AI-assisted biparametric MRI surveillance of prostate cancer: feasibility study

Feasibility study of AI-assisted multi-parameter MRI diagnosis of prostate cancer

Distinguishing between benign and malignant prostate lesions in magnetic resonance imaging (MRI) poses challenges that affect prostate cancer screening accuracy. We propose a novel computer-aided diagnosis (CAD) system to extract cancerous lesions from the prostate in multi-parametric MRI (mp-MRI), assessing the feasibility of using artificial intelligence for detecting clinically significant prostate cancer (PCa). A retrospective study was conducted on 106 patients who underwent mp-MRI from 2021 to 2024 at a single center. We analyzed three sequences (T2W, DCE, and DWI) and collected 137 mp-MRI images corresponding to pathological sections. From these, we obtained 274 sets of ROI data, using 206 for training and validation, and 68 for testing. A feature extractor was developed using a pre-trained ResNet50 model combined with a multi-head attention mechanism to fuse modality-specific features and perform classification. The experimental results indicate that our model demonstrates high classification performance, achieving an AUC of 0.89. The PR curve shows high precision across most recall values, with an AUC of 0.91. We developed a novel CAD system based on deep learning ResNet50 models to assess the risk of prostate malignancy in mpMRI images. High classification ability is achieved, and combining the attention mechanism or optimization strategy can improve the performance of the model in medical imaging.

Prostate Cancer Classification and Interpretation With Multiparametric Magnetic Resonance Imaging and Gleason Grade Score Using DarkNet53 Model

BACKGROUND

Prostate Cancer (PCa) increases the mortality rate of males worldwide and is caused by genetics, lifestyle, and age reasons. The existing automated PCa classification systems face difficulties with overfitting issues, and non-generalizability, leading to poor classification performance.

OBJECTIVE

On this account, this study proposes an automated classification of PCa from MRI images using a hybrid weighted mean of vectors-optimized DarkNet53 classifier model.

METHODOLOGY

The proposed method suggests nonlocal mean filtering for noise reduction, N4ITK bias field correction to enhance image quality, and active contour-based segmentation for accurately identifying the disease region. The feature extraction utilizes the gray level run length matrix and shape features for effective feature extraction. A weighted mean of vectors optimization is used to optimize the feature selection process by hybridizing it with the DarkNet53 model for classification. Finally, the interpretation of achieving the classification has been demonstrated using the explainable AI Grad-CAM model.

RESULTS

After comparing the proposed work with various state-of-the-art algorithms, the proposed model achieves 99.31% accuracy, 98.24% sensitivity, and 98.46% specificity, respectively, highlighting the model's accomplishment using the DarkNet53 classifier.

Development and Validation of a Deep Learning Model Based on MRI and Clinical Characteristics to Predict Risk of Prostate Cancer Progression

Purpose To validate a deep learning (DL) model for predicting the risk of prostate cancer (PCa) progression based on MRI and clinical parameters and compare it with established models. Materials and Methods This retrospective study included 1607 MRI scans of 1143 male patients (median age, 64 years; IQR, 59-68 years) undergoing MRI for suspicion of clinically significant PCa (csPCa) (International Society of Urological Pathology grade > 1) between January 2012 and May 2022 who were negative for csPCa at baseline MRI. A DL model was developed using baseline MRI and clinical parameters (age, prostate-specific antigen [PSA] level, PSA density, and prostate volume) to predict the time to PCa progression (defined as csPCa diagnosis at follow-up). Internal and external testing was performed. The model's ability to predict progression to csPCa was assessed by Cox regression analyses. Predictive performance of the DL model up to 5 years after baseline MRI in comparison with the European Randomized Study of Screening for Prostate Cancer (ERSPC) future-risk calculator, Prostate Cancer Prevention Trial (PCPT) risk calculator, and Prostate Imaging Reporting and Data System (PI-RADS) was assessed using the Harrell C-index. Optimized follow-up intervals were derived from Kaplan-Meier curves. Results DL scores predicted csPCa progression (internal cohort: hazard ratio [HR], 1.97 [95% CI: 1.61, 2.41; P < .001]; external cohort: HR, 1.32 [95% CI: 1.14, 1.55; P < .001]). The model identified a subgroup of patients (approximately 20%) with risks for csPCa of 3% or less, 8% or less, and 18% or less after 1-, 2-, and 4-year follow-up, respectively. DL scores had a C-index of 0.68 (95% CI: 0.63, 0.74) at internal testing and 0.56 (95% CI: 0.51, 0.61) at external testing, outperforming ERSPC and PCPT (both P < .001) at internal testing. Conclusion The DL model accurately predicted PCa progression and provided improved risk estimations, demonstrating its ability to aid in personalized follow-up for low-risk PCa. Keywords: MRI, Prostate Cancer, Deep Learning Supplemental material is available for this article. ©RSNA, 2025.

