Comparison of machine learning algorithms to predict clinically significant prostate cancer of the peripheral zone with multiparametric MRI using clinical assessment categories and radiomic features

Epigenetic profiling of prostate cancer reveals potential prognostic signatures

PURPOSE

While epigenetic profiling discovered biomarkers in several tumor entities, its application in prostate cancer is still limited. We explored DNA methylation-based deconvolution of benign and malignant prostate tissue for biomarker discovery and the potential of radiomics as a non-invasive surrogate.

METHODS

We retrospectively included 30 patients (63 [58-79] years) with prostate cancer (PCa) who had a multiparametric MRI of the prostate before radical prostatectomy between 2014 and 2019. The control group comprised four patients with benign prostate tissue adjacent to the PCa lesions and four patients with benign prostatic hyperplasia. Tissue punches of all lesions were obtained. DNA methylation analysis and reference-free in silico deconvolution were conducted to retrieve Latent Methylation Components (LCMs). LCM-based clustering was analyzed for cellular composition and correlated with clinical disease parameters. Additionally, PCa and adjacent benign lesions were analyzed using radiomics to predict the epigenetic signatures non-invasively.

RESULTS

LCMs identified two clusters with potential prognostic impact. Cluster one was associated with malignant prostate tissue (p < 0.001) and reduced immune-cell-related signatures (p = 0.004) of CD19 and CD4 cells. Cluster one comprised exclusively malignant prostate tissue enriched for significant prostate cancer and advanced tumor stages (p < 0.03 for both). No radiomics model could non-invasively predict the epigenetic clusters.

CONCLUSION

Epigenetic clusters were associated with prognostically and clinically relevant metrics in prostate cancer. Further, immune cell-related signatures differed significantly between prognostically favorable and unfavorable clusters. Further research is necessary to explore potential diagnostic and therapeutic implications.

Radiomic Pipelines for Prostate Cancer in External Beam Radiation Therapy: A Review of Methods and Future Directions

Background: Prostate Cancer (PCa) is asymptomatic at an early stage and often painless, requiring only active surveillance. External Beam Radiotherapy (EBRT) is currently a curative option for localised and locally advanced diseases and a palliative option for metastatic low-volume disease. Although highly effective, especially in a hypofractionation scheme, 17.4% to 39.4% of all patients suffer from cancer recurrence after EBRT. But, radiographic findings also correlate with significant differences in protein expression patterns. In the PCa EBRT workflow, several imaging modalities are available for grading, staging and contouring. Using image data characterisation algorithms (radiomics), one can provide a quantitative analysis of prognostic and predictive treatment outcomes. Methods: This literature review searched for original studies in radiomics for PCa in the context of EBRT. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, this review includes 73 new studies and analyses datasets, imaging modality, segmentation technique, feature extraction, selection and model building methods. Results: Magnetic Resonance Imaging (MRI) is the preferred imaging modality for radiomic studies in PCa but Computed Tomography (CT), Positron Emission Tomography (PET) and Ultrasound (US) may offer valuable insights on tumour characterisation and treatment response prediction. Conclusions: Most radiomic studies used small, homogeneous and private datasets lacking external validation and variability. Future research should focus on collaborative efforts to create large, multicentric datasets and develop standardised methodologies, ensuring the full potential of radiomics in clinical practice.

Analysis of domain shift in whole prostate gland, zonal and lesions segmentation and detection, using multicentric retrospective data

Despite being one of the most prevalent forms of cancer, prostate cancer (PCa) shows a significantly high survival rate, provided there is timely detection and treatment. Computational methods can help make this detection process considerably faster and more robust. However, some modern machine-learning approaches require accurate segmentation of the prostate gland and the index lesion. Since performing manual segmentations is a very time-consuming task, and highly prone to inter-observer variability, there is a need to develop robust semi-automatic segmentation models. In this work, we leverage the large and highly diverse ProstateNet dataset, which includes 638 whole gland and 461 lesion segmentation masks, from 3 different scanner manufacturers provided by 14 institutions, in addition to other 3 independent public datasets, to train accurate and robust segmentation models for the whole prostate gland, zones and lesions. We show that models trained on large amounts of diverse data are better at generalizing to data from other institutions and obtained with other manufacturers, outperforming models trained on single-institution single-manufacturer datasets in all segmentation tasks. Furthermore, we show that lesion segmentation models trained on ProstateNet can be reliably used as lesion detection models.

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

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.

Exploring the efficacy of multi-flavored feature extraction with radiomics and deep features for prostate cancer grading on mpMRI

BACKGROUND

The purpose of this study is to investigate the use of radiomics and deep features obtained from multiparametric magnetic resonance imaging (mpMRI) for grading prostate cancer. We propose a novel approach called multi-flavored feature extraction or tensor, which combines four mpMRI images using eight different fusion techniques to create 52 images or datasets for each patient. We evaluate the effectiveness of this approach in grading prostate cancer and compare it to traditional methods.

METHODS

We used the PROSTATEx-2 dataset consisting of 111 patients' images from T2W-transverse, T2W-sagittal, DWI, and ADC images. We used eight fusion techniques to merge T2W, DWI, and ADC images, namely Laplacian Pyramid, Ratio of the low-pass pyramid, Discrete Wavelet Transform, Dual-Tree Complex Wavelet Transform, Curvelet Transform, Wavelet Fusion, Weighted Fusion, and Principal Component Analysis. Prostate cancer images were manually segmented, and radiomics features were extracted using the Pyradiomics library in Python. We also used an Autoencoder for deep feature extraction. We used five different feature sets to train the classifiers: all radiomics features, all deep features, radiomics features linked with PCA, deep features linked with PCA, and a combination of radiomics and deep features. We processed the data, including balancing, standardization, PCA, correlation, and Least Absolute Shrinkage and Selection Operator (LASSO) regression. Finally, we used nine classifiers to classify different Gleason grades.

