Neural networks for parameter estimation in microstructural MRI: Application to a diffusion-relaxation model of white matter

Specific features of white matter microstructure can be investigated by using biophysical models to interpret relaxation-diffusion MRI brain data. Although more intricate models have the potential to reveal more details of the tissue, they also incur time-consuming parameter estimation that may converge to inaccurate solutions due to a prevalence of local minima in a degenerate fitting landscape. Machine-learning fitting algorithms have been proposed to accelerate the parameter estimation and increase the robustness of the attained estimates. So far, learning-based fitting approaches have been restricted to microstructural models with a reduced number of independent model parameters where dense sets of training data are easy to generate. Moreover, the degree to which machine learning can alleviate the degeneracy problem is poorly understood. For conventional least-squares solvers, it has been shown that degeneracy can be avoided by acquisition with optimized relaxation-diffusion-correlation protocols that include tensor-valued diffusion encoding. Whether machine-learning techniques can offset these acquisition requirements remains to be tested. In this work, we employ artificial neural networks to vastly accelerate the parameter estimation for a recently introduced relaxation-diffusion model of white matter microstructure. We also develop strategies for assessing the accuracy and sensitivity of function fitting networks and use those strategies to explore the impact of the acquisition protocol. The developed learning-based fitting pipelines were tested on relaxation-diffusion data acquired with optimal and sub-optimal acquisition protocols. Networks trained with an optimized protocol were observed to provide accurate parameter estimates within short computational times. Comparing neural networks and least-squares solvers, we found the performance of the former to be less affected by sub-optimal protocols; however, model fitting networks were still susceptible to degeneracy issues and their use could not fully replace a careful design of the acquisition protocol.

Male Breast Cancer Review. A Rare Case of Pure DCIS: Imaging Protocol, Radiomics and Management

Ductal carcinoma in situ (DCIS) of male breast is a rare lesion, often associated with invasive carcinoma. When the in situ component is present in pure form, histological grade is usually low or intermediate. Imaging is difficult as gynaecomastia is often present and can mask underlying findings. We report a rare case of pure high-grade DCIS in a young male patient, with associated intraductal papilloma and atypical ductal hyperplasia. Digital breast tomosynthesis (DBT) showed an area of architectural distortion at the union of outer quadrants of the left breast without gynaecomastia. Triple assessment suggested performing a nipple-sparing mastectomy, which revealed the presence of a focal area of high-grade DCIS of 2 mm. DCIS, even of high grade, is difficult to detect with mammography and even more rare, especially when associated with other proliferative lesions. DBT with 2D synthetic reconstruction is useful as the imaging step of a triple assessment and it should be performed in both symptomatic and asymptomatic high-risk men to differentiate between malignant and benign lesions. We propose a diagnostic model to early detect breast cancer in men, optimizing resources according to efficiency, effectiveness and economy, and look forward to radiomics as a powerful tool to help radiologists.

Magnetic resonance quantification of non-Gaussian water diffusion in hepatic fibrosis staging: a pilot study of diffusion kurtosis imaging to identify reversible hepatic fibrosis

Background

This study aimed to evaluate the diagnostic accuracy of diffusion kurtosis imaging (DKI) in differentiating early hepatic fibrosis (HF) from normal liver and advanced HF in rabbits.

Methods

A total of 35 healthy New Zealand white rabbits were included in the study. A model of HF was established in 30 rabbits through subcutaneous injections of 50% carbon tetrachloride (CCl₄)/olive oil, while 5 rabbits received saline injections. The gradually increased doses of CCl₄ were 0.1, 0.2, and 0.3 mL/kg in weeks 1 to 3, weeks 4 to 6, and weeks 7 to 10, respectively. Two injections were given each week. Two rabbits in the experimental group died. All rabbits underwent DKI with three b values (0, 500, and 1,000 s/mm²) at week 5 (n=8), week 6 (n=9), week 7 (n=8), and week 10 (n=8). Approximately 2 liver lobes per rabbit were selected for histopathology. Mean diffusivity (MD) and mean kurtosis (MK) were calculated. Discrimination capacities of DKI parameters were analyzed and compared by receiver operating characteristic (ROC) analysis.

Results

The meta-analysis of histological data in viral hepatitis (METAVIR) scoring system was used to classify liver lobes into the control group (F0, n=0), early HF group (F1-F2, n=28), and advanced HF group (F3-F4, n=28). MD and MK values were significantly different among the three groups (all P<0.05). MD value was negatively correlated with increased fibrosis level, while MK value was positively correlated with increased fibrosis level (ρ=-0.540, 0.614; P<0.05). The area under ROC curves (AUCs) for MD and MK were 0.886 and 0.875, respectively, for characterization of F0 and F1-F2, and 0.975 and 0.957 for F0 and F3-F4. AUC for MK was 0.751 for characterization of F1-F2 and F3-F4. MD performed better than MK for characterization of F0 and F1-F2 as well as F0 and F3-F4. MK showed good differentiation performance between F1-F2 and F3-F4.

Conclusions

Our results showed that DKI contributed to discriminating reversible early HF from normal liver and advanced HF and as a result, showed promise for use in HF diagnosis.

Radiomic Analysis of Pharmacokinetic Heterogeneity Within Tumor Based on the Unsupervised Decomposition of Dynamic Contrast-Enhanced MRI for Predicting Histological Characteristics of Breast Cancer

BACKGROUND

Breast tumor heterogeneity is associated with histological characteristics. However, pharmacokinetic (PK) heterogeneity within tumor might merit further exploration.

PURPOSE

To enhance the predictive power of molecular subtypes, Ki-67, and tumor grade by analyzing PK heterogeneity within tumor based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).

STUDY TYPE

Retrospective.

POPULATION

Two hundred and eight biopsy-proven breast cancer patients, randomly divided into a training cohort (N = 144) and a testing cohort (N = 64).

FIELD STRENGTH/SEQUENCE

T₁ -weighted DCE-MRI at 3.0 T.

ASSESSMENT

A convex analysis of mixtures-compartmental modeling decomposition method was used to estimate the PK parameter (i.e., the volume transfer constant K^trans ) in tumor subregions with distinct physiological kinetic patterns, including fast-flow kinetics, slow-flow kinetics, and plasma input. Radiomic features based on the PK parameter were calculated from each tumor subregion.

STATISTICAL TESTS

The training cohort was used to build random forest classifiers based on the optimal features determined by the 5-fold cross-validation method. The performance was assessed on the testing cohort using the area under the receiver operating characteristic curve (AUC). The AUCs derived from the tumor subregion-based PK parameter were compared with those of the original images of the entire tumor using the DeLong test. A P-value of <0.05 was considered statistically significant.

RESULTS

The tumor subregion-based PK parameter, which yielded the highest AUCs of 0.8782, 0.7568, 0.7019, 0.7963, 0.8080, and 0.7375 for luminal A, luminal B, basal-like, human epidermal growth factor receptor 2, Ki-67, and tumor grade, respectively, obtained better diagnostic performance than the original images in the entire tumor (highest AUCs = 0.8612, 0.6191, 0.5593, 0.7704, 0.7494, and 0.6261, respectively). In particular, statistically significant improvement in the diagnostic performance was obtained for luminal B.

DATA CONCLUSION

Radiomic analysis of PK heterogeneity within tumor can enhance the predictive performance of radiomic models compared with that of the entire tumor.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY STAGE: 3.

Peptide-Based Drug Delivery Systems

Peptide-based drug delivery systems have many advantages when compared to synthetic systems in that they have better biocompatibility, biochemical and biophysical properties, lack of toxicity, controlled molecular weight via solid phase synthesis and purification. Lysosomes, solid lipid nanoparticles, dendrimers, polymeric micelles can be applied by intravenous administration, however they are of artificial nature and thus may induce side effects and possess lack of ability to penetrate the blood-brain barrier. An analysis of nontoxic drug delivery systems and an establishment of prospective trends in the development of drug delivery systems was needed. This review paper summarizes data, mainly from the past 5 years, devoted to the use of peptide-based carriers for delivery of various toxic drugs, mostly anticancer or drugs with limiting bioavailability. Peptide-based drug delivery platforms are utilized as peptide–drug conjugates, injectable biodegradable particles and depots for delivering small molecule pharmaceutical substances (500 Da) and therapeutic proteins. Controlled drug delivery systems that can effectively deliver anticancer and peptide-based drugs leading to accelerated recovery without significant side effects are discussed. Moreover, cell penetrating peptides and their molecular mechanisms as targeting peptides, as well as stimuli responsive (enzyme-responsive and pH-responsive) peptides and peptide-based self-assembly scaffolds are also reviewed.

Deep learning-based identification of acute ischemic core and deficit from non-contrast CT and CTA

The accurate identification of irreversible infarction and salvageable tissue is important in planning the treatments for acute ischemic stroke (AIS) patients. Computed tomographic perfusion (CTP) can be used to evaluate the ischemic core and deficit, covering most of the territories of anterior circulation, but many community hospitals and primary stroke centers do not have the capability to perform CTP scan in emergency situation. This study aimed to identify AIS lesions from widely available non-contrast computed tomography (NCCT) and CT angiography (CTA) using deep learning. A total of 345AIS patients from our emergency department were included. A multi-scale 3D convolutional neural network (CNN) was used as the predictive model with inputs of NCCT, CTA, and CTA+ (8 s delay after CTA) images. An external cohort with 108 patients was included to further validate the generalization performance of the proposed model. Strong correlations with CTP-RAPID segmentations (r = 0.84 for core, r = 0.83 for deficit) were observed when NCCT, CTA, and CTA+ images were all used in the model. The diagnostic decisions according to DEFUSE3 showed high accuracy when using NCCT, CTA, and CTA+ (0.90±0.04), followed by the combination of NCCT and CTA (0.87±0.04), CTA-alone (0.76±0.06), and NCCT-alone (0.53±0.09).

