Multiparametric ultrasound: evaluation of greyscale, shear wave elastography and contrast-enhanced ultrasound for prostate cancer detection and localization in correlation to radical prostatectomy specimens

Examining the application of the IDEAL framework in the reporting and evaluation of innovative invasive procedures: secondary qualitative analysis of a systematic review

OBJECTIVES

The development of new surgical procedures is fundamental to advancing patient care. The Idea, Developments, Exploration, Assessment and Long-term (IDEAL) framework describes study designs for stages of innovation. It can be difficult to apply due to challenges in defining and identifying innovative procedures. This study examined how the IDEAL framework is operationalised in real-world settings; specifically, the types of innovations evaluated using the framework and how authors justify their choice of IDEAL study design.

DESIGN

Secondary qualitative analysis of a systematic review.

DATA SOURCES

Citation searches (Web of Science and Scopus) identified studies following the IDEAL framework and citing any of the ten key IDEAL/IDEAL_D papers.

ELIGIBILITY CRITERIA

Studies of invasive procedures/devices of any design citing any of the ten key IDEAL/IDEAL_D papers.

DATA EXTRACTION AND SYNTHESIS

All relevant text was extracted. Three frameworks were developed, namely: (1) type of innovation under evaluation; (2) terminology used to describe stage of innovation and (3) reported rationale for IDEAL stage.

RESULTS

48 articles were included. 19/48 described entirely new procedures, including those used for the first time in a different clinical context (n=15/48), reported as IDEAL stage 2a (n=8, 53%). Terminology describing stage of innovation was varied, inconsistent and ambiguous and was not defined. Authors justified their choice of IDEAL study design based on limitations in published evidence (n=36) and unknown feasibility and safety (n=32) outcomes.

CONCLUSION

Identifying stage of innovation is crucial to inform appropriate study design and governance decisions. Authors' rationale for choice of IDEAL stage related to the existing evidence base or lack of sufficient outcome data for procedures. Stage of innovation was poorly defined with inconsistent descriptions. Further work is needed to develop methods to identify innovation to inform practical application of the IDEAL framework. Defining the concept of innovation in terms of uncertainty, risk and degree of evidence may help to inform decision-making.

The Performance of Different Parametric Ultrasounds in Prostate Cancer Diagnosis: Correlation with Radical Prostatectomy Specimens

BACKGROUND

Prostate cancer is a prevalent cancer among men. Multiparametric ultrasound [mpUS] is a diagnostic instrument that uses various types of ultrasounds to diagnose it. This systematic review aims to evaluate the performance of different parametric ultrasounds in diagnosing prostate cancer by associating with radical prostatectomy specimens.

METHODOLOGY

A review was performed on various ultrasound parameters using five databases. Systematic review tools were utilized to eliminate duplicates and identify relevant results. Reviewers used the Quality Assessment of Diagnostic Accuracy Results [QUADAS-2] to evaluate the bias and applicability of the study outcomes.

RESULT

Between 2012 and 2023, eleven studies were conducted to evaluate the performance of the different ultrasound parametric procedures in detecting prostate cancer using grayscale TRUS, SWE, CEUS, and mpUS. The high sensitivity of these procedures was found at 55%, 88.6%, 81%, and 74%, respectively. The specificity of these procedures was found to be 93.4%, 97%, 88%, and 59%, respectively. This high sensitivity and specificity may be associated with the large lesion size. The studies revealed that the sensitivity of these procedures in diagnosing clinically significant prostate cancer was 55%, 73%, 70%, and 74%, respectively, while the specificity was 61%, 78.2%, 62%, and 59%, respectively.

CONCLUSIONS

The mpUS procedure provides high sensitivity and specificity in PCa detection, especially for clinically significant prostate cancer.

Non-Invasive Diagnosis of Prostate Cancer and High-Grade Prostate Cancer Using Multiparametric Ultrasonography and Serological Examination

OBJECTIVES

This study aimed to assess the efficacy of multiparametric ultrasonography (mpUS) combined with serological examination, as a non-invasive method, in detecting prostate cancer (PCa) or high-grade prostate cancer (HGPCa) respectively.

