Value of machine learning-based transrectal multimodal ultrasound combined with PSA-related indicators in the diagnosis of clinically significant prostate cancer

An overview of utilizing artificial intelligence in localized prostate cancer imaging

INTRODUCTION

Prostate cancer (PCa) is a leading cause of cancer-related deaths among men, and accurate diagnosis is critical for effective management. Multiparametric MRI (mpMRI) has become an essential tool in PCa diagnosis due to its superior spatial resolution which enables detailed anatomical, functional information and its resultant ability to detect clinically significant PCa. However, challenges such as subjective interpretation methods and high inter-reader variability remain. In recent years, artificial intelligence (AI) has emerged as a promising solution to enhance the diagnostic performance of mpMRI by automating key tasks such as prostate segmentation, lesion detection, classification.

AREAS COVERED

This review provides a comprehensive overview of the current AI applications in prostate mpMRI, discussing advancements in automated image analysis and how AI-driven models are developed to improve detection and risk stratification. A literature search was conducted to examine both machine learning and deep learning techniques applied in this field, highlighting key studies and future directions.

EXPERT OPINION

While AI models have shown significant promise, their clinical integration remains limited due to the need for larger, multi-institutional validation studies. As AI continues to evolve, multimodal approaches combining imaging with clinical data are likely to play pivotal role in personalized PCa diagnosis, treatment planning.

Multi-branch CNNFormer: a novel framework for predicting prostate cancer response to hormonal therapy

PURPOSE

This study aims to accurately predict the effects of hormonal therapy on prostate cancer (PC) lesions by integrating multi-modality magnetic resonance imaging (MRI) and the clinical marker prostate-specific antigen (PSA). It addresses the limitations of Convolutional Neural Networks (CNNs) in capturing long-range spatial relations and the Vision Transformer (ViT)'s deficiency in localization information due to consecutive downsampling. The research question focuses on improving PC response prediction accuracy by combining both approaches.

METHODS

We propose a 3D multi-branch CNN Transformer (CNNFormer) model, integrating 3D CNN and 3D ViT. Each branch of the model utilizes a 3D CNN to encode volumetric images into high-level feature representations, preserving detailed localization, while the 3D ViT extracts global salient features. The framework was evaluated on a 39-individual patient cohort, stratified by PSA biomarker status.

RESULTS

Our framework achieved remarkable performance in differentiating responders and non-responders to hormonal therapy, with an accuracy of 97.50%, sensitivity of 100%, and specificity of 95.83%. These results demonstrate the effectiveness of the CNNFormer model, despite the cohort's small size.

CONCLUSION

The findings emphasize the framework's potential in enhancing personalized PC treatment planning and monitoring. By combining the strengths of CNN and ViT, the proposed approach offers robust, accurate prediction of PC response to hormonal therapy, with implications for improving clinical decision-making.

Using Machine Learning to Select Breast Implant Volume

BACKGROUND

In breast augmentation surgery, selection of the appropriate breast implant size is a crucial step that can greatly affect patient satisfaction and the outcome of the procedure. However, this decision is often based on the subjective judgment of the surgeon and the patient, which can lead to suboptimal results. The authors aimed to develop a machine-learning approach that can accurately predict the size of breast implants selected for breast augmentation surgery.

METHODS

The authors collected data on patient demographic characteristics, medical history, and surgeon preferences from a sample of 1000 consecutive patients who underwent breast augmentation. This information was used to train and test a supervised machine-learning model to predict the size of breast implant needed.

RESULTS

The study demonstrated the effectiveness of the algorithm in predicting breast implant size, achieving a Pearson correlation coefficient of 0.9335 ( P < 0.001). The model generated accurate predictions in 86% of instances, with a mean absolute error of 27.10 mL. Its effectiveness was confirmed in the reoperation group, in which 36 of 57 patients (63%) would have received a more suitable implant size if the model's suggestion had been followed, potentially avoiding reoperation.

