Research progress on deep learning in magnetic resonance imaging-based diagnosis and treatment of prostate cancer: a review on the current status and perspectives

Deep learning and radiomics-driven algorithm for automated identification of May-Thurner syndrome in Iliac CTV imaging

Objective

This research aimed to create a dataset of Iliac CTV scans for automated May-Thurner syndrome (MTS) detection using deep learning and radiomics. In addition, it sought to establish an automated segmentation model for Iliac Vein CTV scans and construct a radiomic signature for MTS diagnosis.

Methods

We collected a dataset of 490 cases meeting specific inclusion and exclusion criteria, anonymized to comply with HIPAA regulations. Iliac Vein CTV scans were prepared with contrast agent administration, followed by image acquisition and evaluation. A deep learning-based segmentation model, UPerNet, was employed using 10-fold cross-validation. Radiomic features were extracted from the scans and used to construct a diagnostic radiomic signature. Statistical analysis, including Dice values and ROC analysis, was conducted to evaluate segmentation and diagnostic performance.

Results

The dataset consisted of 201 positive cases of MTS and 289 negative cases. The UPerNet segmentation model exhibited remarkable accuracy in identifying MTS regions. A Dice coefficient of 0.925 (95% confidence interval: 0.875-0.961) was observed, indicating the precision and reliability of our segmentation model. Radiomic analysis produced a diagnostic radiomic signature with significant clinical potential. ROC analysis demonstrated promising results, underscoring the efficacy of the developed model in distinguishing MTS cases. The radiomic signature demonstrated strong diagnostic capabilities for MTS. Within the training dataset, it attained a notable area under the curve (AUC) of 0.891, with a 95% confidence interval ranging from 0.825 to 0.956, showcasing its effectiveness. This diagnostic capability extended to the validation dataset, where the AUC remained strong at 0.892 (95% confidence interval: 0.793-0.991). These results highlight the accuracy of our segmentation model and the diagnostic value of our radiomic signature in identifying MTS cases.

Conclusion

This study presents a comprehensive approach to automate MTS detection from Iliac CTV scans, combining deep learning and radiomics. The results suggest the potential clinical utility of the developed model in diagnosing MTS, offering a non-invasive and efficient alternative to traditional methods.

Revolutionizing prostate cancer therapy: Artificial intelligence - Based nanocarriers for precision diagnosis and treatment

Prostate cancer is one of the major health challenges in the world and needs novel therapeutic approaches to overcome the limitations of conventional treatment. This review delineates the transformative potential of artificial intelligence (AL) in enhancing nanocarrier-based drug delivery systems for prostate cancer therapy. With its ability to optimize nanocarrier design and predict drug delivery kinetics, AI has revolutionized personalized treatment planning in oncology. We discuss how AI can be integrated with nanotechnology to address challenges related to tumor heterogeneity, drug resistance, and systemic toxicity. Emphasis is placed on strong AI-driven advancements in the design of nanocarriers, structural optimization, targeting of ligands, and pharmacokinetics. We also give an overview of how AI can better predict toxicity, reduce costs, and enable personalized medicine. While challenges persist in the way of data accessibility, regulatory hurdles, and interactions with the immune system, future directions based on explainable AI (XAI) models, integration of multimodal data, and green nanocarrier designs promise to move the field forward. Convergence between AI and nanotechnology has been one key step toward safer, more effective, and patient-tailored cancer therapy.

Integrating shear wave elastography and multiparametric MRI for accurate prostate cancer diagnosis

OBJECTIVE

To develop a risk prediction model for prostate cancer (PCa) by integrating Shear Wave Elastography (SWE) with Multiparametric Magnetic Resonance Imaging (mpMRI), thereby improving screening accuracy and specificity while reducing unnecessary invasive procedures.