METHODS

A cohort of 245 individuals with clinically suspected PCa were enrolled. All subjects underwent a comprehensive evaluation, including basic data collection, serological testing, mpUS and prostate biopsy. Random Forest (RF) models were developed, and the mean area under the curve (AUC) in 100 cross-validations was used to assess the performance in distinguishing PCa from HGPCa.

RESULTS

mpUS features showed significant differences (p < 0.001) between the PCa and non-PCa groups, as well as between the HGPCa and low-grade prostate cancer (LGPCa) groups including prostate-specific antigen density (PSAD), transrectal real-time elastography (TRTE) and intensity difference (ID). The RF model, based on these features, demonstrated an excellent discriminative ability for PCa with a mean area under the curve (AUC) of 0.896. Additionally, another model incorporating free prostate-specific antigen (FPSA) and color Doppler flow imaging (CDFI) achieved a high accuracy in predicting HGPCa with a mean AUC of 0.830. The nomogram derived from these models exhibited excellent individualized prediction of PCa and HGPCa.

CONCLUSION

The RF models incorporating mpUS and serological variables achieved satisfactory accuracies in predicting PCa and HGPCa.

Comparative Assessment of Different Ultrasound Technologies in the Detection of Prostate Cancer: A Systematic Review and Meta-Analysis

The present study aimed to assess the diagnostic test accuracy of different ultrasound scanning technologies in the detection of prostate cancer. A systematic search was conducted using the Cochrane Guidelines for Screening and Diagnostic Tests. We performed a systematic search in the international databases PubMed, Medline, Ovid, Embase and Cochrane Library. Searches were designed to find all studies that evaluated Micro-US, mpUS, SWE and CEUS as the main detection modalities for prostate cancer. This study was registered with Research Registry of systematic review and meta-analysis. The QUADAS-2 tool was utilized to perform quality assessment and bias analysis. The literature search generated 1376 studies. Of these, 320 studies were screened for eligibility, with 1056 studies being excluded. Overall, 26 studies with a total of 6370 patients met the inclusion criteria. The pooled sensitivity for grayscale, CEUS, SWE, Micro-US and mpUS modalities were 0.66 (95% CI 0.54-0.73) 0.73 (95% CI 0.58-0.88), 0.82 (95% CI 0.75-0.90), 0.85 (95% CI 0.76-0.94) and 0.87 (95% CI 0.71-1.03), respectively. Moreover, the pooled specificity for grayscale, CEUS, SWE, Micro-US and mpUS modalities were 0.56 (95% CI 0.21-0.90), 0.78 (95% CI 0.67-0.88), 0.76 (95% CI 0.65-0.88), 0.43 (95% CI 0.28-0.59) and 0.68 (95% CI 0.54-0.81), respectively. In terms of sensitivity, substantial heterogeneity between studies was detected (I2 = 72%, p = 0.000 < 0.05). In relation to specificity, extreme heterogeneity was detected (I2 = 93%, p = 0.000 < 0.05). Some studies proved that advanced ultrasound modalities such as mpUS, Micro-US, shear-wave elastography, contrast enhanced and micro-ultrasound are promising methods for the detection of prostate cancer.

Clinical Trial Protocol: Developing an Image Classification Algorithm for Prostate Cancer Diagnosis on Three-dimensional Multiparametric Transrectal Ultrasound

Introduction and hypothesis

The tendency toward population-based screening programs for prostate cancer (PCa) is expected to increase demand for prebiopsy imaging. This study hypothesizes that a machine learning image classification algorithm for three-dimensional multiparametric transrectal prostate ultrasound (3D mpUS) can detect PCa accurately.

Design

This is a phase 2 prospective multicenter diagnostic accuracy study. A total of 715 patients will be included in a period of approximately 2 yr. Patients are eligible in case of suspected PCa for which prostate biopsy is indicated or in case of biopsy-proven PCa for which radical prostatectomy (RP) will be performed. Exclusion criteria are prior treatment for PCa or contraindications for ultrasound contrast agents (UCAs).

