients into low- and high-GGs.

Artificial intelligence and imaging biomarkers for prostate radiation therapy during and after treatment

Magnetic resonance imaging (MRI) is increasingly used in the management of prostate cancer (PCa). Quantitative MRI (qMRI) parameters, derived from multi-parametric MRI, provide indirect measures of tumour characteristics such as cellularity, angiogenesis and hypoxia. Using Artificial Intelligence (AI), relevant information and patterns can be efficiently identified in these complex data to develop quantitative imaging biomarkers (QIBs) of tumour function and biology. Such QIBs have already demonstrated potential in the diagnosis and staging of PCa. In this review, we explore the role of these QIBs in monitoring treatment response during and after PCa radiotherapy (RT). Recurrence of PCa after RT is not uncommon, and early detection prior to development of metastases provides an opportunity for salvage treatments with curative intent. However, the current method of monitoring treatment response using prostate-specific antigen levels lacks specificity. QIBs, derived from qMRI and developed using AI techniques, can be used to monitor biological changes post-RT providing the potential for accurate and early diagnosis of recurrent disease.

Quantitative study of preoperative staging of gastric cancer using intravoxel incoherent motion diffusion-weighted imaging as a potential clinical index

PURPOSE

To determine the utility of intravoxel incoherent motion (IVIM) diffusion-weighted imaging in quantitative analysis of preoperative tumor (T) and node (N) stages of gastric cancer, and to quantify the diagnostic threshold of IVIM parameters for serosal invasion and lymphatic metastasis.

MATERIALS AND METHODS

From October 2016 to February 2020, 98 patients with gastric cancer who were receiving treatment in Zhongshan Hospital, China, were subject to an IVIM sequence imaging analysis. The IVIM sequence data were imported into software for post-processing of tumor regions of interest, and the IVIM parameters (the microvascular volume fraction (f), the molecular diffusion coefficient (D) and perfusion-related incoherent microcirculation (D*) were calculated. The variation of these IVIM parameters with different tumor-node metastasis (TNM) stages were analyzed by one-way analysis of variance. The IVIM parameters of serosal invasion and lymphatic metastasis were examined by receiver operating characteristic curve analysis and t-tests.

RESULTS

A total of 98 gastric cancer patients (65 males and 33 females) with an average age of 61.9 years were enrolled in this study. There were 14 patients in stage T1, 14 in stage T2, 10 in stage T3 and 60 in stage T4_a+b. There were 37 patients in stage N0, 19 in stage N1, 18 in stage N2 and 24 in stage N3. Statistically significant associations were found between the D values and T stages of gastric cancer. The D values of stage T4 cancers were significantly different from those of stage T2, T3 and T4 cancers. The D value decreased with increasing T stage. The mean D values of stages were 1.432 × 10^-3 mm²/s (T1), 1.225 × 10^-3 mm²/s (T2), 1.154 × 10^-3 mm²/s (T3) and 0.9468 × 10^-3 mm²/s (T4). The extent of the invasion of serosa was found to be significantly correlated with D value, with the diagnostic threshold for D being 1.107 × 10^-3 mm²/s. In addition, different pathological N stages of gastric cancer lesions showed statistically significantly variations in f values, but no correlation was found with different N stages. Finally, the extent of lymphatic metastasis was found to be correlated with D values, with the diagnostic threshold being 1.1739 × 10^-3 mm²/s. There was no statistically significant correlation between the IVIM MRI parameters and tumor size. The grade of tumor was found to be significantly correlated with D* value, with the diagnostic threshold for D* being 1.516 × 10^-2 mm²/s. There was no statistically significant correlation between the ADC value and tumor size. There was a significant difference in the ADC values among different T and N stage cancers. ADC value had statistically significant to distinguish gastric cancer with or without serosal invasion, its detection efficiency was not as high as that of D value, with an AUC of 0.628 and 0.830, respectively. The ADC value was not statistically significant in distinguishing gastric cancer with or without lymphatic metastasis (P ≥ 0.05). The ADC value had not statistically significant in distinguishing gastric cancer between low and medium-high grade (P ≥ 0.05).

CONCLUSION

We found that significant differences existed between whole-volume IVIM parameters of different T or N stages in gastric cancers, and were able to quantify different T or N stages of gastric cancer by the values of these parameters. The results of this quantitative study provide new tools for evaluating the prognosis of gastric cancer and will be valuable for the development of an new imaging method for determining the morphological stages of gastric cancer.

Intravoxel Incoherent Motion Diffusion-Weighted Imaging Used to Detect Prostate Cancer and Stratify Tumor Grade: A Meta-Analysis

Objectives: Intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) is a promising non-invasive imaging technique to detect and grade prostate cancer (PCa). However, the results regarding the diagnostic performance of IVIM-DWI in the characterization and classification of PCa have been inconsistent among published studies. This meta-analysis was performed to summarize the diagnostic performance of IVIM-DWI in the differential diagnosis of PCa from non-cancerous tissues and to stratify the tumor Gleason grades in PCa.

Materials and Methods: Studies concerning the differential diagnosis of prostate lesions using IVIM-DWI were systemically searched in PubMed, Embase, and Web of Science without time limitation. Review Manager 5.3 was used to calculate the standardized mean difference (SMD) and 95% confidence intervals of the apparent diffusion coefficient (ADC), tissue diffusivity (D), pseudodiffusivity (D^*), and perfusion fraction (f). Stata 12.0 was used to pool the sensitivity, specificity, and area under the curve (AUC), as well as publication bias and heterogeneity. Fagan's nomogram was used to predict the post-test probabilities.

Results: Twenty studies with 854 patients confirmed with PCa were included. Most of the included studies showed a low to unclear risk of bias and low concerns regarding applicability. PCa showed a significantly lower ADC (SMD = −2.34; P < 0.001) and D values (SMD = −1.86; P < 0.001) and a higher D^* value (SMD = 0.29; P = 0.01) than non-cancerous tissues, but no difference was noted with the f value (SMD = −0.16; P = 0.50). Low-grade PCa showed higher ADC (SMD = 0.63; P < 0.001) and D values (SMD = 0.80; P < 0.001) than the high-grade lesions. ADC showed comparable diagnostic performance (sensitivity = 86%; specificity = 86%; AUC = 0.87) but higher post-test probabilities (60, 53, 36, and 36% for ADC, D, D^*, and f values, respectively) compared with the D (sensitivity = 82%; specificity = 82%; AUC = 0.85), D^* (sensitivity = 70%; specificity = 70%; AUC = 0.75), and f values (sensitivity = 73%; specificity = 68%; AUC = 0.76).

Conclusion: IVIM parameters are adequate to differentiate PCa from non-cancerous tissues with good diagnostic performance but are not superior to the ADC value. Diffusion coefficients can further stratify the tumor Gleason grades in PCa.