Artificial Intelligence and Machine Learning in Prostate Cancer Patient Management-Current Trends and Future Perspectives

Exploiting biochemical data to improve osteosarcoma diagnosis with deep learning

Early and accurate diagnosis of osteosarcomas (OS) is of great clinical significance, and machine learning (ML) based methods are increasingly adopted. However, current ML-based methods for osteosarcoma diagnosis consider only X-ray images, usually fail to generalize to new cases, and lack explainability. In this paper, we seek to explore the capability of deep learning models in diagnosing primary OS, with higher accuracy, explainability, and generality. Concretely, we analyze the added value of integrating the biochemical data, i.e., alkaline phosphatase (ALP) and lactate dehydrogenase (LDH), and design a model that incorporates the numerical features of ALP and LDH and the visual features of X-ray imaging through a late fusion approach in the feature space. We evaluate this model on real-world clinic data with 848 patients aged from 4 to 81. The experimental results reveal the effectiveness of incorporating ALP and LDH simultaneously in a late fusion approach, with the accuracy of the considered 2608 cases increased to 97.17%, compared to 94.35% in the baseline. Grad-CAM visualizations consistent with orthopedic specialists further justified the model's explainability.

Circulating IgG Fragments for Gastric Cancer and Esophageal Cancer

Blood serum of patients with gastric (n = 68) and esophageal (n = 43) cancer was assessed for proteolytic fragments of IgG. Serum samples of 20 healthy donors were used as a control. We analyzed indicators of hemostasis (prothrombin time, fibrinogen, plasminogen activity, a2-antiplasmin activity, protein C activity) in blood plasma and the level of total IgG in the blood serum. The median IgG-LysK of healthy donors was lower than in esophageal cancer and in patients with gastric cancer. ROC-analysis showed high sensitivity (91%) and specificity (85%) in the group with esophageal cancer but 68% and 85%, respectively, in patients with gastric cancer. Analysis of false negatives IgG-LysK in cancer patients showed that most patients had an advanced stage of cancer accompanied by metastases. Total IgG in the plasma of patients with false-negative IgG-LysK values was 30% lower than in samples with positive values, while the level of a2-antiplasmin was increased and the prothrombin time was shorter. These changes in blood homeostasis may be the reason for an increase in the proportion of false-negative values of the IgG-LysK coefficient. Circulatory IgG-LysK levels increase in the early stages of such cancers as gastric and esophageal cancers. Thus, when used in a panel with other more specific markers for these pathologies, this indicator can significantly increase the early detection of cancer.

Associations of systemic immune-inflammation index with high risk for prostate cancer in middle-aged and older US males: A population-based study

BACKGROUND

Systemic immune-inflammation index (SII) provides convincing evaluation of systemic immune and inflammatory condition in human body. Its correlation with prostate cancer (PCa) risk remains uncharted. The principal objective of this investigation was to elucidate the association between SII and the risk for PCa in middle-aged and elderly males.

MATERIALS AND METHODS

Analysis entailed multivariate linear and logistic regression, generalized additive model, and smoothing curve fitting using resource from 2007 to 2010 National Health and Nutrition Examination Survey (NHANES). To ascertain robustness and consistency of this association across different demographic strata, we conducted rigorous subgroup analyses and interaction tests.

RESULTS

Among 3359 participants, those with elevated SII displayed higher total prostate-specific antigen (tPSA) levels, higher risk for PCa, and lower free/total PSA (f/t PSA) ratio. Specifically, each unit increase of log2 (SII) was associated with a 0.22 ng/mL increase in tPSA (β: 0.22, 95% confidence intervals [CI] 0.05-0.38), a 2.22% decline in f/t PSA ratio (β: -2.22, 95% CI -3.20 to -1.23), and a 52% increased odds of being at high risk for PCa (odds ratio [OR]: 1.52, 95% CI 1.13-2.04). People in the top quartile of log2 (SII) exhibited 0.55 ng/mL increased tPSA (β: 0.55, 95% CI 0.19-0.90), 4.39% reduced f/t PSA ratio (β: -4.39, 95% CI -6.50 to -2.27), and 168% increased odds of being at high risk for PCa (OR: 2.68, 95% CI 1.32-5.46) compared to those in the bottom quartile.

CONCLUSION

Systemic immune and inflammatory condition, as represented by SII, is independently and positively associated with tPSA levels and the risk for PCa, as well as independently and negatively associated with f/t PSA ratio among middle-aged and older US males. These findings may enhance the effectiveness of PCa screening in predicting positive biopsy results.

Challenges and perspectives in use of artificial intelligence to support treatment recommendations in clinical oncology

Artificial intelligence (AI) promises to be the next revolutionary step in modern society. Yet, its role in all fields of industry and science need to be determined. One very promising field is represented by AI-based decision-making tools in clinical oncology leading to more comprehensive, personalized therapy approaches. In this review, the authors provide an overview on all relevant technical applications of AI in oncology, which are required to understand the future challenges and realistic perspectives for decision-making tools. In recent years, various applications of AI in medicine have been developed focusing on the analysis of radiological and pathological images. AI applications encompass large amounts of complex data supporting clinical decision-making and reducing errors by objectively quantifying all aspects of the data collected. In clinical oncology, almost all patients receive a treatment recommendation in a multidisciplinary cancer conference at the beginning and during their treatment periods. These highly complex decisions are based on a large amount of information (of the patients and of the various treatment options), which need to be analyzed and correctly classified in a short time. In this review, the authors describe the technical and medical requirements of AI to address these scientific challenges in a multidisciplinary manner. Major challenges in the use of AI in oncology and decision-making tools are data security, data representation, and explainability of AI-based outcome predictions, in particular for decision-making processes in multidisciplinary cancer conferences. Finally, limitations and potential solutions are described and compared for current and future research attempts.

CASCADE: Context-Aware Data-Driven AI for Streamlined Multidisciplinary Tumor Board Recommendations in Oncology

This study addresses the potential of machine learning in predicting treatment recommendations for patients with hepatocellular carcinoma (HCC). Using an IRB-approved retrospective study of patients discussed at a multidisciplinary tumor board, clinical and imaging variables were extracted and used in a gradient-boosting machine learning algorithm, XGBoost. The algorithm's performance was assessed using confusion matrix metrics and the area under the Receiver Operating Characteristics (ROC) curve. The study included 140 patients (mean age 67.7 ± 8.9 years), and the algorithm was found to be predictive of all eight treatment recommendations made by the board. The model's predictions were more accurate than those based on published therapeutic guidelines by ESMO and NCCN. The study concludes that a machine learning model incorporating clinical and imaging variables can predict treatment recommendations made by an expert multidisciplinary tumor board, potentially aiding clinical decision-making in settings lacking subspecialty expertise.

Unlocking the potential of robotic-assisted bronchoscopy: overcoming challenging anatomy and locations

Robotic-assisted bronchoscopy (RAB) was recently added to the armamentarium of tools used in sampling peripheral lung nodules. Protocols and guidelines have since been published advocating use of large oral artificial airways, use of confirmatory technologies such as radial endobronchial ultrasound (R-EBUS), and preferably limiting sampling to pulmonary parenchymal lesions. We present three clinical cases where RAB was used unconventionally to sample pulmonary nodules in unusual locations and in patients with challenging airway anatomy. In case 1, we introduced the ion catheter through a nasal airway in a patient with trismus. In case 2, we established a diagnosis by sampling a station 5 lymph node, and in case 3, we sampled a lesion located behind an airway stump from previous thoracic surgery. All three patients would have presented significant challenges for alternative biopsy modalities such as CT-guided needle biopsy or video-assisted thoracic surgery.