Protocol overview

Study participants will undergo 3D mpUS, consisting of 3D grayscale, 4D contrast-enhanced ultrasound, and 3D shear wave elastography (SWE). Whole-mount RP histopathology will provide the ground truth to train the image classification algorithm. Patients included prior to prostate biopsy will be used for subsequent preliminary validation. There is a small, anticipated risk for participants associated with the administration of a UCA. Informed consent has to be given prior to study participation, and (serious) adverse events will be reported.

Statistical analysis

The primary outcome will be the diagnostic performance of the algorithm for detecting clinically significant PCa (csPCa) on a per-voxel and a per-microregion level. Diagnostic performance will be reported as the area under the receiver operating characteristic curve. Clinically significant PCa is defined as the International Society of Urological grade group ≥2. Full-mount RP histopathology will be used as the reference standard. Secondary outcomes will be sensitivity, specificity, negative predictive value, and positive predictive value for csPCa on a per-patient level, evaluated in patients included prior to prostate biopsy, using biopsy results as the reference standard. A further analysis will be performed on the ability of the algorithm to differentiate between low-, intermediate-, and high-risk tumors.

Discussion and summary

This study aims to develop an ultrasound-based imaging modality for PCa detection. Subsequent head-to-head validation trials with magnetic resonance imaging have to be performed in order to determine its role in clinical practice for risk stratification in patients suspected for PCa.

Shear-wave elastography combined with contrast-enhanced ultrasound algorithm for noninvasive characterization of focal liver lesions

PURPOSE

To establish shear-wave elastography (SWE) combined with contrast-enhanced ultrasound (CEUS) algorithm (SCCA) and improve the diagnostic performance in differentiating focal liver lesions (FLLs).

MATERIAL AND METHODS

We retrospectively selected patients with FLLs between January 2018 and December 2019 at the First Affiliated Hospital of Sun Yat-sen University. Histopathology was used as a standard criterion except for hemangiomas and focal nodular hyperplasia. CEUS with SonoVue (Bracco Imaging) and SCCA combining CEUS and maximum value of elastography with < 20 kPa and > 90 kPa thresholds were used for the diagnosis of FLLs. The diagnostic performance of CEUS and SCCA was calculated and compared.

RESULTS

A total of 171 FLLs were included, with 124 malignant FLLs and 47 benign FLLs. The area under curve (AUC), sensitivity, and specificity in detecting malignant FLLs were 0.83, 91.94%, and 74.47% for CEUS, respectively, and 0.89, 91.94%, and 85.11% for SCCA, respectively. The AUC of SCCA was significantly higher than that of CEUS (P = 0.019). Decision curves indicated that SCCA provided greater clinical benefits. The SCCA provided significantly improved prediction of clinical outcomes, with a net reclassification improvement index of 10.64% (P = 0.018) and integrated discrimination improvement of 0.106 (P = 0.019). For subgroup analysis, we divided the FLLs into a chronic-liver-disease group (n = 88 FLLs) and a normal-liver group (n = 83 FLLs) according to the liver background. In the chronic-liver-disease group, there were no differences between the CEUS-based and SCCA diagnoses. In the normal-liver group, the AUC of SCCA and CEUS in the characterization of FLLs were 0.89 and 0.83, respectively (P = 0.018).

CONCLUSION

SCCA is a feasible tool for differentiating FLLs in patients with normal liver backgrounds. Further investigations are necessary to validate the universality of this algorithm.

Contrast-enhanced ultrasound targeted versus conventional ultrasound guided systematic prostate biopsy for the accurate diagnosis of prostate cancer: A meta-analysis

BACKGROUND

Conventional transrectal ultrasonography (TRUS) guided prostate biopsy is the standard method for accurate diagnosis of prostate cancer (PCa). However, the limitations of this technique in terms of missed diagnosis cannot be ignored. Based on previous studies, contrast-enhanced ultrasound (CEUS) may be able to more distinctly detect malignant lesions with increased microvessels. Therefore, to evaluate the diagnostic efficiency and clinical application prospects of CEUS-guided prostate biopsy for patients with suspected PCa, we performed a meta-analysis comparing CEUS-targeted with TRUS-guided systematic biopsy.