Prostate MRI and artificial intelligence during active surveillance: should we jump on the bandwagon?

OBJECTIVE

To review the components of past and present active surveillance (AS) protocols, provide an overview of the current studies employing artificial intelligence (AI) in AS of prostate cancer, discuss the current challenges of AI in AS, and offer recommendations for future research.

METHODS

Research studies on the topic of MRI-based AI were reviewed to summarize current possibilities and diagnostic accuracies for AI methods in the context of AS. Established guidelines were used to identify possibilities for future refinement using AI.

RESULTS

Preliminary results show the role of AI in a range of diagnostic tasks in AS populations, including the localization, follow-up, and prognostication of prostate cancer. Current evidence is insufficient to support a shift to AI-based AS, with studies being limited by small dataset sizes, heterogeneous inclusion and outcome definitions, or lacking appropriate benchmarks.

CONCLUSION

The AI-based integration of prostate MRI is a direction that promises substantial benefits for AS in the future, but evidence is currently insufficient to support implementation. Studies with standardized inclusion criteria and standardized progression definitions are needed to support this. The increasing inclusion of patients in AS protocols and the incorporation of MRI as a scheduled examination in AS protocols may help to alleviate these challenges in future studies.

CLINICAL RELEVANCE STATEMENT

This manuscript provides an overview of available evidence for the integration of prostate MRI and AI in active surveillance, addressing its potential for clinical optimizations in the context of established guidelines, while highlighting the main challenges for implementation.

KEY POINTS

Active surveillance is currently based on diagnostic tests such as PSA, biopsy, and imaging. Prostate MRI and AI demonstrate promising diagnostic accuracy across a variety of tasks, including the localization, follow-up and risk estimation in active surveillance cohorts. A transition to AI-based active surveillance is not currently realistic; larger studies using standardized inclusion criteria and outcomes are necessary to improve and validate existing evidence.

Biparametric MRI in prostate cancer during active surveillance: is it safe?

Active surveillance (AS) is the preferred option for patients presenting with low-intermediate-risk prostate cancer. MRI now plays a crucial role for baseline assessment and ongoing monitoring of AS. The Prostate Cancer Radiological Estimation of Change in Sequential Evaluation (PRECISE) recommendations aid radiological assessment of progression; however, current guidelines do not advise on MRI protocols nor on frequency. Biparametric (bp) imaging without contrast administration offers advantages such as reduced costs and increased throughput, with similar outcomes to multiparametric (mp) MRI shown in the biopsy naïve setting. In AS follow-up, the paradigm shifts from MRI lesion detection to assessment of progression, and patients have the further safety net of continuing clinical surveillance. As such, bpMRI may be appropriate in clinically stable patients on routine AS follow-up pathways; however, there is currently limited published evidence for this approach. It should be noted that mpMRI may be mandated in certain patients and potentially offers additional advantages, including improving image quality, new lesion detection, and staging accuracy. Recently developed AI solutions have enabled higher quality and faster scanning protocols, which may help mitigate against disadvantages of bpMRI. In this article, we explore the current role of MRI in AS and address the need for contrast-enhanced sequences. CLINICAL RELEVANCE STATEMENT: Active surveillance is the preferred plan for patients with lower-risk prostate cancer, and MRI plays a crucial role in patient selection and monitoring; however, current guidelines do not currently recommend how or when to perform MRI in follow-up. KEY POINTS: Noncontrast biparametric MRI has reduced costs and increased throughput and may be appropriate for monitoring stable patients. Multiparametric MRI may be mandated in certain patients, and contrast potentially offers additional advantages. AI solutions enable higher quality, faster scanning protocols, and could mitigate the disadvantages of biparametric imaging.

