Cancers

Research

Jump to: Other

17 pages, 2678 KiB

Open AccessArticle

A Multiparametric MRI and Baseline-Clinical-Feature-Based Dense Multimodal Fusion Artificial Intelligence (MFAI) Model to Predict Castration-Resistant Prostate Cancer Progression

by Dianning He, Haoming Zhuang, Ying Ma, Bixuan Xia, Aritrick Chatterjee, Xiaobing Fan, Shouliang Qi, Wei Qian, Zhe Zhang and Jing Liu

Cancers 2025, 17(9), 1556; https://doi.org/10.3390/cancers17091556 - 3 May 2025

Viewed by 181

Abstract

Objectives: The primary objective of this study was to identify whether patients with prostate cancer (PCa) could progress to denervation-resistant prostate cancer (CRPC) after 12 months of hormone therapy. Methods: A total of 96 PCa patients with baseline clinical data who underwent multiparametric [...] Read more.

Objectives: The primary objective of this study was to identify whether patients with prostate cancer (PCa) could progress to denervation-resistant prostate cancer (CRPC) after 12 months of hormone therapy. Methods: A total of 96 PCa patients with baseline clinical data who underwent multiparametric magnetic resonance imaging (MRI) between September 2018 and September 2022 were included in this retrospective study. Patients were classified as progressing or not progressing to CRPC on the basis of their outcome after 12 months of hormone therapy. A dense multimodal fusion artificial intelligence (Dense-MFAI) model was constructed by incorporating a squeeze-and-excitation block and a spatial pyramid pooling layer into a dense convolutional network (DenseNet), as well as integrating the eXtreme Gradient Boosting machine learning algorithm. The accuracy, sensitivity, specificity, positive predictive value, negative predictive value, receiver operating characteristic curves, area under the curve (AUC) and confusion matrices were used as classification performance metrics. Results: The Dense-MFAI model demonstrated an accuracy of 94.2%, with an AUC of 0.945, when predicting the progression of patients with PCa to CRPC after 12 months of hormone therapy. The experimental validation demonstrated that combining radiomics feature mapping with baseline clinical characteristics significantly improved the model’s classification performance, confirming the importance of multimodal data. Conclusions: The Dense-MFAI model proposed in this study has the ability to more accurately predict whether a PCa patient could progress to CRPC. This model can assist urologists in developing the most appropriate treatment plan and prognostic measures. Full article

(This article belongs to the Special Issue MRI in Prostate Cancer)

► Show Figures

Figure 1

13 pages, 1153 KiB

Open AccessFeature PaperArticle

Quantitative Multi-Parametric MRI of the Prostate Reveals Racial Differences

by Aritrick Chatterjee, Xiaobing Fan, Jessica Slear, Gregory Asare, Ambereen N. Yousuf, Milica Medved, Tatjana Antic, Scott Eggener, Gregory S. Karczmar and Aytekin Oto

Cancers 2024, 16(20), 3499; https://doi.org/10.3390/cancers16203499 - 16 Oct 2024

Cited by 1 | Viewed by 1230

Abstract

Purpose: This study investigates whether quantitative MRI and histology of the prostate reveal differences between races, specifically African Americans (AAs) and Caucasian Americans (CAs), that can affect diagnosis. Materials and Methods: Patients (98 CAs, 47 AAs) with known or suspected prostate cancer (PCa) [...] Read more.

Purpose: This study investigates whether quantitative MRI and histology of the prostate reveal differences between races, specifically African Americans (AAs) and Caucasian Americans (CAs), that can affect diagnosis. Materials and Methods: Patients (98 CAs, 47 AAs) with known or suspected prostate cancer (PCa) underwent 3T MRI (T2W, DWI, and DCE-MRI) prior to biopsy or prostatectomy. Quantitative mpMRI metrics: ADC, T2, and DCE empirical mathematical model parameters were calculated. Results: AAs had a greater percentage of higher Gleason-grade lesions compared to CAs. There were no significant differences in the quantitative ADC and T2 values between AAs and CAs. The cancer signal enhancement rate (α) on DCE-MRI was significantly higher for AAs compared to CAs (AAs: 13.3 ± 9.3 vs. CAs: 6.1 ± 4.7 s⁻¹, p < 0.001). The DCE signal washout rate (β) was significantly lower in benign tissue of AAs (AAs: 0.01 ± 0.09 s⁻¹ vs. CAs: 0.07 ± 0.07 s⁻¹, p < 0.001) and significantly elevated in cancer tissue in AAs (AAs: 0.12 ± 0.07 s⁻¹ vs. CAs: 0.07 ± 0.08 s⁻¹, p = 0.02). DCE significantly improves the differentiation of PCa from benign in AAs (α: 52%, β: 62% more effective in AAs compared to CAs). Histologic analysis showed cancers have a greater proportion (p = 0.04) of epithelium (50.9 ± 12.3 vs. 44.7 ± 12.8%) and lower lumen (10.5 ± 6.9 vs. 16.2 ± 6.8%) in CAs compared to AAs. Conclusions: This study shows that AAs have different quantitative DCE-MRI values for benign prostate and prostate cancer and different histologic makeup in PCa compared to CAs. Quantitative DCE-MRI can significantly improve the performance of MRI for PCa diagnosis in African Americans but is much less effective for Caucasian Americans. Full article

