Artificial intelligence in prostate cancer: Definitions, current research, and future directions

George, Rose; Htoo, Arkar; Cheng, Monica; Masterson, Timothy M.; Huang, Kun; Adra, Nabil; Kaimakliotis, Hristos Z.; Akgul, Mahmut; Cheng, Liang

doi:10.1016/j.urolonc.2022.03.003

Cited by 9 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, the applications of machine learning, as a subfield of artificial intelligence, are rapidly developing in PCa due to the numerous technological domains involved in the diagnosis, prognosis, and treatment. The first artificial intelligence‐based pathology solution for prostate biopsy has been approved by the United States Food and Drug Administration, which enhanced the observation and interpretation of low‐level image analysis tasks and high‐level inference and prediction assignments in clinical practice 34 . A latest study of 1130 consecutive patients from a prospective database even demonstrated that the supervised machine learning algorithms could firmly predict biochemical recurrence after radical prostatectomy and surpass the conventional nomograms 35 .…”

Section: Discussionmentioning

confidence: 99%

“…The first artificial intelligence‐based pathology solution for prostate biopsy has been approved by the United States Food and Drug Administration, which enhanced the observation and interpretation of low‐level image analysis tasks and high‐level inference and prediction assignments in clinical practice. 34 A latest study of 1130 consecutive patients from a prospective database even demonstrated that the supervised machine learning algorithms could firmly predict biochemical recurrence after radical prostatectomy and surpass the conventional nomograms. 35 Nevertheless, the development, operation, and regulation of artificial intelligence‐based procedures require abundant clinical information and the collaboration of clinicians (such as urologists, radiologists, and pathologists), programmers, and engineers.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Development and validation of a novel nomogram predicting clinically significant prostate cancer in biopsy‐naive men based on multi‐institutional analysis

Ge,

Zhang,

et al. 2023

Cancer Medicine

View full text Add to dashboard Cite

BackgroundPrediction of clinically significant prostate cancer (csPCa) is essential to select biopsy‐naive patients for prostate biopsy. This study was to develop and validate a nomogram based on clinicodemographic parameters and exclude csPCa using prostate‐specific antigen density (PSAD) stratification.MethodsIndependent predictors were determined via univariate and multivariate logistic analysis and adopted for developing a predictive nomogram, which was assessed in terms of discrimination, calibration, and net benefit. Different PSAD thresholds were used for deciding immediate biopsies in patients with Prostate Imaging‐Reporting and Data System (PI‐RADS) 3 lesions.ResultsA total of 932 consecutive patients who underwent ultrasound‐guided transperineal cognitive biopsy were enrolled in our study. In the development cohort, age (odds ratio [OR], 1.075; 95% confidence interval [CI], 1.036–1.114), PSAD (OR, 6.003; 95% CI, 2.826–12.751), and PI‐RADS (OR, 3.419; 95% CI, 2.453–4.766) were significant predictors for csPCa. On internal and external validation, this nomogram showed high areas under the curve of 0.943, 0.922, and 0.897, and low Brier scores of 0.092, 0.102, and 0.133 and insignificant unreliability tests of 0.713, 0.490, and 0.859, respectively. Decision curve analysis revealed this model could markedly improve clinical net benefit. The probability of excluding csPCa was 98.51% in patients with PI‐RADS 3 lesions and PSAD <0.2 ng/ml2.ConclusionThis novel nomogram including age, PSAD, and PI‐RADS could be applied to accurately predict csPCa, and 44.08% of patients with equivocal imaging findings plus PSAD <0.2 ng/ml2 could safely forgo biopsy.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Development and validation of a novel nomogram predicting clinically significant prostate cancer in biopsy‐naive men based on multi‐institutional analysis

Ge,

Zhang,

et al. 2023

Cancer Medicine

View full text Add to dashboard Cite

show abstract

“…In the United States, prostate cancer is the most common non-cutaneous malignancy and the second leading cause of cancer death in men [9,46]. It is the sixth most common cancer worldwide and is often diagnosed by a prostate biopsy and graded according to the Gleason scale [46,47]. Other forms of screening and diagnostics include the prostatespecific antigen (PSA) blood test, MRI imaging of the prostate, and newer tests including urine biomarkers and genetic testing.…”

Section: Prostate Cancer Screeningmentioning

confidence: 99%

A Narrative Review of the Use of Artificial Intelligence in Breast, Lung, and Prostate Cancer

Patel,

Huang,

Rashid

et al. 2023

Life

View full text Add to dashboard Cite

Artificial intelligence (AI) has been an important topic within radiology. Currently, AI is used clinically to assist with the detection of lesions through detection systems. However, a number of recent studies have demonstrated the increased value of neural networks in radiology. With an increasing number of screening requirements for cancers, this review aims to study the accuracy of the numerous AI models used in the detection and diagnosis of breast, lung, and prostate cancers. This study summarizes pertinent findings from reviewed articles and provides analysis on the relevancy to clinical radiology. This study found that whereas AI is showing continual improvement in radiology, AI alone does not surpass the effectiveness of a radiologist. Additionally, it was found that there are multiple variations on how AI should be integrated with a radiologist’s workflow.

show abstract

“…Gleason grading, in particular, is the most reliable method for assessing aggressiveness [7] , [8] , [9] . However, interobserver and intraobserver variability in Gleason scores can result in under or over-treatment of patients in real-world scenarios [5] , [10] . Moreover, manually labeling pathological images for diagnosis is time-consuming and expensive [11] , [12] , [13] , [14] .…”

Section: Introductionmentioning

confidence: 99%

Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading

Kong,

Wang,

Xiang

et al. 2024

Computational and Structural Biotechnology Journal

View full text Add to dashboard Cite

Artificial intelligence in prostate cancer: Definitions, current research, and future directions

Cited by 9 publications

References 44 publications

Development and validation of a novel nomogram predicting clinically significant prostate cancer in biopsy‐naive men based on multi‐institutional analysis

Development and validation of a novel nomogram predicting clinically significant prostate cancer in biopsy‐naive men based on multi‐institutional analysis

A Narrative Review of the Use of Artificial Intelligence in Breast, Lung, and Prostate Cancer

Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading

Contact Info

Product

Resources

About