Radiomics-based machine learning analysis and characterization of breast lesions with multiparametric diffusion-weighted MR

Background

This study aimed to evaluate the utility of radiomics-based machine learning analysis with multiparametric DWI and to compare the diagnostic performance of radiomics features and mean diffusion metrics in the characterization of breast lesions.

Methods

This retrospective study included 542 lesions from February 2018 to November 2018. One hundred radiomics features were computed from mono-exponential (ME), biexponential (BE), stretched exponential (SE), and diffusion-kurtosis imaging (DKI). Radiomics-based analysis was performed by comparing four classifiers, including random forest (RF), principal component analysis (PCA), L1 regularization (L1R), and support vector machine (SVM). These four classifiers were trained on a training set with 271 patients via ten-fold cross-validation and tested on an independent testing set with 271 patients. The diagnostic performance of the mean diffusion metrics of ME (mADC_{all b}, mADC_0–1000), BE (mD, mD^*, mf), SE (mDDC, mα), and DKI (mK, mD) were also calculated for comparison. The area under the receiver operating characteristic curve (AUC) was used to compare the diagnostic performance.

Results

RF attained higher AUCs than L1R, PCA and SVM. The AUCs of radiomics features for the differential diagnosis of breast lesions ranged from 0.80 (BE_D*) to 0.85 (BE_D). The AUCs of the mean diffusion metrics ranged from 0.54 (BE_mf) to 0.79 (ME_mADC_0–1000). There were significant differences in the AUCs between the mean values of all diffusion metrics and radiomics features of AUCs (all P < 0.001) for the differentiation of benign and malignant breast lesions. Of the radiomics features computed, the most important sequence was BE_D (AUC: 0.85), and the most important feature was FO-10 percentile (Feature Importance: 0.04).

Conclusions

The radiomics-based analysis of multiparametric DWI by RF enables better differentiation of benign and malignant breast lesions than the mean diffusion metrics.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12967-021-03117-5.

Machine Learning: Applications and Advanced Progresses of Radiomics in Endocrine Neoplasms

Endocrine neoplasms remain a great threat to human health. It is extremely important to make a clear diagnosis and timely treatment of endocrine tumors. Machine learning includes radiomics, which has long been utilized in clinical cancer research. Radiomics refers to the extraction of valuable information by analyzing a large amount of standard data with high-throughput medical images mainly including computed tomography, positron emission tomography, magnetic resonance imaging, and ultrasound. With the quantitative imaging analysis and model building, radiomics can reflect specific underlying characteristics of a disease that otherwise could not be evaluated visually. More and more promising results of radiomics in oncological practice have been seen in recent years. Radiomics may have the potential to supplement traditional imaging analysis and assist in providing precision medicine for patients. Radiomics had developed rapidly in endocrine neoplasms practice in the past decade. In this review, we would introduce the general workflow of radiomics and summarize the applications and developments of radiomics in endocrine neoplasms in recent years. The limitations of current radiomic research studies and future development directions would also be discussed.

Radiomics Signatures Based on Multiparametric MRI for the Preoperative Prediction of the HER2 Status of Patients with Breast Cancer

OBJECTIVES

The aim of our study was to preoperatively predict the human epidermal growth factor receptor 2 (HER2) status of patients with breast cancer using radiomics signatures based on single-parametric and multiparametric magnetic resonance imaging (MRI).

METHODS

Three hundred six patients with invasive ductal carcinoma of no special type (IDC-NST) were retrospectively enrolled. Quantitative imaging features were extracted from fat-suppressed T2-weighted and dynamic contrast-enhanced T1 weighted (DCE-T1) preoperative MRI. Then, three radiomics signatures based on fat-suppressed T2-weighted images, DCE-T1 images and their combination were developed using a support vector machine (SVM) to predict the HER2-positive vs HER2-negative status of patients with breast cancer. The area under the curve (AUC), accuracy, sensitivity, and specificity were calculated to assess the predictive performances of the signatures.

RESULTS

Twenty-eight quantitative radiomics features, namely, 14 texture features, 4 first-order features, 9 wavelet features, and 1 shape feature, were used to construct radiomics signatures. The performance of the radiomics signatures for distinguishing HER2-positive from HER2-negative breast cancer based on fat-suppressed T2-weighted images, DCE-T1 images, and their combination had an AUC of 0.74 (95% confidence interval [CI], 0.700 to 0.770), 0.71 (0.673 to 0.738), and 0.86 (0.832 to 0.882) in the primary cohort and 0.70 (0.666 to 0.744), 0.68 (0.650 to 0.726), and 0.81 (0.776 to 0.837) in the validation cohort, respectively.

CONCLUSION

Radiomics signatures based on multiparametric MRI represent a potential and efficient alternative tool to evaluate the HER2 status in patients with breast cancer.

The State of the Art of Theranostic Nanomaterials for Lung, Breast, and Prostate Cancers

The synthesis and engineering of nanomaterials offer more robust systems for the treatment of cancer, with technologies that combine therapy with imaging diagnostic tools in the so-called nanotheranostics. Among the most studied systems, there are quantum dots, liposomes, polymeric nanoparticles, inorganic nanoparticles, magnetic nanoparticles, dendrimers, and gold nanoparticles. Most of the advantages of nanomaterials over the classic anticancer therapies come from their optimal size, which prevents the elimination by the kidneys and enhances their permeation in the tumor due to the abnormal blood vessels present in cancer tissues. Furthermore, the drug delivery and the contrast efficiency for imaging are enhanced, especially due to the increased surface area and the selective accumulation in the desired tissues. This property leads to the reduced drug dose necessary to exert the desired effect and for a longer action within the tumor. Finally, they are made so that there is no degradation into toxic byproducts and have a lower immune response triggering. In this article, we intend to review and discuss the state-of-the-art regarding the use of nanomaterials as therapeutic and diagnostic tools for lung, breast, and prostate cancer, as they are among the most prevalent worldwide.

Intravoxel Incoherent Motion Diffusion-Weighted Imaging for Predicting and Monitoring the Response of Anti-Angiogenic Treatment in the Orthotopic Nude Mouse Model of Lung Adenocarcinoma

BACKGROUND

The treatment efficacy of angiogenesis inhibitor could be underestimated at an early stage based on tumor volume changes. Intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI) can quantitatively assess tumors at the cellular level, but it is unclear whether it can provide useful information for assessing treatment response of anti-angiogenic treatment for lung adenocarcinoma.

PURPOSE

To determine the use of IVIM-DWI for non-invasive monitoring of the early response to anti-angiogenic treatment in the orthotopic transplantation of lung adenocarcinoma model.

STUDY TYPE

Prospective.

POPULATION

Thirty-seven nude mice were randomized into two groups: treatment group (received bevacizumab + cisplatin, N = 20) and control group (received saline, N = 17).

FIELD STRENGTH/SEQUENCE

Single-shot turbo spin-echo (TSE) IVIM-DWI, TSE T2-weighted imaging at 3.0 T.

ASSESSMENT

Tumor volume, IVIM parameters (apparent diffusion coefficient [ADC], diffusivity [D], perfusion fraction [f], and pseudo-diffusion coefficient [D*]) were measured before and 2 hours, 3, 7, 10 and 14 days after treatment. Regions of interest were manually drawn along the inner edge of the tumor by two radiologists with 5 and 10-year experience in magnetic resonance imaging. Pathological examinations (hematoxylin and eosin stain, cluster of differentiation 34) were performed.

STATISTICAL TESTS

Kolmogorov-Smirnov test, repeated-measure two-way analysis of variance test, Mann-Whitney U test, Pearson correlation analysis, receiver operating characteristic curve. P < 0.05 was considered statistically significant.

RESULTS

The tumor volume of the two groups was significantly different only on day 14 (control group vs. treatment group, 43.15 ± 18.28 mm³ vs. 28.41 ± 1.71 mm³ ). ADC_2h , ADC_10d , D_2h , D_7d , D_10d , and D_14d were significantly higher, while f_10d and f_14d were significantly lower in the treatment group compared to those of the control group. Both the △ADC_2h (r = -0.631) and △D_2h (r = -0.700) showed moderate correlations with the relative tumor volume on day 14.

DATA CONCLUSION

IVIM has the potential to predict and monitor the early response to anti-angiogenic treatment, earlier than size changes, for lung adenocarcinoma.

LEVEL OF EVIDENCE

2 TECHNICAL EFFICACY: Stage 4.

Quantitative diffusion MRI of the abdomen and pelvis

Diffusion MRI has enormous potential and utility in the evaluation of various abdominal and pelvic disease processes including cancer and noncancer imaging of the liver, prostate, and other organs. Quantitative diffusion MRI is based on acquisitions with multiple diffusion encodings followed by quantitative mapping of diffusion parameters that are sensitive to tissue microstructure. Compared to qualitative diffusion-weighted MRI, quantitative diffusion MRI can improve standardization of tissue characterization as needed for disease detection, staging, and treatment monitoring. However, similar to many other quantitative MRI methods, diffusion MRI faces multiple challenges including acquisition artifacts, signal modeling limitations, and biological variability. In abdominal and pelvic diffusion MRI, technical acquisition challenges include physiologic motion (respiratory, peristaltic, and pulsatile), image distortions, and low signal-to-noise ratio. If unaddressed, these challenges lead to poor technical performance (bias and precision) and clinical outcomes of quantitative diffusion MRI. Emerging and novel technical developments seek to address these challenges and may enable reliable quantitative diffusion MRI of the abdomen and pelvis. Through systematic validation in phantoms, volunteers, and patients, including multicenter studies to assess reproducibility, these emerging techniques may finally demonstrate the potential of quantitative diffusion MRI for abdominal and pelvic imaging applications.

[A diffusion-weighted image denoising algorithm using HOSVD combined with Rician noise corrected model]

OBJECTIVE

To propose a novel diffusion-weighted (DW) image denoising algorithm based on HOSVD to improve the signal-to-noise ratio (SNR) of DW images and the accuracy of subsequent quantization parameters.