METHODS

A total of 479 patients who visited Sun Yat-sen Memorial Hospital between May 2019 and July 2023 were included in this retrospective study, with 162 diagnosed with PCa. The patients were randomly divided into a training set (349 cases) and a validation set (130 cases). The primary measurements consisted of the Young's modulus from SWE, the PI-RADS score from mpMRI, and laboratory indicators such as total PSA (tPSA), free PSA (fPSA), and their densities. A multifactorial prediction model integrating imaging and clinical data was constructed and validated.

RESULTS

The combined model incorporating SWE and mpMRI exhibited high accuracy and robustness in diagnosing PCa, with area under the curve (AUC) values of 0.92 for the training set and 0.91 for the validation set, significantly outperforming individual indicators (P<0.001). The model achieved a sensitivity of 94.87% and a specificity of 96.12%, indicating superior performance in distinguishing PCa from benign lesions. Receiver operating characteristic (ROC) curve analysis and DeLong's test confirmed that the combined model exhibited the highest diagnostic accuracy, reducing false positives and minimizing unnecessary biopsies.

CONCLUSIONS

The multifactorial prediction model integrating both imaging and clinical data provides a more precise and reliable tool for the early diagnosis of PCa, with significant potential for clinical application.

Systematic Review of AI-Assisted MRI in Prostate Cancer Diagnosis: Enhancing Accuracy Through Second Opinion Tools

BACKGROUND

Prostate cancer is a leading cause of cancer-related deaths in men worldwide, making accurate diagnosis critical for effective treatment. Recent advancements in artificial intelligence (AI) and machine learning (ML) have shown promise in improving the diagnostic accuracy of prostate cancer.

OBJECTIVES

This systematic review aims to evaluate the effectiveness of AI-based tools in diagnosing prostate cancer using MRI, with a focus on accuracy, specificity, sensitivity, and clinical utility compared to conventional diagnostic methods.

METHODS

A comprehensive search was conducted across PubMed, Embase, Ovid MEDLINE, Web of Science, Cochrane Library, and Institute of Electrical and Electronics Engineers (IEEE) Xplore for studies published between 2019 and 2024. Inclusion criteria focused on full-text, English-language studies involving AI for Magnetic Resonance Imaging (MRI) -based prostate cancer diagnosis. Diagnostic performance metrics such as area under curve (AUC), sensitivity, and specificity were analyzed, with risk of bias assessed using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool.

RESULTS

Seven studies met the inclusion criteria, employing various AI techniques, including deep learning and machine learning. These studies reported improved diagnostic accuracy (with AUC scores of up to 97%) and moderate sensitivity, with performance varying based on training data quality and lesion characteristics like Prostate Imaging Reporting and Data System (PI-RADS) scores.

CONCLUSIONS

AI has significant potential to enhance prostate cancer diagnosis, particularly when used for second opinions in MRI interpretations. While these results are promising, further validation in diverse populations and clinical settings is necessary to fully integrate AI into standard practice.

Enhancing prostate cancer segmentation on multiparametric magnetic resonance imaging with background information and gland masks

BACKGROUND

The landscape of prostate cancer (PCa) segmentation within multiparametric magnetic resonance imaging (MP-MRI) was fragmented, with a noticeable lack of consensus on incorporating background details, culminating in inconsistent segmentation outputs. Given the complex and heterogeneous nature of PCa, conventional imaging segmentation algorithms frequently fell short, prompting the need for specialized research and refinement.

PURPOSE

This study sought to dissect and compare various segmentation methods, emphasizing the role of background information and gland masks in achieving superior PCa segmentation. The goal was to systematically refine segmentation networks to ascertain the most efficacious approach.

METHODS

A cohort of 232 patients (ages 61-73 years old, prostate-specific antigen: 3.4-45.6 ng/mL), who had undergone MP-MRI followed by prostate biopsies, was analyzed. An advanced segmentation model, namely Attention-Unet, which combines U-Net with attention gates, was employed for training and validation. The model was further enhanced through a multiscale module and a composite loss function, culminating in the development of Matt-Unet. Performance metrics included Dice Similarity Coefficient (DSC) and accuracy (ACC).