RESULTS

Our results show that the SVM classifier with deep features linked with PCA achieved the most promising results, with an AUC of 0.94 and a balanced accuracy of 0.79. Logistic regression performed best when using only the deep features, with an AUC of 0.93 and balanced accuracy of 0.76. Gaussian Naive Bayes had lower performance compared to other classifiers, while KNN achieved high performance using deep features linked with PCA. Random Forest performed well with the combination of deep features and radiomics features, achieving an AUC of 0.94 and balanced accuracy of 0.76. The Voting classifiers showed higher performance when using only the deep features, with Voting 2 achieving the highest performance, with an AUC of 0.95 and balanced accuracy of 0.78.

CONCLUSION

Our study concludes that the proposed multi-flavored feature extraction or tensor approach using radiomics and deep features can be an effective method for grading prostate cancer. Our findings suggest that deep features may be more effective than radiomics features alone in accurately classifying prostate cancer.

T2-Weighted MRI Radiomic Features Predict Prostate Cancer Presence and Eventual Biochemical Recurrence

Prostate cancer (PCa) is the most diagnosed non-cutaneous cancer in men. Despite therapies such as radical prostatectomy, which is considered curative, distant metastases may form, resulting in biochemical recurrence (BCR). This study used radiomic features calculated from multi-parametric magnetic resonance imaging (MP-MRI) to evaluate their ability to predict BCR and PCa presence. Data from a total of 279 patients, of which 46 experienced BCR, undergoing MP-MRI prior to surgery were assessed for this study. After surgery, the prostate was sectioned using patient-specific 3D-printed slicing jigs modeled using the T2-weighted imaging (T2WI). Sectioned tissue was stained, digitized, and annotated by a GU-fellowship trained pathologist for cancer presence. Digitized slides and annotations were co-registered to the T2WI and radiomic features were calculated across the whole prostate and cancerous lesions. A tree regression model was fitted to assess the ability of radiomic features to predict BCR, and a tree classification model was fitted with the same radiomic features to classify regions of cancer. We found that 10 radiomic features predicted eventual BCR with an AUC of 0.97 and classified cancer at an accuracy of 89.9%. This study showcases the application of a radiomic feature-based tool to screen for the presence of prostate cancer and assess patient prognosis, as determined by biochemical recurrence.

Novel radiomic analysis on bi-parametric MRI for characterizing differences between MR non-visible and visible clinically significant prostate cancer

Background

around one third of clinically significant prostate cancer (CsPCa) foci are reported to be MRI non-visible (MRI─).

Objective

To quantify the differences between MR visible (MRI+) and MRI^─ CsPCa using intra- and peri-lesional radiomic features on bi-parametric MRI (bpMRI).

Methods

This retrospective and multi-institutional study comprised 164 patients with pre-biopsy 3T prostate multi-parametric MRI from 2014 to 2017. The MRI^─ CsPCa referred to lesions with PI-RADS v2 score < 3 but ISUP grade group > 1. Three experienced radiologists were involved in annotating lesions and PI-RADS assignment. The validation set (D_v) comprised 52 patients from a single institution, the remaining 112 patients were used for training (D_t). 200 radiomic features were extracted from intra-lesional and peri-lesional regions on bpMRI.Logistic regression with least absolute shrinkage and selection operator (LASSO) and 10-fold cross-validation was applied on D_t to identify radiomic features associated with MRI^─ and MRI⁺ CsPCa to generate corresponding risk scores R^MRI─ and R^MRI+. R_bpMRI was further generated by integrating R^MRI─ and R^MRI+. Statistical significance was determined using the Wilcoxon signed-rank test.

Results

Both intra-lesional and peri-lesional bpMRI Haralick and CoLlAGe radiomic features were significantly associated with MRI^─ CsPCa (p < 0.05). Intra-lesional ADC Haralick and CoLlAGe radiomic features were significantly different among MRI^─ and MRI⁺ CsPCa (p < 0.05). R_bpMRI yielded the highest AUC of 0.82 (95 % CI 0.72-0.91) compared to AUCs of R^MRI+ 0.76 (95 % CI 0.63-0.89), and PI-RADS 0.58 (95 % CI 0.50-0.72) on D_v. R_bpMRI correctly reclassified 10 out of 14 MRI^─ CsPCa on D_v.

Conclusion

Our preliminary results demonstrated that both intra-lesional and peri-lesional bpMRI radiomic features were significantly associated with MRI^─ CsPCa. These features could assist in CsPCa identification on bpMRI.

Value of handcrafted and deep radiomic features towards training robust machine learning classifiers for prediction of prostate cancer disease aggressiveness

There is a growing piece of evidence that artificial intelligence may be helpful in the entire prostate cancer disease continuum. However, building machine learning algorithms robust to inter- and intra-radiologist segmentation variability is still a challenge. With this goal in mind, several model training approaches were compared: removing unstable features according to the intraclass correlation coefficient (ICC); training independently with features extracted from each radiologist's mask; training with the feature average between both radiologists; extracting radiomic features from the intersection or union of masks; and creating a heterogeneous dataset by randomly selecting one of the radiologists' masks for each patient. The classifier trained with this last resampled dataset presented with the lowest generalization error, suggesting that training with heterogeneous data leads to the development of the most robust classifiers. On the contrary, removing features with low ICC resulted in the highest generalization error. The selected radiomics dataset, with the randomly chosen radiologists, was concatenated with deep features extracted from neural networks trained to segment the whole prostate. This new hybrid dataset was then used to train a classifier. The results revealed that, even though the hybrid classifier was less overfitted than the one trained with deep features, it still was unable to outperform the radiomics model.