METHODS

This HOSVDbased denoising method incorporated the sparse constraint and noise-correction model. The signal expectations with Rician noise were integrated into the traditional HOSVD denoising framework for direct denoising of the DW images with Rician noise. HOSVD denoising was performed directly on each local DW image block to avoid the stripe artifacts. We compared the proposed method with 4 image denoising algorithms (LR + Edge, GL-HOSVD, BM3D and NLM) to verify the effect of the proposed method.

RESULTS

The experimental results showed that the proposed method effectively reduced the noise of DW images while preserving the image details and edge structure information. The proposed algorithm was significantly better than LR +Edge, BM3D and NLM in terms of quantitative metrics of PSNR, SSIM and FA-RMSE and in visual evaluation of denoising images and FA images. GL-HOSVD obtained good denoising results but introduced stripe artifacts at a high noise level during the denoising process. In contrast, the proposed method achieved good denoising results without causing stripe artifacts.

CONCLUSION

This HOSVD-based denoising method allows direct processing of DW images with Rician noise without introducing artifacts and can provide accurate quantitative parameters for diagnostic purposes.

Application of Diffusion Kurtosis Imaging and Dynamic Contrast-Enhanced Magnetic Resonance Imaging in Differentiating Benign and Malignant Head and Neck Lesions

BACKGROUND

Preoperative differentiation of head and neck lesions is important for treatment plan selection.

PURPOSE

To evaluate the diagnostic value of diffusion kurtosis imaging (DKI) and dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in differentiating benign from malignant head and neck lesions and subgroups, including lymphoma subgroup (LS), Warthin's tumor subgroup (WS), malignant tumor subgroup (excluding lymphoma) (MTS), and benign tumor subgroup (excluding Warthin's tumor) (BTS).

STUDY TYPE

Retrospective.

POPULATION

Seventy-four patients with 79 head and neck lesions (44 benign, 35 malignant), divided into four subgroups: LS (14), WS (12), MTS (21), and BTS (32).

FIELD STRENGTH/SEQUENCES

A 3.0 T, single-shot echo-planar sequence with 5 b-values for DKI and enhanced T1 high-resolution isotropic volume excitation (eTHRIVE) sequence for DCE-MRI.

ASSESSMENT

The mean diffusivity (MD) and mean kurtosis (MK) derived from DKI and the time-signal intensity curve (TIC), peak time (T_peak ), and washout ratio (WR) based on DCE-MRI were measured. The diagnostic efficiencies of DKI and DCE-MRI, alone and in combination, were calculated and compared. The parameters mentioned above were compared between the four subgroups.

STATISTICAL TEST

Mann-Whitney U test, chi-square test, receiver operating characteristic curve, Delong test, one-way analysis of variance test, and Kruskal-Wallis H test. A P value < 0.05 was considered statistically significant.

RESULTS

The combination of TIC and parameters of DKI and DCE-MRI for differentiating benign and malignant lesions with 94.94% accuracy is superior to DKI or DCE-MRI alone with approximately 75% accuracy. MD, MK, T_peak , and WR showed significant differences among the four subgroups. The accuracy of MD and MK was 91.14% and 92.41% for differentiating BTS from the other three subgroups. WR achieved 100% accuracy for discriminating WS from LS or MTS. MD and MK both differentiated LS from MTS with 97.14% accuracy.

DATA CONCLUSION

A combination of DKI and DCE-MRI can effectively differentiate head and neck lesions with good accuracy.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Evaluation of peripheral nerve acute crush injury in rabbits: comparison among diffusion kurtosis imaging, diffusion tensor imaging and electromyography

OBJECTIVE

Diffusion kurtosis imaging (DKI) has been proven to provide additional value for assessing many central nervous system diseases compared with conventional diffusion tensor imaging (DTI); however, whether it has the same value in peripheral nerve injury is unclear. This study aimed to investigate the performance of DKI, DTI, and electromyography (EMG) in evaluating peripheral nerve crush injury (PNCI) in rabbits.

MATERIALS AND METHODS

A total of 27 New Zealand white rabbits were selected to establish a PNCI model. Longitudinal DTI, DKI, and EMG were evaluated before surgery and 1 day, 3 days, 1 week, 2 weeks, 4 weeks, 6 weeks, and 8 weeks after surgery. At each time point, two rabbits were randomly selected for pathological examination.

RESULTS

The results showed that fractional anisotropy (FA) derived from both DKI and DTI demonstrated a significant difference between injured and control nerves at all time points (all P < 0.005) mean kurtosis of the injured nerve was lower than that on the control side after 2-8 weeks (all P < 0.05). No statistically significant difference was found in radial kurtosis, axial kurtosis, and apparent diffusion coefficient at almost every time point. The difference in compound muscle action potential (CMAP) of the bilateral gastrocnemius at each time point was statistically significant (all P < 0.001).

CONCLUSIONS

CMAP was a sensitive and reliable method to assess acute PNCI without being affected by perineural edema. DKI may not be superior to DTI in evaluating peripheral nerves, DTI with a shorter scanning time was preferred as an effective choice for evaluating acute peripheral nerve traumatic injury.

Volumetric CT Texture Analysis of Intrahepatic Mass-Forming Cholangiocarcinoma for the Prediction of Postoperative Outcomes: Fully Automatic Tumor Segmentation Versus Semi-Automatic Segmentation

Objective

To determine whether volumetric CT texture analysis (CTTA) using fully automatic tumor segmentation can help predict recurrence-free survival (RFS) in patients with intrahepatic mass-forming cholangiocarcinomas (IMCCs) after surgical resection.

Materials and Methods

This retrospective study analyzed the preoperative CT scans of 89 patients with IMCCs (64 male; 25 female; mean age, 62.1 years; range, 38–78 years) who underwent surgical resection between January 2005 and December 2016. Volumetric CTTA of IMCCs was performed in late arterial phase images using both fully automatic and semi-automatic liver tumor segmentation techniques. The time spent on segmentation and texture analysis was compared, and the first-order and second-order texture parameters and shape features were extracted. The reliability of CTTA parameters between the techniques was evaluated using intraclass correlation coefficients (ICCs). Intra- and interobserver reproducibility of volumetric CTTAs were also obtained using ICCs. Cox proportional hazard regression were used to predict RFS using CTTA parameters and clinicopathological parameters.

Results

The time spent on fully automatic tumor segmentation and CTTA was significantly shorter than that for semi-automatic segmentation: mean ± standard deviation of 1 minutes 37 seconds ± 50 seconds vs. 10 minutes 48 seconds ± 13 minutes 44 seconds (p < 0.001). ICCs of the texture features between the two techniques ranged from 0.215 to 0.980. ICCs for the intraobserver and interobserver reproducibility using fully automatic segmentation were 0.601–0.997 and 0.177–0.984, respectively. Multivariable analysis identified lower first-order mean (hazard ratio [HR], 0.982; p = 0.010), larger pathologic tumor size (HR, 1.171; p < 0.001), and positive lymph node involvement (HR, 2.193; p = 0.014) as significant parameters for shorter RFS using fully automatic segmentation.

Conclusion

Volumetric CTTA parameters obtained using fully automatic segmentation could be utilized as prognostic markers in patients with IMCC, with comparable reproducibility in significantly less time compared with semi-automatic segmentation.

Staging Liver Fibrosis: Comparison of Native T1 Mapping, T2 Mapping, and T1ρ: An Experimental Study in Rats With Bile Duct Ligation and Carbon Tetrachloride at 11.7 T MRI

BACKGROUND

T1, T2, and T1ρ might be potential biomarkers for assessing liver fibrosis. However, few studies reported the value of them in different animal models.

PURPOSE

To investigate and compare the performances of T1, T2, and T1ρ for noninvasively staging liver fibrosis in bile duct ligation (BDL) or carbon tetrachloride (CCl₄ ) model.

STUDY TYPE

Prospective animal model.

SUBJECTS

Liver fibrosis was induced by BDL or injection of CCl₄ in 120 rats.

FIELD STRENGTH/SEQUENCE

11.7 T, T1 mapping with 10 repetition times, T2 mapping with 32 echo times, and T1ρ with 10 spin-lock times.

ASSESSMENT

T1, T2, and T1ρ were measured and correlated with liver fibrosis stages, as well as the degree of inflammation, steatosis, iron deposition, and the expression of cytokeratin 19. The discriminative performance of T1, T2, and T1ρ for staging liver fibrosis was compared.

STATISTICAL TESTS

One-way analysis of variance (ANOVA), Spearman's correlation analysis, factorial design ANOVA, and receiver operating characteristic curves (P < 0.05 was considered statistically significant).

RESULTS

T1, T2, and T1ρ (BDL: rho = 0.73, 0.85, 0.68; CCl₄ : rho = 0.80, 0.29, 0.61) were significantly correlated with liver fibrosis stages, while there was no significant difference in T2 among stage F0-F4 in the CCl₄ model (P = 0.204). The area under the curves (AUCs) range of T1, T2, and T1ρ for predicting ≥F1, ≥F2, ≥F3, and F4 were 0.76-0.95, 0.89-0.98, and 0.80-0.94 in the CCl₄ model. For the CCl₄ model, the AUCs range of T1, T2, and T1ρ for predicting ≥F1, ≥F2, ≥F3, and F4 were 0.83-0.95, 0.61-0.74, and 0.73-0.89, respectively. T2 had significantly higher AUC in the BDL model than CCl₄ model for diagnosing liver fibrosis.

DATA CONCLUSION

The most sensitive and accurate method for staging liver fibrosis appeared to be T1 in our animal models followed by T1ρ. T2 may not be suitable for evaluating liver fibrosis.

LEVEL OF EVIDENCE

1 TECHNICAL EFFICACY STAGE: 2.

Continuous diffusion spectrum computation for diffusion-weighted magnetic resonance imaging of the kidney tubule system

Background

The use of rigid multi-exponential models (with a priori predefined numbers of components) is common practice for diffusion-weighted MRI (DWI) analysis of the kidney. This approach may not accurately reflect renal microstructure, as the data are forced to conform to the a priori assumptions of simplified models. This work examines the feasibility of less constrained, data-driven non-negative least squares (NNLS) continuum modelling for DWI of the kidney tubule system in simulations that include emulations of pathophysiological conditions.