RESULTS

The Matt-Unet model, which integrated background information and gland masks, outperformed the baseline U-Net model using raw images, yielding significant gains (DSC: 0.7215 vs. 0.6592; ACC: 0.8899 vs. 0.8601, p < 0.001).

CONCLUSION

A targeted and practical PCa segmentation method was designed, which could significantly improve PCa segmentation on MP-MRI by combining background information and gland masks. The Matt-Unet model showcased promising capabilities for effectively delineating PCa, enhancing the precision of MP-MRI analysis.

Machine Learning for Dynamic Prognostication of Patients With Hepatocellular Carcinoma Using Time-Series Data: Survival Path Versus Dynamic-DeepHit HCC Model

Objectives

Patients with intermediate or advanced hepatocellular carcinoma (HCC) require repeated disease monitoring, prognosis assessment and treatment planning. In 2018, a novel machine learning methodology "survival path" (SP) was developed to facilitate dynamic prognosis prediction and treatment planning. One year after, a deep learning approach called Dynamic Deephit was developed. The performance of the two state-of-art models in dynamic prognostication have not been compared.

Methods

We trained and tested the SP and Dynamic DeepHit models in a large cohort of 2511 HCC patients using time-series data. The time-series data were converted into data of time slices, with an interval of three months. The time-dependent c-index for OS at given prediction time (t = 1, 6, 12, 18 months) and evaluation time (∆t = 3, 6, 9, 12, 18, 24, 36, 48 months) were compared.

Results

The comparison between SP model and Dynamic DeepHit-HCC model showed the latter had significant better performance at the time of initial admission. The time-dependent c-index of Dynamic DeepHit-HCC model gradually decreased with the extension of time (from 0.756 to 0.639 in the training set; from 0.787 to 0.661 in internal testing set; from 0.725 to 0.668 in multicenter testing set); while the time-dependent c-index of SP model displayed an increased trend (from 0.665 to 0.748 in the training set; from 0.608 to 0.743 in internal testing set; from 0.643 to 0.720 in multicenter testing set). When the prediction time comes to 6 months or later since initial treatment, the survival path model outperformed the dynamic DeepHit model at late evaluation times (∆t > 12 months).

Conclusions

This research highlighted the unique strengths of both models. The SP model had advantage in long term prediction while the Dynamic DeepHit-HCC model had advantages in prediction at near time points. Fine selection of models is needed in dealing with different scenarios.

Omics Studies of Specialized Cells and Stem Cells under Microgravity Conditions

The primary objective of omics in space with focus on the human organism is to characterize and quantify biological factors that alter structure, morphology, function, and dynamics of human cells exposed to microgravity. This review discusses exciting data regarding genomics, transcriptomics, epigenomics, metabolomics, and proteomics of human cells and individuals in space, as well as cells cultured under simulated microgravity. The NASA Twins Study significantly heightened interest in applying omics technologies and bioinformatics in space and terrestrial environments. Here, we present the available publications in this field with a focus on specialized cells and stem cells exposed to real and simulated microgravity conditions. We summarize current knowledge of the following topics: (i) omics studies on stem cells, (ii) omics studies on benign specialized different cell types of the human organism, (iii) discussing the advantages of this knowledge for space commercialization and exploration, and (iv) summarizing the emerging opportunities for translational regenerative medicine for space travelers and human patients on Earth.