Transfer learning with CNNs for efficient prostate cancer and BPH detection in transrectal ultrasound images

Early detection of prostate cancer (PCa) and benign prostatic hyperplasia (BPH) is crucial for maintaining the health and well-being of aging male populations. This study aims to evaluate the performance of transfer learning with convolutional neural networks (CNNs) for efficient classification of PCa and BPH in transrectal ultrasound (TRUS) images. A retrospective experimental design was employed in this study, with 1380 TRUS images for PCa and 1530 for BPH. Seven state-of-the-art deep learning (DL) methods were employed as classifiers with transfer learning applied to popular CNN architectures. Performance indices, including sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), Kappa value, and Hindex (Youden's index), were used to assess the feasibility and efficacy of the CNN methods. The CNN methods with transfer learning demonstrated a high classification performance for TRUS images, with all accuracy, specificity, sensitivity, PPV, NPV, Kappa, and Hindex values surpassing 0.9400. The optimal accuracy, sensitivity, and specificity reached 0.9987, 0.9980, and 0.9980, respectively, as evaluated using twofold cross-validation. The investigated CNN methods with transfer learning showcased their efficiency and ability for the classification of PCa and BPH in TRUS images. Notably, the EfficientNetV2 with transfer learning displayed a high degree of effectiveness in distinguishing between PCa and BPH, making it a promising tool for future diagnostic applications.

Exploring the efficacy of artificial neural networks in predicting lung cancer recurrence: a retrospective study based on patient records

Background

Lung cancer remains a significant public health concern, accounting for a considerable number of cancer-related deaths worldwide. Neural networks have emerged as a promising tool that can aid in the diagnosis and treatment of various cancers. Consequently, there has been a growing interest in exploring the potential of artificial intelligence (AI) methods in medicine. The present study aimed to evaluate the effectiveness of a neural network in predicting lung cancer recurrence.

Methods

The study employed retrospective data from 2,296 medical records of patients diagnosed with lung cancer and admitted to the Warmińsko-Mazurskie Center for Lung Diseases in Olsztyn, Poland. The statistical software STATISTICA 7.1, equipped with the Neural Networks module (StatSoft Inc., Tulsa, USA), was utilized to analyze the data. The neural network model was trained using patient information regarding gender, treatment, smoking status, family history, and symptoms of cancer.

Results

The study employed a multilayer perceptron neural network with a two-phase learning process. The network demonstrated high predictive ability, as indicated by the percentage of correct classifications, which amounted to 87.5%, 89.1%, and 89.9% for the training, validation, and test sets, respectively.

Conclusions

The findings of this study support the potential usefulness of a neural network-based predictive model in assessing the risk of lung cancer recurrence. Further research is warranted to validate these findings and to explore AI's broader implications in cancer diagnosis and treatment.

A Narrative Review of the Use of Artificial Intelligence in Breast, Lung, and Prostate Cancer

Artificial intelligence (AI) has been an important topic within radiology. Currently, AI is used clinically to assist with the detection of lesions through detection systems. However, a number of recent studies have demonstrated the increased value of neural networks in radiology. With an increasing number of screening requirements for cancers, this review aims to study the accuracy of the numerous AI models used in the detection and diagnosis of breast, lung, and prostate cancers. This study summarizes pertinent findings from reviewed articles and provides analysis on the relevancy to clinical radiology. This study found that whereas AI is showing continual improvement in radiology, AI alone does not surpass the effectiveness of a radiologist. Additionally, it was found that there are multiple variations on how AI should be integrated with a radiologist's workflow.

Deep learning approach for accurate prostate cancer identification and stratification using combined immunostaining of cytokeratin, p63, and racemase

BACKGROUND

Prostate cancer (PCa) is the most frequently diagnosed cancer in men worldwide, affecting around 1.4 million individuals. Current PCa diagnosis relies on histological analysis of prostate biopsy samples, an activity that is both time-consuming and prone to observer bias. Previous studies have demonstrated that immunostaining of cytokeratin, p63, and racemase can significantly improve the sensitivity and the specificity of PCa detection compared to traditional H&E staining.

METHODS

This study introduces a novel approach that combines diagnosis-specific immunohistochemical (IHC) staining and deep learning techniques to provide reliable stratification of prostate glands. Our approach leverages a customized segmentation network, called K-PPM, that incorporates adaptive kernels and multiscale feature integration to enhance the functional information of IHC. To address the high class-imbalance problem in the dataset, we propose a weighted adaptive patch-extraction and specific-class kernel update.

RESULTS

Our system achieved noteworthy results, with a mean Dice Score Coefficient of 90.36% and a mean absolute error of 1.64 % in specific-class gland quantification on whole slides. These findings demonstrate the potential of our system as a valuable support tool for pathologists, reducing workload and decreasing diagnostic inter-observer variability.

CONCLUSIONS

Our study presents innovative approaches that have broad applicability to other digital pathology areas beyond PCa diagnosis. As a fully automated system, this model can serve as a framework for improving the histological and IHC diagnosis of other types of cancer.

Exploring the Use of Artificial Intelligence and Robotics in Prostate Cancer Management

Integrating artificial intelligence (AI) and robotics in prostate cancer (PCa) offers a game-changing breakthrough with far-reaching implications for diagnosis, treatment, and research. AI-driven algorithms have tremendous promise for assisting early diagnosis by analyzing invisible trends within medical imaging devices such as MRI and ultrasounds. In addition, by evaluating big datasets containing patient data, genetic attributes, and treatment outcomes, these AI algorithms offer the possibility of allowing individualized treatment regimens. This ability to personalize actions to specific patients might improve therapy efficacy while reducing side effects. Robotics can increase accuracy in less invasive surgery, revolutionize therapies like prostatectomies, and improve recovery time for patients. Robotic-assisted procedures provide clinicians with remarkable skills and flexibility, allowing clinicians to negotiate complicated anatomical structures more precisely. However, the symbiotic combination of AI and robotics has several drawbacks. Concerns about data privacy, algorithm biases, and the need to continually assess AI's diagnostic proficiency offer significant hurdles. To ensure patient privacy and data security, the ethical and regulatory aspects of integrating AI and robotics require proper attention. However, combining AI and robotics opens up a galaxy of possibilities. The joint use of AI and robotics can potentially speed up drug development procedures by filtering through massive databases, resulting in the identification of new medicinal compounds. Furthermore, combining AI and robotics might usher in an innovative era of personalized medicine, allowing healthcare providers to design therapies based on detailed patient profiles. The merging of AI and robotics in PCa care gives up unprecedented prospects. While limitations highlight the necessity for caution, the possibilities of better diagnostics, tailored therapies, and new research pathways highlight the transformational abilities of AI and robotics in determining the future of PCa management. This study explores the limitations and opportunities presented by using AI and robotics in the context of PCa.

Deep Learning for Lung Cancer Diagnosis, Prognosis and Prediction Using Histological and Cytological Images: A Systematic Review

Lung cancer is one of the deadliest cancers worldwide, with a high incidence rate, especially in tobacco smokers. Lung cancer accurate diagnosis is based on distinct histological patterns combined with molecular data for personalized treatment. Precise lung cancer classification from a single H&E slide can be challenging for a pathologist, requiring most of the time additional histochemical and special immunohistochemical stains for the final pathology report. According to WHO, small biopsy and cytology specimens are the available materials for about 70% of lung cancer patients with advanced-stage unresectable disease. Thus, the limited available diagnostic material necessitates its optimal management and processing for the completion of diagnosis and predictive testing according to the published guidelines. During the new era of Digital Pathology, Deep Learning offers the potential for lung cancer interpretation to assist pathologists' routine practice. Herein, we systematically review the current Artificial Intelligence-based approaches using histological and cytological images of lung cancer. Most of the published literature centered on the distinction between lung adenocarcinoma, lung squamous cell carcinoma, and small cell lung carcinoma, reflecting the realistic pathologist's routine. Furthermore, several studies developed algorithms for lung adenocarcinoma predominant architectural pattern determination, prognosis prediction, mutational status characterization, and PD-L1 expression status estimation.

Artificial Intelligence in the Advanced Diagnosis of Bladder Cancer-Comprehensive Literature Review and Future Advancement

Artificial intelligence is highly regarded as the most promising future technology that will have a great impact on healthcare across all specialties. Its subsets, machine learning, deep learning, and artificial neural networks, are able to automatically learn from massive amounts of data and can improve the prediction algorithms to enhance their performance. This area is still under development, but the latest evidence shows great potential in the diagnosis, prognosis, and treatment of urological diseases, including bladder cancer, which are currently using old prediction tools and historical nomograms. This review focuses on highly significant and comprehensive literature evidence of artificial intelligence in the management of bladder cancer and investigates the near introduction in clinical practice.