METHODS

A systematic search of PubMed, Web of Science, Embase and CNKI was performed up to March, 2022 for the relevant published studies. After data extraction and quality assessment, meta-analysis was performed using the RevMan 5.3 software.

RESULTS

The results showed that the overall sensitivity was higher for CEUS targeted biopsy than systematic biopsy (P = .03), so was the accuracy (P = .03). However, significant heterogeneity and inconsistent results from certain subgroup analyses challenged the validity of the results. Meanwhile, CEUS yielded a much higher sensitivity in patients with prostate specific antigen (PSA) level of 4 to 10 ng/mL (P = .007). On the other hand, the positive rate of each core (P < .001) and the detection rate of clinically significant PCa (P = .006) were significantly improved using CEUS.

CONCLUSION

CEUS showed the advantage of a higher detection rate of clinically significant PCa, which might provide more specific indications for subsequent treatment. More feasible, real-time data are required to confirm our findings.

Multiparametric Intraoperative Ultrasound in Oncological Neurosurgery: A Pictorial Essay

Intraoperative ultrasound (ioUS) is increasingly used in current neurosurgical practice. This is mainly explained by its affordability, handiness, multimodal real-time nature, and overall by its image spatial and temporal resolution. Identification of lesion and potential residue, analysis of the vascularization pattern, and characterization of the nature of the mass are only some of the advantages that ioUS offers to guide safe and efficient tumor resection. Technological advances in ioUS allow to achieve both structural and functional imaging. B-mode provides high-resolution visualization of the lesion and of its boundaries and relationships. Pioneering modes, such as contrast-enhanced ultrasound (CEUS), ultrasensitive Doppler, and elastosonography, are tools with great potential in characterizing different functional aspects of the lesion in a qualitative and quantitative manner. As already happening for many organs and pathologies, the combined use of different US modalities offers new insights in a multiparametric fashion. In this study, we present the potential of our multiparametric approach for ioUS during neuro-oncological surgery. In this effort, we provide a pictorial essay focusing on the most frequent pathologies: low- and high-grade gliomas, meningiomas, and brain metastases.

The usefulness of elastography in the evaluation and management of adult men with varicocele: A systematic review

Objective

To review the role of elastography in the evaluation and decision-making of adult, infertile men with varicocele.

Methods

A systematic search using the terms (Elastography) AND (Varicocele), (Stiffness) AND (Varicocele), (Elastography) AND (Male infertility) was performed in Pubmed/Medline. Studies reporting a) elastographic characteristics in varicocele-bearing comparing to normal testicles, and b) the correlation of elastography with varicocele grading, parameters of spermatogenesis, and outcomes of varicocele treatment were selected. Exclusion criteria were animal, adolescents, abstracts, and non-English language studies.

Results

In total, 453 articles were identified; 11 eligible studies were selected. Several modalities were used (shear wave elastography, strain elastography, quasistatic ultrasound elastography, acoustic radiation force impulse). Varicocele-bearing testicles have significantly different stiffness and elasticity in comparison to normal and non-varicocele testicles. Although not in full agreement, elastography readings are correlated with semen parameters. Conflicting results were reported regarding grading as most of the studies failed to demonstrate a significant correlation. Shear wave elastography showed a significant correlation with the improvement in semen parameters after varicocelectomy, but the association with pregnancy rates is unknown. Finally, no studies were identified comparing elastography with other modalities.

Conclusions

Elastography can detect changes in the architecture of varicocele-bearing testicles. Although the role of the modality in grading is uncertain, elastography showed a meaningful correlation with spermatogenesis parameters. Importantly, elastography readings could predict the improvement in semen parameters after varicocelectomy which is useful in terms of decision-making in infertile men with varicocele.