Advancing Prostate Cancer Diagnosis: A Deep Learning Approach for Enhanced Detection in MRI Images

Prostate cancer remains a leading cause of mortality among men globally, necessitating advancements in diagnostic methodologies to improve detection and treatment outcomes. Magnetic Resonance Imaging has emerged as a crucial technique for the detection of prostate cancer, with current research focusing on the integration of deep learning frameworks to refine this diagnostic process. This study employs a comprehensive approach using multiple deep learning models, including a three-dimensional (3D) Convolutional Neural Network, a Residual Network, and an Inception Network to enhance the accuracy and robustness of prostate cancer detection. By leveraging the complementary strengths of these models through an ensemble method and soft voting technique, the study aims to achieve superior diagnostic performance. The proposed methodology demonstrates state-of-the-art results, with the ensemble model achieving an overall accuracy of 91.3%, a sensitivity of 90.2%, a specificity of 92.1%, a precision of 89.8%, and an F1 score of 90.0% when applied to MRI images from the SPIE-AAPM-NCI PROSTATEx dataset. Evaluation of the models involved meticulous pre-processing, data augmentation, and the use of advanced deep-learning architectures to analyze the whole MRI slices and volumes. The findings highlight the potential of using an ensemble approach to significantly improve prostate cancer diagnostics, offering a robust and precise tool for clinical applications.

Exploring the relationship between anastasis and mitochondrial ROS-mediated ferroptosis in metastatic chemoresistant cancers: a call for investigation

Ferroptosis induces significant changes in mitochondrial morphology, including membrane condensation, volume reduction, cristae alteration, and outer membrane rupture, affecting mitochondrial function and cellular fate. Recent reports have described the intrinsic cellular iron metabolism and its intricate connection to ferroptosis, a significant kind of cell death characterized by iron dependence and oxidative stress regulation. Furthermore, updated molecular insights have elucidated the significance of mitochondria in ferroptosis and its implications in various cancers. In the context of cancer therapy, understanding the dual role of anastasis and ferroptosis in chemoresistance is crucial. Targeting the molecular pathways involved in anastasis may enhance the efficacy of ferroptosis inducers, providing a synergistic approach to overcome chemoresistance. Research into how DNA damage response (DDR) proteins, metabolic changes, and redox states interact during anastasis and ferroptosis can offer new insights into designing combinatorial therapeutic regimens against several cancers associated with stemness. These treatments could potentially inhibit anastasis while simultaneously inducing ferroptosis, thereby reducing the likelihood of cancer cells evading death and developing resistance to chemotherapy. The objective of this study is to explore the intricate interplay between anastasis, ferroptosis, EMT and chemoresistance, and immunotherapeutics to better understand their collective impact on cancer therapy outcomes. We searched public research databases including google scholar, PubMed, relemed, and the national library of medicine related to this topic. In this review, we discussed the interplay between the tricarboxylic acid cycle and glycolysis implicated in modulating ferroptosis, adding complexity to its regulatory mechanisms. Additionally, the regulatory role of reactive oxygen species (ROS) and the electron transport chain (ETC) in ferroptosis has garnered significant attention. Lipid metabolism, particularly involving GPX4 and System Xc- plays a significant role in both the progression of ferroptosis and cancer. There is a need to investigate the intricate interplay between anastasis, ferroptosis, and chemoresistance to better understand cancer therapy clinical outcomes. Integrating anastasis, and ferroptosis into strategies targeting chemoresistance and exploring its potential synergy with immunotherapy represent promising avenues for advancing chemoresistant cancer treatment. Understanding the intricate interplay among mitochondria, anastasis, ROS, and ferroptosis is vital in oncology, potentially revolutionizing personalized cancer treatment and drug development.

Exploring the relationship between anastasis and mitochondrial ROS-mediated ferroptosis in metastatic chemoresistant cancers: a call for investigation