Volumetric visceral fat machine learning phenotype on CT for differential diagnosis of inflammatory bowel disease

OBJECTIVES

To investigate whether volumetric visceral adipose tissue (VAT) features extracted using radiomics and three-dimensional convolutional neural network (3D-CNN) approach are effective in differentiating Crohn's disease (CD) and ulcerative colitis (UC).

METHODS

This retrospective study enrolled 316 patients (mean age, 36.25 ± 13.58 [standard deviation]; 219 men) with confirmed diagnosis of CD and UC who underwent CT enterography between 2012 and 2021. Volumetric VAT was semi-automatically segmented on the arterial phase images. Radiomics analysis was performed using principal component analysis (PCA) and the least absolute shrinkage and selection operator (LASSO) logistic regression algorithm. We developed a 3D-CNN model using VAT imaging data from the training cohort. Clinical covariates including age, sex, modified body mass index, and disease duration that impact VAT were added to the machine learning model for adjustment. The model's performance was evaluated on the testing cohort separating from the model's development process by its discrimination and clinical utility.

RESULTS

Volumetric VAT radiomics analysis with LASSO had the highest AUC value of 0.717 (95% CI, 0.614-0.820), though difference of diagnostic performance among the 3D-CNN model (AUC = 0.693; 95% CI, 0.587-0.798) and radiomics analysis with PCA (AUC = 0.662; 95% CI, 0.548-0.776) and LASSO have not reached statistical significance (all p > 0.05). The radiomics score was higher in UC than in CD on the testing cohort (mean ± SD, UC 0.29 ± 1.05 versus CD -0.60 ± 1.25; p < 0.001). The LASSO model with adjustment of clinical covariates reached an AUC of 0.775 (95%CI, 0.683-0.868).

CONCLUSION

The developed volumetric VAT-based radiomics and 3D-CNN models provided comparable and effective performance for the characterization of CD from UC.

KEY POINTS

• High-output feature data extracted from volumetric visceral adipose tissue on CT enterography had an effective diagnostic performance for differentiating Crohn's disease from ulcerative colitis. • With adjustment of clinical covariates that cause difference in volumetric visceral adipose tissue, adjusted clinical machine learning model reached stronger performance when distinguishing Crohn's disease patients from ulcerative colitis patients.

Differential diagnosis of prostate cancer and benign prostatic hyperplasia based on DCE-MRI using bi-directional CLSTM deep learning and radiomics

Dynamic contrast-enhanced MRI (DCE-MRI) is routinely included in the prostate MRI protocol for a long time; its role has been questioned. It provides rich spatial and temporal information. However, the contained information cannot be fully extracted in radiologists' visual evaluation. More sophisticated computer algorithms are needed to extract the higher-order information. The purpose of this study was to apply a new deep learning algorithm, the bi-directional convolutional long short-term memory (CLSTM) network, and the radiomics analysis for differential diagnosis of PCa and benign prostatic hyperplasia (BPH). To systematically investigate the optimal amount of peritumoral tissue for improving diagnosis, a total of 9 ROIs were delineated by using 3 different methods. The results showed that bi-directional CLSTM with ± 20% region growing peritumoral ROI achieved the mean AUC of 0.89, better than the mean AUC of 0.84 by using the tumor alone without any peritumoral tissue (p = 0.25, not significant). For all 9 ROIs, deep learning had higher AUC than radiomics, but only reaching the significant difference for ± 20% region growing peritumoral ROI (0.89 vs. 0.79, p = 0.04). In conclusion, the kinetic information extracted from DCE-MRI using bi-directional CLSTM may provide helpful supplementary information for diagnosis of PCa.

The Low Rate of Adherence to Checklist for Artificial Intelligence in Medical Imaging Criteria Among Published Prostate MRI Artificial Intelligence Algorithms

OBJECTIVE

To determine the rigor, generalizability, and reproducibility of published classification and detection artificial intelligence (AI) models for prostate cancer (PCa) on MRI using the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) guidelines, a 42-item checklist that is considered a measure of best practice for presenting and reviewing medical imaging AI research.

MATERIALS AND METHODS

This review searched English literature for studies proposing PCa AI detection and classification models on MRI. Each study was evaluated with the CLAIM checklist. The additional outcomes for which data were sought included measures of AI model performance (eg, area under the curve [AUC], sensitivity, specificity, free-response operating characteristic curves), training and validation and testing group sample size, AI approach, detection versus classification AI, public data set utilization, MRI sequences used, and definition of gold standard for ground truth. The percentage of CLAIM checklist fulfillment was used to stratify studies into quartiles. Wilcoxon's rank-sum test was used for pair-wise comparisons.

RESULTS

In all, 75 studies were identified, and 53 studies qualified for analysis. The original CLAIM items that most studies did not fulfill includes item 12 (77% no): de-identification methods; item 13 (68% no): handling missing data; item 15 (47% no): rationale for choosing ground truth reference standard; item 18 (55% no): measurements of inter- and intrareader variability; item 31 (60% no): inclusion of validated interpretability maps; item 37 (92% no): inclusion of failure analysis to elucidate AI model weaknesses. An AUC score versus percentage CLAIM fulfillment quartile revealed a significant difference of the mean AUC scores between quartile 1 versus quartile 2 (0.78 versus 0.86, P = .034) and quartile 1 versus quartile 4 (0.78 versus 0.89, P = .003) scores. Based on additional information and outcome metrics gathered in this study, additional measures of best practice are defined. These new items include disclosure of public dataset usage, ground truth definition in comparison to other referenced works in the defined task, and sample size power calculation.