Biparametric vs. Multiparametric MRI in the Detection of Cancer in Transperineal Targeted-Biopsy-Proven Peripheral Prostate Cancer Lesions Classified as PI-RADS Score 3 or 3+1: The Added Value of ADC Quantification

BACKGROUND

Biparametric MRI (bpMRI) has an important role in the diagnosis of prostate cancer (PCa), by reducing the cost and duration of the procedure and adverse reactions. We assess the additional benefit of the ADC map in detecting prostate cancer (PCa). Additionally, we examine whether the ADC value correlates with the presence of clinically significant tumors (csPCa).

METHODS

104 peripheral lesions classified as PI-RADS v2.1 score 3 or 3+1 at the mpMRI underwent transperineal MRI/US fusion-guided targeted biopsy.

RESULTS

The lesions were classified as PI-RADS 3 or 3+1; at histopathology, 30 were adenocarcinomas, 21 of which were classified as csPCa. The ADC threshold that maximized the Youden index in order to predict the presence of a tumor was 1103 (95% CI (990, 1243)), with a sensitivity of 0.8 and a specificity of 0.59; both values were greater than those found using the contrast medium, which were 0.5 and 0.54, respectively. Similar results were also found with csPCa, where the optimal ADC threshold was 1096 (95% CI (988, 1096)), with a sensitivity of 0.86 and specificity of 0.59, compared to 0.49 and 0.59 observed in the mpMRI.

CONCLUSIONS

Our study confirms the possible use of a quantitative parameter (ADC value) in the risk stratification of csPCa, by reducing the number of biopsies and, therefore, the number of unwarranted diagnoses of PCa and the risk of overtreatment.

Using deep learning to optimize the prostate MRI protocol by assessing the diagnostic efficacy of MRI sequences

PURPOSE

To explore diagnostic deep learning for optimizing the prostate MRI protocol by assessing the diagnostic efficacy of MRI sequences.

METHOD

This retrospective study included 840 patients with a biparametric prostate MRI scan. The MRI protocol included a T2-weighted image, three DWI sequences (b50, b400, and b800 s/mm2), a calculated ADC map, and a calculated b1400 sequence. Two accelerated MRI protocols were simulated, using only two acquired b-values to calculate the ADC and b1400. Deep learning models were trained to detect prostate cancer lesions on accelerated and full protocols. The diagnostic performances of the protocols were compared on the patient-level with the area under the receiver operating characteristic (AUROC), using DeLong's test, and on the lesion-level with the partial area under the free response operating characteristic (pAUFROC), using a permutation test. Validation of the results was performed among expert radiologists.

RESULTS

No significant differences in diagnostic performance were found between the accelerated protocols and the full bpMRI baseline. Omitting b800 reduced 53% DWI scan time, with a performance difference of + 0.01 AUROC (p = 0.20) and -0.03 pAUFROC (p = 0.45). Omitting b400 reduced 32% DWI scan time, with a performance difference of -0.01 AUROC (p = 0.65) and + 0.01 pAUFROC (p = 0.73). Multiple expert radiologists underlined the findings.

CONCLUSIONS

This study shows that deep learning can assess the diagnostic efficacy of MRI sequences by comparing prostate MRI protocols on diagnostic accuracy. Omitting either the b400 or the b800 DWI sequence can optimize the prostate MRI protocol by reducing scan time without compromising diagnostic quality.

The Novel Green Learning Artificial Intelligence for Prostate Cancer Imaging: A Balanced Alternative to Deep Learning and Radiomics

The application of artificial intelligence (AI) on prostate magnetic resonance imaging (MRI) has shown promising results. Several AI systems have been developed to automatically analyze prostate MRI for segmentation, cancer detection, and region of interest characterization, thereby assisting clinicians in their decision-making process. Deep learning, the current trend in imaging AI, has limitations including the lack of transparency "black box", large data processing, and excessive energy consumption. In this narrative review, the authors provide an overview of the recent advances in AI for prostate cancer diagnosis and introduce their next-generation AI model, Green Learning, as a promising solution.