Abbreviations

ARFI: acoustic radiation force impulse; CDUS: colour Doppler ultrasonography; DWI: diffusion-weighted imaging; PRISMA: Preferred Reporting Items for Systematic Reviews and Meta-Analyses; SWE: shear wave elastography; VC: varicocele.

Use of TDI during MRI/US fusion-guided biopsy for suspected prostate cancer

BACKGROUND

Tissue Doppler imaging (TDI) uses the Doppler principle to quantify the movement of biological tissues.

OBJECTIVE

To investigate the contribution of TDI parameters derived during magnetic resonance imaging and ultrasound (MRI/US) fusion-guided biopsy for prostate cancer (PCa) discrimination.

METHODS

From March 2016 to Dec. 2018, 75 men with suspected PCa prospectively underwent fusion-guided prostate biopsy. TDI overlaid on predefined target lesion were compared to the confirmed contralateral tumor-free area of the prostate gland (using Image J). Diagnostic value of TDI parameters was assessed using histopathology as standard of reference.

RESULTS

Thirty-seven patients were diagnosed with PCa (49.3%), among them 27 with clinically significant PCa (Gleason score >  3 + 3 = 6 (ISUP 1). The LES/REF ratio was lower in confirmed PCa patients compared to patients without PCa (0.42, IQR, 0.22-0.59 vs. 0.52, IQR, 0.40-0.72, p = 0.017). TDI parameters allowed differentiation of low-risk from high-to-intermediate-risk PCa (ISUP 2 versus ISUP 3) based on lower pixel counts within the target ROI (1340, IQR 596-2430 vs. 2687, IQR 2453-3216, p = 0.004), lower pixel percentage (16.4 IQR 11.4-29.5 vs. 27.3, IQR 22.1-39.5; p = 0.005), and lower LES/REF ratios (0.29, IQR 0.19-0.51 vs. 0.52, IQR 0.47-0.74, p = 0.001).

CONCLUSION

TDI of prostate lesions prelocated by MRI discriminates between cancerous and noncancerous lesions and further seems to enable characterization of PCa aggressiveness. This widely available US technique may improve confidence in target lesion localization for tissue sampling.

Comparison of biopsy strategies for prostate biopsy according to lesion size and PSA density in MRI-directed biopsy pathway

PURPOSE

To investigate whether the detection of clinically significant prostate cancer (csPCa) and the added value of focal saturation biopsy and systematic biopsy (SBx) differ according to index lesion size, and to compare the current guidelines for csPCa detection.

METHODS

This retrospective study included consecutive men who underwent MRI and subsequent SBx and MRI-targeted biopsy (TBx) for a suspicious lesion between April 2019 and February 2020. Lesion visibility on transrectal ultrasound (US) and added value of focal saturation biopsy and SBx were compared according to index lesion size using chi-square and McNemar tests. csPCa detection rates and the proportion of biopsy-indicated men were compared among four biopsy strategies based on current guidelines.

RESULTS

Of 313 men evaluated (median age, 65; interquartile range 60‒71), csPCa was detected in 110 (35%). In lesions < 10 mm, greater US invisibility (42.7% of lesions < 10 mm versus 20.0% of lesions ≥ 10 mm; p < 0.001) and higher added value of focal saturation biopsy and SBx (11.1% and 17.1% in lesions < 10 mm versus 4.2% and 6.3% in lesions ≥ 10 mm) were observed, compared with lesions ≥ 10 mm. Consideration of prostate-specific antigen (PSA) density > 0.15 ng/mL/mL as a cutoff in unsuspicious MRI led to a 14% reduction (44/313) in men who needed biopsy.

CONCLUSION

Determination of the biopsy strategy in terms of the need for focal saturation biopsy or SBx should be made considering lesion size. The use of PSA density in non-suspicious MRI can lead to a reduction in biopsy-indicated men.