Beyond blood biomarkers: the role of SelectMDX in clinically significant prostate cancer identification

INTRODUCTION

New potential biomarkers to pre-intervention identification of a clinically significant prostate cancer (csPCa) will prevent overdiagnosis and overtreatment and limit quality of life impairment of PCa patients.

AREAS COVERED

We have developed a comprehensive review focusing our research on the increasing knowledge of the role of SelectMDX® in csPCa detection. Areas identified as clinically relevant are the ability of SelectMDX® to predict csPCa in active surveillance setting, its predictive ability when combined with multiparametric MRI and the role of SelectMDX® in the landscape of urinary biomarkers.

EXPERT OPINION

Several PCa biomarkers have been developed either alone or in combination with clinical variables to improve csPCa detection. SelectMDX® score includes genomic markers, age, PSA, prostate volume, and digital rectal examination. Several studies have shown consistency in the ability to improve detection of csPCa, avoidance of unnecessary prostate biopsies, helpful in decision-making for clinical benefit of PCa patients with future well designed, and impactful studies.

Machine-Learning-Based Tool to Predict Target Prostate Biopsy Outcomes: An Internal Validation Study

The aim of this study is to present a personalized predictive model (PPM) with a machine learning (ML) system that is able to identify and classify patients with suspected prostate cancer (PCa) following mpMRI. We extracted all the patients who underwent fusion biopsy (FB) from March 2014 to December 2019, while patients from August 2020 to April 2021 were included as a validation set. The proposed system was based on the following four ML methods: a fuzzy inference system (FIS), the support vector machine (SVM), k-nearest neighbors (KNN), and self-organizing maps (SOMs). Then, a system based on fuzzy logic (FL) + SVM was compared with logistic regression (LR) and standard diagnostic tools. A total of 1448 patients were included in the training set, while 181 patients were included in the validation set. The area under the curve (AUC) of the proposed FIS + SVM model was comparable with the LR model but outperformed the other diagnostic tools. The FIS + SVM model demonstrated the best performance, in terms of negative predictive value (NPV), on the training set (78.5%); moreover, it outperformed the LR in terms of specificity (92.1% vs. 83%). Considering the validation set, our model outperformed the other methods in terms of NPV (60.7%), sensitivity (90.8%), and accuracy (69.1%). In conclusion, we successfully developed and validated a PPM tool using the FIS + SVM model to calculate the probability of PCa prior to a prostate FB, avoiding useless ones in 15% of the cases.

Reliability of Multiparametric Magnetic Resonance Imaging in Patients with a Previous Negative Biopsy: Comparison with Biopsy-Naïve Patients in the Detection of Clinically Significant Prostate Cancer

Background: Multiparametric magnetic resonance is an established imaging utilized in the diagnostic pathway of prostate cancer. The aim of this study is to evaluate the accuracy and reliability of multiparametric magnetic resonance imaging (mpMRI) in the detection of clinically significant prostate cancer, defined as Gleason Score ≥ 4 + 3 or a maximum cancer core length 6 mm or longer, in patients with a previous negative biopsy. Methods: The study was conducted as a retrospective observational study at the University of Naples "Federico II", Italy. Overall, 389 patients who underwent systematic and target prostate biopsy between January 2019 and July 2020 were involved and were divided into two groups: Group A, which included biopsy-naïve patients; Group B, which included re-biopsy patients. All mpMRI images were obtained using three Tesla instruments and were interpreted according to PIRADS (Prostate Imaging Reporting and Data System) version 2.0. Results: 327 patients were biopsy-naïve, while 62 belonged to the re-biopsy group. Both groups were comparable in terms of age, total PSA (prostate-specific antigen), and number of cores obtained at the biopsy. 2.2%, 8.8%, 36.1%, and 83.4% of, respectively, PIRADS 2, 3, 4, and 5 biopsy-naïve patients reported a clinically significant prostate cancer compared to 0%, 14.3%, 39%, and 66.6% of re-biopsy patients (p < 0.0001-p = 0.040). No difference was reported in terms of post-biopsy complications. Conclusions: mpMRI confirms its role as a reliable diagnostic tool prior to performing prostate biopsy in patients who underwent a previous negative biopsy, reporting a comparable detection rate of clinically significant prostate cancer.

Generative Adversarial Networks Can Create High Quality Artificial Prostate Cancer Magnetic Resonance Images

The recent integration of open-source data with machine learning models, especially in the medical field, has opened new doors to studying disease progression and/or regression. However, the ability to use medical data for machine learning approaches is limited by the specificity of data for a particular medical condition. In this context, the most recent technologies, like generative adversarial networks (GANs), are being looked upon as a potential way to generate high-quality synthetic data that preserve the clinical variability of a condition. However, despite some success, GAN model usage remains largely minimal when depicting the heterogeneity of a disease such as prostate cancer. Previous studies from our group members have focused on automating the quantitative multi-parametric magnetic resonance imaging (mpMRI) using habitat risk scoring (HRS) maps on the prostate cancer patients in the BLaStM trial. In the current study, we aimed to use the images from the BLaStM trial and other sources to train the GAN models, generate synthetic images, and validate their quality. In this context, we used T2-weighted prostate MRI images as training data for Single Natural Image GANs (SinGANs) to make a generative model. A deep learning semantic segmentation pipeline trained the model to segment the prostate boundary on 2D MRI slices. Synthetic images with a high-level segmentation boundary of the prostate were filtered and used in the quality control assessment by participating scientists with varying degrees of experience (more than ten years, one year, or no experience) to work with MRI images. Results showed that the most experienced participating group correctly identified conventional vs. synthetic images with 67% accuracy, the group with one year of experience correctly identified the images with 58% accuracy, and the group with no prior experience reached 50% accuracy. Nearly half (47%) of the synthetic images were mistakenly evaluated as conventional. Interestingly, in a blinded quality assessment, a board-certified radiologist did not significantly differentiate between conventional and synthetic images in the context of the mean quality of synthetic and conventional images. Furthermore, to validate the usability of the generated synthetic images from prostate cancer MRIs, we subjected these to anomaly detection along with the original images. Importantly, the success rate of anomaly detection for quality control-approved synthetic data in phase one corresponded to that of the conventional images. In sum, this study shows promise that high-quality synthetic images from MRIs can be generated using GANs. Such an AI model may contribute significantly to various clinical applications which involve supervised machine-learning approaches.

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.

Evaluation of artificial intelligence techniques in disease diagnosis and prediction

A broad range of medical diagnoses is based on analyzing disease images obtained through high-tech digital devices. The application of artificial intelligence (AI) in the assessment of medical images has led to accurate evaluations being performed automatically, which in turn has reduced the workload of physicians, decreased errors and times in diagnosis, and improved performance in the prediction and detection of various diseases. AI techniques based on medical image processing are an essential area of research that uses advanced computer algorithms for prediction, diagnosis, and treatment planning, leading to a remarkable impact on decision-making procedures. Machine Learning (ML) and Deep Learning (DL) as advanced AI techniques are two main subfields applied in the healthcare system to diagnose diseases, discover medication, and identify patient risk factors. The advancement of electronic medical records and big data technologies in recent years has accompanied the success of ML and DL algorithms. ML includes neural networks and fuzzy logic algorithms with various applications in automating forecasting and diagnosis processes. DL algorithm is an ML technique that does not rely on expert feature extraction, unlike classical neural network algorithms. DL algorithms with high-performance calculations give promising results in medical image analysis, such as fusion, segmentation, recording, and classification. Support Vector Machine (SVM) as an ML method and Convolutional Neural Network (CNN) as a DL method is usually the most widely used techniques for analyzing and diagnosing diseases. This review study aims to cover recent AI techniques in diagnosing and predicting numerous diseases such as cancers, heart, lung, skin, genetic, and neural disorders, which perform more precisely compared to specialists without human error. Also, AI's existing challenges and limitations in the medical area are discussed and highlighted.

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.