CONCLUSION

A large proportion of AI studies do not fulfill key items in CLAIM guidelines within their methods and results sections. The percentage of CLAIM checklist fulfillment is weakly associated with improved AI model performance. Additions or supplementations to CLAIM are recommended to improve publishing standards and aid reviewers in determining study rigor.

Imaging bridges pathology and radiology

In recent years, medical disciplines have moved closer together and rigid borders have been increasingly dissolved. The synergetic advantage of combining multiple disciplines is particularly important for radiology, nuclear medicine, and pathology to perform integrative diagnostics. In this review, we discuss how medical subdisciplines can be reintegrated in the future using state-of-the-art methods of digitization, data science, and machine learning. Integration of methods is made possible by the digitalization of radiological and nuclear medical images, as well as pathological images. 3D histology can become a valuable tool, not only for integration into radiological images but also for the visualization of cellular interactions, the so-called connectomes. In human pathology, it has recently become possible to image and calculate the movements and contacts of immunostained cells in fresh tissue explants. Recording the movement of a living cell is proving to be informative and makes it possible to study dynamic connectomes in the diagnosis of lymphoid tissue. By applying computational methods including data science and machine learning, new perspectives for analyzing and understanding diseases become possible.

Evaluation of automatic discrimination between benign and malignant prostate tissue in the era of high precision digital pathology

BACKGROUND

Prostate cancer is a major health concern in aging men. Paralleling an aging society, prostate cancer prevalence increases emphasizing the need for efficient diagnostic algorithms.

METHODS

Retrospectively, 106 prostate tissue samples from 48 patients (mean age, [Formula: see text] years) were included in the study. Patients suffered from prostate cancer (n = 38) or benign prostatic hyperplasia (n = 10) and were treated with radical prostatectomy or Holmium laser enucleation of the prostate, respectively. We constructed tissue microarrays (TMAs) comprising representative malignant (n = 38) and benign (n = 68) tissue cores. TMAs were processed to histological slides, stained, digitized and assessed for the applicability of machine learning strategies and open-source tools in diagnosis of prostate cancer. We applied the software QuPath to extract features for shape, stain intensity, and texture of TMA cores for three stainings, H&E, ERG, and PIN-4. Three machine learning algorithms, neural network (NN), support vector machines (SVM), and random forest (RF), were trained and cross-validated with 100 Monte Carlo random splits into 70% training set and 30% test set. We determined AUC values for single color channels, with and without optimization of hyperparameters by exhaustive grid search. We applied recursive feature elimination to feature sets of multiple color transforms.

RESULTS

Mean AUC was above 0.80. PIN-4 stainings yielded higher AUC than H&E and ERG. For PIN-4 with the color transform saturation, NN, RF, and SVM revealed AUC of [Formula: see text], [Formula: see text], and [Formula: see text], respectively. Optimization of hyperparameters improved the AUC only slightly by 0.01. For H&E, feature selection resulted in no increase of AUC but to an increase of 0.02-0.06 for ERG and PIN-4.

CONCLUSIONS

Automated pipelines may be able to discriminate with high accuracy between malignant and benign tissue. We found PIN-4 staining best suited for classification. Further bioinformatic analysis of larger data sets would be crucial to evaluate the reliability of automated classification methods for clinical practice and to evaluate potential discrimination of aggressiveness of cancer to pave the way to automatic precision medicine.

Detection of prostate cancer using diffusion-relaxation correlation spectrum imaging with support vector machine model - a feasibility study

BACKGROUND

To evaluate the performance of diffusion-relaxation correlation spectrum imaging (DR-CSI) with support vector machine (SVM) in detecting prostate cancer (PCa).

METHODS

In total, 114 patients (mean age, 66 years, range, 48-87 years) who received a prostate MRI and underwent biopsy were enrolled in three stages. Thirty-nine were assigned for the exploration stage to establish the model, 18 for the validation stage to choose the appropriate scale for mapping and 57 for the test stage to compare the diagnostic performance of the DR-CSI and PI-RADS.

RESULTS

In the exploration stage, the DR-CSI model was established and performed better than the ADC and T₂ values (both P < 0.001). The validation result shows that at least 2 pixels were required for both the long-axis and short-axis in the mapping procedure. In the test stage, DR-CSI had higher accuracy than PI-RADS ≥ 3 as a positive finding based on patient (84.2% vs. 63.2%, P = 0.004) and lesion (78.8% vs. 57.6%, P = 0.001) as well as PI-RADS ≥ 4 on lesion (76.5% vs. 64.7%, P = 0.029), while there was no significant difference between DR-CSI and PI-RADS ≥ 4 based on patient (P = 0.508). For clinically significant PCa, DR-CSI had higher accuracy than PI-RADS ≥ 3 based on patients (84.2% vs. 63.2%, P = 0.004) and lesions (62.4% vs. 48.2%, P = 0.036). There was no significant difference between DR-CSI and PI-RADS ≥ 4 (P = 1.000 and 0.845 for the patient and lesion levels, respectively).

CONCLUSIONS

DR-CSI combined with the SVM model may improve the diagnostic accuracy of PCa.

TRIAL REGISTRATION

This study was approved by the Ethics Committee of our institute (Approval No. KY2018-213). Written informed consent was obtained from all participants.