Methods

Non-linear least squares (LS) fitting was used as reference for the simulations. For performance assessment, a threshold of 5% or 10% for the mean absolute percentage error (MAPE) of NNLS and LS results was used. As ground truth, a tri-exponential model using defined volume fractions and diffusion coefficients for each renal compartment (tubule system: D_tubules , f_tubules ; renal tissue: D_tissue , f_tissue ; renal blood: D_blood , f_blood ;) was applied. The impact of: (I) signal-to-noise ratio (SNR) =40-1,000, (II) number of b-values (n=10-50), (III) diffusion weighting (b-range_small =0-800 up to b-range_large =0-2,180 s/mm²), and (IV) fixation of the diffusion coefficients D_tissue and D_blood was examined. NNLS was evaluated for baseline and pathophysiological conditions, namely increased tubular volume fraction (ITV) and renal fibrosis (10%: grade I, mild) and 30% (grade II, moderate).

Results

NNLS showed the same high degree of reliability as the non-linear LS. MAPE of the tubular volume fraction (f_tubules ) decreased with increasing SNR. Increasing the number of b-values was beneficial for f_tubules precision. Using the b-range_large led to a decrease in MAPE _ftubules compared to b-range_small. The use of a medium b-value range of b=0-1,380 s/mm² improved f_tubules precision, and further b_max increases beyond this range yielded diminishing improvements. Fixing D_blood and D_tissue significantly reduced MAPE _ftubules and provided near perfect distinction between baseline and ITV conditions. Without constraining the number of renal compartments in advance, NNLS was able to detect the (fourth) fibrotic compartment, to differentiate it from the other three diffusion components, and to distinguish between 10% vs. 30% fibrosis.

Conclusions

This work demonstrates the feasibility of NNLS modelling for DWI of the kidney tubule system and shows its potential for examining diffusion compartments associated with renal pathophysiology including ITV fraction and different degrees of fibrosis.

Value of Machine Learning with Multiphases CE-MRI Radiomics for Early Prediction of Pathological Complete Response to Neoadjuvant Therapy in HER2-Positive Invasive Breast Cancer

Background

To assess the value of radiomics based on multiphases contrast-enhanced magnetic resonance imaging (CE-MRI) for early prediction of pathological complete response (pCR) to neoadjuvant therapy (NAT) in patients with human epithelial growth factor receptor 2 (HER2) positive invasive breast cancer.

Methods

A total of 127 patients with newly diagnosed primary HER2 positive invasive breast cancer underwent CE-MRI before NAT and performed surgery after NAT. Radiomic features were extracted from the 1^st postcontrast CE-MRI phase (CE₁) and multi-phases CE-MRI (CE_m),respectively. With selected features using a forward stepwise regression, 23 machine learning classifiers based on CE₁ and CE_m were constructed respectively for differentiating pCR and non-pCR patients. The performances of classifiers were assessed and compared by their accuracy, sensitivity, specificity and AUC (area under curve). The optimal machine learning classification was used to discriminate pCR vs non-pCR in mass and non-mass groups, uni-focal and unilateral multi-focal groups, respectively.

Results

For the task of pCR classification, 6 radiomic features from CE₁ and 6 from CE_m were selected for the construction of machine learning models, respectively. The linear SVM based on CE_m outperformed the logistic regression model using CE₁ with an AUC of 0.84 versus 0.69. In mass and non-mass enhancement groups, the accuracy of linear SVM achieved 84% and 76%. Whereas in unifocal and unilateral multifocal cases, 79% and 75% accuracy were achieved by linear SVM.

Conclusion

Multiphases CE-MRI imaging may offer more heterogeneity information in the tumor and provide a non-invasive approach for early prediction of pCR to NAT in patients with HER2-positive invasive breast cancer.

Cathepsin B-Activated Fluorescent and Photoacoustic Imaging of Tumor

Early diagnosis is crucial to the treatment of cancer. Cathepsin B (CTB) plays an important role in numerous cancers, which is a promising biomarker for early diagnosis of cancer. It is necessary to exploit new probes for visualization of CTB in vivo. Fluorescent/photoacoustic (FL/PA) imaging is a powerful tool for in vivo study which possesses both excellent sensitivity and spatial resolution. To our knowledge, there has been no FL/PA probe to image CTB in vitro or in vivo. Therefore, we developed two CTB-activated FL/PA probes HCy-Cit-Val and HCy-Gly-Leu-Phe-Gly, which could successfully monitor CTB activity in vivo. Both two probes had excellent sensitivity and selectivity in vitro. Cell imaging showed that HCy-Cit-Val or HCy-Gly-Leu-Phe-Gly could image endogenous CTB in lysosome with 6.8-fold or 5.1-fold enhancement of the FL signal and 5.8-fold or 3.4-fold enhancement of the PA signal compared to their inhibitor contrast groups. Tumor imaging in vivo further confirmed the good applicability of these two probes to monitor CTB activity with high sensitivity and spatial resolution. Moreover, the property of HCy-Cit-Val is superior to HCy-Gly-Leu-Phe-Gly due to the higher catalytic efficiency of CTB toward HCy-Cit-Val than HCy-Gly-Leu-Phe-Gly. We envision that our FL/PA probe HCy-Cit-Val will be suitable for clinical early diagnosis of CTB-related cancer in the near future.

Recent Radiomics Advancements in Breast Cancer: Lessons and Pitfalls for the Next Future

Radiomics is an emerging translational field of medicine based on the extraction of high-dimensional data from radiological images, with the purpose to reach reliable models to be applied into clinical practice for the purposes of diagnosis, prognosis and evaluation of disease response to treatment. We aim to provide the basic information on radiomics to radiologists and clinicians who are focused on breast cancer care, encouraging cooperation with scientists to mine data for a better application in clinical practice. We investigate the workflow and clinical application of radiomics in breast cancer care, as well as the outlook and challenges based on recent studies. Currently, radiomics has the potential ability to distinguish between benign and malignant breast lesions, to predict breast cancer’s molecular subtypes, the response to neoadjuvant chemotherapy and the lymph node metastases. Even though radiomics has been used in tumor diagnosis and prognosis, it is still in the research phase and some challenges need to be faced to obtain a clinical translation. In this review, we discuss the current limitations and promises of radiomics for improvement in further research.

Computer-Aided Diagnosis Evaluation of the Correlation Between Magnetic Resonance Imaging With Molecular Subtypes in Breast Cancer

Background

There is a demand for additional alternative methods that can allow the differentiation of the breast tumor into molecular subtypes precisely and conveniently.

Purpose

The present study aimed to determine suitable optimal classifiers and investigate the general applicability of computer-aided diagnosis (CAD) to associate between the breast cancer molecular subtype and the extracted MR imaging features.

Methods

We analyzed a total of 264 patients (mean age: 47.9 ± 9.7 years; range: 19–81 years) with 264 masses (mean size: 28.6 ± 15.86 mm; range: 5–91 mm) using a Unet model and Gradient Tree Boosting for segmentation and classification.

Results

The tumors were segmented clearly by the Unet model automatically. All the extracted features which including the shape features,the texture features of the tumors and the clinical features were input into the classifiers for classification, and the results showed that the GTB classifier is superior to other classifiers, which achieved F1-Score 0.72, AUC 0.81 and score 0.71. Analyzed the different features combinations, we founded that the texture features associated with the clinical features are the optimal features to different the breast cancer subtypes.

Conclusion

CAD is feasible to differentiate the breast cancer subtypes, automatical segmentation were feasible by Unet model and the extracted texture features from breast MR imaging with the clinical features can be used to help differentiating the molecular subtype. Moreover, in the clinical features, BPE and age characteristics have the best potential for subtype.

Applicability of deep learning-based reconstruction trained by brain and knee 3T MRI to lumbar 1.5T MRI

Background

Several deep learning-based methods have been proposed for addressing the long scanning time of magnetic resonance imaging. Most are trained using brain 3T magnetic resonance images, but is unclear whether performance is affected when applying these methods to different anatomical sites and at different field strengths.

Purpose

To validate the denoising performance of deep learning-based reconstruction method trained by brain and knee 3T magnetic resonance images when applied to lumbar 1.5T magnetic resonance images.

Material and Methods

Using a 1.5T scanner, we obtained lumber T2-weighted sequences in 10 volunteers using three different scanning times: 228 s (standard), 119 s (double-fast), and 68 s (triple-fast). We compared the images obtained by the standard sequence with those obtained by the deep learning-based reconstruction-applied faster sequences.

Results

Signal-to-noise ratio values were significantly higher for deep learning-based reconstruction-double-fast than for standard and did not differ significantly between deep learning-based reconstruction-triple-fast and standard. Contrast-to-noise ratio values also did not differ significantly between deep learning-based reconstruction-triple-fast and standard. Qualitative scores for perceived signal-to-noise ratio and overall image quality were significantly higher for deep learning-based reconstruction-double fast and deep learning-based reconstruction-triple-fast than for standard. Average scores for sharpness, contrast, and structure visibility were equal to or higher for deep learning-based reconstruction-double-fast and deep learning-based reconstruction-triple-fast than for standard, but the differences were not statistically significant. The average scores for artifact were lower for deep learning-based reconstruction-double-fast and deep learning-based reconstruction-triple-fast than for standard, but the differences were not statistically significant.

Conclusion

The deep learning-based reconstruction method trained by 3T brain and knee images may reduce the scanning time of 1.5T lumbar magnetic resonance images by one-third without sacrificing image quality.

Comparative study of placental T2* and intravoxel incoherent motion in the prediction of fetal growth restriction

INTRODUCTION

Both transverse relaxation time (T2*) and intravoxel incoherent motion (IVIM) on magnetic resonance imaging (MRI) are promising for discriminating fetal growth restriction (FGR). We aimed to compare the utility of these two parameters and their combination in the same cohort.