Artificial intelligence and radiomics in evaluation of kidney lesions: a comprehensive literature review

Radiomics and artificial intelligence (AI) may increase the differentiation of benign from malignant kidney lesions, differentiation of angiomyolipoma (AML) from renal cell carcinoma (RCC), differentiation of oncocytoma from RCC, differentiation of different subtypes of RCC, to predict Fuhrman grade, to predict gene mutation through molecular biomarkers and to predict treatment response in metastatic RCC undergoing immunotherapy. Neural networks analyze imaging data. Statistical, geometrical, textural features derived are giving quantitative data of contour, internal heterogeneity and gray zone features of lesions. A comprehensive literature review was performed, until July 2022. Studies investigating the diagnostic value of radiomics in differentiation of renal lesions, grade prediction, gene alterations, molecular biomarkers and ongoing clinical trials have been analyzed. The application of AI and radiomics could lead to improved sensitivity, specificity, accuracy in detecting and differentiating between renal lesions. Standardization of scanner protocols will improve preoperative differentiation between benign, low-risk cancers and clinically significant renal cancers and holds the premises to enhance the diagnostic ability of imaging tools to characterize renal lesions.

Development and validation of a predictive model for diagnosing prostate cancer after transperineal prostate biopsy

Objective

This study aimed to develop and validate a nomogram to predict the probability of prostate cancer (PCa) after transperineal prostate biopsy by combining patient clinical information and biomarkers.

Methods

First, we retrospectively collected the clinicopathologic data from 475 patients who underwent prostate biopsy at our hospital between January 2019 to August 2021. Univariate and multivariate logistic regression analyses were used to select risk factors. Then, we established the nomogram prediction model based on the risk factors. The model performance was assessed by receiver operating characteristic (ROC) curves, calibration plots and the Hosmer–Lemeshow test. Decision curve analysis (DCA) was used to evaluate the net benefit of the model at different threshold probabilities. The model was validated in an independent cohort of 197 patients between September 2021 and June 2022.

Results

The univariate and multivariate logistic regression analyses based on the development cohort indicated that the model should include the following factors: age (OR = 1.056, p = 0.001), NEUT (OR = 0.787, p = 0.008), HPR (OR = 0.139, p &lt; 0.001), free/total (f/T) PSA (OR = 0.013, p = 0.015), and PI-RADS (OR = 3.356, p &lt; 0.001). The calibration curve revealed great agreement. The internal nomogram validation showed that the C-index was 0.851 (95% CI 0.809-0.894). Additionally, the AUC was 0.851 (95% CI 0.809-0.894), and the Hosmer–Lemeshow test result presented p = 0.143 &gt; 0.05. Finally, according to decision curve analysis, the model was clinically beneficial.

Conclusion

Herein, we provided a nomogram combining patients’ clinical data with biomarkers to help diagnose prostate cancers.

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.

Domain generalization for prostate segmentation in transrectal ultrasound images: A multi-center study

Prostate biopsy and image-guided treatment procedures are often performed under the guidance of ultrasound fused with magnetic resonance images (MRI). Accurate image fusion relies on accurate segmentation of the prostate on ultrasound images. Yet, the reduced signal-to-noise ratio and artifacts (e.g., speckle and shadowing) in ultrasound images limit the performance of automated prostate segmentation techniques and generalizing these methods to new image domains is inherently difficult. In this study, we address these challenges by introducing a novel 2.5D deep neural network for prostate segmentation on ultrasound images. Our approach addresses the limitations of transfer learning and finetuning methods (i.e., drop in performance on the original training data when the model weights are updated) by combining a supervised domain adaptation technique and a knowledge distillation loss. The knowledge distillation loss allows the preservation of previously learned knowledge and reduces the performance drop after model finetuning on new datasets. Furthermore, our approach relies on an attention module that considers model feature positioning information to improve the segmentation accuracy. We trained our model on 764 subjects from one institution and finetuned our model using only ten subjects from subsequent institutions. We analyzed the performance of our method on three large datasets encompassing 2067 subjects from three different institutions. Our method achieved an average Dice Similarity Coefficient (Dice) of 94.0±0.03 and Hausdorff Distance (HD95) of 2.28 mm in an independent set of subjects from the first institution. Moreover, our model generalized well in the studies from the other two institutions (Dice: 91.0±0.03; HD95: 3.7 mm and Dice: 82.0±0.03; HD95: 7.1 mm). We introduced an approach that successfully segmented the prostate on ultrasound images in a multi-center study, suggesting its clinical potential to facilitate the accurate fusion of ultrasound and MRI images to drive biopsy and image-guided treatments.

Computer classification and construction of a novel prognostic signature based on moonlighting genes in prostate cancer

Advanced prostate cancer (PRAD) patients have poor prognosis and rising morbidity despite the ongoing iteration of molecular therapeutic agents. As newly discovered proteins with several functions, Moonlighting proteins have showed an important role in tumor progression but has not been extensively investigated in PRAD. Our study aimed to identify moonlighting-related prognostic biomarkers and prospective PRAD therapy targets. 103 moonlighting genes were gathered from previous literatures. A PRAD classification and multivariate Cox prognostic signature were constructed using dataset from The Cancer Genome Atlas (TCGA). Subsequently, we tested our signature’s potential to predict biochemical failure-free survival (BFFS) using GSE21032, a prostate cancer dataset from Gene Expression Omnibus (GEO). The performance of this signature was demonstrated by Kaplan-Meier (KM), receiver operator characteristic (ROC), areas under ROC curve (AUC), and calibration curves. Additionally, immune infiltration investigation was conducted to determine the impact of these genes on immune system. This signature’s influence on drug susceptibility was examined using CellMiner’s drug database. Both training and validation cohorts demonstrated well predictive capacity of this 9-gene signature for PRAD. The 3-year AUCs for TCGA-PRAD and GSE21032 were 0.802 and 0.60 respectively. It can effectively classify patients into various biochemical recurrence risk groups. These genes were also assessed to be connected with tumor mutation burden (TMB), immune infiltration and therapy. This work created and validated a moonlighting gene signature, revealing fresh perspectives on moonlighting proteins in predicting prognosis and improving treatment of PRAD.

Comparison of systematic randomized 12-core transrectal ultrasonography-guided prostate biopsy with magnetic resonance imaging-transrectal ultrasonography fusion-targeted prostate biopsy

We aimed to compare the complications and pathological outcomes between systematic 12-core transrectal ultrasonography guided prostate biopsy (TRUS-PB) and magnetic resonance imaging-TRUS fusion targeted prostate biopsy (MRI-TRUS FTPB). We examined 10,901 patients who underwent prostate biopsy from May 2003 to December 2017 retrospectively. Among them, 10,325 patients underwent 12-core TRUS-PB and 576 patients underwent MRI-TRUS FTPB. The clinicopathological features and complications in both groups were compared. After propensity score matching, there were no significant differences in the clinical features and complication rates between both groups (P > .05). In the multivariate analyses, the prostate volume was shown to be the only significant predictor of overall complications, infectious complications, bleeding related complications, and Clavien-Dindo grade ≥ 2 complications after prostate biopsy (P < .001). The present study demonstrates the safety of MRI-TRUS FTPB in terms of complications, compared with that of TRUS-PB. Although the combination of MRI-TRUS FTPB and 12-core TRUS-PB provides enhanced diagnostic power, MRI-TRUS FGB alone could provide a reasonable diagnostic value for prostate cancer if the apparent diffusion coefficient suspicious grade of prostate cancer is ≥4. When the Likert suspicious grade of prostate cancer on the apparent diffusion coefficient map of multiparametric MRI was 3, 13.9% (27/194) of the patients were diagnosed with clinically significant prostate cancer (csPCa); 44.4% (12/27) of them were confirmed as csPCa at the MRI-targeted cores. When the apparent diffusion coefficient suspicious grade was ≥4, 43.0% (108/251) were diagnosed with csPCa; 76.8% (83/108) of them were confirmed to have csPCa at the MRI-targeted cores.

Inter-reader agreement of the prostate imaging reporting and data system version v2.1 for detection of prostate cancer: A systematic review and meta-analysis

Objectives

We aimed to systematically assess the inter-reader agreement of the Prostate Imaging Reporting and Data System Version (PI-RADS) v2.1 for the detection of prostate cancer (PCa).