A dynamic-static combination model based on radiomics features for prostate cancer using multiparametric MRI

Objective. To propose a new dynamic multiparametric magnetic resonance imaging (mpMRI) radiomics method for the detection of prostate cancer (PCa), and establish a combined model using dynamic and static radiomics features based on this method.Approach. A total of 166 patients (82 PCa patients and 84 non-PCa patients) were enrolled in the study, and 31 872 mpMRI images were performed in a radiomics workflow. The whole prostate segmentation and traditional static radiomics features extraction were performed on intravoxel incoherent motion diffusion-weighted imaging (IVIM-DWI,bvalue of 10, 50, 100, 150, 200, 400, 600, 800, 1000, 1500 s mm^-2respectively), apparent diffusion coefficient (ADC), and T2-weighted imaging (T2WI) sequences respectively. Through the building of eachb-value DWI model and the analysis of the static key radiomics features, three types of dynamic features called standard discrete (SD), parameter (P) and relative change rate (RCR) were constructed. And the b-value parameters used to construct dynamic features were divided into three groups ('Df_', 'Db_' and 'Da_'): the front part (10-200 s mm^-2), the back part (400-1500 s mm^-2), and all (10-1500 s mm^-2) of theb-values set, respectively. Afterwards, the dynamic mpMRI model and combined model construction were constructed, and the PCa discrimination performance of each model was evaluated.Main results.The models based on dynamic features showed good potential for PCa identification. Where, the results of Db_SD, Da_P and Db_P models were encouraging (test cohort AUCs: 90.78%, 87.60%, 86.3%), which was better than the commonly used ADC model (AUC of ADC was 75.48%). Among the combined models, the models using static features of T2WI and dynamic features performed the best. The AUC of Db_SD + T2WI, Db_P + T2WI and Db_RCR + T2WI model was 92.90%, 91.29% and 81.46%.Significance.The dynamic-static combination model based on dynamic mpMRI radiomics method has a good effect on the identification of PCa. This method has broad application prospects in PCa individual diagnosis management.

Joint models for dynamic prediction in localised prostate cancer: a literature review

BACKGROUND

Prostate cancer is a very prevalent disease in men. Patients are monitored regularly during and after treatment with repeated assessment of prostate-specific antigen (PSA) levels. Prognosis of localised prostate cancer is generally good after treatment, and the risk of having a recurrence is usually estimated based on factors measured at diagnosis. Incorporating PSA measurements over time in a dynamic prediction joint model enables updates of patients' risk as new information becomes available. We review joint model strategies that have been applied to model time-dependent PSA trajectories to predict time-to-event outcomes in localised prostate cancer.

METHODS

We identify articles that developed joint models for prediction of localised prostate cancer recurrence over the last two decades. We report, compare, and summarise the methodological approaches and applications that use joint modelling accounting for two processes: the longitudinal model (PSA), and the time-to-event process (clinical failure). The methods explored differ in how they specify the association between these two processes.

RESULTS

Twelve relevant articles were identified. A range of methodological frameworks were found, and we describe in detail shared-parameter joint models (9 of 12, 75%) and joint latent class models (3 of 12, 25%). Within each framework, these articles presented model development, estimation of dynamic predictions and model validations.

CONCLUSIONS

Each framework has its unique principles with corresponding advantages and differing interpretations. Regardless of the framework used, dynamic prediction models enable real-time prediction of individual patient prognosis. They utilise all available longitudinal information, in addition to baseline prognostic risk factors, and are superior to traditional baseline-only prediction models.

Radiomics Models Based on Magnetic Resonance Imaging for Prediction of the Response to Bortezomib-Based Therapy in Patients with Multiple Myeloma

Purpose. To identify significant radiomics features based on MRI and establish effective models for predicting the response to bortezomib-based regimens. Materials and Methods. In total, 95 MM patients treated with bortezomib-based therapy were enrolled, including 77 with bortezomib, cyclophosphamide, and dexamethasone (BCD) and 18 with bortezomib, lenalidomide, and dexamethasone (VRD). Based on T1-weighted imaging (T1WI) and T2-weighted imaging with fat suppression (T2WI-fs), radiomics features were extracted and then selected. The random forest (RF), $k$ -nearest neighbor, support vector machine, logistic regression, decision tree, and Bayes models were built using the selected features. The predictive power of six models for response to BCD and VRD regimens were evaluated. The correlation between the selected features and progression-free survival (PFS) was also analyzed. Results. Four wavelet features were correlated with BCD treatment response. The six models all showed predictive power for BCD regimen (AUC: 0.84-0.896 in the training set, 0.801-0.885 in the validation set), and RF performed relatively better than others. Nevertheless, all the BCD-based models were incapable of predicting the VRD treatment response. The wavelet-HLH_firstorder_kurtosis was also associated with PFS (log-rank $P=0.019$ ). Conclusion. The four wavelet features were valuable biomarkers for predicting the response to BCD regimen. The six models based on these features showed predictive power, and RF was the best. One wavelet feature was also a survival-related biomarker. MRI-based radiomics had the potential to guide clinicians in MM management.

Current Value of Biparametric Prostate MRI with Machine-Learning or Deep-Learning in the Detection, Grading, and Characterization of Prostate Cancer: A Systematic Review

Prostate cancer detection with magnetic resonance imaging is based on a standardized MRI-protocol according to the PI-RADS guidelines including morphologic imaging, diffusion weighted imaging, and perfusion. To facilitate data acquisition and analysis the contrast-enhanced perfusion is often omitted resulting in a biparametric prostate MRI protocol. The intention of this review is to analyze the current value of biparametric prostate MRI in combination with methods of machine-learning and deep learning in the detection, grading, and characterization of prostate cancer; if available a direct comparison with human radiologist performance was performed. PubMed was systematically queried and 29 appropriate studies were identified and retrieved. The data show that detection of clinically significant prostate cancer and differentiation of prostate cancer from non-cancerous tissue using machine-learning and deep learning is feasible with promising results. Some techniques of machine-learning and deep-learning currently seem to be equally good as human radiologists in terms of classification of single lesion according to the PIRADS score.

