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.

The evolving role of contrast-enhanced ultrasound in urology: a review

PURPOSE

Ultrasound's versatility and ease of use has expanded its application in many clinical settings. Technological advancements with contrast-enhanced ultrasound (CEUS) have allowed high quality imaging similar to CT or MRI with lower risk of contrast toxicity and radiation exposure. In this review article we examine the development of CEUS and its vast applications in the field of urology.

METHODS

A PubMed literature search was performed using keywords: contrast enhanced ultrasound, prostate cancer, renal cancer, and multiparametric ultrasound.

RESULTS

The development of CEUS has improved transrectal ultrasound imaging with increased detection of prostate cancer (PCa). Further enhancements of CEUS such as subharmonic imaging (SHI), flash replenishment imaging (FRI) and contrast ultrasound dispersion imaging (CUDI) allow improved PCa diagnosis. CEUS has also emerged as an important tool in characterizing suspicious renal mass without compromising renal function with contrast imaging.

CONCLUSION

CEUS has modernized imaging and diagnosis of prostate and renal cancer. Future advancements and utilization of CEUS will allow its expansion into other urological subspecialties.

The CADMUS trial - Multi-parametric ultrasound targeted biopsies compared to multi-parametric MRI targeted biopsies in the diagnosis of clinically significant prostate cancer

OBJECTIVE

To compare the proportion of clinically significant prostate cancers (PCa) found in lesions detected by multiparametric MRI (mpMRI) with that found in lesions detected by multiparametric ultrasound (mpUSS), in men at risk.

PATIENTS AND METHODS

CADMUS (Cancer Detection by Multiparametric Ultrasound of the prostate) is a prospective, multi-centre paired cohort diagnostic utility study with built-in randomisation of order of biopsies. The trial is registered ISRCTN38541912. All patients will undergo the index test under evaluation (mpUSS±biopsies), as well as the standard test (mpMRI±biopsies). Eligible men will be those at risk of harbouring prostate cancer usually recommended for prostate biopsy, either for the first time or as a repeat, who have not had any prior treatment for prostate cancer. Men in need of repeat biopsy will include those with prior negative results but ongoing suspicion, and those with an existing prostate cancer diagnosis but a need for accurate risk stratification. Both scans will be reported blind to the results of the other and the order in which the targeted biopsies derived from the two different imaging modalities are taken will be randomised. Comparison will be drawn between biopsy results of lesions detected by mpUSS with those lesions detected by mpMRI. Agreement over position between the two imaging modalities will be studied.

DISCUSSION

CADMUS will provide level one evidence on the performance of mpUSS derived targeted biopsies in the identification of clinically significant prostate cancer in comparison to mpMRI targeted biopsies. Recruitment is underway and expected to complete in 2018.

Multiparametric Ultrasound for Targeting Prostate Cancer: Combining ARFI, SWEI, QUS and B-Mode

Diagnosing prostate cancer through standard transrectal ultrasound (TRUS)-guided biopsy is challenging because of the sensitivity and specificity limitations of B-mode imaging. We used a linear support vector machine (SVM) to combine standard TRUS imaging data with acoustic radiation force impulse (ARFI) imaging data, shear wave elasticity imaging (SWEI) data and quantitative ultrasound (QUS) midband fit data to enhance lesion contrast into a synthesized multiparametric ultrasound volume. This SVM was trained and validated using a subset of 20 patients and tested on a second subset of 10 patients. Multiparametric US led to a statistically significant improvements in contrast, contrast-to-noise ratio (CNR) and generalized CNR (gCNR) when compared with standard TRUS B-mode and SWEI; in contrast and CNR when compared with MF; and in CNR when compared with ARFI. ARFI, MF and SWEI also outperformed TRUS B-mode in contrast, with MF outperforming B-mode in CNR and gCNR as well. ARFI, although only yielding statistically significant differences in contrast compared with TRUS B-mode, captured critical qualitative features for lesion identification. Multiparametric US enhanced lesion visibility metrics and is a promising technique for targeted TRUS-guided prostate biopsy in the future.