Methods

We included studies reporting inter-reader agreement of different radiologists that applied PI-RADS v2.1 for the detection of PCa. Quality assessment of the included studies was performed with the Guidelines for Reporting Reliability and Agreement Studies. The summary estimates of the inter-reader agreement were pooled with the random-effect model and categorized (from slight to almost perfect) according to the kappa (κ) value. Multiple subgroup analyses and meta-regression were performed to explore various clinical settings.

Results

A total of 12 studies comprising 2475 patients were included. The pooled inter-reader agreement for whole gland was κ=0.65 (95% CI 0.56-0.73), and for transitional zone (TZ) lesions was κ=0.62 (95% CI 0.51-0.72). There was substantial heterogeneity presented throughout the studies (I²= 95.6%), and meta-regression analyses revealed that only readers’ experience (<5 years vs. ≥5 years) was the significant factor associated with heterogeneity (P<0.01). In studies providing head-to-head comparison, there was no significant difference in inter-reader agreement between PI-RADS v2.1 and v2.0 for both the whole gland (0.64 vs. 0.57, p=0.37), and TZ (0.61 vs. 0.59, p=0.81).

Conclusions

PI-RADS v2.1 demonstrated substantial inter-reader agreement among radiologists for whole gland and TZ lesions. However, the difference in agreement between PI-RADS v2.0 and v2.1 was not significant for the whole gland or the TZ.

Bibliometric analysis of the global research development of bone metastases in prostate cancer: A 22-year study

Background

Prostate cancer (PCa) is the second most diagnosed cancer in men. Most PCa-related deaths result from metastatic disease. Metastases occur most often in the bones (90%). However, the current treatments for bone metastases in PCa are not very effective. Here we present an overview of the current research situation of bone metastases in PCa, focusing on hotspots and trends.

Methods

We searched the Web of Science Core Collection database for publications related to bone metastases in PCa published between 1999 and 2021. We used VOSviewer, CiteSpace, and a bibliometric online platform to perform a bibliometric analysis of countries, institutions, authors, journals, references, and keywords.

Results

A total of 4,832 related articles were included in the present study. The USA published the most articles in the field, followed by China and England. The University of Texas MD Anderson Cancer Center is the leading institution in the research field of bone metastases in PCa. Saad F, from Canada, has made great achievements in this area by publishing 91 related articles. Prostate is the journal which published most related articles, and Mundy GR, 2002, Nat Rev Cancer, is the most cited article in this field. Furthermore, the analysis of author keywords can be divided into five clusters: (1) diagnosis of PCa, (2) mechanism of bone metastasis, (3) drug treatments of bone metastases, (4) radiotherapy of bone metastases, and (5) treatments and prognosis of PCa.

Conclusions

mCRPC has been the hottest topic in PCa in recent years. CT is the most common diagnostic method for bone metastases. Enzalutamide and radium-223, as important treatments for bone metastases in PCa, bring about widespread attention. Furthermore, the researchers focus on the tumor microenvironment and biomarkers to explore the mechanism and the therapeutic targets of bone metastases in PCa.

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.

Multiparametric MRI-based nomograms in predicting positive surgical margins of prostate cancer after laparoscopic radical prostatectomy

Background

Positive surgical margins (PSMs) are an independent risk factor of biochemical recurrence in patients with prostate cancer (PCa) after laparoscopic radical prostatectomy; however, limited MRI-based predictive tools are available. This study aimed to develop a novel nomogram combining clinical and multiparametric MRI (mpMRI) parameters to reduce PSMs by improving surgical planning.

Methods

One hundred and three patients with PCa (55 patients with negative surgical margins [NSMs] and 48 patients with PSMs) were included in this retrospective study. The following parameters were obtained using GE Functool post-processing software: diffusion-weighted imaging (DWI); intravoxel incoherent motion model (IVIM); and diffusion kurtosis imaging (DKI). Patients were divided into different training sets and testing sets for different targets according to a ratio of 7:3. The least absolute shrinkage and selection operator (LASSO) regression algorithm was used to analyze the data set to select the optimal MRI predictors. Preoperatively clinical parameters used to build a clinical nomogram (C-nomogram). Multivariable logistic regression analysis was used to build an MRI nomogram (M-nomogram) by introducing the MRI parameters. Based on the MRI and clinical parameters, build an MRI combined with clinical parameters nomogram (MC-nomogram). Comparisons with the M-nomogram and MC-nomogram were based on discrimination, calibration, and decision curve analysis (DCA). A 3-fold cross-validation method was used to assess the stability of the nomogram.

Results

There was no statistical difference in AUC between the C-nomogram (sensitivity=64%, specificity=65% and AUC=0.683), the M-nomogram (sensitivity=57%, specificity=88% and AUC=0.735) and the MC-nomogram (sensitivity= 64%, specificity=82% and AUC=0.756). The calibration curves of the three nomograms used to predict the risk of PSMs in patients with PCa showed good agreement. The net benefit of the MC-nomogram was higher than the others (range, 0.2-0.7).

Conclusions

The mpMRI-based nomogram can predict PSMs in PCa patients. Although its AUC (0.735) is not statistically different from that of the clinical-based nomogram AUC (0.683). However, mpMRI-based nomogram has higher specificity (88% VS. 63%), model stability, and clinical benefit than clinical-based nomogram. And the predictive ability of mpMRI plus clinical parameters for PSMs is further improved.

Machine Learning to Delineate Surgeon and Clinical Factors That Anticipate Positive Surgical Margins After Robot-Assisted Radical Prostatectomy

Purpose: Automated performance metrics (APMs), derived from instrument kinematic and systems events data during robotic surgery, are validated objective measures of surgeon performance. Our previous studies showed that APMs are strong outcome predictors of urinary continence after robot-assisted radical prostatectomy (RARP). We now use machine learning to investigate how surgeon performance (i.e., APMs) and clinical factors can predict positive surgical margins (PSMs) after RARP. Methods: We prospectively collected data of patients undergoing RARP at our institution from 2016 to 2019. Random Forest model predicted PSMs based on 15 clinical factors and 38 APMs from 11 standardized RARP steps. Out-of-bag Gini impurity index determined the top 10 variables of importance (VOI). APMs in the top 10 VOI were assessed for confounding effects by extracapsular extension (ECE) and pathologic T (pT) through Poisson regression with Generalized Estimating Equation. Results: 55/236 (23.3%) cases had PSMs. Of the 55 cases with PSMs, 9 (16.4%) were pT2 and 46 (83.6%), pT3. The full model, including clinical factors and APMs, achieved area under the curve (AUC) 0.74. When assessing clinical factors or APMs alone, the model achieved AUC 0.72 and 0.64, respectively. The strongest PSM predictors were ECE and pT stage, followed by APMs in specific steps. After adjusting for ECE and pT stage, most APMs remained as independent predictors of PSM. Conclusion: Using machine learning methods, we found that the strongest predictors of PSMs after RARP are nonmodifiable, disease-driven factors (ECE and pT). While APMs provide minimal additional insight into when PSMs may occur, they are nonetheless capable of independently predicting PSMs based on objective measures of surgeon performance.

On an Affordable Approach towards the Diagnosis and Care for Prostate Cancer Patients Using Urine, FTIR and Prediction Machines

Prostate cancer is a widespread form of cancer that affects patients globally and is challenging to diagnose, especially in its early stages. The common means of diagnosing cancer involve mostly invasive methods, such as the use of patient’s blood as well as digital biopsies, which are relatively expensive and require a considerable amount of expertise. Studies have shown that various cancer biomarkers can be present in urine samples from patients who have prostate cancers; this paper aimed to leverage this information and investigate this further by using urine samples from a group of patients alongside FTIR analysis for the prediction of prostate cancer. This investigation was carried out using three sets of data where all spectra were preprocessed with the linear series decomposition learner (LSDL) and post-processed using signal processing methods alongside a contrast across nine machine-learning models, the results of which showcased that the proposed modeling approach carries potential to be used for clinical prediction of prostate cancer. This would allow for a much more affordable and high-throughput means for active prediction and associated care for patients with prostate cancer. Further investigations on the prediction of cancer stage (i.e., early or late stage) were carried out, where high prediction accuracy was obtained across the various metrics that were investigated, further showing the promise and capability of urine sample analysis alongside the proposed and presented modeling approaches.