METHODS

Twenty-seven FGR and 24 control pregnancies after 28 weeks of gestation in which both T2* and IVIM scans were performed on a 3.0 T MRI were recruited. We compared the T2* Z-score, perfusion fraction (f), diffusion coefficient (D) and pseudodiffusion coefficient (D*) between groups. Binary logistic regression analysis and areas under the curve (AUCs) with receiver operating characteristic (ROC) curve were used to evaluate the diagnostic efficacy of these parameters and their combination.

RESULTS

Compared with normal pregnancies, T2* Z-score (0.036 ± 0.95 vs. -2.479 ± 1.56, p < 0.001), f (0.2753 ± 0.035 vs. 0.3304 ± 0.035, p < 0.001), D* (48279.82 ± 7497.36 μm2/s vs. 56167.92 ± 8549.87 μm2/s, p = 0.001) and D (1664.32 ± 288.53 μm2/s vs. 1887.15 ± 204.08 μm2/s, p = 0.002) were significantly decreased in FGR pregnancies. However, only AUC(T2* Z-score) (0.903) and AUC(f) (0.873) were good predictors of FGR. The AUC(T2* Z-score-IVIM) (0.937), calculated with the combination of T2* Z-score and f, was similar to AUC(T2* Z-score) and ACU(f).

DISCUSSION

Both T2* and f were effective in discriminating FGR. However, the combination of the two parameters did not further improve diagnostic efficacy. We suggest that T2* might be more suitable for evaluating placental dysfunction, as it is fast to obtain and easy to measure.

Multifunctional theranostic nanoparticles for biomedical cancer treatments - A comprehensive review

Modern-day search for the novel agents (their preparation and consequent implementation) to effectively treat the cancer is mainly fuelled by the historical failure of the conventional treatment modalities. Apart from that, the complexities such as higher rate of cell mutations, variable tumor microenvironment, patient-specific disparities, and the evolving nature of cancers have made this search much stronger in the latest times. As a result of this, in about two decades, the theranostic nanoparticles (TNPs) - i.e., nanoparticles that integrate therapeutic and diagnostic characteristics - have been developed. The examples for TNPs include mesoporous silica nanoparticles, luminescence nanoparticles, carbon-based nanomaterials, metal nanoparticles, and magnetic nanoparticles. These TNPs have emerged as single and powerful cancer-treating multifunctional nanoplatforms, as they widely provide the necessary functionalities to overcome the previous/conventional limitations including lack of the site-specific delivery of anti-cancer drugs, and real-time continuous monitoring of the target cancer sites while performing therapeutic actions. This has been mainly possible due to the association of the as-developed TNPs with the already-available unique diagnostic (e.g., luminescence, photoacoustic, and magnetic resonance imaging) and therapeutic (e.g., photothermal, photodynamic, hyperthermia therapy) modalities in the biomedical field. In this review, we have discussed in detail about the recent developments on the aforementioned important TNPs without/with targeting ability (i.e., attaching them with ligands or tumor-specific antibodies) and also the strategies that are implemented to increase their tumor accumulation and to enhance their theranostic efficacies for effective biomedical cancer treatments.

Evaluation of Pancreatic Fibrosis Grading by Multi Parametric Quantitative Magnetic Resonance Imaging

BACKGROUND

Early detection and grading of pancreatic fibrosis (PF) are important and challenging clinical goals.

PURPOSE

To determine main pancreatic duct (MPD) diameter, pancreatic thickness, and grades of PF via magnetic resonance elastography (MRE), T1 mapping, and intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI), assessing respective diagnostic performances.

STUDY TYPE

Prospective.

SUBJECTS

Histopathologic and imaging records (MRE, T1 mapping, and IVIM-DWI) generated by 144 patients between December 2018 and May 2020 were collected for analysis. Grades of PF were distributed as follows: F0, 82; F1, 22; F2, 22; and F3, 18.

FIELD STRENGTH/SEQUENCE

3 T pancreatic MRI, encompassing MRE, T1 mapping, and IVIM-DWI.

ASSESSMENT

In all patients, T1 relaxation times, pancreatic stiffness values, IVIM-DWI parameters, MPD diameter, and pancreatic thickness were measured.

STATISTICAL TESTS

Receiver operating characteristic (ROC) analysis served to assess imaging parameters useful in diagnosing PF. To identify relations between specific parameters and grades of PF, logistic regression analysis was invoked.

RESULTS

Both pancreatic stiffness (r = 0.754; P < 0.001) and T1 relaxation time (r = 0.433; P < 0.001) correlated significantly with PF (%). To determine PF grades ≥F1, a combined model (area under the curve [AUC] = 0.906) performed significantly better than pancreatic stiffness (AUC = 0.855; P < 0.001) or T1 relaxation time (AUC = 0.754; P < 0.001) alone. For PF grades ≥F2 or grade F3, both the combined model (≥F2: AUC = 0.910; F3: AUC = 0.939) and pancreatic stiffness (≥F2: AUC = 0.906; F3: AUC = 0.929) outperformed T1 relaxation time (≥F2: AUC = 0.768 [P = 0.005 and P = 0.004, respectively]; F3: AUC = 0.816 [both P < 0.005]). All IVIM-DWI parameters generated AUC values <0.700.

DATA CONCLUSION

A combination of MRE and T1 mapping seems promising in diagnosing various grades of PF, particularly at an early stage.

LEVEL OF EVIDENCE

1 TECHNICAL EFFICACY: Stage 2.

Predicting the Level of Tumor-Infiltrating Lymphocytes in Patients With Breast Cancer: Usefulness of Mammographic Radiomics Features

Objectives

This study aimed to investigate whether radiomics classifiers from mammography can help predict tumor-infiltrating lymphocyte (TIL) levels in breast cancer.

Methods

Data from 121 consecutive patients with pathologically-proven breast cancer who underwent preoperative mammography from February 2018 to May 2019 were retrospectively analyzed. Patients were randomly divided into a training dataset (n = 85) and a validation dataset (n = 36). A total of 612 quantitative radiomics features were extracted from mammograms using the Pyradiomics software. Radiomics feature selection and radiomics classifier were generated through recursive feature elimination and logistic regression analysis model. The relationship between radiomics features and TIL levels in breast cancer patients was explored. The predictive capacity of the radiomics classifiers for the TIL levels was investigated through receiver operating characteristic curves in the training and validation groups. A radiomics score (Rad score) was generated using a logistic regression analysis method to compute the training and validation datasets, and combining the Mann–Whitney U test to evaluate the level of TILs in the low and high groups.

Results

Among the 121 patients, 32 (26.44%) exhibited high TIL levels, and 89 (73.56%) showed low TIL levels. The ER negativity (p = 0.01) and the Ki-67 negative threshold level (p = 0.03) in the low TIL group was higher than that in the high TIL group. Through the radiomics feature selection, six top-class features [Wavelet GLDM low gray-level emphasis (mediolateral oblique, MLO), GLRLM short-run low gray-level emphasis (craniocaudal, CC), LBP2D GLRLM short-run high gray-level emphasis (CC), LBP2D GLDM dependence entropy (MLO), wavelet interquartile range (MLO), and LBP2D median (MLO)] were selected to constitute the radiomics classifiers. The radiomics classifier had an excellent predictive performance for TIL levels both in the training and validation sets [area under the curve (AUC): 0.83, 95% confidence interval (CI), 0.738–0.917, with positive predictive value (PPV) of 0.913; AUC: 0.79, 95% CI, 0.615–0.964, with PPV of 0.889, respectively]. Moreover, the Rad score in the training dataset was higher than that in the validation dataset (p = 0.007 and p = 0.001, respectively).

Conclusion

Radiomics from digital mammograms not only predicts the TIL levels in breast cancer patients, but can also serve as non-invasive biomarkers in precision medicine, allowing for the development of treatment plans.

Nucleolin-Targeted Ratiometric Fluorescent Carbon Dots with a Remarkably Large Emission Wavelength Shift for Precise Imaging of Cathepsin B in Living Cancer Cells

As one of the most promising biomarkers for numerous malignant tumors, accurate and reliable reporting of Cathepsin B (CTSB) activity is of great significance to achieve efficient diagnosis of cancers at an early stage and predicting metastasis. Here, we report a vigorous ratiometric fluorescent method integrating a cancer-targeting recognition moiety with a remarkably large emission wavelength shift into a single matrix to report CTSB activity sensitively and specifically. As a proof of concept, we synthesized amine-rich carbon quantum dots (CQDs) with a blue fluorescence, which offered an efficient scaffolding to covalently assemble the nucleolin-targeting recognition nucleic acid aptamer AS1411 and a CTSB-cleavable peptide substrate Gly-Arg-Arg-Gly-Lys-Gly-Gly-Cys-COOH that tethered with a near-infrared (NIR) fluorophore chlorin e6 (Ce6-GRRGKGGC, Ce6-Pep), enabling a cancer-targeting and CTSB stimulus-responsive ratiometric nanoprobe AS1411-Ce6-CQDs. Owing to the efficient fluorescence resonance energy transfer (FRET) process from the CQDs to Ce6 inside the assembly of nanoprobe, the blue fluorescence of CQDs at ∼450 nm was remarkably quenched, along with an obvious NIR fluorescence enhancement of Ce6 at ∼650 nm. After selective entry into cancer cells via nucleolin-mediated endocytosis, the overexpressed CTSB in lysosome could cleave Ce6-Pep and trigger the Ce6 moiety dissociation from AS1411-Ce6-CQDs, thus leading to the termination of FRET process, achieving the efficient ratiometric fluorescence response toward endogenous CTSB with a remarkably large emission wavelength shift of ∼200 nm from NIR to blue emission region. Notably, the nanoprobe AS1411-Ce6-CQDs exhibited an excellent specificity for ratiometric fluorescent sensing of CTSB activity with an ultralow detection limit of 0.096 ng/mL, demonstrating its promising use for early precise cancer diagnosis in the near future.