Overview of radiomics in prostate imaging and future directions

Recent advancements in imaging technology and analysis methods have led to an analytic framework known as radiomics. This framework extracts comprehensive high-dimensional features from imaging data and performs data mining to build analytical models for improved decision-support. Its features include many categories spanning texture and shape; thus, it can provide abundant information for precision medicine. Many studies of prostate radiomics have shown promising results in the assessment of pathological features, prediction of treatment response, and stratification of risk groups. Herein, we aimed to provide a general overview of radiomics procedures, discuss technical issues, explain various clinical applications, and suggest future research directions, especially for prostate imaging.

Machine and Deep Learning Prediction Of Prostate Cancer Aggressiveness Using Multiparametric MRI

Prostate cancer (PCa) is the most frequent male malignancy and the assessment of PCa aggressiveness, for which a biopsy is required, is fundamental for patient management. Currently, multiparametric (mp) MRI is strongly recommended before biopsy. Quantitative assessment of mpMRI might provide the radiologist with an objective and noninvasive tool for supporting the decision-making in clinical practice and decreasing intra- and inter-reader variability. In this view, high dimensional radiomics features and Machine Learning (ML) techniques, along with Deep Learning (DL) methods working on raw images directly, could assist the radiologist in the clinical workflow. The aim of this study was to develop and validate ML/DL frameworks on mpMRI data to characterize PCas according to their aggressiveness. We optimized several ML/DL frameworks on T2w, ADC and T2w+ADC data, using a patient-based nested validation scheme. The dataset was composed of 112 patients (132 peripheral lesions with Prostate Imaging Reporting and Data System (PI-RADS) score ≥ 3) acquired following both PI-RADS 2.0 and 2.1 guidelines. Firstly, ML/DL frameworks trained and validated on PI-RADS 2.0 data were tested on both PI-RADS 2.0 and 2.1 data. Then, we trained, validated and tested ML/DL frameworks on a multi PI-RADS dataset. We reported the performances in terms of Area Under the Receiver Operating curve (AUROC), specificity and sensitivity. The ML/DL frameworks trained on T2w data achieved the overall best performance. Notably, ML and DL frameworks trained and validated on PI-RADS 2.0 data obtained median AUROC values equal to 0.750 and 0.875, respectively, on unseen PI-RADS 2.0 test set. Similarly, ML/DL frameworks trained and validated on multi PI-RADS T2w data showed median AUROC values equal to 0.795 and 0.750, respectively, on unseen multi PI-RADS test set. Conversely, all the ML/DL frameworks trained and validated on PI-RADS 2.0 data, achieved AUROC values no better than the chance level when tested on PI-RADS 2.1 data. Both ML/DL techniques applied on mpMRI seem to be a valid aid in predicting PCa aggressiveness. In particular, ML/DL frameworks fed with T2w images data (objective, fast and non-invasive) show good performances and might support decision-making in patient diagnostic and therapeutic management, reducing intra- and inter-reader variability.

Comparison of clinical-computed tomography model with 2D and 3D radiomics models to predict occult peritoneal metastases in advanced gastric cancer

PURPOSE

To compare the ability of a clinical-computed tomography (CT) model vs. 2D and 3D radiomics models for predicting occult peritoneal metastasis (PM) in patients with advanced gastric cancer (AGC).

METHODS

In this retrospective study, we included 49 patients with occult PM and 49 control patients (without PM) who underwent preoperative CT and subsequent surgery between January 2016 and December 2018. Clinical information and CT semantic features were collected, and CT radiomics features were extracted. A predictive clinical-CT model was created using multivariate logistic regression. The least absolute shrinkage and selection operator algorithm and logistic regression were used for constructing 2D and 3D radiomics models. These models were validated with an external cohort (n = 30). Receiver operating characteristics curve with area under the curve (AUC), sensitivity, and specificity were used to evaluate predictive performance.

RESULTS

Tumor size, mild ascites, and serum CA125 were independent factors predictive of occult PM. The clinical-CT model of these independent factors showed better diagnostic performance than 2D and 3D radiomics models. In the external validation cohort, the AUCs of different models were as follows-clinical-CT model: 0.853 (sensitivity, 66.7%; specificity, 93.3%); 2D radiomics model: 0.622 (sensitivity, 80.0%; specificity, 46.7%); and 3D radiomics model: 0.676 (sensitivity, 60.0%; specificity, 86.0%). The clinical-CT model nomogram showed good clinical predictive efficiency to assess occult PM.

CONCLUSION

The clinical-CT model was better than the radiomics models in predicting occult PM in AGC.

Radiomics in prostate cancer: an up-to-date review

Prostate cancer (PCa) is the most common worldwide diagnosed malignancy in male population. The diagnosis, the identification of aggressive disease, and the post-treatment follow-up needs a more comprehensive and holistic approach. Radiomics is the extraction and interpretation of images phenotypes in a quantitative manner. Radiomics may give an advantage through advancements in imaging modalities and through the potential power of artificial intelligence techniques by translating those features into clinical outcome prediction. This article gives an overview on the current evidence of methodology and reviews the available literature on radiomics in PCa patients, highlighting its potential for personalized treatment and future applications.

State of the art of radiomic analysis in the clinical management of prostate cancer: A systematic review

We present the current clinical applications of radiomics in the context of prostate cancer (PCa) management. Several online databases for original articles using a combination of the following keywords: "(radiomic or radiomics) AND (prostate cancer or prostate tumour or prostate tumor or prostate neoplasia)" have been searched. The selected papers have been pooled as focus on (i) PCa detection, (ii) assessing the clinical significance of PCa, (iii) biochemical recurrence prediction, (iv) radiation-therapy outcome prediction and treatment efficacy monitoring, (v) metastases detection, (vi) metastases prediction, (vii) prediction of extra-prostatic extension. Seventy-six studies were included for qualitative analyses. Classifiers powered with radiomic features were able to discriminate between healthy tissue and PCa and between low- and high-risk PCa. However, before radiomics can be proposed for clinical use its methods have to be standardized, and these first encouraging results need to be robustly replicated in large and independent cohorts.