(This article belongs to the Special Issue MRI in Prostate Cancer)

► Show Figures

Figure 1

11 pages, 1224 KiB

Open AccessArticle

Magnetic Resonance Elastography for the Detection and Classification of Prostate Cancer

by Seung Ho Kim, Joo Yeon Kim and Moon Jung Hwang

Cancers 2024, 16(20), 3494; https://doi.org/10.3390/cancers16203494 - 15 Oct 2024

Cited by 2 | Viewed by 1187

Abstract

We investigated the feasibility of magnetic resonance elastography (MRE) using a pelvic acoustic driver for the detection and classification of prostate cancer (PCa). A total of 75 consecutive patients (mean age, 70; range, 56–86) suspected of having PCa and who underwent multi-parametric MRI [...] Read more.

We investigated the feasibility of magnetic resonance elastography (MRE) using a pelvic acoustic driver for the detection and classification of prostate cancer (PCa). A total of 75 consecutive patients (mean age, 70; range, 56–86) suspected of having PCa and who underwent multi-parametric MRI including MRE and subsequent surgical resection were included. The analyzed regions consisted of cancer (n = 69), benign prostatic hyperplasia (BPH) (n = 70), and normal parenchyma (n = 70). A histopathologic topographic map served as the reference standard for each region. One radiologist and one pathologist performed radiologic–pathologic correlation, and the radiologist measured stiffness values in each region of interest on elastograms automatically generated by dedicated software. Paired t-tests were used to compare stiffness values between two regions. ROC curve analysis was also used to extract a cutoff value between two regions. The stiffness value of PCa (unit, kilopascal (kPa); 4.9 ± 1.1) was significantly different to that of normal parenchyma (3.6 ± 0.3, p < 0.0001) and BPH (4.5 ± 1.4, p = 0.0454). Under a cutoff value of 4.2 kPa, a maximum accuracy of 87% was estimated, with a sensitivity of 73%, a specificity of 99%, and an AUC of 0.839 for discriminating PCa from normal parenchyma. Between PCa and BPH, a maximum accuracy of 62%, a sensitivity of 70%, a specificity of 56%, and an AUC of 0.598 were estimated at a 4.5 kPa cutoff. The stiffness values tended to increase as the ISUP grade increased. In conclusion, it is feasible to detect and classify PCa using pelvic MRE. Our observations suggest that MRE could be a supplement to multi-parametric MRI for PCa detection. Full article

(This article belongs to the Special Issue MRI in Prostate Cancer)

► Show Figures

Figure 1

20 pages, 6501 KiB

Open AccessArticle

A Deep Learning-Based Framework for Highly Accelerated Prostate MR Dispersion Imaging

by Kai Zhao, Kaifeng Pang, Alex LingYu Hung, Haoxin Zheng, Ran Yan and Kyunghyun Sung

Cancers 2024, 16(17), 2983; https://doi.org/10.3390/cancers16172983 - 27 Aug 2024

Cited by 1 | Viewed by 1470

Abstract

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) measures microvascular perfusion by capturing the temporal changes of an MRI contrast agent in a target tissue, and it provides valuable information for the diagnosis and prognosis of a wide range of tumors. Quantitative DCE-MRI analysis commonly [...] Read more.

Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) measures microvascular perfusion by capturing the temporal changes of an MRI contrast agent in a target tissue, and it provides valuable information for the diagnosis and prognosis of a wide range of tumors. Quantitative DCE-MRI analysis commonly relies on the nonlinear least square (NLLS) fitting of a pharmacokinetic (PK) model to concentration curves. However, the voxel-wise application of such nonlinear curve fitting is highly time-consuming. The arterial input function (AIF) needs to be utilized in quantitative DCE-MRI analysis. and in practice, a population-based arterial AIF is often used in PK modeling. The contribution of intravascular dispersion to the measured signal enhancement is assumed to be negligible. The MR dispersion imaging (MRDI) model was recently proposed to account for intravascular dispersion, enabling more accurate PK modeling. However, the complexity of the MRDI hinders its practical usability and makes quantitative PK modeling even more time-consuming. In this paper, we propose fast MR dispersion imaging (fMRDI) to effectively represent the intravascular dispersion and highly accelerated PK parameter estimation. We also propose a deep learning-based, two-stage framework to accelerate PK parameter estimation. We used a deep neural network (NN) to estimate PK parameters directly from enhancement curves. The estimation from NN was further refined using several steps of NLLS, which is significantly faster than performing NLLS from random initializations. A data synthesis module is proposed to generate synthetic training data for the NN. Two data-processing modules were introduced to improve the model’s stability against noise and variations. Experiments on our in-house clinical prostate MRI dataset demonstrated that our method significantly reduces the processing time, produces a better distinction between normal and clinically significant prostate cancer (csPCa) lesions, and is more robust against noise than conventional DCE-MRI analysis methods. Full article

(This article belongs to the Special Issue MRI in Prostate Cancer)

► Show Figures

Figure 1

12 pages, 1768 KiB

Open AccessArticle

Is There an Added Value of Quantitative DCE-MRI by Magnetic Resonance Dispersion Imaging for Prostate Cancer Diagnosis?

by Auke Jager, Jorg R. Oddens, Arnoud W. Postema, Razvan L. Miclea, Ivo G. Schoots, Peet G. T. A. Nooijen, Hans van der Linden, Jelle O. Barentsz, Stijn W. T. P. J. Heijmink, Hessel Wijkstra, Massimo Mischi and Simona Turco

Cancers 2024, 16(13), 2431; https://doi.org/10.3390/cancers16132431 - 1 Jul 2024

Cited by 1 | Viewed by 1504

Abstract

In this multicenter, retrospective study, we evaluated the added value of magnetic resonance dispersion imaging (MRDI) to standard multiparametric MRI (mpMRI) for PCa detection. The study included 76 patients, including 51 with clinically significant prostate cancer (csPCa), who underwent radical prostatectomy and had [...] Read more.

In this multicenter, retrospective study, we evaluated the added value of magnetic resonance dispersion imaging (MRDI) to standard multiparametric MRI (mpMRI) for PCa detection. The study included 76 patients, including 51 with clinically significant prostate cancer (csPCa), who underwent radical prostatectomy and had an mpMRI including dynamic contrast-enhanced MRI. Two radiologists performed three separate randomized scorings based on mpMRI, MRDI and mpMRI+MRDI. Radical prostatectomy histopathology was used as the reference standard. Imaging and histopathology were both scored according to the Prostate Imaging-Reporting and Data System V2.0 sector map. Sensitivity and specificity for PCa detection were evaluated for mpMRI, MRDI and mpMRI+MRDI. Inter- and intra-observer variability for both radiologists was evaluated using Cohen’s Kappa. On a per-patient level, sensitivity for csPCa for radiologist 1 (R1) for mpMRI, MRDI and mpMRI+MRDI was 0.94, 0.82 and 0.94, respectively. For the second radiologist (R2), these were 0.78, 0.94 and 0.96. R1 detected 4% additional csPCa cases using MRDI compared to mpMRI, and R2 detected 20% extra csPCa cases using MRDI. Inter-observer agreement was significant only for MRDI (Cohen’s Kappa = 0.4250, p = 0.004). The results of this study show the potential of MRDI to improve inter-observer variability and the detection of csPCa. Full article

(This article belongs to the Special Issue MRI in Prostate Cancer)

► Show Figures

Figure 1

11 pages, 1052 KiB

Open AccessArticle

Comparing Two Targeted Biopsy Schemes for Detecting Clinically Significant Prostate Cancer in Magnetic Resonance Index Lesions: Two- to Four-Core versus Saturated Transperineal Targeted Biopsy

by Juan Morote, Nahuel Paesano, Natàlia Picola, Berta Miró, José M. Abascal, Pol Servian, Enrique Trilla and Olga Méndez

Cancers 2024, 16(13), 2306; https://doi.org/10.3390/cancers16132306 - 23 Jun 2024

Cited by 1 | Viewed by 1475

Abstract

Since the optimal scheme for targeted biopsies of magnetic resonance imaging (MRI) suspicious lesions remains unclear, we compare the efficacy of two schemes for these index lesions. A prospective trial was conducted in 1161 men with Prostate Imaging Reporting and Data System v [...] Read more.