Radiomics based on multiparametric MRI for extrathyroidal extension feature prediction in papillary thyroid cancer

BACKGROUND

To determine the predictive capability of MRI-based radiomics for extrathyroidal extension detection in papillary thyroid cancer (PTC) pre-surgically.

METHODS

The present retrospective trial assessed individuals with thyroid nodules examined by multiparametric MRI and subsequently administered thyroid surgery. Diagnosis and extrathyroidal extension (ETE) feature of PTC were based on pathological assessment. The thyroid tumors underwent manual segmentation, for radiomic feature extraction. Participants were randomized to the training and testing cohorts, at a ratio of 7:3. The mRMR (maximum correlation minimum redundancy) algorithm and the least absolute shrinkage and selection operator were utilized for radiomics feature selection. Then, a radiomics predictive model was generated via a linear combination of the features. The model's performance in distinguishing the ETE feature of PTC was assessed by analyzing the receiver operating characteristic curve.

RESULTS

Totally 132 patients were assessed in this study, including 92 and 40 in the training and test cohorts, respectively). Next, the 16 top-performing features, including 4, 7 and 5 from diffusion weighted (DWI), T2-weighted (T2 WI), and contrast-enhanced T1-weighted (CE-T1WI) images, respectively, were finally retained to construct the radiomics signature. There were 8 RLM, 5 CM, 2 shape, and 1 SZM features. The radiomics prediction model achieved AUCs of 0.96 and 0.87 in the training and testing sets, respectively.

CONCLUSIONS

Our study indicated that MRI radiomics approach had the potential to stratify patients based on ETE in PTCs preoperatively.

Recent Advances in Photodynamic Therapy for Deep-Seated Tumors with the Aid of Nanomedicine

Photodynamic therapy (PDT) works through photoactivation of a specific photosensitizer (PS) in a tumor in the presence of oxygen. PDT is widely applied in oncology to treat various cancers as it has a minimally invasive procedure and high selectivity, does not interfere with other treatments, and can be repeated as needed. A large amount of reactive oxygen species (ROS) and singlet oxygen is generated in a cancer cell during PDT, which destroys the tumor effectively. However, the efficacy of PDT in treating a deep-seated tumor is limited due to three main reasons: Limited light penetration depth, low oxygen concentration in the hypoxic core, and poor PS accumulation inside a tumor. Thus, PDT treatments are only approved for superficial and thin tumors. With the advancement of nanotechnology, PDT to treat deep-seated or thick tumors is becoming a reachable goal. In this review, we provide an update on the strategies for improving PDT with nanomedicine using different sophisticated-design nanoparticles, including two-photon excitation, X-ray activation, targeting tumor cells with surface modification, alteration of tumor cell metabolism pathways, release of therapeutic gases, improvement of tumor hypoxia, and stimulation of host immunity. We focus on the difficult-to-treat pancreatic cancer as a model to demonstrate the influence of advanced nanomedicine in PDT. A bright future of PDT application in the treatment of deep-seated tumors is expected.

Prediction of muscle invasion of bladder cancer: A comparison between DKI and conventional DWI

OBJECTIVES

To prospectively compare the diagnostic efficacy of conventional diffusion-weighted imaging (DWI) and diffusion kurtosis imaging (DKI) in differentiating between muscle-invasive bladder cancer (MIBC) and non-muscle-invasive bladder cancer (NMIBC).

METHODS

Multiple b value DWIs were performed using a 3-T magnetic resonance (MR) imaging unit in fifty-one patients with bladder cancer including MIBC and NMIBC confirmed by histopathological findings. DWI data were postprocessed using mono-exponential and DKI models to calculate the apparent diffusion coefficient (ADC), apparent diffusional kurtosis (K_app), and kurtosis-corrected diffusion coefficient (D_app). Receiver-operating characteristic (ROC) analysis was performed to compare the diagnostic efficacy of all diffusion parameters.

RESULTS

All parameters differed significantly between MIBC and NIMBC including increased K_app, decreased D_app and ADC (all p < 0.001). Only the combination of D_app and K_app was significantly higher than ADC (p < 0.05), whilst D_app and K_app were not statistically different from ADC.

CONCLUSIONS

Both conventional DWI and DKI models are beneficial in differentiating between MIBC and NMIBC, whilst the combination of D_app and K_app can produce a more robust value than conventional ADC value in evaluating aggressiveness of bladder cancer.

Deep Learning-Based Denoising for High b-Value at 2000 s/mm2 Diffusion-Weighted Imaging

Diffusion-weighted imaging (DWI) allows white matter quantification of the white matter tracts of the brain. However, at a high b-value (≥ 2000 s/mm2), DWI acquisition suffers from noise due to longer acquisition times obscuring white matter interpretation. DWI denoising techniques can be used to acquire high b-value DWI without increasing the number of signal averages. We used a residual learning-based convolutional neural network (DnCNN) to reduce noise in high b-value DWI based on the literature review. We applied the proposed denoising method on high b-value, retrospectively collected DWI data with multiple noise levels. Experimental results show an improved image quality after denoising in retrospective DWI (average PSNR before and after denoising: 27.63 ± 1.06 dB and 51.76 ± 1.95 dB, respectively). The prospective DWI included one and two signal averages for denoising. DWI with four signal averages was used as the reference. Representative images show high b-value prospective DW images denoised using the DnCNN. We demonstrated DnCNN for cases of multiple noise levels and signal averages. For the prospective study, the PSNR values for 1-NEX before and after denoising were 27.39 ± 3.75 dB and 27.68 ± 3.75 dB. For 2-NEX, the PSNR values before and after denoising were 27.51 ± 4.18 dB and 27.75 ± 4.05 dB.

Facile Synthesis of Melanin-Dye Nanoagent for NIR-II Fluorescence/Photoacoustic Imaging-Guided Photothermal Therapy

Background

Laryngeal cancer is the second most common type of primary epithelial malignant tumor in the head and neck region, and the development of therapies that are more precise, efficient, and safe is necessary to preserve patient speech and swallowing functions as much as possible. Multi-modal imaging-guided photothermal therapy (PTT) can precisely delineate tumors, monitor the real-time accumulation of photothermal agents at the tumor site, accurately select the optimal region for irradiation, and predict the best time for laser treatment. Compared with exogeneous photothermal agents, endogenous melanin materials have better biosafety in vivo, in terms of native biocompatibility and biodegradability, as well as good near-infrared (NIR) absorbance. An NIR-II dye can be attached to melanin via a facile method, and applying a melanin-dye-based nanoprobe could be an excellent choice for the elimination of superficial laryngeal cancer while avoiding total laryngectomy.

Methods

In this work, a promising nanoprobe was constructed using a facile EDC/NHS strategy involving an NIR-II dye and melanin nanoparticles.

Results

The nanoprobe exhibited good water solubility, dispersibility, strong NIR-II fluorescence and photoacoustic (PA) signals, and higher photothermal performance. Cellular studies showed that the nanoprobe had low toxicity, excellent biocompatibility, and significantly enhanced imaging properties. After the nanoprobe was intravenously injected into Hep-2 laryngeal xenografts, superior dual-modal images were obtained at various time points, which revealed that the optimal photothermal treatment time was 8 h. Subsequently, PTT was carried out in vivo, and laryngeal tumors were completely eliminated after laser irradiation without any obvious side effects.

Conclusion

These results indicate the immense potential of nanoprobes for the NIR-II fluorescence/PA imaging-guided photothermal therapy of laryngeal cancer.

Prediction of the clinicopathological subtypes of breast cancer using a fisher discriminant analysis model based on radiomic features of diffusion-weighted MRI

BACKGROUND

The clinicopathological classification of breast cancer is proposed according to therapeutic purposes. It is simplified and can be conducted easily in clinical practice, and this subtyping undoubtedly contributes to the treatment selection of breast cancer. This study aims to investigate the feasibility of using a Fisher discriminant analysis model based on radiomic features of diffusion-weighted MRI for predicting the clinicopathological subtypes of breast cancer.

METHODS

Patients who underwent breast magnetic resonance imaging were confirmed by retrieving data from our institutional picture archiving and communication system (PACS) between March 2013 and September 2017. Five clinicopathological subtypes were determined based on the status of ER, PR, HER2 and Ki-67 from the immunohistochemical test. The radiomic features of diffusion-weighted imaging were derived from the volume of interest (VOI) of each tumour. Fisher discriminant analysis was performed for clinicopathological subtyping by using a backward selection method. To evaluate the diagnostic performance of the radiomic features, ROC analyses were performed to differentiate between immunohistochemical biomarker-positive and -negative groups.

RESULTS

A total of 84 radiomic features of four statistical methods were included after preprocessing. The overall accuracy for predicting the clinicopathological subtypes was 96.4% by Fisher discriminant analysis, and the weighted accuracy was 96.6%. For predicting diverse clinicopathological subtypes, the prediction accuracies ranged from 92 to 100%. According to the cross-validation, the overall accuracy of the model was 82.1%, and the accuracies of the model for predicting the luminal A, luminal B_HER2-, luminal B_HER2+, HER2 positive and triple negative subtypes were 79, 77, 88, 92 and 73%, respectively. According to the ROC analysis, the radiomic features had excellent performance in differentiating between different statuses of ER, PR, HER2 and Ki-67.

CONCLUSIONS

The Fisher discriminant analysis model based on radiomic features of diffusion-weighted MRI is a reliable method for the prediction of clinicopathological breast cancer subtypes.

Multi-parametric MRI lesion heterogeneity biomarkers for breast cancer diagnosis

PURPOSE

To identify intra-lesion imaging heterogeneity biomarkers in multi-parametric Magnetic Resonance Imaging (mpMRI) for breast lesion diagnosis.