Ferroptosis induces significant changes in mitochondrial morphology, including membrane condensation, volume reduction, cristae alteration, and outer membrane rupture, affecting mitochondrial function and cellular fate. Recent reports have described the intrinsic cellular iron metabolism and its intricate connection to ferroptosis, a significant kind of cell death characterized by iron dependence and oxidative stress regulation. Furthermore, updated molecular insights have elucidated the significance of mitochondria in ferroptosis and its implications in various cancers. In the context of cancer therapy, understanding the dual role of anastasis and ferroptosis in chemoresistance is crucial. Targeting the molecular pathways involved in anastasis may enhance the efficacy of ferroptosis inducers, providing a synergistic approach to overcome chemoresistance. Research into how DNA damage response (DDR) proteins, metabolic changes, and redox states interact during anastasis and ferroptosis can offer new insights into designing combinatorial therapeutic regimens against several cancers associated with stemness. These treatments could potentially inhibit anastasis while simultaneously inducing ferroptosis, thereby reducing the likelihood of cancer cells evading death and developing resistance to chemotherapy. The objective of this study is to explore the intricate interplay between anastasis, ferroptosis, EMT and chemoresistance, and immunotherapeutics to better understand their collective impact on cancer therapy outcomes. We searched public research databases including google scholar, PubMed, relemed, and the national library of medicine related to this topic. In this review, we discussed the interplay between the tricarboxylic acid cycle and glycolysis implicated in modulating ferroptosis, adding complexity to its regulatory mechanisms. Additionally, the regulatory role of reactive oxygen species (ROS) and the electron transport chain (ETC) in ferroptosis has garnered significant attention. Lipid metabolism, particularly involving GPX4 and System Xc- plays a significant role in both the progression of ferroptosis and cancer. There is a need to investigate the intricate interplay between anastasis, ferroptosis, and chemoresistance to better understand cancer therapy clinical outcomes. Integrating anastasis, and ferroptosis into strategies targeting chemoresistance and exploring its potential synergy with immunotherapy represent promising avenues for advancing chemoresistant cancer treatment. Understanding the intricate interplay among mitochondria, anastasis, ROS, and ferroptosis is vital in oncology, potentially revolutionizing personalized cancer treatment and drug development.

Fundamental evaluation regarding the relationship between albumin-binding and tumor accumulation of PSMA-targeting radioligands

OBJECTIVE

The marked success of prostate-specific membrane antigen (PSMA)-targeting radioligands with albumin binder (ALB) is attributed to the improvement of blood retention and tumor accumulation. [111In]In-PNT-DA1, our PSMA-targeting radioligand with ALB, also achieved improved tumor accumulation due to its prolonged blood retention. Although the advantage of ALBs is related to their reversible binding to albumin, the relationship between albumin-binding and tumor accumulation of PSMA-targeting radioligands remains unclear because of the lack of information about radioligands with stronger albumin-binding than ALBs. In this study, we designed and synthesized [111In]In-PNT-DM-HSA, a new radioligand that consists of a PSMA-targeting radioligand covalently bound to albumin. The pharmacokinetics of [111In]In-PNT-DM-HSA was compared with those of [111In]In-PNT-DA1 and [111In]In-PSMA-617, a non-ALB-conjugated radioligand, to evaluate the relationship between albumin-binding and tumor accumulation.

METHOD

The [111In]In-PNT-DM-HSA was prepared by incubation of [111In]In-PNT-DM, a PSMA-targeting radioligand including a maleimide group, and human serum albumin (HSA). The ability of [111In]In-PNT-DM-HSA was evaluated by in vitro assays. A biodistribution study using LNCaP tumor-bearing mice was conducted to compare the pharmacokinetics of [111In]In-PNT-DM-HSA, [111In]In-PNT-DA1, and [111In]In-PSMA-617.

RESULTS

The [111In]In-PNT-DM-HSA was obtained at a favorable radiochemical yield and high radiochemical purity. In vitro assays revealed that [111In]In-PNT-DM-HSA had fundamental characteristics as a PSMA-targeting radioligand interacting with albumin covalently. In a biodistribution study, [111In]In-PNT-DM-HSA and [111In]In-PNT-DA1 showed higher blood retention than [111In]In-PSMA-617. On the other hand, the tumor accumulation of [111In]In-PNT-DA1 was much higher than [111In]In-PNT-DM-HSA and [111In]In-PSMA-617.

