Usefulness of grayscale values measuring hypoechoic lesions for predicting prostate cancer: An experimental pilot study

Yoo, Jung-Sun; Lee, Kwang Suk

doi:10.1016/j.prnil.2021.11.002

Cited by 6 publications

(12 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, it is essential to identify the number of non-cancerous hypoechoic lesions for improved sensitivity while missing the number of neoplastic isoechoic lesions decreases sensitivity. This finding corresponds with previous studies that have examined the grayscale realization correlation with biopsy [46,47]. Conversely, Sauvain et al [48] compared the efficacy of grayscale and power Doppler sonography in detecting prostate cancer.…”

Section: Discussionsupporting

confidence: 89%

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

Jawli,

Nabi,

Huang

2024

Cancers

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionsupporting

confidence: 89%

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

Jawli,

Nabi,

Huang

2024

Cancers

View full text Add to dashboard Cite

show abstract

“…AI is a model that predicts based on learned data, and authors considered shapes and color as learned data. Several studies using numerical data of color using red/green/blue (RGB) method 8 have already been reported in other carcinomas 9 – 11 , and we also have reported the study using numerical color data for hypoechoic lesions of transrectal ultrasound 12 . Accordingly, the authors performed deep learning of AI by collecting WLI and NBI cystoscopic images of histopathologically confirmed benign and malignant lesions and confirmed the diagnostic performance and ability to identify tumor contours.…”

Section: Introductionmentioning

confidence: 59%

“…However, there were no studies using RGB method in the field of cystoscopy, and no studies in the field of urology that machine-learned the average RGB inside AI-identified tumor contours so we could not comparable, but this also presented good results. We have reported a successful study by applying the RGB method in transrectal ultrasound 12 . The color of bladder mass is different from that of the normal bladder mucosa, we made numerical data that the color of bladder tumor through RGB method.…”

Section: Discussionmentioning

confidence: 99%

Deep learning diagnostics for bladder tumor identification and grade prediction using RGB method

Yoo

Koo

Chung

et al. 2022

Sci Rep

View full text Add to dashboard Cite

We evaluate the diagnostic performance of deep learning artificial intelligence (AI) for bladder cancer, which used white-light images (WLIs) and narrow-band images, and tumor grade prediction of AI based on tumor color using the red/green/blue (RGB) method. This retrospective study analyzed 10,991 cystoscopic images of suspicious bladder tumors using a mask region-based convolutional neural network with a ResNeXt-101-32 × 8d-FPN backbone. The diagnostic performance of AI was evaluated by calculating sensitivity, specificity, and diagnostic accuracy, and its ability to detect cancers was investigated using the dice score coefficient (DSC). Using the support vector machine model, we analyzed differences in tumor colors according to tumor grade using the RGB method. The sensitivity, specificity, diagnostic accuracy and DSC of AI were 95.0%, 93.7%, 94.1% and 74.7%. In WLIs, there were differences in red and blue values according to tumor grade (p < 0.001). According to the average RGB value, the performance was ≥ 98% for the diagnosis of benign vs. low-and high-grade tumors using WLIs and > 90% for the diagnosis of chronic non-specific inflammation vs. carcinoma in situ using WLIs. The diagnostic performance of the AI-assisted diagnosis was of high quality, and the AI could distinguish the tumor grade based on tumor color.

show abstract

“…The inclusion criteria for the studies were either patients with a clinical suspicion of PC or patients with an elevated or increasing PSA. Moreover, 11 studies were performed with Micro-US [ 31 , 32 , 33 , 34 , 35 , 36 , 37 , 38 , 39 , 40 , 41 ], 2 studies with mpUS [ 30 , 42 ], 4 studies with grayscale [ 30 , 43 , 44 , 45 ], 7 studies with SWE [ 30 , 46 , 47 , 48 , 49 , 50 , 51 ] and 5 studies with CEUS [ 9 , 30 , 52 , 53 , 54 ].…”

Section: Resultsmentioning

confidence: 99%

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

Alghamdi

Kernohan

et al. 2023

Cancers

View full text Add to dashboard Cite

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.

show abstract

Usefulness of grayscale values measuring hypoechoic lesions for predicting prostate cancer: An experimental pilot study

Cited by 6 publications

References 24 publications

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

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

Deep learning diagnostics for bladder tumor identification and grade prediction using RGB method

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

Contact Info

Product

Resources

About