The auxiliary diagnosis of thyroid echogenic foci based on a deep learning segmentation model: A two-center study

OBJECTIVE

The aim of this study is to develop AI-assisted software incorporating a deep learning (DL) model based on static ultrasound images. The software aims to aid physicians in distinguishing between malignant and benign thyroid nodules with echogenic foci and to investigate how the AI-assisted DL model can enhance radiologists' diagnostic performance.

METHODS

For this retrospective study, a total of 2724 ultrasound (US) scans were collected from two independent institutions, encompassing 1038 echogenic foci nodules. All echogenic foci were confirmed by pathology. Three DL segmentation models (DeepLabV3+, U-Net, and PSPNet) were developed, with each model using two different backbones to extract features from the nodular regions with echogenic foci. Evaluation indexes such as Mean Intersection over Union (MIoU), Mean Pixel Accuracy (MPA), and Dice coefficients were employed to assess the performance of the segmentation model. The model demonstrating the best performance was selected to develop the AI-assisted diagnostic software, enabling radiologists to benefit from AI-assisted diagnosis. The diagnostic performance of radiologists with varying levels of seniority and beginner radiologists in assessing high-echo nodules was then compared, both with and without the use of auxiliary strategies. The area under the receiver operating characteristic curve (AUROC) was used as the primary evaluation index, both with and without the use of auxiliary strategies.

RESULTS

In the analysis of Institution 2, the DeepLabV3+ (backbone is MobileNetV2 exhibited optimal segmentation performance, with MIoU = 0.891, MPA = 0.945, and Dice = 0.919. The combined AUROC (0.693 [95% CI 0.595-0.791]) of radiology beginners using AI-assisted strategies was significantly higher than those without such strategies (0.551 [0.445-0.657]). Additionally, the combined AUROC of junior physicians employing adjuvant strategies improved from 0.674 [0.574-0.774] to 0.757 [0.666-0.848]. Similarly, the combined AUROC of senior physicians increased slightly, rising from 0.745 [0.652-0.838] to 0.813 [0.730-0.896]. With the implementation of AI-assisted strategies, the accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of both senior physicians and beginners in the radiology department underwent varying degrees of improvement.

CONCLUSIONS

This study demonstrates that the DL-based auxiliary diagnosis model using US static images can improve the performance of radiologists and radiology students in identifying thyroid echogenic foci.

Delta radiomic patterns on serial bi-parametric MRI are associated with pathologic upgrading in prostate cancer patients on active surveillance: preliminary findings

Objective

The aim of this study was to quantify radiomic changes in prostate cancer (PCa) progression on serial MRI among patients on active surveillance (AS) and evaluate their association with pathologic progression on biopsy.

Methods

This retrospective study comprised N = 121 biopsy-proven PCa patients on AS at a single institution, of whom N = 50 at baseline conformed to the inclusion criteria. ISUP Gleason Grade Groups (GGG) were obtained from 12-core TRUS-guided systematic biopsies at baseline and follow-up. A biopsy upgrade (AS+) was defined as an increase in GGG (or in number of positive cores) and no upgrade (AS-) was defined when GGG remained the same during a median period of 18 months. Of N = 50 patients at baseline, N = 30 had MRI scans available at follow-up (median interval = 18 months) and were included for delta radiomic analysis. A total of 252 radiomic features were extracted from the PCa region of interest identified by board-certified radiologists on 3T bi-parametric MRI [T2-weighted (T2W) and apparent diffusion coefficient (ADC)]. Delta radiomic features were computed as the difference of radiomic feature between baseline and follow-up scans. The association of AS+ with age, prostate-specific antigen (PSA), Prostate Imaging Reporting and Data System (PIRADS v2.1) score, and tumor size was evaluated at baseline and follow-up. Various prediction models were built using random forest (RF) classifier within a threefold cross-validation framework leveraging baseline radiomics (Cbr), baseline radiomics + baseline clinical (Cbrbcl), delta radiomics (CΔr), delta radiomics + baseline clinical (CΔrbcl), and delta radiomics + delta clinical (CΔrΔcl).

