Artificial Intelligence System for Predicting Prostate Cancer Lesions from Shear Wave Elastography Measurements

Elastography of the Male Pelvic Region-Perspectives on Malignant Lesions

Ultrasound elastography is widely used to assess tissue stiffness for lesion characterization, including differentiation between benign and malignant lesions. This study focuses on the use of elastography in the male pelvis, including the prostate, testicles, and rectum, by comparing elastography types (shear wave and strain). This article provides a summary of the existing literature on the use of elastography in the male pelvic region and outlines the clinical perspective. Ultrasound elastography is a good technique for evaluating and monitoring lesions in the male pelvic region.

Evaluation of endometrial receptivity in women with unexplained infertility by shear wave elastography

OBJECTIVES

The endometrium of most unexplained infertility (UI) patients has been altered histologically. Shear wave elastography (SWE) is utilized to assess the signature of living tissue. This study aimed to explore the value of SWE in evaluating endometrial receptivity (ER) in UI patients.

METHODS

In total, 59 UI patients (UI group) and 52 normal control women (NC group) who received fertility consultation in our hospital were included between January 2022 and June 2023. We divided them into the late-proliferative phase of UI group (LPUI; n = 59), mid-secretory phase of UI group (MPUI; n = 41), late-proliferative phase of NC group (LPNC; n = 52), and mid-secretory phase of NC group (MPNC; n = 45). Transvaginal ultrasonography and SWE were performed during the LP and MP. Endometrial thickness (EMT), uterine artery pulsatility index (UA-PI), endometrial mean elasticity (E-mean), and mean shear wave velocities (SWV-mean) were measured.

RESULTS

There were significant differences in E-mean, SWV-mean, EMT, and UA-PI between the UI group and the NC group during both the LP and MP (p MPNC vs MPUI < 0.05, p LPNC vs LPUI < 0.05). E-mean and SWV-mean decreased with increasing EMT but increased with increasing UA-PI (p < 0.05). The most effective parameter for evaluating ER in UI patients is the E-mean (AUC = 0.89).

CONCLUSIONS

UI patients exhibited thinner endometrium, increased endometrial stiffness, and poor endometrial blood perfusion. E-mean was the most effective parameter to evaluate ER in UI patients. The study preliminarily proved that SWE is a promising non-invasive tool for evaluating the condition of endometrium.

CRITICAL RELEVANCE STATEMENT

This study aimed to explore the significance of endometrial elasticity measured by SWE in evaluating patients with UI. The findings revealed a correlation between EMT, UA-PI, and E-mean. Endometrial elasticity can serve as an effective indicator for predicting ER.

KEY POINTS

1. To explore the significance of endometrial elasticity in assessing patients with UI. 2. The endometrium of UI patient exhibited thinness, stiffness, and poor blood perfusion. 3. Endometrial elasticity serves as a valuable indicator for evaluating endometrial receptivity.

Novel non-MRI imaging techniques for primary diagnosis of prostate cancer: micro-ultrasound, contrast-enhanced ultrasound, elastography, multiparametric ultrasound, and PSMA PET/CT

BACKGROUND

Multiparametric magnetic resonance imaging (mpMRI) provides enhanced diagnostic accuracy in the detection of prostate cancer, but is not devoid of limitations. Given the recent evolution of non-MRI imaging techniques, this critical review of the literature aimed at summarizing the available evidence on ultrasound-based and nuclear medicine imaging technologies in the initial diagnosis of PCa.

METHODS

Three databases (PubMed®, Web of Science™, and Scopus®) were queried for studies examining their diagnostic performance in the primary diagnosis of PCa, weighted against a histological confirmation of PCa diagnosis, using a free-text protocol. Retrospective and prospective studies, both comparative and non-comparative, systematic reviews (SR) and meta-analysis (MA) were included. Based on authors' expert opinion, studies were selected, data extracted, and results qualitatively described.

RESULTS

Micro-ultrasound (micro-US) appears as an appealing diagnostic strategy given its high accuracy in detection of PCa, apparently non-inferior to mpMRI. The use of multiparametric US (mpUS) likely gives an advantage in terms of effectiveness coming from the combination of different modalities, especially when certain modalities are combined. Prostate-specific membrane antigen (PSMA) PET/CT may represent a whole-body, one-step approach for appropriate diagnosis and staging of PCa. The direct relationship between lesions avidity of radiotracers and histopathologic and prognostic features, and its valid diagnostic performance represents appealing characteristics. However, intrinsic limits of each of these techniques exist and further research is needed before definitively considering them reliable tools for accurate PCa diagnosis. Other novel technologies, such as elastography and multiparametric US, currently relies on a limited number of studies, and therefore evidence about them remains preliminary.

CONCLUSION

Evidence on the role of non-MRI imaging options in the primary diagnosis of PCa is steadily building up. This testifies a growing interest towards novel technologies that might allow overcoming some of the limitations of current gold standard MRI imaging.