CONCLUSIONS

These results indicate that the moderate reversible binding of ALB with albumin, not covalent binding, may play a critical role in enhancing the tumor accumulation of PSMA-targeting radioligands.

Advancements in nanomedicine: Precision delivery strategies for male pelvic malignancies - Spotlight on prostate and colorectal cancer

BACKGROUND

Pelvic malignancies consistently pose significant global health challenges, adversely affecting the well-being of the male population. It is anticipated that clinicians will continue to confront these cancers in their practice. Nanomedicine offers promising strategies that revolutionize the treatment of male pelvic malignancies by providing precise delivery methods that aim to improve the efficacy of therapeutic outcomes while minimizing side effects. Nanoparticles are designed to encapsulate therapeutic agents and selectively target cancer cells. They can also be loaded with theragnostic agents, enabling multifunctional capabilities.

OBJECTIVE

This review aims to summarize the latest nanomedicine research into clinical applications, focusing on nanotechnology-based treatment strategies for male pelvic malignancies, encompassing chemotherapy, radiotherapy, immunotherapy, and other cutting-edge therapies. The review is structured to assist physicians, particularly those with limited knowledge of biochemistry and bioengineering, in comprehending the functionalities and applications of nanomaterials.

METHODS

Multiple databases, including PubMed, the National Library of Medicine, and Embase, were utilized to locate and review recently published articles on advancements in nano-drug delivery for prostate and colorectal cancers.

CONCLUSION

Nanomedicine possesses considerable potential in improving therapeutic outcomes and reducing adverse effects for male pelvic malignancies. Through precision delivery methods, this emerging field presents innovative treatment modalities to address these challenging diseases. Nevertheless, the majority of current studies are in the preclinical phase, with a lack of sufficient evidence to fully understand the precise mechanisms of action, absence of comprehensive pharmacotoxicity profiles, and uncertainty surrounding long-term consequences.

Artificial intelligence in the healthcare sector: comparison of deep learning networks using chest X-ray images

Purpose

Artificial intelligence has led to significant developments in the healthcare sector, as in other sectors and fields. In light of its significance, the present study delves into exploring deep learning, a branch of artificial intelligence.

Methods

In the study, deep learning networks ResNet101, AlexNet, GoogLeNet, and Xception were considered, and it was aimed to determine the success of these networks in disease diagnosis. For this purpose, a dataset of 1,680 chest X-ray images was utilized, consisting of cases of COVID-19, viral pneumonia, and individuals without these diseases. These images were obtained by employing a rotation method to generate replicated data, wherein a split of 70 and 30% was adopted for training and validation, respectively.

Results

The analysis findings revealed that the deep learning networks were successful in classifying COVID-19, Viral Pneumonia, and Normal (disease-free) images. Moreover, an examination of the success levels revealed that the ResNet101 deep learning network was more successful than the others with a 96.32% success rate.

Conclusion

In the study, it was seen that deep learning can be used in disease diagnosis and can help experts in the relevant field, ultimately contributing to healthcare organizations and the practices of country managers.

Unleashing novel horizons in advanced prostate cancer treatment: investigating the potential of prostate specific membrane antigen-targeted nanomedicine-based combination therapy