Dynamic contrast enhanced ultrasound in gastrointestinal diseases: A current trend or an indispensable tool?

Contrast enhanced ultrasound (CEUS) has been widely implemented in clinical practice because of the enormous quantity of information it provides, along with its low cost, reproducibility, minimal invasiveness, and safety of the second-generation ultrasound contrast agents. To overcome the limitation of CEUS given by the subjective evaluation of the contrast enhancement behaviour, quantitative analysis of contrast kinetics with generation of time-intensity curves has been introduced in recent years. The quantification of perfusion parameters [named as dynamic-CEUS (D-CEUS)] has several applications in gastrointestinal neoplastic and inflammatory disorders. However, the limited availability of large studies and the heterogeneity of the technologies employed have precluded the standardisation of D-CEUS, which potentially represents a valuable tool for clinical practice in management of gastrointestinal diseases. In this article, we reviewed the evidence exploring the application of D-CEUS in gastrointestinal diseases, with a special focus on liver, pancreas, and inflammatory bowel diseases.

Multiparametric ultrasound in the diagnosis and monitoring of ischemic colitis: description of a case of ischemic colitis of the right colon and revision of the literature

The aim of this paper is to describe the usefulness of multiparametric US in the diagnosis and subsequent follow-up of a case of right-side ischemic colitis and to present a review of the data reported in the literature. Ischemic colitis is frequently diagnosed in the field of gastroenterology. Diagnosis is usually based on the outcome of endoscopy and histological examination, and in case of right-side ischemic colitis also on the results of contrast-enhanced CT. In the described case, multiparametric US indicated the diagnosis including a prognostic judgment, and during follow-up US-monitored patency of the stents positioned under angiographic guidance. One of the available US techniques, CEUS, seems to have a special role in the detection of residual vascularization of the gastrointestinal tract affected by ischemia. However, before introducing this method into daily clinical practice, further studies are required to confirm its diagnostic accuracy.

Multiparametric ultrasound in the evaluation of kidney disease in elderly

After the age of 30 years, GFR progressively declines at an average rate of 8 mL/min/1.73 m/decade. A problem of advanced age is that the evaluation of renal function on the basis of indicators valid in young adults, such as creatininemia, is unreliable. In fact, many patients with chronic renal failure may have serum creatinine levels within the normal range even if they have a significant reduction in renal function. Ultrasound has become a routine method of investigation in renal disease: kidney size and parenchymal echogenicity are considered markers of renal function, so US is useful in assessing the presence and degree of renal failure. CEUS is useful in the evaluation of kidney disease in the elderly: the increased hemodynamic resistance of renal microvessels reduces perfusion in the renal cortex, so fewer microbubbles enter the renal cortex. EcoColor and EcoDoppler are also useful in the evaluation of senile alterations: here, the distribution of color-signals, as compared to that in the young adult population, appears more attenuated, limited to intersegmental and interlobar districts. Among the ecoDoppler parameters, the resistance index can be considered a marker of renal damage progression, with attention needing to paid to possible concomitant confounding factors. Ultrasonography, color-Doppler and CEUS are a non-invasive and convenient modality for managing kidney disease; their integration with anamnestic, objective and laboratory data permits fast and reliable clinical, diagnostic, and therapeutic classification. It also allows early therapeutic intervention and, ultimately, improvements in patient management.

The combined value of mpUS and mpMRI-TRUS fusion for the diagnosis of clinically significant prostate cancer

Objective

To evaluate the combined efficacy of multiparametric ultrasonography (mpUS) and multiparametric magnetic resonance imaging/transrectal ultrasound (mpMRI-TRUS) fusion for detecting clinically significant prostate cancer (csPCa).

Methods

From November 2019 to September 2021, biopsy-naïve patients underwent mpMRI-TRUS fusion imaging combined with mpUS-guided targeted biopsies (TB) and systematic biopsies (SB). To further evaluate the additional diagnostic value of mpUS, the imaging features of 202 focus obtained from fusion imaging were assessed. The diagnostic accuracies of mpMRI-TRUS fusion imaging and the combination of mpMRI-TRUS fusion imaging with mpUS for csPCa were comparatively evaluated.