The Cavernous Nerve Injury Rat Model: A Pictorial Essay on Post-Radical Prostatectomy Erectile Dysfunction Research

Understanding and addressing post-radical prostatectomy (RP) erectile dysfunction (ED) is of paramount importance for clinicians. Cavernous nerve (CN) injury rat model studies have provided consistently promising experimental data regarding regaining erectile function (EF) after nerve damage-induced ED. However, these findings have failed to translate efficiently into clinical practice, with post-RP ED therapeutic management remaining cumbersome and enigmatic. This disparity highlights the need for further standardization and optimization of the elaborate surgical preparation protocols and multifaceted reporting parameters involved in reliable CN injury rat model experimentation. Even so, despite its technical complexity, this animal model remains instrumental in exploring the functional implications of RP, i.e., surgical lesions of the neurovascular bundles (NVBs). Herein, besides cavernous nerve (CN) dissection, injury, and electrostimulation, multiple pressure measurements, i.e., mean arterial pressure (MAP) and intra-cavernosal pressure (ICP), must also be achieved. A transverse cervical incision allows for carotid artery cannulation and MAP measurements. Conversely, ICP measurements entail circumcising the penis, exposing the ischiocavernous muscle, and inserting a needle into the corporal body. Finally, using an abdominal incision, the prostate is revealed, and the major pelvic ganglia (MPG) and CNs are dissected bilaterally. Specific surgical techniques are used to induce CN injuries. Herein, we provide a narrative and illustrative overview regarding these complex experimental procedures and their particular requirements, reflecting on current evidence and future research perspectives.

Canine prostatic serum esterase and strain and 2D-shear wave sonoelastography for evaluation of normal prostate in dogs: Preliminary results

Canine prostatic serum esterase (CPSE) is considered a useful tool to identify prostate disorders in dogs, with increasing interest in ultrasound (US)-based sonoelastography to non-invasively detect prostate disorders. Since no report is available about a possible correlation between these diagnostic tools, we aimed to investigate a possible correlation between strain elastography (SE) and 2D-shear wave elastography (SWE) and CPSE. Twenty-one dogs were included and, on each animal, CPSE was evaluated followed by a complete US examination and SE and 2D-SWE application. Healthy dogs were identified based on the CPSE results. All the dogs included were characterized by normal CPSE values (<52.3 ng/mL) and normal US prostate appearance. The prostate was characterized by intermediate stiffness with SE (pattern III - 84.7% for the left lobe and 79.27% for the right lobe) and softer than the abdominal wall (SR 0.6 for the left lobe and 0.56 for the right lobe), with low values for both m/s and kilopascals (kPa) for 2D-SWE, pointing that the healthy tissue is not hard. 2D-SWE results were, respectively, 13.51 ± 5.55 kPa and 2.31 ± 0.42 m/s for the left lobe and 18.05 ± 6.47 kPa and 2.39 ± 0.43 m/s for the right lobe. The significant difference between the right and left measurements expressed with kPa, not evidenced with m/s, can be considered indicative of m/s as the most reliable measurement to be considered regarding the prostate parenchyma. Even though no linear correlation was detected between CPSE and elastography values, these preliminary results evidence that the healthy prostates were characterized by a similar elastographic pattern, thus pointing that these techniques can be potentially useful to be applied in case of prostatic disorders to improve the accuracy of the final diagnosis in a non-invasive way.

TRUSformer: improving prostate cancer detection from micro-ultrasound using attention and self-supervision

PURPOSE

A large body of previous machine learning methods for ultrasound-based prostate cancer detection classify small regions of interest (ROIs) of ultrasound signals that lie within a larger needle trace corresponding to a prostate tissue biopsy (called biopsy core). These ROI-scale models suffer from weak labeling as histopathology results available for biopsy cores only approximate the distribution of cancer in the ROIs. ROI-scale models do not take advantage of contextual information that are normally considered by pathologists, i.e., they do not consider information about surrounding tissue and larger-scale trends when identifying cancer. We aim to improve cancer detection by taking a multi-scale, i.e., ROI-scale and biopsy core-scale, approach.

METHODS

Our multi-scale approach combines (i) an "ROI-scale" model trained using self-supervised learning to extract features from small ROIs and (ii) a "core-scale" transformer model that processes a collection of extracted features from multiple ROIs in the needle trace region to predict the tissue type of the corresponding core. Attention maps, as a by-product, allow us to localize cancer at the ROI scale.

RESULTS

We analyze this method using a dataset of micro-ultrasound acquired from 578 patients who underwent prostate biopsy, and compare our model to baseline models and other large-scale studies in the literature. Our model shows consistent and substantial performance improvements compared to ROI-scale-only models. It achieves [Formula: see text] AUROC, a statistically significant improvement over ROI-scale classification. We also compare our method to large studies on prostate cancer detection, using other imaging modalities.

CONCLUSIONS

Taking a multi-scale approach that leverages contextual information improves prostate cancer detection compared to ROI-scale-only models. The proposed model achieves a statistically significant improvement in performance and outperforms other large-scale studies in the literature. Our code is publicly available at www.github.com/med-i-lab/TRUSFormer .

