Evaluation of an Automated Analysis Tool for Prostate Cancer Prediction Using Multiparametric Magnetic Resonance Imaging

Computer-aided detection of prostate cancer in early stages using multi-parameter MRI: A promising approach for early diagnosis

BACKGROUND

Transrectal ultrasound-guided prostate biopsy is the gold standard diagnostic test for prostate cancer, but it is an invasive examination of non-targeted puncture and has a high false-negative rate.

OBJECTIVE

In this study, we aimed to develop a computer-assisted prostate cancer diagnosis method based on multiparametric MRI (mpMRI) images.

METHODS

We retrospectively collected 106 patients who underwent radical prostatectomy after diagnosis with prostate biopsy. mpMRI images, including T2 weighted imaging (T2WI), diffusion weighted imaging (DWI), and dynamic-contrast enhanced (DCE), and were accordingly analyzed. We extracted the region of interest (ROI) about the tumor and benign area on the three sequential MRI axial images at the same level. The ROI data of 433 mpMRI images were obtained, of which 202 were benign and 231 were malignant. Of those, 50 benign and 50 malignant images were used for training, and the 333 images were used for verification. Five main feature groups, including histogram, GLCM, GLGCM, wavelet-based multi-fractional Brownian motion features and Minkowski function features, were extracted from the mpMRI images. The selected characteristic parameters were analyzed by MATLAB software, and three analysis methods with higher accuracy were selected.

RESULTS

Through prostate cancer identification based on mpMRI images, we found that the system uses 58 texture features and 3 classification algorithms, including Support Vector Machine (SVM), K-nearest Neighbor (KNN), and Ensemble Learning (EL), performed well. In the T2WI-based classification results, the SVM achieved the optimal accuracy and AUC values of 64.3% and 0.67. In the DCE-based classification results, the SVM achieved the optimal accuracy and AUC values of 72.2% and 0.77. In the DWI-based classification results, the ensemble learning achieved optimal accuracy as well as AUC values of 75.1% and 0.82. In the classification results based on all data combinations, the SVM achieved the optimal accuracy and AUC values of 66.4% and 0.73.

CONCLUSION

The proposed computer-aided diagnosis system provides a good assessment of the diagnosis of the prostate cancer, which may reduce the burden of radiologists and improve the early diagnosis of prostate cancer.

PI-RADSAI: introducing a new human-in-the-loop AI model for prostate cancer diagnosis based on MRI

BACKGROUND

This study aims to develop and validate an artificial intelligence (AI)-aided Prostate Imaging Reporting and Data System (PI-RADSAI) for prostate cancer (PCa) diagnosis based on MRI.

METHODS

The deidentified MRI data of 1540 biopsy-naïve patients were collected from four centres. PI-RADSAI is a two-stage, human-in-the-loop AI capable of emulating the diagnostic acumen of subspecialists for PCa on MRI. The first stage uses a UNet-Seg model to detect and segment biopsy-candidate prostate lesions, whereas the second stage leverages UNet-Seg segmentation is trained specifically with subspecialist' knowledge-guided 3D-Resnet to achieve an automatic AI-aided diagnosis for PCa.

RESULTS

In the independent test set, UNet-Seg identified 87.2% (628/720) of target lesions, with a Dice score of 44.9% (range, 22.8-60.2%) in segmenting lesion contours. In the ablation experiment, the model trained with the data from three centres was superior (kappa coefficient, 0.716 vs. 0.531) to that trained with single-centre data. In the internal and external tests, the triple-centre PI-RADSAI model achieved an overall agreement of 58.4% (188/322) and 60.1% (92/153) with a referential subspecialist in scoring target lesions; when one-point margin of error was permissible, the agreement rose to 91.3% (294/322) and 97.3% (149/153), respectively. In the paired test, PI-RADSAI outperformed 5/11 (45.5%) and matched the performance of 3/11 (27.3%) general radiologists in achieving a clinically significant PCa diagnosis (area under the curve, internal test, 0.801 vs. 0.770, p < 0.01; external test, 0.833 vs. 0.867, p = 0.309).