Since the optimal scheme for targeted biopsies of magnetic resonance imaging (MRI) suspicious lesions remains unclear, we compare the efficacy of two schemes for these index lesions. A prospective trial was conducted in 1161 men with Prostate Imaging Reporting and Data System v 2.1 3–5 undergoing targeted and 12-core systematic biopsy in four centers between 2021 and 2023. Two- to four-core MRI-transrectal ultrasound fusion-targeted biopsies via the transperineal route were conducted in 900 men in three centers, while a mapping per 0.5 mm core method (saturated scheme) was employed in 261 men biopsied in another center. A propensity-matched 261 paired cases were selected for avoiding confounders other than the targeted biopsy scheme. CsPCa (grade group ≥ 2) was identified in 125 index lesions (41.1%) when the two- to four-core scheme was employed, while in 187 (71.9%) when the saturated biopsy (p < 0.001) was used. Insignificant PCa (iPCa) was detected in 18 and 11.1%, respectively (p = 0.019). Rates of csPCa and iPCa remained similar in systematic biopsies. CsPCa detected only in systematic biopsies were 5 and 1.5%, respectively (p = 0.035) in each group. The saturated scheme for targeted biopsies detected more csPCa and less iPCa than did the two- to four-core scheme in the index lesions. The rate of csPCa detected only in the systematic biopsies decreased when the saturated scheme was employed. Full article

(This article belongs to the Special Issue MRI in Prostate Cancer)

► Show Figures

Figure 1

11 pages, 5252 KiB

Open AccessArticle

Reasons for Discordance between ⁶⁸Ga-PSMA-PET and Magnetic Resonance Imaging in Men with Metastatic Prostate Cancer

by Jade Wang, Elisabeth O’Dwyer, Juana Martinez Zuloaga, Kritika Subramanian, Jim C. Hu, Yuliya S. Jhanwar, Himanshu Nagar, Arindam RoyChoudhury, John Babich, Sandra Huicochea Castellanos, Joseph R. Osborne and Daniel J. A. Margolis

Cancers 2024, 16(11), 2056; https://doi.org/10.3390/cancers16112056 - 29 May 2024

Viewed by 1410

Abstract

Background: PSMA PET has emerged as a “gold standard” imaging modality for assessing prostate cancer metastases. However, it is not universally available, and this limits its impact. In contrast, whole-body MRI is much more widely available but misses more lesions. This study aims [...] Read more.

Background: PSMA PET has emerged as a “gold standard” imaging modality for assessing prostate cancer metastases. However, it is not universally available, and this limits its impact. In contrast, whole-body MRI is much more widely available but misses more lesions. This study aims to improve the interpretation of whole-body MRI by comparing false negative scans retrospectively to PSMA PET. Methods: This study was a retrospective sub-analysis of a prospectively collected database of patients who participated in a clinical trial of PSMA PET/MRI comparing PSMA PET and whole-body MRI from 2018–2021. Subjects whose separately read PSMA PET and MRI diagnostic reports showed discrepancies (“false negative” MRI cases) were selected for sub-analysis. The cases were reviewed by the same attending radiologist who originally read the scans. The radiologist noted specific features on MRI indicating metastatic disease that were initially missed. Results: Of 263 cases, 38 (14%) met the inclusion criteria and were reviewed. Six classes of mpMRI false negatives were identified: anatomically normal (18, 47%), atypical MRI appearance (6, 16%), mischaracterization (1, 3%), undercall (6, 16%), obscured (4, 11%), and no abnormality on MRI (3, 8%). Considering that the atypical and undercalled cases could have been adjusted in retrospect, and that 4 additional cases had positive lesions to the same extent and 11 further cases had disease confined to the pelvis, only 11 (4%) of the original 263 would have had disease outside of a conventional radiation treatment plan. Conclusion: Notably, almost 50% of the cases, including most lymph node metastases, were anatomically normal using standard criteria. This suggests that current anatomic criteria for evaluating prostate cancer lymph node metastases are not ideal, and there is a need for improved criteria. In addition, 32% of cases involved some element of human interpretive error, and, therefore, improving reader training may lead to more accurate results. Full article