Results

An AUC of 0.64 ± 0.09 was obtained for Cbr, which increased to 0.70 ± 0.18 with the integration of clinical variables (Cbrbcl). CΔr yielded an AUC of 0.74 ± 0.15. Integrating delta radiomics with baseline clinical variables yielded an AUC of 0.77 ± 0.23. CΔrΔclresulted in the best AUC of 0.84 ± 0.20 (p < 0.05) among all combinations.

Conclusion

Our preliminary findings suggest that delta radiomics were more strongly associated with upgrade events compared to PIRADS and other clinical variables. Delta radiomics on serial MRI in combination with changes in clinical variables (PSA and tumor volume) between baseline and follow-up showed the strongest association with biopsy upgrade in PCa patients on AS. Further independent multi-site validation of these preliminary findings is warranted.

Reliability and Efficiency of the CAPRI-3 Metastatic Prostate Cancer Registry Driven by Artificial Intelligence

BACKGROUND

Manual data collection is still the gold standard for disease-specific patient registries. However, CAPRI-3 uses text mining (an artificial intelligence (AI) technology) for patient identification and data collection. The aim of this study is to demonstrate the reliability and efficiency of this AI-driven approach.

METHODS

CAPRI-3 is an observational retrospective multicenter cohort registry on metastatic prostate cancer. We tested the patient-identification algorithm and automated data extraction through manual validation of the same patients in two pilots in 2019 and 2022.

RESULTS

Pilot one identified 2030 patients and pilot two 9464 patients. The negative predictive value of the algorithm was maximized to prevent false exclusions and reached 94.8%. The completeness and accuracy of the automated data extraction were 92.3% or higher, except for date fields and inaccessible data (images/pdf) (10-88.9%). Additional manual quality control took over 3 h less time per patient than the original fully manual CAPRI registry (105 vs. 300 min).

CONCLUSIONS

The CAPRI-3 patient-identification algorithm is a sound replacement for excluding ineligible candidates. The AI-driven data extraction is largely accurate and complete, but manual quality control is needed for less reliable and inaccessible data. Overall, the AI-driven approach of the CAPRI-3 registry is reliable and timesaving.

PI-RADS: Where Next?

Prostate MRI plays an important role in the clinical management of localized prostate cancer, mainly assisting in biopsy decisions and guiding biopsy procedures. The Prostate Imaging Reporting and Data System (PI-RADS) has been available to radiologists since 2012, with the most up-to-date and actively used version being PI-RADS version 2.1. This review article discusses the current use of PI-RADS, including its limitations and controversies, and summarizes research that aims to improve future iterations of this system.

Explainable artificial intelligence (XAI) in radiology and nuclear medicine: a literature review

Rational

Deep learning (DL) has demonstrated a remarkable performance in diagnostic imaging for various diseases and modalities and therefore has a high potential to be used as a clinical tool. However, current practice shows low deployment of these algorithms in clinical practice, because DL algorithms lack transparency and trust due to their underlying black-box mechanism. For successful employment, explainable artificial intelligence (XAI) could be introduced to close the gap between the medical professionals and the DL algorithms. In this literature review, XAI methods available for magnetic resonance (MR), computed tomography (CT), and positron emission tomography (PET) imaging are discussed and future suggestions are made.

Methods

PubMed, Embase.com and Clarivate Analytics/Web of Science Core Collection were screened. Articles were considered eligible for inclusion if XAI was used (and well described) to describe the behavior of a DL model used in MR, CT and PET imaging.

Results

A total of 75 articles were included of which 54 and 17 articles described post and ad hoc XAI methods, respectively, and 4 articles described both XAI methods. Major variations in performance is seen between the methods. Overall, post hoc XAI lacks the ability to provide class-discriminative and target-specific explanation. Ad hoc XAI seems to tackle this because of its intrinsic ability to explain. However, quality control of the XAI methods is rarely applied and therefore systematic comparison between the methods is difficult.

Conclusion

There is currently no clear consensus on how XAI should be deployed in order to close the gap between medical professionals and DL algorithms for clinical implementation. We advocate for systematic technical and clinical quality assessment of XAI methods. Also, to ensure end-to-end unbiased and safe integration of XAI in clinical workflow, (anatomical) data minimization and quality control methods should be included.

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.