Results

A total of 202 prostate lesions (160 patients) were included in the final analysis, of which 105 were csPCa, 16 were ciPCa, and 81 were noncancerous. The median patient age was 69 (65–73) years and the median tPSA was 22.07 (11.22–62.80) ng/mL. For csPCa, the detection rate of TB was higher than that of SB (50.0% vs. 45.5%, p < 0.05). The imaging characteristics of mpUS in the PCa and non-PCa groups were significantly different (p < 0.001). When compared with mpMRI-TRUS fusion imaging, the positive predictive value, false positive rate, and area under the curve (AUC) of csPCa diagnosis by mpMRI-TRUS fusion imaging combined with mpUS increased by 11.30%, decreased by 19.58%, and increased from 0.719 to 0.770 (p < 0.05), respectively.

Conclusion

TB can improve the detection rate of csPCa and hence can be effectively used in the diagnosis and risk assessment of csPCa. The mpUS-enriched valuable diagnostic information for mpMRI-TRUS fusion imaging and their combination showed a higher diagnostic value for csPCa, which can guide subsequent clinical treatment.

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.

Robotic Transrectal Computed Tomographic Ultrasound with Artificial Neural Network Analysis: First Validation and Comparison with MRI-Guided Biopsies and Radical Prostatectomy

INTRODUCTION

There is still a lack of availability of high-quality multiparametric magnetic resonance imaging (mpMRI) interpreted by experienced uro-radiologists to rule out clinically significant PC (csPC). Consequently, we developed a new imaging method based on computed tomographic ultrasound (US) supported by artificial neural network analysis (ANNA).

METHODS

Two hundred and two consecutive patients with visible mpMRI lesions were scanned and recorded by robotic CT-US during mpMRI-TRUS biopsy. Only significant index lesions (ISUP ≥2) verified by whole-mount pathology were retrospectively analyzed. Their visibility was reevaluated by 2 blinded investigators by grayscale US and ANNA.

RESULTS

In the cohort, csPC was detected in 105 cases (52%) by mpMRI-TRUS biopsy. Whole-mount histology was available in 44 cases (36%). In this subgroup, mean PSA level was 8.6 ng/mL, mean prostate volume was 33 cm3, and mean tumor volume was 0.5 cm3. Median PI-RADS and ISUP of index lesions were 4 and 3, respectively. Index lesions were visible in grayscale US and ANNA in 25 cases (57%) and 30 cases (68%), respectively. Combining CT-US-ANNA, we detected index lesions in 35 patients (80%).

CONCLUSIONS

The first results of multiparametric CT-US-ANNA imaging showed promising detection rates in patients with csPC. US imaging with ANNA has the potential to complement PC diagnosis.

Advances in vascular anatomy and pathophysiology using high resolution and multiparametric sonography

B-mode and Color Doppler are the first-line imaging modalities in cardiovascular diseases. However, conventional ultrasound (US) provides a lower spatial and temporal resolution (70-100 frames per second) compared to ultrafast technology which acquires several thousand frames per second. Consequently, the multiparametric ultrafast platforms manage new imaging algorithms as high-frequency ultrasound, contrast-enhanced ultrasound, shear wave elastography, vector flow, and local pulse wave imaging. These advances allow better ultrasound performances, more detailed blood flow visualization and vessel walls' characterization, and many future applications for vascular viscoelastic properties evaluation.In this paper, we provide an overview of each new technique's principles and concepts and the real or potential applications of these modalities on the study of the artery and venous anatomy and pathophysiology of the upper limb before and after creating a native or prosthetic arterio-venous fistula. In particular, we focus on high-frequency ultrasound that could predict cannulation readiness and its potential role in the venous valvular status evaluation before vascular access creation; on contrast-enhanced ultrasound that could improve the peri-operative imaging evaluation during US-guided angioplasty; on shear wave elastography and local pulse wave imaging that could evaluate preoperative vessels stiffness and their potential predictive role in vascular access failure; on vector flow imaging that could better characterize the different components of the vascular access complex flow.

