T2 mapping for the characterization of prostate lesions

Improved quantitative parameter estimation for prostate T2 relaxometry using convolutional neural networks

OBJECTIVE

Quantitative parameter mapping conventionally relies on curve fitting techniques to estimate parameters from magnetic resonance image series. This study compares conventional curve fitting techniques to methods using neural networks (NN) for measuring T2 in the prostate.

MATERIALS AND METHODS

Large physics-based synthetic datasets simulating T2 mapping acquisitions were generated for training NNs and for quantitative performance comparisons. Four combinations of different NN architectures and training corpora were implemented and compared with four different curve fitting strategies. All methods were compared quantitatively using synthetic data with known ground truth, and further compared on in vivo test data, with and without noise augmentation, to evaluate feasibility and noise robustness.

RESULTS

In the evaluation on synthetic data, a convolutional neural network (CNN), trained in a supervised fashion using synthetic data generated from naturalistic images, showed the highest overall accuracy and precision amongst the methods. On in vivo data, this best performing method produced low-noise T2 maps and showed the least deterioration with increasing input noise levels.

DISCUSSION

This study showed that a CNN, trained with synthetic data in a supervised manner, may provide superior T2 estimation performance compared to conventional curve fitting, especially in low signal-to-noise regions.

Value of MRI - T2 Mapping to Differentiate Clinically Significant Prostate Cancer

Standardized reporting of multiparametric prostate MRI (mpMRI) is widespread and follows international standards (Pi-RADS). However, quantitative measurements from mpMRI are not widely comparable. Although T2 mapping sequences can provide repeatable quantitative image measurements and extract reliable imaging biomarkers from mpMRI, they are often time-consuming. We therefore investigated the value of quantitative measurements on a highly accelerated T2 mapping sequence, in order to establish a threshold to differentiate benign from malignant lesions. For this purpose, we evaluated a novel, highly accelerated T2 mapping research sequence that enables high-resolution image acquisition with short acquisition times in everyday clinical practice. In this retrospective single-center study, we included 54 patients with clinically indicated MRI of the prostate and biopsy-confirmed carcinoma (n = 37) or exclusion of carcinoma (n = 17). All patients had received a standard of care biopsy of the prostate, results of which were used to confirm or exclude presence of malignant lesions. We used the linear mixed-effects model-fit by REML to determine the difference between mean values of cancerous tissue and healthy tissue. We found good differentiation between malignant lesions and normal appearing tissue in the peripheral zone based on the mean T2 value. Specifically, the mean T2 value for tissue without malignant lesions was (151.7 ms [95% CI: 146.9-156.5 ms] compared to 80.9 ms for malignant lesions [95% CI: 67.9-79.1 ms]; p < 0.001). Based on this assessment, a limit of 109.2 ms is suggested. Aditionally, a significant correlation was observed between T2 values of the peripheral zone and PI-RADS scores (p = 0.0194). However, no correlation was found between the Gleason Score and the T2 relaxation time. Using REML, we found a difference of -82.7 ms in mean values between cancerous tissue and healthy tissue. We established a cut-off-value of 109.2 ms to accurately differentiate between malignant and non-malignant prostate regions. The addition of T2 mapping sequences to routine imaging could benefit automated lesion detection and facilitate contrast-free multiparametric MRI of the prostate.

Predicting the status of lymphovascular space invasion using quantitative parameters from synthetic MRI in cervical squamous cell carcinoma without lymphatic metastasis

Purpose

To investigate the value of quantitative longitudinal relaxation time (T1), transverse relaxation time (T2), and proton density (PD) maps derived from synthetic magnetic resonance imaging (MRI) for evaluating the status of lymphovascular space invasion (LVSI) in cervical squamous cell carcinoma (CSCC) without lymph node metastasis (LNM).

Material and methods

Patients with suspected cervical cancer who visited our hospital from May 2020 to March 2023 were collected. All patients underwent preoperative MRI, including routine sequences and synthetic MRI. Patients with pathologically confirmed CSCC without lymphatic metastasis were included in this study. The subjects were divided into negative- and positive-LVSI groups based on the status of LVSI. Quantitative parameters of T1, T2, and PD values derived from synthetic MRI were compared between the two groups using independent samples t-test. Receiver operating characteristic curves were used to determine the diagnostic efficacy of the parameters.

Results

59 patients were enrolled in this study and were classified as positive (n = 32) and negative LVSI groups (n = 27). T1 and T2 values showed significant differences in differentiating negative-LVSI from positive-LVSI CSCC (1307.39 ± 122.02 vs. 1193.03 ± 107.86, P<0.0001; 88.42 ± 7.24 vs. 80.99 ± 5.50, P<0.0001, respectively). The area under the curve (AUC) for T1, T2 values and a combination of T1 and T2 values were 0.756, 0.799, 0.834 respectively, and there is no statistically significant difference in the diagnostic efficacy between individual and combined diagnosis of each parameter.

Conclusions

Quantitative parameters derived from synthetic MRI can be used to evaluate the LVSI status in patients with CSCC without LNM.

Retrospective T2 quantification from conventional weighted MRI of the prostate based on deep learning

Purpose

To develop a deep learning-based method to retrospectively quantify T2 from conventional T1- and T2-weighted images.