Synthetic Elastography Using B-Mode Ultrasound Through a Deep Fully Convolutional Neural Network

Shear-wave elastography (SWE) permits local estimation of tissue elasticity, an important imaging marker in biomedicine. This recently developed, advanced technique assesses the speed of a laterally traveling shear wave after an acoustic radiation force "push" to estimate local Young's moduli in an operator-independent fashion. In this work, we show how synthetic SWE (sSWE) images can be generated based on conventional B-mode imaging through deep learning. Using side-by-side-view B-mode/SWE images collected in 50 patients with prostate cancer, we show that sSWE images with a pixel-wise mean absolute error of 4.5 ± 0.96 kPa with regard to the original SWE can be generated. Visualization of high-level feature levels through t -distributed stochastic neighbor embedding reveals substantial overlap between data from two different scanners. Qualitatively, we examined the use of the sSWE methodology for B-mode images obtained with a scanner without SWE functionality. We also examined the use of this type of network in elasticity imaging in the thyroid. Limitations of the technique reside in the fact that networks have to be retrained for different organs, and that the method requires standardization of the imaging settings and procedure. Future research will be aimed at the development of sSWE as an elasticity-related tissue typing strategy that is solely based on B-mode ultrasound acquisition, and the examination of its clinical utility.

Outcome selection, measurement and reporting for new surgical procedures and devices: a systematic review of IDEAL/IDEAL-D studies to inform development of a core outcome set

BACKGROUND

Outcome selection, measurement and reporting for the evaluation of new surgical procedures and devices is inconsistent and lacks standardization. A core outcome set may promote the safe and transparent evaluation of surgical innovations. This systematic review examined outcome selection, measurement and reporting in studies conducted within the IDEAL (Idea, Development, Exploration, Assessment and Long-term monitoring) framework to examine current practice and inform the development of a core outcome set for early-phase studies of surgical procedures/devices.

METHODS

Web of Science and Scopus citation searches were performed to identify author-reported IDEAL/IDEAL-D studies for any surgical procedure/device. Outcomes were extracted verbatim, including contextual information regarding outcome selection and measurement. Outcomes were categorized to inform a conceptual framework of outcome domains relevant to evaluating innovation.

RESULTS

Some 48 studies were identified. Outcome selection, measurement and reporting varied widely across studies in different IDEAL stages. From 1737 outcomes extracted, 22 domains specific to evaluating innovation were conceptualized under seven broad categories: procedure completion success/failure; modifications; unanticipated events; surgeons' experiences; patients' experiences; resource use specific to the innovative procedure/device; and other innovation-specific outcomes. Most innovation-specific outcomes were measured and reported in only a small number of studies.

CONCLUSION

This review highlighted the need for guidance and standardization in outcome selection and reporting in the evaluation of new surgical procedures/devices. Novel outcome domains specific to innovation have been identified to establish a core outcome set for future evaluations of surgical innovations.

Multifunctional nanobubbles carrying indocyanine green and paclitaxel for molecular imaging and the treatment of prostate cancer

BACKGROUND

Combining ultrasound imaging with photoacoustic imaging provides tissue imaging with high contrast and resolution, thereby enabling rapid, direct measurements and the tracking of tumour growth and metastasis. Moreover, ultrasound-targeted nanobubble destruction (UTND) provides an effective way to deliver drugs, effectively increasing the content of the drug in the tumour area and reducing potential side effects, thereby successfully contributing to the treatment of tumours.

