Automated diagnosis of prostate cancer location by artificial intelligence in multiparametric MRI

2018 ◽  
Vol 17 (2) ◽  
pp. e888-e889 ◽  
Author(s):  
Y. Oishi ◽  
T. Kitta ◽  
N. Shinohara ◽  
H. Nosato ◽  
H. Sakanashi ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
Multiparametric Mri ◽  
Automated Diagnosis

scholarly journals MP20-04 AUTOMATED DIAGNOSIS OF PROSTATE CANCER LOCATION AND FORM BY ARTIFICIAL INTELLIGENCE IN MULTIPARAMETRIC MRI

2018 ◽  
Vol 199 (4S) ◽  
Author(s):  
Yuichiro Oishi ◽  
Takeya Kitta ◽  
Nobuo Shinohara ◽  
Hirokazu Nosato ◽  
Hidenori Sakanashi ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
Multiparametric Mri ◽  
Automated Diagnosis

scholarly journals Artificial Intelligence Is a Promising Prospect for the Detection of Prostate Cancer Extracapsular Extension With Mp-mri: A Two-center Comparative Study

2021 ◽  
Author(s):  
Ying Hou ◽  
Yi-Hong Zhang ◽  
Jie Bao ◽  
Mei-Ling Bao ◽  
Guang Yang ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
Paired Comparison ◽  
Characteristic Curve ◽  
Multiparametric Mri ◽  
Training Data ◽  
Urinary Continence ◽  
Data Sets ◽  
Extracapsular Extension ◽  
Promising Alternative

Abstract Purpose: A balance between preserving urinary continence and achievement of negative margins is of clinical relevance while implementary difficulty. Preoperatively accurate detection of prostate cancer (PCa) extracapsular extension (ECE) is thus crucial for determining appropriate treatment options. We aimed to develop and clinically validate an artificial intelligence (AI)-assisted tool for the detection of ECE in patients with PCa using multiparametric MRI. Methods: 849 patients with localized PCa underwent multiparametric MRI before radical prostatectomy were retrospectively included from two medical centers. The AI tool was built on a ResNeXt network embedded with a spatial attention map of experts’ prior knowledges (PAGNet) from 596 training data sets. The tool was validated in 150 internal and 103 external data sets, respectively; and its clinical applicability was compared with expert-based interpretation and AI-expert interaction.Results: An index PAGNet model using a single-slice image yielded the highest areas under the receiver operating characteristic curve (AUC) of 0.857 (95% confidence interval [CI], 0.827-0.884), 0.807 (95% CI, 0.735-0.867) and 0.728 (95% CI, 0.631-0.811) in the training, internal test and external test cohorts, compared to the conventional ResNeXt networks. For experts, the inter-reader agreement was observed in only 437/849 (51.5%) patients with a Kappa value 0.343. And the performance of two experts (AUC, 0.632 to 0.741 vs 0.715 to 0.857) was lower (paired comparison, all p values < 0.05) than that of AI assessment. When expert’ interpretations were adjusted by the AI assessments, the performance of both two experts was improved.Conclusion: Our AI tool, showing improved accuracy, offers a promising alternative to human experts for imaging staging of PCa ECE using multiparametric MRI.

scholarly journals Multicenter Multireader Evaluation of an Artificial Intelligence–Based Attention Mapping System for the Detection of Prostate Cancer With Multiparametric MRI

2020 ◽  
Vol 215 (4) ◽  
pp. 903-912 ◽  
Author(s):  
Sherif Mehralivand ◽  
Stephanie A. Harmon ◽  
Joanna H. Shih ◽  
Clayton P. Smith ◽  
Nathan Lay ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
Multiparametric Mri ◽  
Mapping System

scholarly journals Diagnosis and Localization of Prostate Cancer via Automated Multiparametric MRI Equipped with Artificial Intelligence

Uro ◽  
2022 ◽  
Vol 2 (1) ◽  
pp. 21-29
Author(s):  
Yuichiro Oishi ◽  
Takeya Kitta ◽  
Takahiro Osawa ◽  
Takashige Abe ◽  
Nobuo Shinohara ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
Radical Prostatectomy ◽  
Roc Curve ◽  
Texture Features ◽  
Peripheral Zone ◽  
Multiparametric Mri ◽  
Shape Estimation ◽  
Chi Square ◽  
Mri Scans