Diagnostic accuracy of multiparametric ultrasound in the diagnosis of prostate cancer: systematic review and meta-analysis

OBJECTIVES

Ultrasound (US) technology has recently made advances that have led to the development of modalities including elastography and contrast-enhanced ultrasound. The use of different US modalities in combination may increase the accuracy of PCa diagnosis. This study aims to assess the diagnostic accuracy of multiparametric ultrasound (mpUS) in the PCa diagnosis.

METHODS

Through September 2023, we searched through Cochrane CENTRAL, PubMed, Embase, Scopus, Web of Science, ClinicalTrial.gov, and Google Scholar for relevant studies. We used standard methods recommended for meta-analyses of diagnostic evaluation. We plot the SROC curve, which stands for summary receiver operating characteristic. To determine how confounding factors affected the results, meta-regression analysis was used.

RESULTS

Finally, 1004 patients from 8 studies that were included in this research were examined. The diagnostic odds ratio for PCa was 20 (95% confidence interval (CI), 8-49) and the pooled estimates of mpUS for diagnosis were as follows: sensitivity, 0.88 (95% CI, 0.81-0.93); specificity, 0.72 (95% CI, 0.59-0.83); positive predictive value, 0.75 (95% CI, 0.63-0.87); and negative predictive value, 0.82 (95% CI, 0.71-0.93). The area under the SROC curve was 0.89 (95% CI, 0.86-0.92). There was a significant heterogeneity among the studies (p < 0.01). According to meta-regression, both the sensitivity and specificity of mpUS in the diagnosis of clinically significant PCa (csPCa) were inferior to any PCa.

CONCLUSION

The diagnostic accuracy of mpUS in the diagnosis of PCa is moderate, but the accuracy in the diagnosis of csPCa is significantly lower than any PCa. More relevant research is needed in the future.

CRITICAL RELEVANCE STATEMENT

This study provides urologists and sonographers with useful data by summarizing the accuracy of multiparametric ultrasound in the detection of prostate cancer.

KEY POINTS

• Recent studies focused on the role of multiparametric ultrasound in the diagnosis of prostate cancer. • This meta-analysis revealed that multiparametric ultrasound has moderate diagnostic accuracy for prostate cancer. • The diagnostic accuracy of multiparametric ultrasound in the diagnosis of clinically significant prostate cancer is significantly lower than any prostate cancer.

Classification and risk assessment of ovarian-adnexal lesions using parametric and radiomic analysis of co-registered ultrasound-photoacoustic tomographic images

Ovarian-adnexal lesions are conventionally assessed with ultrasound (US) under the guidance of the Ovarian-Adnexal Reporting and Data System (O-RADS). However, the low specificity of O-RADS results in many unnecessary surgeries. Here, we use co-registered US and photoacoustic tomography (PAT) to improve the diagnostic accuracy of O-RADS. Physics-based parametric algorithms for US and PAT were developed to estimate the acoustic and photoacoustic properties of 93 ovarian lesions. Additionally, statistics-based radiomic algorithms were applied to quantify differences in the lesion texture on US-PAT images. A machine learning model (US-PAT KNN model) was developed based on an optimized subset of eight US and PAT imaging features to classify a lesion as either cancer, one of four subtypes of benign lesions, or a normal ovary. The model achieved an area under the receiver operating characteristic curve (AUC) of 0.969 and a balanced six-class classification accuracy of 86.0 %.

Role of Multiparametric Ultrasound in Evaluating Hepatic Acute Graft-versus-Host Disease: An Animal Study

OBJECTIVE

Hepatic acute graft-versus-host disease (aGVHD) is a serious complication of allogeneic hematopoietic stem cell transplantation (allo-HSCT) and is one of the leading causes of early non-recurrent death. The current diagnosis is based mainly based on clinical diagnosis, and there is a lack of non-invasive quantitative diagnosis methods. We propose a multiparametric ultrasound (MPUS) imaging method and explore its effectiveness in evaluating hepatic aGVHD.