The role of radiomics with machine learning in the prediction of muscle-invasive bladder cancer: A mini review

Bladder cancer is a common malignant tumor in the urinary system. Depending on whether bladder cancer invades muscle tissue, it is classified into non-muscle-invasive bladder cancer (NMIBC) and muscle-invasive bladder cancer (MIBC). It is crucial to accurately diagnose the muscle invasion of bladder cancer for its clinical management. Although imaging modalities such as CT and multiparametric MRI play an important role in this regard, radiomics has shown great potential with the development and innovation of precision medicine. It features outstanding advantages such as non-invasive and high efficiency, and takes on important significance in tumor assessment and laor liberation. In this article, we provide an overview of radiomics in the prediction of muscle-invasive bladder cancer and reflect on its future trends and challenges.

Artificial intelligence for prostate MRI: open datasets, available applications, and grand challenges

Artificial intelligence (AI) for prostate magnetic resonance imaging (MRI) is starting to play a clinical role for prostate cancer (PCa) patients. AI-assisted reading is feasible, allowing workflow reduction. A total of 3,369 multi-vendor prostate MRI cases are available in open datasets, acquired from 2003 to 2021 in Europe or USA at 3 T (n = 3,018; 89.6%) or 1.5 T (n = 296; 8.8%), 346 cases scanned with endorectal coil (10.3%), 3,023 (89.7%) with phased-array surface coils; 412 collected for anatomical segmentation tasks, 3,096 for PCa detection/classification; for 2,240 cases lesions delineation is available and 56 cases have matching histopathologic images; for 2,620 cases the PSA level is provided; the total size of all open datasets amounts to approximately 253 GB. Of note, quality of annotations provided per dataset highly differ and attention must be paid when using these datasets (e.g., data overlap). Seven grand challenges and commercial applications from eleven vendors are here considered. Few small studies provided prospective validation. More work is needed, in particular validation on large-scale multi-institutional, well-curated public datasets to test general applicability. Moreover, AI needs to be explored for clinical stages other than detection/characterization (e.g., follow-up, prognosis, interventions, and focal treatment).

Tasks for artificial intelligence in prostate MRI

The advent of precision medicine, increasing clinical needs, and imaging availability among many other factors in the prostate cancer diagnostic pathway has engendered the utilization of artificial intelligence (AI). AI carries a vast number of potential applications in every step of the prostate cancer diagnostic pathway from classifying/improving prostate multiparametric magnetic resonance image quality, prostate segmentation, anatomically segmenting cancer suspicious foci, detecting and differentiating clinically insignificant cancers from clinically significant cancers on a voxel-level, and classifying entire lesions into Prostate Imaging Reporting and Data System categories/Gleason scores. Multiple studies in all these areas have shown many promising results approximating accuracies of radiologists. Despite this flourishing research, more prospective multicenter studies are needed to uncover the full impact and utility of AI on improving radiologist performance and clinical management of prostate cancer. In this narrative review, we aim to introduce emerging medical imaging AI paper quality metrics such as the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) and Field-Weighted Citation Impact (FWCI), dive into some of the top AI models for segmentation, detection, and classification.

The state of the art for artificial intelligence in lung digital pathology

Lung diseases carry a significant burden of morbidity and mortality worldwide. The advent of digital pathology (DP) and an increase in computational power have led to the development of artificial intelligence (AI)-based tools that can assist pathologists and pulmonologists in improving clinical workflow and patient management. While previous works have explored the advances in computational approaches for breast, prostate, and head and neck cancers, there has been a growing interest in applying these technologies to lung diseases as well. The application of AI tools on radiology images for better characterization of indeterminate lung nodules, fibrotic lung disease, and lung cancer risk stratification has been well documented. In this article, we discuss methodologies used to build AI tools in lung DP, describing the various hand-crafted and deep learning-based unsupervised feature approaches. Next, we review AI tools across a wide spectrum of lung diseases including cancer, tuberculosis, idiopathic pulmonary fibrosis, and COVID-19. We discuss the utility of novel imaging biomarkers for different types of clinical problems including quantification of biomarkers like PD-L1, lung disease diagnosis, risk stratification, and prediction of response to treatments such as immune checkpoint inhibitors. We also look briefly at some emerging applications of AI tools in lung DP such as multimodal data analysis, 3D pathology, and transplant rejection. Lastly, we discuss the future of DP-based AI tools, describing the challenges with regulatory approval, developing reimbursement models, planning clinical deployment, and addressing AI biases. © 2022 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

A Genetic Folding Strategy Based Support Vector Machine to Optimize Lung Cancer Classification

Cancer is defined as an abnormal growth of human cells classified into benign and malignant. The site makes further classification of cancers of initiation and genomic underpinnings. Lung cancer displays extreme heterogeneity, making genomic classification vital for future targeted therapies. Especially considering lung cancers account for 1.76 million deaths worldwide annually. However, tumors do not always correlate to cancer as they can be benign, severely dysplastic (pre-cancerous), or malignant (cancerous). Lung cancer presents with ambiguous symptoms, thus is difficult to diagnose and is detected later compared to other cancers. Diagnosis relies heavily on radiology and invasive procedures. Different models developed employing Artificial Intelligence (AI), and Machine Learning (ML) have been used to classify various cancers. In this study, the authors propose a Genetic Folding Strategy (GFS) based model to predict lung cancer from a lung cancer dataset. We developed and implemented GF to improve Support Vector Machines (SVM) classification kernel functions and used it to classify lung cancer. We developed and implemented GF to improve SVM classification kernel functions and used it to classify lung cancer. Classification performance evaluations and comparisons between the authors' GFS model and three SVM kernels, linear, polynomial and radial basis function, were conducted thoroughly on real lung cancer datasets. While using GFS in classifying lung cancer, the authors obtained an accuracy of 96.2%. This is the highest current accuracy compared to other kernels.

Radiomic Machine Learning and External Validation Based on 3.0 T mpMRI for Prediction of Intraductal Carcinoma of Prostate With Different Proportion

Purpose

To assess the association of radiomics features based on multiparametric MRI (mpMRI) with the proportion of intraductal carcinoma of prostate (IDC-P) and validate the predictive models.

Materials and Methods

We retrospectively included pre-treatment MR images of prostate cancer (PCa) with IDC components of high proportion (≥10%, hpIDC-P), low proportion (<10%, lpIDC-P), and pure acinar adenocarcinoma (PAC) from our institution for training and internal validation and cooperated cohort for external validation. Normalized images of T2WI, diffusion weighted imaging (DWI) and apparent diffusion coefficient (ADC) map, and dynamic contrast enhanced (DCE) sequences were used for radiomics modeling. The clinical model was built based on serum total prostate specific antigen (tPSA) and Gleason score (GS), and the integrated model was the combination of Rad-score and clinicopathological data. The discrimination ability was assessed by area under the receiver operating characteristic curve (ROC-AUC) in the internal and external validation sets and compared by DeLong test.

Results

Overall, 97 patients with hpIDC-P, 87 lpIDC-P, and 78 PAC were included for training and internal validation, and 11, 16, and 19 patients for external validation. The integrated model for predicting hpIDC-P got the best ROC-AUC of 0.88 (95%CI = 0.83-0.93) in internal and 0.86 (95%CI = 0.72-1.0) in external validation, which both outperformed clinical models (AUC=0.78, 95% CI = 0.72-0.85, AUC=0.69, 95% CI = 0.5-0.85, respectively) based solely on GS, and the radiomics model (AUC=0.85, 95% CI = 0.79-0.91) was slightly inferior to the integrated model and better than the clinical model in internal dataset. The integrated model for predicting lpIDC-P outperformed both radiomics and clinical models in the internal dataset, while slightly inferior to the integrated model for predicting hpIDC-P.

Conclusions

Radiomics signature improved differentiation of both hpIDC-P and lpIDC-P versus PAC when compared with the clinical model based on Gleason score, and was validated in an external cohort.

The Application of Biopsy Density in Transperineal Templated-Guided Biopsy Patients With PI-RADS<3

Background

In patients with multiparameter magnetic resonance imaging (mpMRI) low-possibility but highly clinical suspicion of prostate cancer, the biopsy core is unclear. Our study aims to introduce the biopsy density (BD; the ratio of biopsy cores to prostate volume) and investigates the BD-predictive value of prostate cancer and clinically significant prostate cancer (csPCa) in PI-RADS<3 patients.