Methods

Twenty-five subjects were imaged using a multi-echo spin-echo sequence to estimate reference prostate T2 maps. Conventional T1- and T2-weighted images were acquired as the input images. A U-Net based neural network was developed to directly estimate T2 maps from the weighted images using a four-fold cross-validation training strategy. The structural similarity index (SSIM), peak signal-to-noise ratio (PSNR), mean percentage error (MPE), and Pearson correlation coefficient were calculated to evaluate the quality of network-estimated T2 maps. To explore the potential of this approach in clinical practice, a retrospective T2 quantification was performed on a high-risk prostate cancer cohort (Group 1) and a low-risk active surveillance cohort (Group 2). Tumor and non-tumor T2 values were evaluated by an experienced radiologist based on region of interest (ROI) analysis.

Results

The T2 maps generated by the trained network were consistent with the corresponding reference. Prostate tissue structures and contrast were well preserved, with a PSNR of 26.41 ± 1.17 dB, an SSIM of 0.85 ± 0.02, and a Pearson correlation coefficient of 0.86. Quantitative ROI analyses performed on 38 prostate cancer patients revealed estimated T2 values of 80.4 ± 14.4 ms and 106.8 ± 16.3 ms for tumor and non-tumor regions, respectively. ROI measurements showed a significant difference between tumor and non-tumor regions of the estimated T2 maps (P < 0.001). In the two-timepoints active surveillance cohort, patients defined as progressors exhibited lower estimated T2 values of the tumor ROIs at the second time point compared to the first time point. Additionally, the T2 difference between two time points for progressors was significantly greater than that for non-progressors (P = 0.010).

Conclusion

A deep learning method was developed to estimate prostate T2 maps retrospectively from clinically acquired T1- and T2-weighted images, which has the potential to improve prostate cancer diagnosis and characterization without requiring extra scans.

State-of-the-art Prostate Imaging

Prostate cancer is one of the most common cancers in men. In addition to methods such as prostate-specific antigen test, digital rectal examination, and transrectal ultrasonography, magnetic resonance imaging has an important role for accurate and reproducible diagnosis. However, guidance in targeted biopsies and recent use in determining localization for treatment increase its importance. Due to technical difficulties, patient tolerance, and differences in interpretation, the prostate imaging reporting and data system recommends preparations for the patient and magnetic resonance imaging techniques. However, techniques continue to be developed to improve the diagnosis rate and image quality. In our article, patient preparation before imaging and techniques were tried to be discussed in detail. In addition, current approaches in biparametric magnetic resonance imaging and radiomics and new techniques such as T1 and T2 mapping will be mentioned.

Study of T2 mapping in quantifying and discriminating uterine lesions under different magnetic field strengths: 1.5 T vs. 3.0 T

BACKGROUND

MRI is the best imaging tool for the evaluation of uterine tumors, but conventional MRI diagnosis results rely on radiologists and contrast agents (if needed). As a new objective, reproducible and contrast-agent free quantification technique, T2 mapping has been applied to a number of diseases, but studies on the evaluation of uterine lesions and the influence of magnetic field strength are few. Therefore, the aim of this study was to systematically investigate and compare the performance of T2 mapping as a nonenhanced imaging tool in discriminating common uterine lesions between 1.5 T and 3.0 T MRI systems.

METHODS

A total of 50 healthy subjects and 126 patients with suspected uterine lesions were enrolled in our study, and routine uterine MRI sequences with additional T2 mapping sequences were performed. T2 maps were calculated by monoexponential fitting using a custom code in MATLAB. T2 values of normal uterine structures in the healthy group and lesions (benign: adenomyosis, myoma, endometrial polyps; malignant: cervical cancer, endometrial carcinoma) in the patient group were collected. The differences in T2 values between 1.5 T MRI and 3.0 T MRI in any normal structure or lesion were compared. The comparison of T2 values between benign and malignant lesions was also performed under each magnetic field strength, and the diagnostic efficacies of the T2 value obtained through receiver operating characteristic (ROC) analysis were compared between 1.5 T and 3.0 T.

RESULTS

The mean T2 value of any normal uterine structure or uterine lesion under 3.0 T MRI was significantly lower than that under 1.5 T MRI (p < 0.05). There were significant differences in T2 values between each lesion subgroup under both 1.5 T and 3.0 T MRI. Moreover, the T2 values of benign lesions (71.1 ± 22.0 ms at 1.5 T and 63.4 ± 19.1 ms at 3.0 T) were also significantly lower than those of malignant lesions (101.1 ± 4.5 ms at 1.5 T and 93.5 ± 5.1 ms at 3.0 T) under both field strengths. In the aspect of differentiating benign from malignant lesions, the area under the curve of the T2 value under 3.0 T (0.94) was significantly higher than that under 1.5 T MRI (0.90) (p = 0.02).

CONCLUSION

T2 mapping can be a potential tool for quantifying common uterine lesions, and it has better performance in distinguishing benign from malignant lesions under 3.0 T MRI.

Imaging in translational cancer research

This review is aimed at presenting some of the recent developments in translational cancer imaging research, with a focus on novel, recently established, or soon to be established cross-sectional imaging techniques for computed tomography (CT), magnetic resonance imaging (MRI), and positron-emission tomography (PET) imaging, including computational investigations based on machine-learning techniques.