CONCLUSIONS

Our closed-loop PI-RADSAI outperforms or matches the performance of more than 70% of general readers in the MRI assessment of PCa. This system might provide an alternative to radiologists and offer diagnostic benefits to clinical practice, especially where subspecialist expertise is unavailable.

Computer-aided diagnosis in prostate cancer: a retrospective evaluation of the Watson Elementary® system for preoperative tumor characterization in patients treated with robot-assisted radical prostatectomy

PURPOSE

Computer-aided diagnosis (CAD) may improve prostate cancer (PCa) detection and support multiparametric magnetic resonance imaging (mpMRI) readers for better characterization. We evaluated Watson Elementary^® (WE^®) CAD system results referring to definitive pathological examination in patients treated with robot-assisted radical prostatectomy (RARP) in a tertiary referral center.

METHODS

Patients treated with RARP between 2020 and 2021 were selected. WE^® calculates the Malignancy Attention Index (MAI), starting from the information contained in the mpMRI images. Outcome measures were the capability to predict the presence of PCa, to correctly locate the dominant lesion, to delimit the largest diameter of the dominant lesion, and to predict the extraprostatic extension (EPE).

RESULTS

Overall, tumor presence was confirmed in 46 (92%) WE^® highly suspicious areas, while it was confirmed in 43 (86%) mpMRI PI-RADS ≥ 4 lesions. The WE^® showed a positive agreement with mpMRI of 92%. In 98% of cases, visible tumor at WE^® showed that the highly suspicious areas were within the same prostate sector of the dominant tumor nodule at pathology. WE^® showed a 2.5 mm median difference of diameter with pathology, compared with a 3.8 mm of mpMRI versus pathology (p = 0.019). In prediction of EPE, WE^® and mpMRI showed sensitivity, specificity, positive and negative predictive value of 0.81 vs 0.71, 0.56 vs 0.60, 0.88 vs 0.85 and 0.42 vs 0.40, respectively.

CONCLUSION

The WE^® system resulted accurate in the PCa dominant lesion detection, localization and delimitation providing additional information concerning EPE prediction.

Performance of Artificial Intelligence-Aided Diagnosis System for Clinically Significant Prostate Cancer with MRI: A Diagnostic Comparison Study

BACKGROUND

The high level of expertise required for accurate interpretation of prostate MRI.

PURPOSE

To develop and test an artificial intelligence (AI) system for diagnosis of clinically significant prostate cancer (CsPC) with MRI.

STUDY TYPE

Retrospective.

SUBJECTS

One thousand two hundred thirty patients from derivation cohort between Jan 2012 and Oct 2019, and 169 patients from a publicly available data (U-Net: 423 for training/validation and 49 for test and TrumpeNet: 820 for training/validation and 579 for test).

FIELD STRENGTH/SEQUENCE

3.0T/scanners, T₂ -weighted imaging (T₂ WI), diffusion-weighted imaging, and apparent diffusion coefficient map.

ASSESSMENT

Close-loop AI system was trained with an Unet for prostate segmentation and a TrumpetNet for CsPC detection. Performance of AI was tested in 410 internal and 169 external sets against 24 radiologists categorizing into junior, general and subspecialist group. Gleason score >6 was identified as CsPC at pathology.

STATISTICAL TESTS

Area under the receiver operating characteristic curve (AUC-ROC); Delong test; Meta-regression I² analysis.

RESULTS

In average, for internal test, AI had lower AUC-ROC than subspecialists (0.85 vs. 0.92, P < 0.05), and was comparable to junior (0.84, P = 0.76) and general group (0.86, P = 0.35). For external test, both AI (0.86) and subspecialist (0.86) had higher AUC than junior (0.80, P < 0.05) and general reader (0.83, P < 0.05). In individual, it revealed moderate diagnostic heterogeneity in 24 readers (Mantel-Haenszel I²  = 56.8%, P < 0.01), and AI outperformed 54.2% (13/24) of readers in summary ROC analysis. In multivariate test, Gleason score, zonal location, PI-RADS score and lesion size significantly impacted the accuracy of AI; while effect of data source, MR device and parameter settings on AI performance is insignificant (P > 0.05).