(This article belongs to the Special Issue MRI in Prostate Cancer)

► Show Figures

Figure 1

13 pages, 4255 KiB

Open AccessEditor’s ChoiceArticle

Development and Validation of an Explainable Radiomics Model to Predict High-Aggressive Prostate Cancer: A Multicenter Radiomics Study Based on Biparametric MRI

by Giulia Nicoletti, Simone Mazzetti, Giovanni Maimone, Valentina Cignini, Renato Cuocolo, Riccardo Faletti, Marco Gatti, Massimo Imbriaco, Nicola Longo, Andrea Ponsiglione, Filippo Russo, Alessandro Serafini, Arnaldo Stanzione, Daniele Regge and Valentina Giannini

Cancers 2024, 16(1), 203; https://doi.org/10.3390/cancers16010203 - 1 Jan 2024

Cited by 6 | Viewed by 3387

Abstract

In the last years, several studies demonstrated that low-aggressive (Grade Group (GG) ≤ 2) and high-aggressive (GG ≥ 3) prostate cancers (PCas) have different prognoses and mortality. Therefore, the aim of this study was to develop and externally validate a radiomic model to [...] Read more.

In the last years, several studies demonstrated that low-aggressive (Grade Group (GG) ≤ 2) and high-aggressive (GG ≥ 3) prostate cancers (PCas) have different prognoses and mortality. Therefore, the aim of this study was to develop and externally validate a radiomic model to noninvasively classify low-aggressive and high-aggressive PCas based on biparametric magnetic resonance imaging (bpMRI). To this end, 283 patients were retrospectively enrolled from four centers. Features were extracted from apparent diffusion coefficient (ADC) maps and T2-weighted (T2w) sequences. A cross-validation (CV) strategy was adopted to assess the robustness of several classifiers using two out of the four centers. Then, the best classifier was externally validated using the other two centers. An explanation for the final radiomics signature was provided through Shapley additive explanation (SHAP) values and partial dependence plots (PDP). The best combination was a naïve Bayes classifier trained with ten features that reached promising results, i.e., an area under the receiver operating characteristic (ROC) curve (AUC) of 0.75 and 0.73 in the construction and external validation set, respectively. The findings of our work suggest that our radiomics model could help distinguish between low- and high-aggressive PCa. This noninvasive approach, if further validated and integrated into a clinical decision support system able to automatically detect PCa, could help clinicians managing men with suspicion of PCa. Full article

(This article belongs to the Special Issue MRI in Prostate Cancer)

► Show Figures

Figure 1

16 pages, 3248 KiB

Open AccessArticle

Prostate Cancers Invisible on Multiparametric MRI: Pathologic Features in Correlation with Whole-Mount Prostatectomy

by Aritrick Chatterjee, Alexander Gallan, Xiaobing Fan, Milica Medved, Pranadeep Akurati, Roger M. Bourne, Tatjana Antic, Gregory S. Karczmar and Aytekin Oto

Cancers 2023, 15(24), 5825; https://doi.org/10.3390/cancers15245825 - 13 Dec 2023

Cited by 7 | Viewed by 1893

Abstract

We investigated why some prostate cancers (PCas) are not identified on multiparametric MRI (mpMRI) by using ground truth reference from whole-mount prostatectomy specimens. A total of 61 patients with biopsy-confirmed PCa underwent 3T mpMRI followed by prostatectomy. Lesions visible on MRI prospectively or [...] Read more.