METHODS

In this study, 48 female Wistar rats were used as receptors and 12 male Fischer 344 rats were used as donors for allo-HSCT to establish aGVHD models. After transplantation, 8 rats were randomly selected for ultrasonic examination weekly, including color Doppler ultrasound, contrast-enhanced ultrasound (CEUS) and shear wave dispersion (SWD) imaging. The values of nine ultrasonic parameters were obtained. Hepatic aGVHD was subsequently diagnosed by histopathological analysis. A classification model for predicting hepatic aGVHD was established using principal component analysis and support vector machines.

RESULTS

According to the pathological results, the transplanted rats were categorized into the hepatic aGVHD and non-GVHD (nGVHD) groups. All parameters obtained by MPUS differed statistically between the two groups. The first three contributing percentages of principal component analysis results were resistivity index, peak intensity and shear wave dispersion slope, respectively. The accuracy of classifying aGVHD and nGVHD using support vector machines reached 100%. The accuracy of the multiparameter classifier was significantly higher than that of the single parameter.

CONCLUSION

The MPUS imaging method has proven to be useful in detecting hepatic aGVHD.

Multiparametric Ultrasound Imaging of Prostate Cancer Using Deep Neural Networks

OBJECTIVE

A deep neural network (DNN) was trained to generate a multiparametric ultrasound (mpUS) volume from four input ultrasound-based modalities (acoustic radiation force impulse [ARFI] imaging, shear wave elasticity imaging [SWEI], quantitative ultrasound-midband fit [QUS-MF], and B-mode) for the detection of prostate cancer.

METHODS

A DNN was trained using co-registered ARFI, SWEI, MF, and B-mode data obtained in men with biopsy-confirmed prostate cancer prior to radical prostatectomy (15 subjects, comprising 980,620 voxels). Data were obtained using a commercial scanner that was modified to allow user control of the acoustic beam sequences and provide access to the raw image data. For each subject, the index lesion and a non-cancerous region were manually segmented using visual confirmation based on whole-mount histopathology data.

RESULTS

In a prostate phantom, the DNN increased lesion contrast-to-noise ratio (CNR) compared to a previous approach that used a linear support vector machine (SVM). In the in vivo test datasets (n = 15), the DNN-based mpUS volumes clearly portrayed histopathology-confirmed prostate cancer and significantly improved CNR compared to the linear SVM (2.79 ± 0.88 vs. 1.98 ± 0.73, paired-sample t-test p < 0.001). In a sub-analysis in which the input modalities to the DNN were selectively omitted, the CNR decreased with fewer inputs; both stiffness- and echogenicity-based modalities were important contributors to the multiparametric model.

CONCLUSION

The findings from this study indicate that a DNN can be optimized to generate mpUS prostate volumes with high CNR from ARFI, SWEI, MF, and B-mode and that this approach outperforms a linear SVM approach.

Multiparametric ultrasound as a new concept of assessment of liver tissue damage

Liver disease accounts for approximately 2 million deaths per year worldwide. All chronic liver diseases (CLDs), whether of toxic, genetic, autoimmune, or infectious origin, undergo typical histological changes in the structure of the tissue. These changes may include the accumulation of extracellular matrix material, fats, triglycerides, or tissue scarring. Noninvasive methods for diagnosing CLD, such as conventional B-mode ultrasound (US), play a significant role in diagnosis. Doppler US, when coupled with B-mode US, can be helpful in evaluating the hemodynamics of hepatic vessels and detecting US findings associated with hepatic decompensation. US elastography can assess liver stiffness, serving as a surrogate marker for liver fibrosis. It is important to note that interpreting these values should not rely solely on a histological classification. Contrast-enhanced US (CEUS) provides valuable information on tissue perfusion and enables excellent differentiation between benign and malignant focal liver lesions. Clinical evaluation, the etiology of liver disease, and the patient current comorbidities all influence the interpretation of liver stiffness measurements. These measurements are most clinically relevant when interpreted as a probability of compensated advanced CLD. B-mode US offers a subjective estimation of fatty infiltration and has limited sensitivity for mild steatosis. The controlled attenuation parameter requires a dedicated device, and cutoff values are not clearly defined. Quan-titative US parameters for liver fat estimation include the attenuation coefficient, backscatter coefficient, and speed of sound. These parameters offer the advantage of providing fat quantification alongside B-mode evaluation and other US parameters. Multiparametric US (MPUS) of the liver introduces a new concept for complete noninvasive diagnosis. It encourages examiners to utilize the latest features of an US machine, including conventional B-mode, liver stiffness evaluation, fat quantification, dispersion imaging, Doppler US, and CEUS for focal liver lesion characterization. This comprehensive approach allows for diagnosis in a single examination, providing clinicians worldwide with a broader perspective and becoming a cornerstone in their diagnostic arsenal. MPUS, in the hands of skilled clinicians, becomes an invaluable predictive tool for diagnosing, staging, and monitoring CLD.