DATA CONCLUSION

Our AI system can match and to some case exceed clinicians for the diagnosis of CsPC with prostate MRI.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Prostate Cancer Detection with mpMRI According to PI-RADS v2 Compared with Systematic MRI/TRUS-Fusion Biopsy: A Prospective Study

Background: mpMRI assesses prostate lesions through their PI-RADS score. The primary goal of this prospective study was to demonstrate the correlation of PI-RADS v2 score and the volume of a lesion with the presence and clinical significance of prostate cancer (PCa). The secondary goal was to determine the extent of additionally PCa in inconspicuous areas. Methods: All 157 patients underwent a perineal MRI/TRUS-fusion prostate biopsy. Targeted biopsies as well as a systematic biopsy were performed. The presence of PCa in the probes was specified by the ISUP grading system. Results: In total, 258 lesions were biopsied. Of the PI-RADS 3 lesions, 24% were neoplastic. This was also true for 36.9% of the PI-RADS 4 lesions and for 59.5% of the PI-RADS 5 lesions. Correlation between ISUP grades and lesion volume was significant (p < 0.01). In the non-suspicious mpMRI areas carcinoma was revealed in 19.7% of the patients. Conclusions: The study shows that the PI-RADS v2 score and the lesion volume correlate with the presence and clinical significance of PCa. However, there are two major points to consider: First, there is a high number of false positive findings. Second, inconspicuous mpMRI areas revealed PCa.

Diagnostic accuracy of different computer-aided diagnostic systems for prostate cancer based on magnetic resonance imaging: A systematic review with diagnostic meta-analysis

BACKGROUND

Computer-aided detection (CAD) system for accurate and automated prostate cancer (PCa) diagnosis have been developed, however, the diagnostic test accuracy of different CAD systems is still controversial. This systematic review aimed to assess the diagnostic accuracy of CAD systems based on magnetic resonance imaging for PCa.

METHODS

Cochrane library, PubMed, EMBASE and China Biology Medicine disc were systematically searched until March 2019 for original diagnostic studies. Two independent reviewers selected studies on CAD based on magnetic resonance imaging diagnosis of PCa and extracted the requisite data. Pooled sensitivity, specificity, and the area under the summary receiver operating characteristic curve were calculated to estimate the diagnostic accuracy of CAD system.

RESULTS

Fifteen studies involving 1945 patients were included in our analysis. The diagnostic meta-analysis showed that overall sensitivity of CAD system ranged from 0.47 to 1.00 and, specificity from 0.47 to 0.89. The pooled sensitivity of CAD system was 0.87 (95% CI: 0.76-0.94), pooled specificity 0.76 (95% CI: 0.62-0.85), and the area under curve (AUC) 0.89 (95% CI: 0.86-0.91). Subgroup analysis showed that the support vector machines produced the best AUC among the CAD classifiers, with sensitivity ranging from 0.87 to 0.92, and specificity from 0.47 to 0.95. Among different zones of prostate, CAD system produced the best AUC in the transitional zone than the peripheral zone and central gland; sensitivity ranged from 0.89 to 1.00, and specificity from 0.38 to 0.85.

CONCLUSIONS

CAD system can help improve the diagnostic accuracy of PCa especially using the support vector machines classifier. Whether the performance of the CAD system depends on the specific locations of the prostate needs further investigation.

Fusion US/MRI prostate biopsy using a computer aided diagnostic (CAD) system

BACKGROUND

The aim of this study was to investigate the impact of computer aided diagnostic (CAD) system on the detection rate of prostate cancer (PCa) in a series of fusion prostate biopsy (FPB).

METHODS

Two prospective transperineal FPB series (with or without CAD assistance) were analyzed and PCa detection rates compared with per-patient and per-target analyses. The χ² and Mann-Whitney test were used to compare categorical and continuous variables, respectively. Univariable and multivariable regression analyses were applied to identify predictors of any and clinically significant (cs) PCa detection. Subgroup analyses were performed after stratifying for PI-RADS Score and lesion location.