Virtual biopsy in prostate cancer: can machine learning distinguish low and high aggressive tumors on MRI?

In the last decades, MRI was proven a useful tool for the diagnosis and characterization of Prostate Cancer (PCa). In the literature, many studies focused on characterizing PCa aggressiveness, but a few have distinguished between low-aggressive (Gleason Grade Group (GG) <=2) and high-aggressive (GG>=3) PCas based on biparametric MRI (bpMRI). In this study, 108 PCas were collected from two different centers and were divided into training, testing, and validation set. From Apparent Diffusion Coefficient (ADC) map and T2-Weighted Image (T2WI), we extracted texture features, both 3D and 2D, and we implemented three different methods of Feature Selection (FS): Minimum Redundance Maximum Relevance (MRMR), Affinity Propagation (AP), and Genetic Algorithm (GA). From the resulting subsets of predictors, we trained Support Vector Machine (SVM), Decision Tree, and Ensemble Learning classifiers on the training set, and we evaluated their prediction ability on the testing set. Then, for each FS method, we chose the best classifier, based on both training and testing performances, and we further assessed their generalization capability on the validation set. Between the three best models, a Decision Tree was trained using only two features extracted from the ADC map and selected by MRMR, achieving, on the validation set, an Area Under the ROC (AUC) equal to 81%, with sensitivity and specificity of 77% and 93%, respectively.Clinical Relevance- Our best model demonstrated to be able to distinguish low-aggressive from high-aggressive PCas with high accuracy. Potentially, this approach could help clinician to noninvasively distinguish between PCas that might need active treatment and those that could potentially benefit from active surveillance, avoiding biopsy-related complications.

Assessment of the optimal number of positive biopsy cores to discriminate between cancer-specific mortality in high-risk versus very high-risk prostate cancer patients

BACKGROUND

Number of positive prostate biopsy cores represents a key determinant between high versus very high-risk prostate cancer (PCa). We performed a critical appraisal of the association between the number of positive prostate biopsy cores and CSM in high versus very high-risk PCa.

METHODS

Within Surveillance, Epidemiology, and End Results database (2010-2016), 13,836 high versus 20,359 very high-risk PCa patients were identified. Discrimination according to 11 different positive prostate biopsy core cut-offs (≥2-≥12) were tested in Kaplan-Meier, cumulative incidence, and multivariable Cox and competing risks regression models.

RESULTS

Among 11 tested positive prostate biopsy core cut-offs, more than or equal to 8 (high-risk vs. very high-risk: n = 18,986 vs. n = 15,209, median prostate-specific antigen [PSA]: 10.6 vs. 16.8 ng/ml, <.001) yielded optimal discrimination and was closely followed by the established more than or equal to 5 cut-off (high-risk vs. very high-risk: n = 13,836 vs. n = 20,359, median PSA: 16.5 vs. 11.1 ng/ml, p < .001). Stratification according to more than or equal to 8 positive prostate biopsy cores resulted in CSM rates of 4.1 versus 14.2% (delta: 10.1%, multivariable hazard ratio: 2.2, p < .001) and stratification according to more than or equal to 5 positive prostate biopsy cores with CSM rates of 3.7 versus 11.9% (delta: 8.2%, multivariable hazard ratio: 2.0, p < .001) in respectively high versus very high-risk PCa.

CONCLUSIONS

The more than or equal to 8 positive prostate biopsy cores cutoff yielded optimal results. It was very closely followed by more than or equal to 5 positive prostate biopsy cores. In consequence, virtually the same endorsement may be made for either cutoff. However, more than or equal to 5 positive prostate biopsy cores cutoff, based on its existing wide implementation, might represent the optimal choice.

Prostate Cancer Radiogenomics-From Imaging to Molecular Characterization

Radiomics and genomics represent two of the most promising fields of cancer research, designed to improve the risk stratification and disease management of patients with prostate cancer (PCa). Radiomics involves a conversion of imaging derivate quantitative features using manual or automated algorithms, enhancing existing data through mathematical analysis. This could increase the clinical value in PCa management. To extract features from imaging methods such as magnetic resonance imaging (MRI), the empiric nature of the analysis using machine learning and artificial intelligence could help make the best clinical decisions. Genomics information can be explained or decoded by radiomics. The development of methodologies can create more-efficient predictive models and can better characterize the molecular features of PCa. Additionally, the identification of new imaging biomarkers can overcome the known heterogeneity of PCa, by non-invasive radiological assessment of the whole specific organ. In the future, the validation of recent findings, in large, randomized cohorts of PCa patients, can establish the role of radiogenomics. Briefly, we aimed to review the current literature of highly quantitative and qualitative results from well-designed studies for the diagnoses, treatment, and follow-up of prostate cancer, based on radiomics, genomics and radiogenomics research.

Challenges in the Use of Artificial Intelligence for Prostate Cancer Diagnosis from Multiparametric Imaging Data

Simple Summary

Prostate Cancer is one of the main threats to men’s health. Its accurate diagnosis is crucial to properly treat patients depending on the cancer’s level of aggressiveness. Tumor risk-stratification is still a challenging task due to the difficulties met during the reading of multi-parametric Magnetic Resonance Images. Artificial Intelligence models may help radiologists in staging the aggressiveness of the equivocal lesions, reducing inter-observer variability and evaluation time. However, these algorithms need many high-quality images to work efficiently, bringing up overfitting and lack of standardization and reproducibility as emerging issues to be addressed. This study attempts to illustrate the state of the art of current research of Artificial Intelligence methods to stratify prostate cancer for its clinical significance suggesting how widespread use of public databases could be a possible solution to these issues.