Prostate cancer (PCa) is a prevalent malignancy with increasing incidence in middle-aged and older men. Despite various treatment options, advanced metastatic PCa remains challenging with poor prognosis and limited effective therapies. Nanomedicine, with its targeted drug delivery capabilities, has emerged as a promising approach to enhance treatment efficacy and reduce adverse effects. Prostate-specific membrane antigen (PSMA) stands as one of the most distinctive and highly selective biomarkers for PCa, exhibiting robust expression in PCa cells. In this review, we explore the applications of PSMA-targeted nanomedicines in advanced PCa management. Our primary objective is to bridge the gap between cutting-edge nanomedicine research and clinical practice, making it accessible to the medical community. We discuss mainstream treatment strategies for advanced PCa, including chemotherapy, radiotherapy, and immunotherapy, in the context of PSMA-targeted nanomedicines. Additionally, we elucidate novel treatment concepts such as photodynamic and photothermal therapies, along with nano-theragnostics. We present the content in a clear and accessible manner, appealing to general physicians, including those with limited backgrounds in biochemistry and bioengineering. The review emphasizes the potential benefits of PSMA-targeted nanomedicines in enhancing treatment efficiency and improving patient outcomes. While the use of PSMA-targeted nano-drug delivery has demonstrated promising results, further investigation is required to comprehend the precise mechanisms of action, pharmacotoxicity, and long-term outcomes. By meticulous optimization of the combination of nanomedicines and PSMA ligands, a novel horizon of PSMA-targeted nanomedicine-based combination therapy could bring renewed hope for patients with advanced PCa.

Unleashing novel horizons in advanced prostate cancer treatment: investigating the potential of prostate specific membrane antigen-targeted nanomedicine-based combination therapy

Prostate cancer (PCa) is a prevalent malignancy with increasing incidence in middle-aged and older men. Despite various treatment options, advanced metastatic PCa remains challenging with poor prognosis and limited effective therapies. Nanomedicine, with its targeted drug delivery capabilities, has emerged as a promising approach to enhance treatment efficacy and reduce adverse effects. Prostate-specific membrane antigen (PSMA) stands as one of the most distinctive and highly selective biomarkers for PCa, exhibiting robust expression in PCa cells. In this review, we explore the applications of PSMA-targeted nanomedicines in advanced PCa management. Our primary objective is to bridge the gap between cutting-edge nanomedicine research and clinical practice, making it accessible to the medical community. We discuss mainstream treatment strategies for advanced PCa, including chemotherapy, radiotherapy, and immunotherapy, in the context of PSMA-targeted nanomedicines. Additionally, we elucidate novel treatment concepts such as photodynamic and photothermal therapies, along with nano-theragnostics. We present the content in a clear and accessible manner, appealing to general physicians, including those with limited backgrounds in biochemistry and bioengineering. The review emphasizes the potential benefits of PSMA-targeted nanomedicines in enhancing treatment efficiency and improving patient outcomes. While the use of PSMA-targeted nano-drug delivery has demonstrated promising results, further investigation is required to comprehend the precise mechanisms of action, pharmacotoxicity, and long-term outcomes. By meticulous optimization of the combination of nanomedicines and PSMA ligands, a novel horizon of PSMA-targeted nanomedicine-based combination therapy could bring renewed hope for patients with advanced PCa.

3D-Vision-Transformer Stacking Ensemble for Assessing Prostate Cancer Aggressiveness from T2w Images

Vision transformers represent the cutting-edge topic in computer vision and are usually employed on two-dimensional data following a transfer learning approach. In this work, we propose a trained-from-scratch stacking ensemble of 3D-vision transformers to assess prostate cancer aggressiveness from T2-weighted images to help radiologists diagnose this disease without performing a biopsy. We trained 18 3D-vision transformers on T2-weighted axial acquisitions and combined them into two- and three-model stacking ensembles. We defined two metrics for measuring model prediction confidence, and we trained all the ensemble combinations according to a five-fold cross-validation, evaluating their accuracy, confidence in predictions, and calibration. In addition, we optimized the 18 base ViTs and compared the best-performing base and ensemble models by re-training them on a 100-sample bootstrapped training set and evaluating each model on the hold-out test set. We compared the two distributions by calculating the median and the 95% confidence interval and performing a Wilcoxon signed-rank test. The best-performing 3D-vision-transformer stacking ensemble provided state-of-the-art results in terms of area under the receiving operating curve (0.89 [0.61-1]) and exceeded the area under the precision-recall curve of the base model of 22% (p < 0.001). However, it resulted to be less confident in classifying the positive class.