RESULTS

Out of 183 FPB, 89 were performed with CAD assistance. At per-patient analysis the detection rate of any PCa and of cs PCa were 56.3% and 30.6%, respectively; the aid of CAD was negligible for either any PCa or csPCa detection rates (P=0.45 and P=0.99, respectively). Conversely in a per-target analysis, CAD-assisted biopsy had significantly higher positive predictive value (PPV) for any PCa versus MRI-only group (58% vs. 37.8%, P=0.001). PI-RADS Score was the only independent predictor of any and csPCa, either in per-patient or per-target multivariable regression analysis (all P<0.029). In a subgroup per-patient analysis of anterior/transitional zone lesions, csPCa detection rate was significantly higher in the CAD cohort (54.5%vs.11.1%, respectively; P=0.028), and CAD assistance was the only predictor of csPCa detection (P=0.013).

CONCLUSIONS

CAD assistance for FPB seems to improve detection of csPCa located in anterior/transitional zone. Enhanced identification and improved contouring of lesions may justify higher diagnostic performance.

Early Diagnosis of Prostate Cancer from the Perspective of Chinese Physicians

Prostate cancer (PCa) is the seventh most diagnosed cancer and the tenth leading cause of cancer mortality in China. Unlike the USA, both incidence and mortality continue to increase. In China, PCa is often diagnosed at a locally advanced or metastatic stage, resulting in a high mortality-to-incidence ratio. Implementing regular screening using a well-validated biomarker may result in the earlier diagnosis of localized disease. Furthermore, it is important to be able to distinguish between low-grade and high-grade disease, to avoid subjecting patients to unnecessary biopsies, undertreatment of significant disease, or overtreatment of indolent disease. While prostate-specific antigen (PSA) is commonly used in PCa screening around the world, its relationship to PCa is still unclear and results vary widely across different studies. New biomarkers, imaging techniques and risk predictive models have been developed in recent years to improve upon the accurate detection of high-grade PCa. Blood- and urine-based biomarkers, such as PSA isoforms, prostate cancer antigen 3, or mRNA transcripts, have been used to improve the detection of high-grade PCa. These markers have also been used to create risk predictive models, which can further improve PCa detection. Furthermore, multiparametric magnetic resonance imaging is becoming increasingly accessible for the detection of PCa. Because of ethnic variations, biomarkers and risk predictive models validated in Western populations cannot be directly applied to Chinese men. Validation of new biomarkers and risk predictive models in the Chinese population may improve PCa screening and reduce mortality of this disease in China.

Computer-aided detection for prostate cancer diagnosis based on magnetic resonance imaging: Protocol for a systematic review and meta-analysis

BACKGROUND

Prostate cancer (PCa) is one of the most common primary malignancies in humans and the second leading cause of cancer-specific mortality among Western males. Computer-aided detection (CAD) systems have been developed for accurate and automated PCa detection and diagnosis, but the diagnostic accuracy of different CAD systems based on magnetic resonance imaging (MRI) for PCa remains controversial. The aim of this study is to systematically review the published evidence to investigate diagnostic accuracy of different CAD systems based on MRI for PCa.

METHODS

We will conduct the systematic review and meta-analysis according to the Preferred Reporting Items for a systematic review and meta-analysis of diagnostic test accuracy studies (PRISMA-DTA) guidelines. Cochrane library, PubMed, EMBASE and Chinese Biomedicine Literature Database will be systematically searched from inception for eligible articles, 2 independent reviewers will select studies on CAD-based MRI diagnosis of PCa and extract the requisite data. The quality of reporting evidence will be assessed using the quality assessment of diagnosis accuracy study (QUADAS-2) tool. Pooled sensitivity, specificity, and the area under the summary receiver operating characteristic (SROC) curves will be calculated to estimate the diagnostic accuracy of CAD system. In addition, we will conduct subgroup analyses according to the type of classifier of CAD systems used and the different prostate zoon.

RESULTS

This study will conduct a meta-analysis of current evidence to investigate the diagnostic accuracy of CAD systems based on MRI for PCa by calculating sensitivity, specificity, and SROC curves.