Methods

Patients underwent transperineal template–guided prostate biopsy from 2012 to 2022. The inclusion criteria were PI-RADS<3 with a positive digital rectal examination or persistent PSA abnormalities. BD was defined as the ratio of the biopsy core to the prostate volume. Clinical data were collected, and we grouped the patients according to pathology results. Kruskal–Wallis test and chi-square test were used in measurement and enumeration data, respectively. Logistics regression was used to choose the factor associated with positive biospy and csPCa. The receiver operating characteristic (ROC) curve was used to evaluate the ability to predict csPCa.

Results

A total of 115 patients were included in our study. Biopsy was positive in 14 of 115 and the International Society of Urological Pathology grade groups 2–5 were in 7 of all the PCa patients. The BD was 0.38 (0.24-0.63) needles per milliliter. Binary logistics analysis suggested that PSAD and BD were correlated with positive biopsy. Meanwhile, BD and PSAD were associated with csPCa. The ROC curve illustrated that BD was a good parameter to predict csPCa (AUC=0.80, 95% CI: 0.69-0.91, p<0.05). The biopsy density combined with PSAD increased the prediction of csPCa (AUC=0.90, 95% CI: 0.85-0.97, p<0.05). The cut-off value of the BD was 0.42 according to the Youden index.

Conclusion

In PI-RADS<3 patients, BD and PSAD are related to csPCa. A biopsy density of more than 0.42 needles per millimeter can increase the csPCa detection rate, which should be considered as an alternative biopsy method when we perform prostate biopsy in patients with PI-RADS<3.

An enhanced Genetic Folding algorithm for prostate and breast cancer detection

Cancer's genomic complexity is gradually increasing as we learn more about it. Genomic classification of various cancers is crucial in providing oncologists with vital information for targeted therapy. Thus, it becomes more pertinent to address issues of patient genomic classification. Prostate cancer is a cancer subtype that exhibits extreme heterogeneity. Prostate cancer contributes to 7.3% of new cancer cases worldwide, with a high prevalence in males. Breast cancer is the most common type of cancer in women and the second most significant cause of death from cancer in women. Breast cancer is caused by abnormal cell growth in the breast tissue, generally referred to as a tumour. Tumours are not synonymous with cancer; they can be benign (noncancerous), pre-malignant (pre-cancerous), or malignant (cancerous). Fine-needle aspiration (FNA) tests are used to biopsy the breast to diagnose breast cancer. Artificial Intelligence (AI) and machine learning (ML) models are used to diagnose with varying accuracy. In light of this, we used the Genetic Folding (GF) algorithm to predict prostate cancer status in a given dataset. An accuracy of 96% was obtained, thus being the current highest accuracy in prostate cancer diagnosis. The model was also used in breast cancer classification with a proposed pipeline that used exploratory data analysis (EDA), label encoding, feature standardization, feature decomposition, log transformation, detect and remove the outliers with Z-score, and the BAGGINGSVM approach attained a 95.96% accuracy. The accuracy of this model was then assessed using the rate of change of PSA, age, BMI, and filtration by race. We discovered that integrating the rate of change of PSA and age in our model raised the model's area under the curve (AUC) by 6.8%, whereas BMI and race had no effect. As for breast cancer classification, no features were removed.

Artificial Intelligence System for Predicting Prostate Cancer Lesions from Shear Wave Elastography Measurements

(1) Objective: To design an artificial intelligence system for prostate cancer prediction using the data obtained by shear wave elastography of the prostate, by comparing it with the histopathological exam of the prostate biopsy specimens. (2) Material and methods: We have conducted a prospective study on 356 patients undergoing transrectal ultrasound-guided prostate biopsy, for suspicion of prostate cancer. All patients were examined using bi-dimensional shear wave ultrasonography, which was followed by standard systematic transrectal prostate biopsy. The mean elasticity of each of the twelve systematic biopsy target zones was recorded and compared with the pathological examination results in all patients. The final dataset has included data from 223 patients with confirmed prostate cancer. Three machine learning classification algorithms (logistic regression, a decision tree classifier and a dense neural network) were implemented and their performance in predicting the positive lesions from the elastographic data measurements was assessed. (3) Results: The area under the curve (AUC) results were as follows: for logistic regression—0.88, for decision tree classifier—0.78 and for the dense neural network—0.94. Further use of an upsampling strategy for the training set of the neural network slightly improved its performance. Using an ensemble learning model, which combined the three machine learning models, we have obtained a final accuracy of 98%. (4) Conclusions: Bi-dimensional shear wave elastography could be very useful in predicting prostate cancer lesions, especially when it benefits from the computational power of artificial intelligence and machine learning algorithms.

From Omics to Multi-Omics Approaches for In-Depth Analysis of the Molecular Mechanisms of Prostate Cancer

Cancer arises following alterations at different cellular levels, including genetic and epigenetic modifications, transcription and translation dysregulation, as well as metabolic variations. High-throughput omics technologies that allow one to identify and quantify processes involved in these changes are now available and have been instrumental in generating a wealth of steadily increasing data from patient tumors, liquid biopsies, and from tumor models. Extensive investigation and integration of these data have led to new biological insights into the origin and development of multiple cancer types and helped to unravel the molecular networks underlying this complex pathology. The comprehensive and quantitative analysis of a molecule class in a biological sample is named omics and large-scale omics studies addressing different prostate cancer stages have been performed in recent years. Prostate tumors represent the second leading cancer type and a prevalent cause of cancer death in men worldwide. It is a very heterogenous disease so that evaluating inter- and intra-tumor differences will be essential for a precise insight into disease development and plasticity, but also for the development of personalized therapies. There is ample evidence for the key role of the androgen receptor, a steroid hormone-activated transcription factor, in driving early and late stages of the disease, and this led to the development and approval of drugs addressing diverse targets along this pathway. Early genomic and transcriptomic studies have allowed one to determine the genes involved in prostate cancer and regulated by androgen signaling or other tumor-relevant signaling pathways. More recently, they have been supplemented by epigenomic, cistromic, proteomic and metabolomic analyses, thus, increasing our knowledge on the intricate mechanisms involved, the various levels of regulation and their interplay. The comprehensive investigation of these omics approaches and their integration into multi-omics analyses have led to a much deeper understanding of the molecular pathways involved in prostate cancer progression, and in response and resistance to therapies. This brings the hope that novel vulnerabilities will be identified, that existing therapies will be more beneficial by targeting the patient population likely to respond best, and that bespoke treatments with increased efficacy will be available soon.

Usefulness of Collaborative Work in the Evaluation of Prostate Cancer from MRI

The aim of this study is to show the usefulness of collaborative work in the evaluation of prostate cancer from T2-weighted MRI using a dedicated software tool. The variability of annotations on images of the prostate gland (central and peripheral zones as well as tumour) by two independent experts was firstly evaluated, and secondly compared with a consensus between these two experts. Using a prostate MRI database, experts drew regions of interest (ROIs) corresponding to healthy prostate (peripheral and central zones) and cancer. One of the experts then drew the ROI with knowledge of the other expert’s ROI. The surface area of each ROI was used to measure the Hausdorff distance and the Dice coefficient was measured from the respective contours. They were evaluated between the different experiments, taking the annotations of the second expert as the reference. The results showed that the significant differences between the two experts disappeared with collaborative work. To conclude, this study shows that collaborative work with a dedicated tool allows consensus between expertise in the evaluation of prostate cancer from T2-weighted MRI.

Application Value of Radiomic Nomogram in the Differential Diagnosis of Prostate Cancer and Hyperplasia

Objective

Prostate cancer and hyperplasia require different treatment strategies and have completely different outcomes; thus, preoperative identification of prostate cancer and hyperplasia is very important. The purpose of this study was to evaluate the application value of magnetic resonance imaging (MRI)-derived radiomic nomogram based on T2-weighted images (T2WI) in differentiating prostate cancer and hyperplasia.