Abstract

Many efforts have been carried out for the standardization of multiparametric Magnetic Resonance (mp-MR) images evaluation to detect Prostate Cancer (PCa), and specifically to differentiate levels of aggressiveness, a crucial aspect for clinical decision-making. Prostate Imaging—Reporting and Data System (PI-RADS) has contributed noteworthily to this aim. Nevertheless, as pointed out by the European Association of Urology (EAU 2020), the PI-RADS still has limitations mainly due to the moderate inter-reader reproducibility of mp-MRI. In recent years, many aspects in the diagnosis of cancer have taken advantage of the use of Artificial Intelligence (AI) such as detection, segmentation of organs and/or lesions, and characterization. Here a focus on AI as a potentially important tool for the aim of standardization and reproducibility in the characterization of PCa by mp-MRI is reported. AI includes methods such as Machine Learning and Deep learning techniques that have shown to be successful in classifying mp-MR images, with similar performances obtained by radiologists. Nevertheless, they perform differently depending on the acquisition system and protocol used. Besides, these methods need a large number of samples that cover most of the variability of the lesion aspect and zone to avoid overfitting. The use of publicly available datasets could improve AI performance to achieve a higher level of generalizability, exploiting large numbers of cases and a big range of variability in the images. Here we explore the promise and the advantages, as well as emphasizing the pitfall and the warnings, outlined in some recent studies that attempted to classify clinically significant PCa and indolent lesions using AI methods. Specifically, we focus on the overfitting issue due to the scarcity of data and the lack of standardization and reproducibility in every step of the mp-MR image acquisition and the classifier implementation. In the end, we point out that a solution can be found in the use of publicly available datasets, whose usage has already been promoted by some important initiatives. Our future perspective is that AI models may become reliable tools for clinicians in PCa diagnosis, reducing inter-observer variability and evaluation time.

Detection of Prostate Cancer Using Biparametric Prostate MRI, Radiomics, and Kallikreins: A Retrospective Multicenter Study of Men With a Clinical Suspicion of Prostate Cancer

BACKGROUND

Accurate detection of clinically significant prostate cancer (csPCa), Gleason Grade Group ≥ 2, remains a challenge. Prostate MRI radiomics and blood kallikreins have been proposed as tools to improve the performance of biparametric MRI (bpMRI).

PURPOSE

To develop and validate radiomics and kallikrein models for the detection of csPCa.

STUDY TYPE

Retrospective.

POPULATION

A total of 543 men with a clinical suspicion of csPCa, 411 (76%, 411/543) had kallikreins available and 360 (88%, 360/411) did not take 5-alpha-reductase inhibitors. Two data splits into training, validation (split 1: single center, n = 72; split 2: random 50% of pooled datasets from all four centers), and testing (split 1: 4 centers, n = 288; split 2: remaining 50%) were evaluated.

FIELD STRENGTH/SEQUENCE

A 3 T/1.5 T, TSE T2-weighted imaging, 3x SE DWI.

ASSESSMENT

In total, 20,363 radiomic features calculated from manually delineated whole gland (WG) and bpMRI suspicion lesion masks were evaluated in addition to clinical parameters, prostate-specific antigen, four kallikreins, MRI-based qualitative (PI-RADSv2.1/IMPROD bpMRI Likert) scores.

STATISTICAL TESTS

For the detection of csPCa, area under receiver operating curve (AUC) was calculated using the DeLong's method. A multivariate analysis was conducted to determine the predictive power of combining variables. The values of P-value < 0.05 were considered significant.

RESULTS

The highest prediction performance was achieved by IMPROD bpMRI Likert and PI-RADSv2.1 score with AUC = 0.85 and 0.85 in split 1, 0.85 and 0.83 in split 2, respectively. bpMRI WG and/or kallikreins demonstrated AUCs ranging from 0.62 to 0.73 in split 1 and from 0.68 to 0.76 in split 2. AUC of bpMRI lesion-derived radiomics model was not statistically different to IMPROD bpMRI Likert score (split 1: AUC = 0.83, P-value = 0.306; split 2: AUC = 0.83, P-value = 0.488).

DATA CONCLUSION

The use of radiomics and kallikreins failed to outperform PI-RADSv2.1/IMPROD bpMRI Likert and their combination did not lead to further performance gains.

LEVEL OF EVIDENCE

1 TECHNICAL EFFICACY: Stage 2.

Associations between Statin/Omega3 Usage and MRI-Based Radiomics Signatures in Prostate Cancer

Prostate cancer is the most common noncutaneous cancer and the second leading cause of cancer deaths among American men. Statins and omega-3 are two medications recently found to correlate with prostate cancer risk and aggressiveness, but the observed associations are complex and controversial. We therefore explore the novel application of radiomics in studying statin and omega-3 usage in prostate cancer patients. On MRIs of 91 prostate cancer patients, two regions of interest (ROIs), the whole prostate and the peripheral region of the prostate, were manually segmented. From each ROI, 944 radiomic features were extracted after field bias correction and normalization. Heatmaps were generated to study the radiomic feature patterns against statin or omega-3 usage. Radiomics models were trained on selected features and evaluated with 500-round threefold cross-validation for each drug/ROI combination. On the 1500 validation datasets, the radiomics model achieved average AUCs of 0.70, 0.74, 0.78, and 0.72 for omega-3/prostate, omega-3/peripheral, statin/prostate, and statin/peripheral, respectively. As the first study to analyze radiomics in relation to statin and omega-3 uses in prostate cancer patients, our study preliminarily established the existence of imaging-identifiable tissue-level changes in the prostate and illustrated the potential usefulness of radiomics for further exploring these medications’ effects and mechanisms in prostate cancer.