METHODS

Dynamic Contrast Enhanced (DCE) and Diffusion Weighted Imaging (DWI) of 73 female patients, with 85 histologically verified breast lesions were acquired. Non-rigid multi-resolution registration was utilized to spatially align sequences. Four (4) DCE (2^nd post-contrast frame, Initial-Enhancement, Post-Initial-Enhancement and Signal-Enhancement-Ratio) and one (1) DWI (Apparent-Diffusion-Coefficient) representations were analyzed, considering a representative lesion slice. 11 1^st-order-statistics and 16 texture features (Gray-Level-Co-occurrence-Matrix (GLCM) and Gray-Level-Run-Length-Matrix (GLRLM) based) were derived from lesion segments, provided by Fuzzy C-Means segmentation, across the 5 representations, resulting in 135 features. Least-Absolute-Shrinkage and Selection-Operator (LASSO) regression was utilized to select optimal feature subsets, subsequently fed into 3 classification schemes: Logistic-Regression (LR), Random-Forest (RF), Support-Vector-Machine-Sequential-Minimal-Optimization (SVM-SMO), assessed with Receiver-Operating-Characteristic (ROC) analysis.

RESULTS

LASSO regression resulted in 7, 6 and 7 features subsets from DCE, DWI and mpMRI, respectively. Best classification performance was obtained by the RF multi-parametric scheme (Area-Under-ROC-Curve, (AUC) ± Standard-Error (SE), AUC ± SE = 0.984 ± 0.025), as compared to DCE (AUC ± SE = 0.961 ± 0.030) and DWI (AUC ± SE = 0.938 ± 0.032) and statistically significantly higher as compared to DWI. The selected mpMRI feature subset highlights the significance of entropy (1^st-order-statistics and 2^nd-order-statistics (GLCM)) and percentile features extracted from 2^nd post-contrast frame, PIE, SER maps and ADC map.

CONCLUSION

Capturing breast intra-lesion heterogeneity, across mpMRI lesion segments with 1^st-order-statistics and texture features (GLCM and GLRLM based), offers a valuable diagnostic tool for breast cancer.

MRI-Based Radiomic Signature as a Prognostic Biomarker for HER2-Positive Invasive Breast Cancer Treated with NAC

Purpose

To identify MRI-based radiomics signature (Rad-score) as a biomarker of risk stratification for disease-free survival (DFS) in patients with HER2-positive invasive breast cancer treated with trastuzumab-based neoadjuvant chemotherapy (NAC) and establish a radiomics-clinicoradiologic-based nomogram that combines Rad-score, MRI findings, and clinicopathological variables for DFS estimation.

Patients and Methods

A total of 127 patients were divided into a training set and testing set according to the ratio of 7:3. Radiomic features were extracted from multiphase CE-MRI (CE_m). Rad-score was calculated using the LASSO (least absolute shrinkage and selection operator) regression analysis. The cutoff point of Rad-score to divide the patients into high- and low-risk groups was determined by receiver operating characteristic curve analysis. A Kaplan–Meier survival curves and the Log rank test were used to investigate the association of the Rad-score with DFS. Univariate and multivariate Cox proportional hazards model were used to determine the association of Rad-score, MRI features, and clinicopathological variables with DFS. A radiomics-clinicoradiologic-based nomogram combining the Rad-score, MRI features, and clinicopathological findings was plotted to validate the radiomic signatures for DFS estimation.

Results

The Rad-score stratified patients into high- and low-risk groups for DFS in the training set (P<0.0001) and was validated in the testing set (P=0.002). The radiomics-clinicoradiologic-based nomogram estimated DFS (training set: C-index=0.974, 95% confidence interval (CI)=0.954–0.994; testing set: C-index=0.917, 95% CI=0.842–0.991) better than the clinicoradiologic-based nomogram (training set: C-index=0.855, 95% CI=0.739–0.971; testing set: C-index=0.831, 95% CI=0.643–0.999).

Conclusion

The Rad-score is an independent biomarker for the estimation of DFS in invasive HER2-positive breast cancer with NAC and the radiomics-clinicoradiologic-based nomogram improved individualized DFS estimation.

Prediction of breast cancer molecular subtypes on DCE-MRI using convolutional neural network with transfer learning between two centers

OBJECTIVES

To apply deep learning algorithms using a conventional convolutional neural network (CNN) and a recurrent CNN to differentiate three breast cancer molecular subtypes on MRI.

METHODS

A total of 244 patients were analyzed, 99 in training dataset scanned at 1.5 T and 83 in testing-1 and 62 in testing-2 scanned at 3 T. Patients were classified into 3 subtypes based on hormonal receptor (HR) and HER2 receptor: (HR+/HER2-), HER2+, and triple negative (TN). Only images acquired in the DCE sequence were used in the analysis. The smallest bounding box covering tumor ROI was used as the input for deep learning to develop the model in the training dataset, by using a conventional CNN and the convolutional long short-term memory (CLSTM). Then, transfer learning was applied to re-tune the model using testing-1(2) and evaluated in testing-2(1).

RESULTS

In the training dataset, the mean accuracy evaluated using tenfold cross-validation was higher by using CLSTM (0.91) than by using CNN (0.79). When the developed model was applied to the independent testing datasets, the accuracy was 0.4-0.5. With transfer learning by re-tuning parameters in testing-1, the mean accuracy reached 0.91 by CNN and 0.83 by CLSTM, and improved accuracy in testing-2 from 0.47 to 0.78 by CNN and from 0.39 to 0.74 by CLSTM. Overall, transfer learning could improve the classification accuracy by greater than 30%.

CONCLUSIONS

The recurrent network using CLSTM could track changes in signal intensity during DCE acquisition, and achieved a higher accuracy compared with conventional CNN during training. For datasets acquired using different settings, transfer learning can be applied to re-tune the model and improve accuracy.

KEY POINTS

• Deep learning can be applied to differentiate breast cancer molecular subtypes. • The recurrent neural network using CLSTM could track the change of signal intensity in DCE images, and achieved a higher accuracy compared with conventional CNN during training. • For datasets acquired using different scanners with different imaging protocols, transfer learning provided an efficient method to re-tune the classification model and improve accuracy.

Could Ultrasound-Based Radiomics Noninvasively Predict Axillary Lymph Node Metastasis in Breast Cancer?

OBJECTIVES

This work aimed to investigate whether quantitative radiomics imaging features extracted from ultrasound (US) can noninvasively predict breast cancer (BC) metastasis to axillary lymph nodes (ALNs).

METHODS

Presurgical B-mode US data of 196 patients with BC were retrospectively studied. The cases were divided into the training and validation cohorts (n = 141 versus 55). The elastic net regression technique was used for selecting features and building a signature in the training cohort. A linear combination of the selected features weighted by their respective coefficients produced a radiomics signature for each individual. A radiomics nomogram was established based on the radiomics signature and US-reported ALN status. In a receiver operating characteristic curve analysis, areas under the curves (AUCs) were determined for assessing the accuracy of the prediction model in predicting ALN metastasis in both cohorts. The clinical value was assessed by a decision curve analysis.

RESULTS

In all, 843 radiomics features per case were obtained from expert-delineated lesions on US imaging in this study. Through radiomics feature selection, 21 features were selected to constitute the radiomics signature for predicting ALN metastasis. Area under the curve values of 0.778 and 0.725 were obtained in the training and validation cohorts, respectively, indicating moderate predictive ability. The radiomics nomogram comprising the radiomics signature and US-reported ALN status showed the best performance for ALN detection in the training cohort (AUC, 0.816) but moderate performance in the validation cohort (AUC, 0.759). The decision curve showed that both the radiomics signature and nomogram displayed good clinical utility.

CONCLUSIONS

This pilot radiomics study provided a noninvasive method for predicting presurgical ALN metastasis status in BC.

Radiomics Analysis and Correlation With Metabolic Parameters in Nasopharyngeal Carcinoma Based on PET/MR Imaging

Objective: Accurate staging is of great importance in treatment selection for patients with nasopharyngeal carcinoma (NPC). The aims of this study were to construct radiomic models of NPC staging based on positron emission tomography (PET) and magnetic resonance (MR) images and to investigate the correlation between metabolic parameters and radiomic features.

Methods: A total of 100 consecutive cases of NPC (70 in training and 30 in the testing cohort) with undifferentiated carcinoma confirmed pathologically were recruited. Metabolic parameters of the local lesions of NPC were measured. A total of 396 radiomic features based on PET and MRI images were calculated [including histogram, Haralick, shape factor, gray level co-occurrence matrix (GLCM), and run length matrix (RLM)] and selected [using maximum relevance and minimum redundancy (mRMR) and least shrinkage and selection operator (LASSO)], respectively. The logistic regression models were established according to these features. Finally, the relationship between the metabolic parameters and radiomic features was analyzed.

Results: We selected the nine most relevant radiomic features (six from MR images and three from PET images) from local NPC lesions. In the PET model, the area under the receiver operating characteristic (ROC) curve (AUC), accuracy, sensitivity, and the specificity of the training group were 0.84, 0.75, 0.90, and 0.69, respectively. In the MR model, those metrics were 0.85, 0.83, 0.75, and 0.86, respectively. Pearson's correlation analysis showed that the metabolic parameters had different degrees of correlation with the selected radiomic features.

Conclusion: The PET and MR radiomic models were helpful in the diagnosis of NPC staging. There were correlations between the metabolic parameters and radiomic features of primary NPC based on PET/MR. In the future, PET/MR-based radiomic models, with further improvement and validation, can be a more useful and economical tool for predicting local invasion and distant metastasis of NPC.

DTI-based radiomics signature for the detection of early diabetic kidney damage

OBJECTIVE

To explore whether a radiomics signature based on diffusion tensor imaging (DTI) can detect early kidney damage in diabetic patients.