Materials and Methods

One hundred forty-six patients (66 cases of prostate cancer and 80 cases of prostate hyperplasia) who were confirmed by surgical pathology between September 2019 and September 2019 were selected. We manually delineated T2WI of all patients using ITK-SNAP software and radiomic analysis using Analysis Kit (AK) software. A total of 396 tumor texture features were extracted. Subsequently, the effective features were selected using the LASSO algorithm, and the radiomic feature model was constructed. Next, combined with independent clinical risk factors, a multivariate Logistic regression model was used to establish a radiomic nomogram. The receiver operator characteristic (ROC) curve was used to evaluate the prediction performance of the radiomic nomogram. Finally, the clinical application value of the nomogram was evaluated by decision curve analysis.

Results

The PSA and the selected imaging features were significantly correlated with the differential diagnosis of prostate cancer and hyperplasia. The radiomic model had good discrimination efficiency for prostate cancer and hyperplasia. The training set (AUC = 0.85; 95% CI: 0.77–0.92) and testing set (AUC = 0.84; 95% CI: 0.72–0.96) were effective. The radiomic nomogram, combined with the radiomic characteristics of MRI and independent clinical risk factors, showed better differentiation efficiency in the training set (AUC = 0.91; 95% CI: 0.85–0.97) and testing set (AUC = 0.90; 95% CI: 0.81–0.99). The decision curve showed the clinical application value of the radiomic nomogram.

Conclusion

The radiomic nomogram of T2-MRI combined with clinical risk factors can easily identify prostate cancer and hyperplasia. It also provides suggestions for further clinical events.

Identification of a Steroid Hormone-Associated Gene Signature Predicting the Prognosis of Prostate Cancer through an Integrative Bioinformatics Analysis

Simple Summary

Prostate cancer (PC) is the second most common cancer worldwide and steroid hormone plays an important role in prostate carcinogenesis. Most patients with PC are initially sensitive to androgen deprivation therapy (ADT) but eventually become hormone refractory and reflect disease progression. The aim of the study was to investigate the genes which regulate the steroid hormone functional pathways and associate with the disease progression of PC. We identified a panel of eight-gene signatures that modulated steroid-hormone pathways and predicted the prognosis of PC using integrative bioinformatics analysis of multiple datasets validated from external cohorts. This panel could be used for predicting the prognosis of PC patients and might be associated with the drug response of hormonal therapies. Moreover, these genes in the signature could be potential targets to develop a novel treatment for castration-resistant PC therapy.

Abstract

The importance of anti-androgen therapy for prostate cancer (PC) has been well recognized. However, the mechanisms underlying prostate cancer resistance to anti-androgens are not completely understood. Therefore, identifying pharmacological targets in driving the development of castration-resistant PC is necessary. In the present study, we sought to identify core genes in regulating steroid hormone pathways and associating them with the disease progression of PC. The selection of steroid hormone-associated genes was identified from functional databases, including gene ontology, KEGG, and Reactome. The gene expression profiles and relevant clinical information of patients with PC were obtained from TCGA and used to examine the genes associated with steroid hormone. The machine-learning algorithm was performed for key feature selection and signature construction. With the integrative bioinformatics analysis, an eight-gene signature, including CA2, CYP2E1, HSD17B, SSTR3, SULT1E1, TUBB3, UCN, and UGT2B7 was established. Patients with higher expression of this gene signature had worse progression-free interval in both univariate and multivariate cox models adjusted for clinical variables. The expression of the gene signatures also showed the aggressiveness consistently in two external cohorts, PCS and PAM50. Our findings demonstrated a validated eight-gene signature could successfully predict PC prognosis and regulate the steroid hormone pathway.

Prostate cancer biomarkers: a practical review based on different clinical scenarios

Traditionally, diagnosis and staging of prostate cancer (PCa) have been based on prostate-specific antigen (PSA) level, digital rectal examination (DRE), and transrectal ultrasound (TRUS) guided prostate biopsy. Biomarkers have been introduced into clinical practice to reduce the overdiagnosis and overtreatment of low-grade PCa and increase the success of personalized therapies for high-grade and high-stage PCa. The purpose of this review was to describe available PCa biomarkers and examine their use in clinical practice. A nonsystematic literature review was performed using PubMed and Scopus to retrieve papers related to PCa biomarkers. In addition, we manually searched websites of major urological associations for PCa guidelines to evaluate available evidence and recommendations on the role of biomarkers and their potential contribution to PCa decision-making. In addition to PSA and its derivates, thirteen blood, urine, and tissue biomarkers are mentioned in various PCa guidelines. Retrospective studies have shown their utility in three main clinical scenarios: (1) deciding whether to perform a biopsy, (2) distinguishing patients who require active treatment from those who can benefit from active surveillance, and (3) defining a subset of high-risk PCa patients who can benefit from additional therapies after RP. Several validated PCa biomarkers have become commercially available in recent years. Guidelines now recommend offering these tests in situations in which the assay result, when considered in combination with routine clinical factors, is likely to affect management. However, the lack of direct comparisons and the unproven benefits, in terms of long-term survival and cost-effectiveness, prevent these biomarkers from being integrated into routine clinical use.

CHAIMELEON Project: Creation of a Pan-European Repository of Health Imaging Data for the Development of AI-Powered Cancer Management Tools

The CHAIMELEON project aims to set up a pan-European repository of health imaging data, tools and methodologies, with the ambition to set a standard and provide resources for future AI experimentation for cancer management. The project is a 4 year long, EU-funded project tackling some of the most ambitious research in the fields of biomedical imaging, artificial intelligence and cancer treatment, addressing the four types of cancer that currently have the highest prevalence worldwide: lung, breast, prostate and colorectal. To allow this, clinical partners and external collaborators will populate the repository with multimodality (MR, CT, PET/CT) imaging and related clinical data. Subsequently, AI developers will enable a multimodal analytical data engine facilitating the interpretation, extraction and exploitation of the information stored at the repository. The development and implementation of AI-powered pipelines will enable advancement towards automating data deidentification, curation, annotation, integrity securing and image harmonization. By the end of the project, the usability and performance of the repository as a tool fostering AI experimentation will be technically validated, including a validation subphase by world-class European AI developers, participating in Open Challenges to the AI Community. Upon successful validation of the repository, a set of selected AI tools will undergo early in-silico validation in observational clinical studies coordinated by leading experts in the partner hospitals. Tool performance will be assessed, including external independent validation on hallmark clinical decisions in response to some of the currently most important clinical end points in cancer. The project brings together a consortium of 18 European partners including hospitals, universities, R&D centers and private research companies, constituting an ecosystem of infrastructures, biobanks, AI/in-silico experimentation and cloud computing technologies in oncology.

Comparison of Different Machine Learning Models in Prediction of Postirradiation Recurrence in Prostate Carcinoma Patients

After primary treatment of localized prostate carcinoma (PC), up to a third of patients have disease recurrence. Different predictive models have already been used either for initial stratification of PC patients or to predict disease recurrence. Recently, artificial intelligence has been introduced in the diagnosis and management of PC with a potential to revolutionize this field. The aim of this study was to analyze machine learning (ML) classifiers in order to predict disease progression in the moment of prostate-specific antigen (PSA) elevation during follow-up. The study cohort consisted of 109 PC patients treated with external beam radiotherapy alone or in combination with androgen deprivation therapy. We developed and evaluated the performance of two ML algorithms based on artificial neural networks (ANN) and naïve Bayes (NB). Of all patients, 72.5% was randomly selected for a training set while the remaining patients were used for testing of the models. The presence/absence of disease progression was defined as the output variable. The input variables for models were conducted from the univariate analysis preformed among two groups of patients in the training set. They included two pretreatment variables (UICC stage and Gleason's score risk group) and five posttreatment variables (nadir PSA, time to nadir PSA, PSA doubling time, PSA velocity, and PSA in the moment of disease reevaluation). The area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, negative predictive value, and predictive accuracy was calculated to test the models' performance. The results showed that specificity was similar for both models, while NB achieved better sensitivity then ANN (100.0% versus 94.4%). The ANN showed an accuracy of 93.3%, and the matching for NB model was 96.7%. In this study, ML classifiers have shown potential for application in routine clinical practice during follow-up when disease progression was suspected.