We investigated why some prostate cancers (PCas) are not identified on multiparametric MRI (mpMRI) by using ground truth reference from whole-mount prostatectomy specimens. A total of 61 patients with biopsy-confirmed PCa underwent 3T mpMRI followed by prostatectomy. Lesions visible on MRI prospectively or retrospectively identified after correlating with histology were considered “identified cancers” (ICs). Lesions that could not be identified on mpMRI were considered “unidentified cancers” (UCs). Pathologists marked the Gleason score, stage, size, and density of the cancer glands and performed quantitative histology to calculate the tissue composition. Out of 115 cancers, 19 were unidentified on MRI. The UCs were significantly smaller and had lower Gleason scores and clinical stage lesions compared with the ICs. The UCs had significantly (p < 0.05) higher ADC (1.34 ± 0.38 vs. 1.02 ± 0.30 μm²/ms) and T2 (117.0 ± 31.1 vs. 97.1 ± 25.1 ms) compared with the ICs. The density of the cancer glands was significantly (p = 0.04) lower in the UCs. The percentage of the Gleason 4 component in Gleason 3 + 4 lesions was nominally (p = 0.15) higher in the ICs (20 ± 12%) compared with the UCs (15 ± 8%). The UCs had a significantly lower epithelium (32.9 ± 21.5 vs. 47.6 ± 13.1%, p = 0.034) and higher lumen volume (20.4 ± 10.0 vs. 13.3 ± 4.1%, p = 0.021) compared with the ICs. Independent from size and Gleason score, the tissue composition differences, specifically, the higher lumen and lower epithelium in UCs, can explain why some of the prostate cancers cannot be identified on mpMRI. Full article

(This article belongs to the Special Issue MRI in Prostate Cancer)

► Show Figures

Figure 1

16 pages, 5145 KiB

Open AccessArticle

Clinical-Genomic Risk Group Classification of Suspicious Lesions on Prostate Multiparametric-MRI

by Radka Stoyanova, Olmo Zavala-Romero, Deukwoo Kwon, Adrian L. Breto, Isaac R. Xu, Ahmad Algohary, Mohammad Alhusseini, Sandra M. Gaston, Patricia Castillo, Oleksandr N. Kryvenko, Elai Davicioni, Bruno Nahar, Benjamin Spieler, Matthew C. Abramowitz, Alan Dal Pra, Dipen J. Parekh, Sanoj Punnen and Alan Pollack

Cancers 2023, 15(21), 5240; https://doi.org/10.3390/cancers15215240 - 31 Oct 2023

Cited by 2 | Viewed by 1815

Abstract

The utilization of multi-parametric MRI (mpMRI) in clinical decisions regarding prostate cancer patients’ management has recently increased. After biopsy, clinicians can assess risk using National Comprehensive Cancer Network (NCCN) risk stratification schema and commercially available genomic classifiers, such as Decipher. We built radiomics-based [...] Read more.

The utilization of multi-parametric MRI (mpMRI) in clinical decisions regarding prostate cancer patients’ management has recently increased. After biopsy, clinicians can assess risk using National Comprehensive Cancer Network (NCCN) risk stratification schema and commercially available genomic classifiers, such as Decipher. We built radiomics-based models to predict lesions/patients at low risk prior to biopsy based on an established three-tier clinical-genomic classification system. Radiomic features were extracted from regions of positive biopsies and Normally Appearing Tissues (NAT) on T2-weighted and Diffusion-weighted Imaging. Using only clinical information available prior to biopsy, five models for predicting low-risk lesions/patients were evaluated, based on: 1: Clinical variables; 2: Lesion-based radiomic features; 3: Lesion and NAT radiomics; 4: Clinical and lesion-based radiomics; and 5: Clinical, lesion and NAT radiomic features. Eighty-three mpMRI exams from 78 men were analyzed. Models 1 and 2 performed similarly (Area under the receiver operating characteristic curve were 0.835 and 0.838, respectively), but radiomics significantly improved the lesion-based performance of the model in a subset analysis of patients with a negative Digital Rectal Exam (DRE). Adding normal tissue radiomics significantly improved the performance in all cases. Similar patterns were observed on patient-level models. To the best of our knowledge, this is the first study to demonstrate that machine learning radiomics-based models can predict patients’ risk using combined clinical-genomic classification. Full article

(This article belongs to the Special Issue MRI in Prostate Cancer)

► Show Figures

Figure 1

15 pages, 7515 KiB

Open AccessArticle

MRI Radiomics-Based Machine Learning Models for Ki67 Expression and Gleason Grade Group Prediction in Prostate Cancer

by Xiaofeng Qiao, Xiling Gu, Yunfan Liu, Xin Shu, Guangyong Ai, Shuang Qian, Li Liu, Xiaojing He and Jingjing Zhang

Cancers 2023, 15(18), 4536; https://doi.org/10.3390/cancers15184536 - 13 Sep 2023

Cited by 11 | Viewed by 2438

Abstract

Purpose: The Ki67 index and the Gleason grade group (GGG) are vital prognostic indicators of prostate cancer (PCa). This study investigated the value of biparametric magnetic resonance imaging (bpMRI) radiomics feature-based machine learning (ML) models in predicting the Ki67 index and GGG of [...] Read more.