Rats, Neuregulins and Radical Prostatectomy: A Conceptual Overview

In the contemporary era of early detection, with mostly curative initial treatment for prostate cancer (PC), mortality rates have significantly diminished. In addition, mean age at initial PC diagnosis has decreased. Despite technical advancements, the probability of erectile function (EF) recovery post radical prostatectomy (RP) has not significantly changed throughout the last decade. Due to virtually unavoidable intraoperative cavernous nerve (CN) lesions and operations with younger patients, post-RP erectile dysfunction (ED) has now begun affecting these younger patients. To address this pervasive limitation, a plethora of CN lesion animal model investigations have analyzed the use of systemic/local treatments for EF recovery post-RP. Most promisingly, neuregulins (NRGs) have demonstrated neurotrophic effects in both neurodegenerative disease and peripheral nerve injury models. Recently, glial growth factor 2 (GGF2) has demonstrated far superior, dose-dependent, neuroprotective/restorative effects in the CN injury rat model, as compared to previous therapeutic counterparts. Although potentially impactful, these initial findings remain limited and under-investigated. In an effort to aid clinicians, our paper reviews post-RP ED pathogenesis and currently available therapeutic tools. To stimulate further experimentation, a standardized preparation protocol and in-depth analysis of applications for the CN injury rat model is provided. Lastly, we report on NRGs, such as GGF2, and their potentially revolutionary clinical applications, in hopes of identifying relevant future research directions.

Artificial Intelligence for Cancer Detection-A Bibliometric Analysis and Avenues for Future Research

After cardiovascular diseases, cancer is responsible for the most deaths worldwide. Detecting a cancer disease early improves the chances for healing significantly. One group of technologies that is increasingly applied for detecting cancer is artificial intelligence. Artificial intelligence has great potential to support clinicians and medical practitioners as it allows for the early detection of carcinomas. During recent years, research on artificial intelligence for cancer detection grew a lot. Within this article, we conducted a bibliometric study of the existing research dealing with the application of artificial intelligence in cancer detection. We analyzed 6450 articles on that topic that were published between 1986 and 2022. By doing so, we were able to give an overview of this research field, including its key topics, relevant outlets, institutions, and articles. Based on our findings, we developed a future research agenda that can help to advance research on artificial intelligence for cancer detection. In summary, our study is intended to serve as a platform and foundation for researchers that are interested in the potential of artificial intelligence for detecting cancer.

Factors other than fibrosis that increase measured shear wave velocity

Shear wave elastography (SWE) is now becoming an indispensable diagnostic tool in the routine examination of liver diseases. In particular, accuracy is required for shear wave propagation velocity measurement, which is directly related to diagnostic accuracy. It is generally accepted that the liver shear wave propagation velocity reflects the degree of fibrosis, but there are still few reports on other factors that increase the shear wave propagation velocity. In this study, we reviewed such factors in the literature and examined their mechanisms. Current SWE measures propagation velocity based on the assumption that the medium has a homogeneous structure, uniform density, and is purely elastic. Otherwise, the measurement is subject to error. The other (confounding) factors that we routinely experience are primarily: (1) Conditions that appear to increase the viscous component; and (2) Conditions that appear to increase tissue density. Clinically, the former includes acute hepatitis, congested liver, biliary obstruction, etc, and the latter includes diffuse infiltration of malignant cells, various storage diseases, tissue necrosis, etc. In any case, it is important to evaluate SWE in the context of the entire clinical picture.

Artificial Intelligence for Clinical Diagnosis and Treatment of Prostate Cancer

As medical science and technology progress towards the era of "big data", a multi-dimensional dataset pertaining to medical diagnosis and treatment is becoming accessible for mathematical modelling. However, these datasets are frequently inconsistent, noisy, and often characterized by a significant degree of redundancy. Thus, extensive data processing is widely advised to clean the dataset before feeding it into the mathematical model. In this context, Artificial intelligence (AI) techniques, including machine learning (ML) and deep learning (DL) algorithms based on artificial neural networks (ANNs) and their types, are being used to produce a precise and cross-sectional illustration of clinical data. For prostate cancer patients, datasets derived from the prostate-specific antigen (PSA), MRI-guided biopsies, genetic biomarkers, and the Gleason grading are primarily used for diagnosis, risk stratification, and patient monitoring. However, recording diagnoses and further stratifying risks based on such diagnostic data frequently involves much subjectivity. Thus, implementing an AI algorithm on a PC's diagnostic data can reduce the subjectivity of the process and assist in decision making. In addition, AI is used to cut down the processing time and help with early detection, which provides a superior outcome in critical cases of prostate cancer. Furthermore, this also facilitates offering the service at a lower cost by reducing the amount of human labor. Herein, the prime objective of this review is to provide a deep analysis encompassing the existing AI algorithms that are being deployed in the field of prostate cancer (PC) for diagnosis and treatment. Based on the available literature, AI-powered technology has the potential for extensive growth and penetration in PC diagnosis and treatment to ease and expedite the existing medical process.