CONCLUSIONS

The findings show that machine learning can accurately predict the needed size of breast implants in augmentation surgery. By integrating the artificial intelligence model into a decision support system for breast augmentation surgery, essential guidance can be provided to surgeons and patients. This approach not only streamlines the implant selection process but also facilitates enhanced communication and decision-making, ultimately leading to more reliable outcomes and improved patient satisfaction.

Radiogenomic analysis of ultrasound phenotypic features coupled to proteomes predicts metastatic risk in primary prostate cancer

BACKGROUND

Primary prostate cancer with metastasis has a poor prognosis, so assessing its risk of metastasis is essential.

METHODS

This study combined comprehensive ultrasound features with tissue proteomic analysis to obtain biomarkers and practical diagnostic image features that signify prostate cancer metastasis.

RESULTS

In this study, 17 ultrasound image features of benign prostatic hyperplasia (BPH), primary prostate cancer without metastasis (PPCWOM), and primary prostate cancer with metastasis (PPCWM) were comprehensively analyzed and combined with the corresponding tissue proteome data to perform weighted gene co-expression network analysis (WGCNA), which resulted in two modules highly correlated with the ultrasound phenotype. We screened proteins with temporal expression trends based on the progression of the disease from BPH to PPCWOM and ultimately to PPCWM from two modules and obtained a protein that can promote prostate cancer metastasis. Subsequently, four ultrasound image features significantly associated with the metastatic biomarker HNRNPC (Heterogeneous nuclear ribonucleoprotein C) were identified by analyzing the correlation between the protein and ultrasound image features. The biomarker HNRNPC showed a significant difference in the five-year survival rate of prostate cancer patients (p < 0.0053). On the other hand, we validated the diagnostic efficiency of the four ultrasound image features in clinical data from 112 patients with PPCWOM and 150 patients with PPCWM, obtaining a combined diagnostic AUC of 0.904. In summary, using ultrasound imaging features for predicting whether prostate cancer is metastatic has many applications.

CONCLUSION

The above study reveals noninvasive ultrasound image biomarkers and their underlying biological significance, which provide a basis for early diagnosis, treatment, and prognosis of primary prostate cancer with metastasis.

Online COVID-19 diagnosis prediction using complete blood count: an innovative tool for public health

BACKGROUND

COVID-19, caused by SARS-CoV-2, presents distinct diagnostic challenges due to its wide range of clinical manifestations and the overlapping symptoms with other common respiratory diseases. This study focuses on addressing these difficulties by employing machine learning (ML) methodologies, particularly the XGBoost algorithm, to utilize Complete Blood Count (CBC) parameters for predictive analysis.

METHODS

We performed a retrospective study involving 2114 COVID-19 patients treated between December 2022 and January 2023 at our healthcare facility. These patients were classified into fever (1057 patients) and pneumonia groups (1057 patients), based on their clinical symptoms. The CBC data were utilized to create predictive models, with model performance evaluated through metrics like Area Under the Receiver Operating Characteristics Curve (AUC), accuracy, sensitivity, specificity, and precision. We selected the top 10 predictive variables based on their significance in disease prediction. The data were then split into a training set (70% of patients) and a validation set (30% of patients) for model validation.

RESULTS

We identified 31 indicators with significant disparities. The XGBoost model outperformed others, with an AUC of 0.920 and high precision, sensitivity, specificity, and accuracy. The top 10 features (Age, Monocyte%, Mean Platelet Volume, Lymphocyte%, SIRI, Eosinophil count, Platelet count, Hemoglobin, Platelet Distribution Width, and Neutrophil count.) were crucial in constructing a more precise predictive model. The model demonstrated strong performance on both training (AUC = 0.977) and validation (AUC = 0.912) datasets, validated by decision curve analysis and calibration curve.

CONCLUSION

ML models that incorporate CBC parameters offer an innovative and effective tool for data analysis in COVID-19. They potentially enhance diagnostic accuracy and the efficacy of therapeutic interventions, ultimately contributing to a reduction in the mortality rate of this infectious disease.