MATERIALS AND METHODS

Twenty-eight healthy volunteers (group A) and thirty type 2 diabetic patients (group B) with micro-normoalbuminuria, a urinary albumin-to-creatinine ratio (ACR) < 30 mg/g and an estimated glomerular filtration rate (eGFR) of 60-120 mL/(min 1.73 m²) were recruited. Kidney DTI was performed using 1.5T magnetic resonance imaging (MRI).The radiologist manually drew regions of interest (ROI) on the fractional anisotropy (FA) map of the right kidney ROI including the cortex and medulla. The texture features of the ROIs were extracted using MaZda software. The Fisher coefficient, mutual information (MI), and probability of classification error and average correlation coefficient (POE + ACC) methods were used to select the texture features. The most valuable texture features were further selected by the least absolute shrinkage and selection operator (LASSO) algorithm. A LASSO regression model based on the radiomics signature was established. The diagnostic performance of the model for detecting early diabetic kidney changes was evaluated by the area under the receiver operating characteristic (ROC) curve (AUC). Empower (R), R, and MedCalc15.8 software were used for statistical analysis RESULTS: A total of 279 texture features were extracted from ROI of the kidney, and 30 most valuable texture features were selected from groups A and B using MaZda software. After LASSO-logistic regression, a diagnostic model of diabetic kidney damage based on texture features was established. Model discrimination evaluation: AUC = 0.882 (0.770 ± 0.952). Model calibration evaluation: Hosmer-Lemeshow X2 = 5.3611, P = 0.7184, P > 0.05, the model has good calibration.

CONCLUSION

The texture features based on DTI could play a promising role in detecting early diabetic kidney damage.

The invasion status of lymphovascular space and lymph nodes in cervical cancer assessed by mono-exponential and bi-exponential DWI-related parameters

AIM

To investigate whether mono-exponential and bi-exponential diffusion-weighted imaging (DWI)-related parameters of the primary tumour can evaluate the status of lymphovascular space invasion (LVSI) and lymph node metastasis (LNM) in patients with cervical carcinoma preoperatively.

MATERIALS AND METHODS

Eighty patients with cervical carcinoma were enrolled, who underwent preoperative multi b-value DWI and radical hysterectomy. They were classified into LVSI(+) versus LVSI(-) and LNM(+) versus LNM(-) according to postoperative pathology. The apparent diffusion coefficient (ADC), pure molecular diffusion (D), pseudo-diffusion coefficient (D∗), and perfusion fraction (f) were calculated from the whole tumour (__whole) and tumour margin (__margin). All parameters were compared between LVSI(+) and LVSI(-) and between LNM(+) and LNM(-). Logistic regression analysis and receiver operating characteristic (ROC) curve analysis were performed to evaluate the diagnostic performance of these parameters.

RESULTS

f__margin and D∗__whole showed significant differences in differentiating LVSI(+) from LVSI(-) tumours (p=0.002, 0.008, respectively), while LNM(+) tumours presented with significantly higher ADC__margin than that of LNM(-) tumours (p=0.009). The other parameters were not independent related factors with the status of LVSI or LNM according to logistic regression analysis (p>0.05). The area under the ROC curve of f__margin combined with D∗__whole in discriminating LVSI(+) from LVSI(-) was 0.826 (95% confidence interval [CI]: 0.691-0.961), while ADC__margin in differentiating LNM(+) from LNM(-) was 0.788 (95% CI: 0.648-0.928).

CONCLUSIONS

The parameters generated from mono-exponential and bi-exponential DWI of the primary cervical carcinoma could help discriminate its status regarding LVSI (f__margin and D∗__whole) and LNM (ADC__margin).

Diffusion Kurtosis Imaging-A Superior Approach to Assess Tumor-Stroma Ratio in Pancreatic Ductal Adenocarcinoma

Extensive desmoplastic stroma is a hallmark of pancreatic ductal adenocarcinoma (PDAC) and contributes to tumor progression and to the relative resistance of tumor cells towards (radio) chemotherapy. Thus, therapies that target the stroma are under intense investigation. To allow the stratification of patients who would profit from such therapies, non-invasive methods assessing the stroma content in relation to tumor mass are required. In the current prospective study, we investigated the usefulness of diffusion-weighted magnetic resonance imaging (DW-MRI), a radiologic method that measures the random motion of water molecules in tissue, in the assessment of PDAC lesions, and more specifically in the desmoplastic tumor stroma. We made use of a sophisticated DW-MRI approach, the so-called diffusion kurtosis imaging (DKI), which possesses potential advantages over conventional and widely used monoexponential diffusion-weighted imaging analysis (cDWI). We found that the diffusion constant D from DKI is highly negatively correlated with the percentage of tumor stroma, the latter determined by histology. D performed significantly better than the widely used apparent diffusion coefficient (ADC) from cDWI in distinguishing stroma-rich (>50% stroma percentage) from stroma-poor tumors (≤50% stroma percentage). Moreover, we could prove the potential of the diffusion constant D as a clinically useful imaging parameter for the differentiation of PDAC-lesions from non-neoplastic pancreatic parenchyma. Therefore, the diffusion constant D from DKI could represent a valuable non-invasive imaging biomarker for assessment of stroma content in PDAC, which is applicable for the clinical diagnostic of PDAC.

PICOT promotes T lymphocyte proliferation by down-regulating cyclin D2 expression

The mammalian protein kinase C-interacting cousin of thioredoxin (PICOT; also termed glutaredoxin 3) is a multi-domain monothiol glutaredoxin that is involved in a wide variety of signaling pathways and biological processes. PICOT is required for normal and transformed cell growth and is critical for embryonic development. Recent studies in T lymphocytes demonstrated that PICOT can translocate to the nucleus and interact with embryonic ectoderm development, a polycomb group protein and a core component of the polycomb repressive complex 2, which contributes to the maintenance of transcriptional repression and chromatin remodeling. Furthermore, PICOT was found to interact with chromatin-bound embryonic ectoderm development and alter the extent of histone 3 lysine 27 trimethylation at the promoter region of selected polycomb repressive complex 2 target genes. PICOT knockdown in Jurkat T cells led to increased histone 3 lysine 27 trimethylation at the promoter region of CCND2, a cell cycle-regulating gene which encodes the cyclin D2 protein. As a result, the expression levels of CCND2 mRNA and protein levels were reduced, concomitantly with inhibition of the cell growth rate. Analysis of multiple data sets from the Cancer Genome Atlas revealed that a high expression of PICOT correlated with a low expression of CCND2 in a large number of human cancers. In addition, this parameter correlated with poor patient survival, suggesting that the ratio between PICOT/CCND2 mRNA levels might serve as a predictor of patient survival in selected types of human cancer.

Radiomics in breast cancer classification and prediction

Breast Cancer (BC) is the common form of cancer in women. Its diagnosis and screening are usually performed through different imaging modalities such as mammography, magnetic resonance imaging and ultrasound. However, mammography and ultrasound-imaging techniques have limited sensitivity and specificity both in identifying lesions and in differentiating malign from benign lesions, especially in presence of dense breast parenchyma. Due to the higher resolution of magnetic resonance images, MRI represents the method with the higher specificity and sensitivity among all the available tools, in both lesions' identification and diagnosis. However, especially for diagnosis, even MRI has limitations that are only partially solved if combined with mammography. Unfortunately, due to the limits of all these imaging tools, in order to have a certain diagnosis, patients often receive painful and costly bioptics procedures. In this context, several computational approaches have been developed to increase sensitivity, while maintaining the same specificity, in BC diagnosis and screening. Amongst these, radiomics has been increasingly gaining ground in oncology to improve cancer diagnosis, prognosis and treatment. Radiomics derives multiple quantitative features from single or multiple medical imaging modalities, highlighting image traits which are not visible to the naked eye and hence significantly augmenting the discriminatory and predictive potential of medical imaging. This review article aims to summarize the state of the art in radiomics-based BC research. The dominating evidence extracted from the literature points towards a high potential of radiomics in disentangling malignant from benign breast lesions, classifying BC types and grades and also in predicting treatment response and recurrence risk. In the era of personalized medicine, radiomics has the potential to improve diagnosis, prognosis, prediction, monitoring, image-based intervention, and assessment of therapeutic response in BC.

Parkinson's Disease Diagnosis Using Neostriatum Radiomic Features Based on T2-Weighted Magnetic Resonance Imaging

Background: Parkinson's disease (PD) is a neurodegenerative disease in which the neostriatum, including the caudate nucleus (CN) and putamen (PU), has an important role in the pathophysiology. However, conventional magnetic resonance imaging (MRI) lacks sufficient specificity to diagnose PD. Therefore, the study's aim was to investigate the feasibility of using a radiomics approach to distinguish PD patients from healthy controls on T2-weighted images of the neostriatum and provide a basis for the clinical diagnosis of PD.

Methods: T2-weighted images from 69 PD patients and 69 age- and sex-matched healthy controls were obtained on the same 3.0T MRI scanner. Regions of interest (ROIs) were manually placed at the CN and PU on the slices showing the largest respective sizes of the CN and PU. We extracted 274 texture features from each ROI and then used the least absolute shrinkage and selection operator regression to perform feature selection and radiomics signature building to identify the CN and PU radiomics signatures consisting of optimal features. We used a receiver operating characteristic curve analysis to assess the diagnostic performance of two radiomics signatures in a training group and estimate the generalization performance in the test group.

Results: There were no significant differences in the demographic and clinical characteristics between the PD patients and healthy controls. The CN and PU radiomics signatures were built using 12 and 7 optimal features, respectively. The performance of the two radiomics signatures to distinguish PD patients from healthy controls was good. In the training and test groups, the AUCs of the CN radiomics signatures were 0.9410 (95% confidence interval [CI]: 0.8986–0.9833) and 0.7732 (95% CI: 0.6292–0.9173), respectively, and the AUCs of the PU radiomics signature were 0.8767 (95% CI: 0.8066–0.9469) and 0.7143 (95% CI: 0.5540–0.8746), respectively. Vertl_GlevNonU_R appeared simultaneously in both the CN and PU radiomics signatures as an optimal feature. A t-test analysis revealed significantly higher levels of texture values of the CN and PU in the PD patients than healthy controls (P < 0.05).

Conclusion: Neostriatum radiomics signatures achieved good diagnostic performance for PD and potentially could serve as a basis for the clinical diagnosis of PD.