RESULTS

In this study, we prepared multifunctional nanobubbles (NBs) carrying indocyanine green (ICG) and paclitaxel (PTX) (ICG-PTX NBs) and studied their applications in ultrasound imaging of prostate cancer as well as their therapeutic effects on prostate cancer when combined with UTND. ICG-PTX NBs were prepared by the mechanical oscillation method. The particle size and zeta potential of the ICG-PTX NBs were 469.5 ± 32.87 nm and - 21.70 ± 1.22 mV, respectively. The encapsulation efficiency and drug loading efficiency of ICG were 68% and 2.52%, respectively. In vitro imaging experiments showed that ICG-PTX NBs were highly amenable to multimodal imaging, including ultrasound, photoacoustic and fluorescence imaging, and the imaging effect was positively correlated with their concentration. The imaging effects of tumour xenografts also indicated that ICG-PTX NBs were of good use for multimodal imaging. In experiments testing the growth of PC-3 cells in vitro and tumour xenografts in vivo, the ICG-PTX NBs + US group showed more significant inhibition of cell proliferation and the promotion of cell apoptosis compared to the other groups (P < 0.05). Blood biochemical analysis of the six groups showed that the levels of aspartate aminotransferase (AST), phenylalanine aminotransferase (ALT), serum creatinine (CRE) and blood urea nitrogen (BUN) in the ICG-PTX NBs and the ICG-PTX NBs + US groups were significantly lower than those in the PTX group (P < 0.05). Moreover, H&E staining of tissue sections from vital organs showed no obvious abnormalities in the ICG-PTX NBs and the ICG-PTX NBs + US groups.

CONCLUSIONS

ICG-PTX NBs can be used as a non-invasive, pro-apoptotic contrast agent that can achieve multimodal imaging, including ultrasound, fluorescence and photoacoustic imaging, and can succeed in the local treatment of prostate cancer providing a potential novel method for integrated research on prostate cancer diagnosis and treatment.

Artificial intelligence in multiparametric prostate cancer imaging with focus on deep-learning methods

Prostate cancer represents today the most typical example of a pathology whose diagnosis requires multiparametric imaging, a strategy where multiple imaging techniques are combined to reach an acceptable diagnostic performance. However, the reviewing, weighing and coupling of multiple images not only places additional burden on the radiologist, it also complicates the reviewing process. Prostate cancer imaging has therefore been an important target for the development of computer-aided diagnostic (CAD) tools. In this survey, we discuss the advances in CAD for prostate cancer over the last decades with special attention to the deep-learning techniques that have been designed in the last few years. Moreover, we elaborate and compare the methods employed to deliver the CAD output to the operator for further medical decision making.

Contrast-Enhanced Ultrasound Quantification: From Kinetic Modeling to Machine Learning

Ultrasound contrast agents (UCAs) have opened up immense diagnostic possibilities by combined use of indicator dilution principles and dynamic contrast-enhanced ultrasound (DCE-US) imaging. UCAs are microbubbles encapsulated in a biocompatible shell. With a rheology comparable to that of red blood cells, UCAs provide an intravascular indicator for functional imaging of the (micro)vasculature by quantitative DCE-US. Several models of the UCA intravascular kinetics have been proposed to provide functional quantitative maps, aiding diagnosis of different pathological conditions. This article is a comprehensive review of the available methods for quantitative DCE-US imaging based on temporal, spatial and spatiotemporal analysis of the UCA kinetics. The recent introduction of novel UCAs that are targeted to specific vascular receptors has advanced DCE-US to a molecular imaging modality. In parallel, new kinetic models of increased complexity have been developed. The extraction of multiple quantitative maps, reflecting complementary variables of the underlying physiological processes, requires an integrative approach to their interpretation. A probabilistic framework based on emerging machine-learning methods represents nowadays the ultimate approach, improving the diagnostic accuracy of DCE-US imaging by optimal combination of the extracted complementary information. The current value and future perspective of all these advances are critically discussed.

Contrast-enhanced ultrasound with dispersion analysis for the localization of prostate cancer: correlation with radical prostatectomy specimens

PURPOSE

To determine the value of two-dimensional (2D) contrast-enhanced ultrasound (CEUS) imaging and the additional value of contrast ultrasound dispersion imaging (CUDI) for the localization of clinically significant prostate cancer (csPCa).

METHODS

In this multicentre study, subjects scheduled for a radical prostatectomy underwent 2D CEUS imaging preoperatively. CUDI maps were generated from the CEUS recordings. Both CEUS recordings and CUDI maps were scored on the likelihood of presenting csPCa (any Gleason ≥ 4 + 3 and Gleason 3 + 4 larger than 0.5 mL) by five observers and compared to radical prostatectomy histopathology. An automated three-dimensional (3D) fusion protocol was used to match imaging with histopathology. Receiver operator curve (ROC) analysis was performed per observer and imaging modality.