Prostate MRI scans for pre-biopsied patients are important. However, fewer radiologists are available for MRI diagnoses, which requires multi-sequential interpretations of multi-slice images. To reduce such a burden, artificial intelligence (AI)-based, computer-aided diagnosis is expected to be a critical technology. We present an AI-based method for pinpointing prostate cancer location and determining tumor morphology using multiparametric MRI. The study enrolled 15 patients who underwent radical prostatectomy between April 2008 and August 2017 at our institution. We labeled the cancer area on the peripheral zone on MR images, comparing MRI with histopathological mapping of radical prostatectomy specimens. Likelihood maps were drawn, and tumors were divided into morphologically distinct regions using the superpixel method. Likelihood maps consisted of pixels, which utilize the cancer likelihood value computed from the T2-weighted, apparent diffusion coefficient, and diffusion-weighted MRI-based texture features. Cancer location was determined based on the likelihood maps. We evaluated the diagnostic performance by the area under the receiver operating characteristic (ROC) curve according to the Chi-square test. The area under the ROC curve was 0.985. Sensitivity and specificity for our approach were 0.875 and 0.961 (p < 0.01), respectively. Our AI-based procedures were successfully applied to automated prostate cancer localization and shape estimation using multiparametric MRI.

scholarly journals Study protocol for a single-centre non-inferior randomised controlled trial on a novel three-dimensional matrix positioning-based cognitive fusion-targeted biopsy and software-based fusion-targeted biopsy for the detection rate of clinically significant prostate cancer in men without a prior biopsy

BMJ Open ◽  
2021 ◽  
Vol 11 (2) ◽  
pp. e041427
Author(s):  
Biming He ◽  
Rongbing Li ◽  
Dongyang Li ◽  
Liqun Huang ◽  
Xiaofei Wen ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Detection Rate ◽  
Three Dimensional ◽  
Multiparametric Mri ◽  
Fusion Method ◽  
Targeted Biopsy ◽  
Cognitive Fusion ◽  
Single Centre ◽  
Clinically Significant ◽  
Randomised Controlled

IntroductionThe classical pathway for diagnosing prostate cancer is systematic 12-core biopsy under the guidance of transrectal ultrasound, which tends to underdiagnose the clinically significant tumour and overdiagnose the insignificant disease. Another pathway named targeted biopsy is using multiparametric MRI to localise the tumour precisely and then obtain the samples from the suspicious lesions. Targeted biopsy, which is mainly divided into cognitive fusion method and software-based fusion method, is getting prevalent for its good performance in detecting significant cancer. However, the preferred targeted biopsy technique in detecting clinically significant prostate cancer between cognitive fusion and software-based fusion is still beyond consensus.Methods and analysisThis trial is a prospective, single-centre, randomised controlled and non-inferiority study in which all men suspicious to have clinically significant prostate cancer are included. This study aims to determine whether a novel three-dimensional matrix positioning cognitive fusion-targeted biopsy is non-inferior to software-based fusion-targeted biopsy in the detection rate of clinically significant cancer in men without a prior biopsy. The main inclusion criteria are men with elevated serum prostate-specific antigen above 4–20 ng/mL or with an abnormal digital rectal examination and have never had a biopsy before. A sample size of 602 participants allowing for a 10% loss will be recruited. All patients will undergo a multiparametric MRI examination, and those who fail to be found with a suspicious lesion, with the anticipation of half of the total number, will be dropped. The remaining participants will be randomly allocated to cognitive fusion-targeted biopsy (n=137) and software-based fusion-targeted biopsy (n=137). The primary outcome is the detection rate of clinically significant prostate cancer for cognitive fusion-targeted biopsy and software-based fusion-targeted biopsy in men without a prior biopsy. The clinically significant prostate cancer will be defined as the International Society of Urological Pathology grade group 2 or higher.Ethics and disseminationEthical approval was obtained from the ethics committee of Shanghai East Hospital, Tongji University School of Medicine, Shanghai, China. The results of the study will be disseminated and published in international peer-reviewed journals.Trial registration numberClinicalTrials.gov Registry (NCT04271527).

Sign in / Sign up

Export Citation Format

Share Document