Can 3D Multiparametric Ultrasound Imaging Predict Prostate Biopsy Outcome?

OBJECTIVES

To assess the value of 3D multiparametric ultrasound imaging, combining hemodynamic and tissue stiffness quantifications by machine learning, for the prediction of prostate biopsy outcomes.

METHODS

After signing informed consent, 54 biopsy-naïve patients underwent a 3D dynamic contrast-enhanced ultrasound (DCE-US) recording, a multi-plane 2D shear-wave elastography (SWE) scan with manual sweeping from base to apex of the prostate, and received 12-core systematic biopsies (SBx). 3D maps of 18 hemodynamic parameters were extracted from the 3D DCE-US quantification and a 3D SWE elasticity map was reconstructed based on the multi-plane 2D SWE acquisitions. Subsequently, all the 3D maps were segmented and subdivided into 12 regions corresponding to the SBx locations. Per region, the set of 19 computed parameters was further extended by derivation of eight radiomic features per parameter. Based on this feature set, a multiparametric ultrasound approach was implemented using five different classifiers together with a sequential floating forward selection method and hyperparameter tuning. The classification accuracy with respect to the biopsy reference was assessed by a group-k-fold cross-validation procedure, and the performance was evaluated by the Area Under the Receiver Operating Characteristics Curve (AUC).

RESULTS

Of the 54 patients, 20 were found with clinically significant prostate cancer (csPCa) based on SBx. The 18 hemodynamic parameters showed mean AUC values varying from 0.63 to 0.75, and SWE elasticity showed an AUC of 0.66. The multiparametric approach using radiomic features derived from hemodynamic parameters only produced an AUC of 0.81, while the combination of hemodynamic and tissue-stiffness quantifications yielded a significantly improved AUC of 0.85 for csPCa detection (p-value < 0.05) using the Gradient Boosting classifier.

CONCLUSIONS

Our results suggest 3D multiparametric ultrasound imaging combining hemodynamic and tissue-stiffness features to represent a promising diagnostic tool for biopsy outcome prediction, aiding in csPCa localization.

Developing a training for 3D transrectal multiparametric ultrasound of the prostate: a human factors engineering approach

OBJECTIVE

Three-dimensional multiparametric ultrasound (3D mpUS) shows promise for accurately diagnosing prostate cancer. However, its technical complexity presents usability challenges. Human Factor Engineering (HFE) studies the interaction between devices and users, by reducing human error, increasing productivity, and enhancing safety. The objective is to develop a training program for 3D mpUS using HFE (NCT04605276).

METHODS

This study employs a human-centered design approach, a principle of HFE, with a formative and summative phase. In the formative phase, six trainees underwent 3D mpUS training and iteratively provided feedback. The summative phase included 15 trainees who completed the finalized training; probe and ultrasound machine handling, contrast agent (CA) preparation, and conducting 3D mpUS. Performance was evaluated through observing 23 tasks.

RESULTS

Feedback from the formative phase led to several improvements. In the summative phase, all pass criteria were met, most errors were related to CA administration or inadequate acquisition termination. Trainee confidence in independently performing 3D mpUS was high, 93% of scans met quality standards.

CONCLUSION

HFE proved effective in generating feedback to improve the training program for 3D mpUS acquisition. The training ensured that users were well prepared to perform the 3D mpUS procedure with minimal errors and a short learning curve.