CONCLUSION

The conclusion of this study will provide evidence to judge whether CAD systems based on MRI have high diagnostic accuracy for PCa.

ETHICS AND DISSEMINATION

Ethics approval is not required for this systematic review as it will involve the collection and analysis of secondary data. The results of the review will be reported in international peer-reviewed journals.

PROSPERO REGISTRATION NUMBER

CRD42019132543.

Improvement of prostate cancer detection combining a computer-aided diagnostic system with TRUS-MRI targeted biopsy

PURPOSE

To validate a novel consensus method, called target-in-target, combining human analysis of mpMRI with automated CAD system analysis, with the aim to increasing the prostate cancer detection rate of targeted biopsies.

METHODS

A cohort of 420 patients was enrolled and 253 patients were rolled out, due to exclusion criteria. 167 patients, underwent diagnostic 3T MpMRI. Two expert radiologists evaluated the exams adopting PI-RADSv2 and CAD system. When a CAD target overlapped with a radiologic one, we performed the biopsy in the overlapping area which we defined as target-in-target. Targeted TRUS-MRI fusion biopsy was performed in 63 patients with a total of 212 targets. The MRI data of all targets were quantitatively analyzed, and diagnostic findings were compared to pathologist's biopsy reports.

RESULTS

CAD system diagnostic performance exhibited sensitivity and specificity scores of 55.2% and 74.1% [AUC = 0.63 (0.54 ÷ 0.71)] , respectively. Human readers achieved an AUC value, in ROC analysis, of 0.71 (0.63 ÷ 0.79). The target-in-target method provided a detection rate per targeted biopsy core of 81.8 % vs. a detection rate per targeted biopsy core of 68.6 % for pure PI-RADS based on target definitions. The higher per-core detection rate of the target-in-target approach was achieved irrespective of the presence of technical flaws and artifacts.

CONCLUSIONS

A novel consensus method combining human reader evaluation with automated CAD system analysis of mpMRI to define prostate biopsy targets was shown to improve the detection rate per biopsy core of TRUS-MRI fusion biopsies. Results suggest that the combination of CAD system analysis and human reader evaluation is a winning strategy to improve targeted biopsy efficiency.

Computer aided detection in prostate cancer diagnostics: A promising alternative to biopsy? A retrospective study from 104 lesions with histological ground truth

BACKGROUND

Prostate cancer (PCa) diagnosis by means of multiparametric magnetic resonance imaging (mpMRI) is a current challenge for the development of computer-aided detection (CAD) tools. An innovative CAD-software (Watson Elementary™) was proposed to achieve high sensitivity and specificity, as well as to allege a correlate to Gleason grade.

AIM/OBJECTIVE

To assess the performance of Watson Elementary™ in automated PCa diagnosis in our hospital´s database of MRI-guided prostate biopsies.

METHODS

The evaluation was retrospective for 104 lesions (47 PCa, 57 benign) from 79, 64.61±6.64 year old patients using 3T T2-weighted imaging, Apparent Diffusion Coefficient (ADC) maps and dynamic contrast enhancement series. Watson Elementary™ utilizes signal intensity, diffusion properties and kinetic profile to compute a proportional Gleason grade predictor, termed Malignancy Attention Index (MAI). The analysis focused on (i) the CAD sensitivity and specificity to classify suspect lesions and (ii) the MAI correlation with the histopathological ground truth.

RESULTS

The software revealed a sensitivity of 46.80% for PCa classification. The specificity for PCa was found to be 75.43% with a positive predictive value of 61.11%, a negative predictive value of 63.23% and a false discovery rate of 38.89%. CAD classified PCa and benign lesions with equal probability (P 0.06, χ2 test). Accordingly, receiver operating characteristic analysis suggests a poor predictive value for MAI with an area under curve of 0.65 (P 0.02), which is not superior to the performance of board certified observers. Moreover, MAI revealed no significant correlation with Gleason grade (P 0.60, Pearson´s correlation).

CONCLUSION

The tested CAD software for mpMRI analysis was a weak PCa biomarker in this dataset. Targeted prostate biopsy and histology remains the gold standard for prostate cancer diagnosis.