RESULTS

133 of 216 (62%) patients were included in the final analysis. Average area under the ROC for all five readers for CEUS, CUDI and the combination was 0.78, 0.79 and 0.78, respectively. This yields a sensitivity and specificity of 81 and 64% for CEUS, 83 and 56% for CUDI and 83 and 55% for the combination. Interobserver agreement for CEUS, CUDI and the combination showed kappa values of 0.20, 0.18 and 0.18 respectively.

CONCLUSION

The sensitivity and specificity of 2D CEUS and CUDI for csPCa localization are moderate. Despite compressing CEUS in one image, CUDI showed a similar performance to 2D CEUS. With a sensitivity of 83% at cutoff point 3, it could become a useful imaging procedure, especially with 4D acquisition, improved quantification and combination with other US imaging techniques such as elastography.

Automated multiparametric localization of prostate cancer based on B-mode, shear-wave elastography, and contrast-enhanced ultrasound radiomics

OBJECTIVES

The aim of this study was to assess the potential of machine learning based on B-mode, shear-wave elastography (SWE), and dynamic contrast-enhanced ultrasound (DCE-US) radiomics for the localization of prostate cancer (PCa) lesions using transrectal ultrasound.

METHODS

This study was approved by the institutional review board and comprised 50 men with biopsy-confirmed PCa that were referred for radical prostatectomy. Prior to surgery, patients received transrectal ultrasound (TRUS), SWE, and DCE-US for three imaging planes. The images were automatically segmented and registered. First, model-based features related to contrast perfusion and dispersion were extracted from the DCE-US videos. Subsequently, radiomics were retrieved from all modalities. Machine learning was applied through a random forest classification algorithm, using the co-registered histopathology from the radical prostatectomy specimens as a reference to draw benign and malignant regions of interest. To avoid overfitting, the performance of the multiparametric classifier was assessed through leave-one-patient-out cross-validation.

RESULTS

The multiparametric classifier reached a region-wise area under the receiver operating characteristics curve (ROC-AUC) of 0.75 and 0.90 for PCa and Gleason > 3 + 4 significant PCa, respectively, thereby outperforming the best-performing single parameter (i.e., contrast velocity) yielding ROC-AUCs of 0.69 and 0.76, respectively. Machine learning revealed that combinations between perfusion-, dispersion-, and elasticity-related features were favored.

CONCLUSIONS

In this paper, technical feasibility of multiparametric machine learning to improve upon single US modalities for the localization of PCa has been demonstrated. Extended datasets for training and testing may establish the clinical value of automatic multiparametric US classification in the early diagnosis of PCa.

KEY POINTS

• Combination of B-mode ultrasound, shear-wave elastography, and contrast ultrasound radiomics through machine learning is technically feasible. • Multiparametric ultrasound demonstrated a higher prostate cancer localization ability than single ultrasound modalities. • Computer-aided multiparametric ultrasound could help clinicians in biopsy targeting.

[Imaging for initial diagnosis of localized prostate cancer]

The initial diagnosis of prostate cancer has been traditionally performed using systematic core biopsies with the use of magnetic resonance imaging (MRI) reserved to problem-solving scenarios. There is currently an ongoing paradigm shift towards the use of MRI prior to targeted biopsy as the standard approach. Prostate cancer therefore does not remain the last solid tumor entity diagnosed by non-targeted techniques but joins other solid tumor entities for which targeted diagnostic approaches have existed for a while. However, the complexity of the background tissue signal in the prostate makes lesion detection challenging. This article will provide an overview of the components of multiparametric prostate MRI and their interpretation using structured interpretation according to the current PI-RADSv2 (Prostate Imaging Reporting and Data System version 2) guidelines and of novel ultrasound techniques for primary diagnosis.