Purpose: The Ki67 index and the Gleason grade group (GGG) are vital prognostic indicators of prostate cancer (PCa). This study investigated the value of biparametric magnetic resonance imaging (bpMRI) radiomics feature-based machine learning (ML) models in predicting the Ki67 index and GGG of PCa. Methods: A total of 122 patients with pathologically proven PCa who had undergone preoperative MRI were retrospectively included. Radiomics features were extracted from T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) maps. Then, recursive feature elimination (RFE) was applied to remove redundant features. ML models for predicting Ki67 expression and GGG were constructed based on bpMRI and different algorithms, including logistic regression (LR), support vector machine (SVM), random forest (RF), and K-nearest neighbor (KNN). The performances of different models were evaluated with receiver operating characteristic (ROC) analysis. In addition, a joint analysis of Ki67 expression and GGG was performed by assessing their Spearman correlation and calculating the diagnostic accuracy for both indices. Results: The ML model based on LR and ADC + T2 (LR_ADC + T2, AUC = 0.8882) performed best in predicting Ki67 expression, and ADC_wavelet-LHH_firstorder_Maximum had the highest feature weighting. The SVM_DWI + T2 (AUC = 0.9248) performed best in predicting GGG, and DWI_wavelet HLL_glcm_SumAverage had the highest feature weighting. The Ki67 and GGG exhibited a weak positive correlation (r = 0.382, p < 0.001), and LR_ADC + DWI had the highest diagnostic accuracy in predicting both (0.6230). Conclusion: The proposed ML models are suitable for predicting both Ki67 expression and GGG in PCa. This algorithm could be used to identify indolent or invasive PCa with a noninvasive, repeatable, and accurate diagnostic method. Full article

(This article belongs to the Special Issue MRI in Prostate Cancer)

► Show Figures

Figure 1

Other

Jump to: Research

20 pages, 1762 KiB

Open AccessSystematic Review

The Role of Radiomics in the Prediction of Clinically Significant Prostate Cancer in the PI-RADS v2 and v2.1 Era: A Systematic Review

by Andreu Antolin, Nuria Roson, Richard Mast, Javier Arce, Ramon Almodovar, Roger Cortada, Almudena Maceda, Manuel Escobar, Enrique Trilla and Juan Morote

Cancers 2024, 16(17), 2951; https://doi.org/10.3390/cancers16172951 - 24 Aug 2024

Cited by 3 | Viewed by 1886

Abstract

Early detection of clinically significant prostate cancer (csPCa) has substantially improved with the latest PI-RADS versions. However, there is still an overdiagnosis of indolent lesions (iPCa), and radiomics has emerged as a potential solution. The aim of this systematic review is to evaluate [...] Read more.

Early detection of clinically significant prostate cancer (csPCa) has substantially improved with the latest PI-RADS versions. However, there is still an overdiagnosis of indolent lesions (iPCa), and radiomics has emerged as a potential solution. The aim of this systematic review is to evaluate the role of handcrafted and deep radiomics in differentiating lesions with csPCa from those with iPCa and benign lesions on prostate MRI assessed with PI-RADS v2 and/or 2.1. The literature search was conducted in PubMed, Cochrane, and Web of Science databases to select relevant studies. Quality assessment was carried out with Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2), Radiomic Quality Score (RQS), and Checklist for Artificial Intelligence in Medical Imaging (CLAIM) tools. A total of 14 studies were deemed as relevant from 411 publications. The results highlighted a good performance of handcrafted and deep radiomics methods for csPCa detection, but without significant differences compared to radiologists (PI-RADS) in the few studies in which it was assessed. Moreover, heterogeneity and restrictions were found in the studies and quality analysis, which might induce bias. Future studies should tackle these problems to encourage clinical applicability. Prospective studies and comparison with radiologists (PI-RADS) are needed to better understand its potential. Full article

(This article belongs to the Special Issue MRI in Prostate Cancer)

► Show Figures

Figure 1

Journal Menu

Journal Browser

MRI in Prostate Cancer

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (12 papers)

Research

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI