Artificial intelligence-based risk stratification, accurate diagnosis and treatment prediction in gynecologic oncology

Multi-model quantitative MRI of uterine cancers in precision medicine's era-a narrative review

PURPOSE

This review aims to summarize the current applications of quantitative MRI biomarkers in the staging, treatment response evaluation, and prognostication of endometrial (EC) and cervical cancer (CC). By focusing on functional imaging techniques, we explore how these biomarkers enhance personalized cancer management beyond traditional morphological assessments.

METHODS

A structured search of the PubMed database from January to May 2024 was conducted to identify relevant studies on quantitative MRI in uterine cancers. We included studies examining MRI biomarkers like Dynamic Contrast-Enhanced MRI (DCE-MRI), Diffusion-Weighted Imaging (DWI), and Magnetic Resonance Spectroscopy (MRS), emphasizing their roles in assessing tumor physiology, microstructure, and metabolic changes.

RESULTS

DCE-MRI provides valuable quantitative biomarkers such as Ktrans and Ve, which reflect microvascular characteristics and tumor aggressiveness, outperforming T2-weighted imaging in detecting critical factors like myometrial and cervical invasion. DWI, including advanced models like Intravoxel Incoherent Motion (IVIM), distinguishes between normal and cancerous tissue and correlates with tumor grade and treatment response. MRS identifies metabolic alterations, such as elevated choline and lipid signals, which serve as prognostic markers in uterine cancers.

CONCLUSION

Quantitative MRI offers a noninvasive method to assess key biomarkers that inform prognosis and guide treatment decisions in uterine cancers. By providing insights into tumor biology, these imaging techniques represent a significant step forward in the precision medicine era, allowing for a more tailored therapeutic approach based on the unique pathological and molecular characteristics of each tumor.

CRITICAL RELEVANCE STATEMENT

Biomarkers obtained from MRI can provide useful quantitative information about the nature of uterine cancers and their prognosis, both at diagnosis and response assessment, allowing better therapeutic strategies to be prepared.

KEY POINTS

Quantitative MRI improves diagnosis and management of uterine cancers through advanced imaging biomarkers. Quantitative MRI biomarkers enhance staging, prognosis, and treatment response assessment in uterine cancers. Quantitative MRI biomarkers support personalized treatment strategies and improve patient management in uterine cancers.

Ovarian Cancer Detection in Ascites Cytology with Weakly Supervised Model on Nationwide Dataset

Conventional ascitic fluid cytology for detecting ovarian cancer is limited by its low sensitivity. To address this issue, this multicenter study developed patch image (PI)-based fully supervised convolutional neural network (CNN) models and clustering-constrained attention multiple-instance learning (CLAM) algorithms for detecting ovarian cancer using ascitic fluid cytology. Whole-slide images (WSIs), 356 benign and 147 cancer, were collected, from which 14,699 benign and 8025 cancer PIs were extracted. Additionally, 131 WSIs (44 benign and 87 cancer) were used for external validation. Six CNN algorithms were developed for cancer detection using PIs. Subsequently, two CLAM algorithms, single branch (CLAM-SB) and multiple branch (CLAM-MB), were developed. ResNet50 demonstrated the best performance, achieving an accuracy of 0.973. The performance when interpreting internal WSIs was an area under the curve (AUC) of 0.982. CLAM-SB outperformed CLAM-MB with an AUC of 0.944 in internal WSIs. Notably, in the external test, CLAM-SB exhibited superior performance with an AUC of 0.866 compared with ResNet50's AUC of 0.804. Analysis of the heatmap revealed that cases frequently misinterpreted by AI were easily interpreted by humans, and vice versa. Because AI and humans were found to function complementarily, implementing computer-aided diagnosis is expected to significantly enhance diagnostic accuracy and reproducibility. Furthermore, the WSI-based learning in CLAM, eliminating the need for patch-by-patch annotation, offers an advantage over the CNN model.

Artificial intelligence in the diagnosis and management of gynecologic cancer

Gynecologic cancers affect over 1.2 million women globally each year. Early diagnosis and effective treatment are essential for improving patient outcomes, yet traditional diagnostic methods often encounter limitations, particularly in low-resource settings. Artificial intelligence (AI) has emerged as a transformative tool that enhances accuracy and efficiency across various aspects of gynecologic oncology, including screening, diagnosis, and treatment. This review examines the current applications of AI in gynecologic cancer care, focusing on areas such as early detection, imaging, personalized treatment planning, and patient monitoring. Based on an analysis of 75 peer-reviewed articles published between 2017 and 2024, we highlight AI's contributions to cervical, ovarian, and endometrial cancer management. AI has notably improved early detection, achieving up to 95% accuracy in cervical cancer screening through AI-enhanced Pap smear analysis and colposcopy. For ovarian and endometrial cancers, AI-driven imaging and biomarker detection have enabled more personalized treatment approaches. In addition, AI tools have enhanced precision in robotic-assisted surgery and radiotherapy, and AI-based histopathology has reduced diagnostic variability. Despite these advancements, challenges such as data privacy, bias, and the need for human oversight must be addressed. The successful integration of AI into clinical practice will require careful consideration of ethical issues and a balanced approach that incorporates human expertise. Overall, AI presents significant potential to improve outcomes in gynecologic oncology, particularly in bridging healthcare gaps in resource-limited settings.

Empowering cancer prevention with AI: unlocking new frontiers in prediction, diagnosis, and intervention

Artificial intelligence is rapidly changing our world at an exponential rate and its transformative power has extensively reached important sectors like healthcare. In the fight against cancer, AI proved to be a novel and powerful tool, offering new hope for prevention and early detection. In this review, we will comprehensively explore the medical applications of AI, including early cancer detection through pathological and imaging analysis, risk stratification, patient triage, and the development of personalized prevention approaches. However, despite the successful impact AI has contributed to, we will also discuss the myriad of challenges that we have faced so far toward optimal AI implementation. There are problems when it comes to the best way in which we can use AI systemically. Having the correct data that can be understood easily must remain one of the most significant concerns in all its uses including sharing information. Another challenge that exists is how to interpret AI models because they are too complicated for people to follow through examples used in their developments which may affect trust, especially among medical professionals. Other considerations like data privacy, algorithm bias, and equitable access to AI tools have also arisen. Finally, we will evaluate possible future directions for this promising field that highlight AI's capacity to transform preventative cancer care.

Potential value of novel multiparametric MRI radiomics for preoperative prediction of microsatellite instability and Ki-67 expression in endometrial cancer

Exploring the potential of advanced artificial intelligence technology in predicting microsatellite instability (MSI) and Ki-67 expression of endometrial cancer (EC) is highly significant. This study aimed to develop a novel hybrid radiomics approach integrating multiparametric magnetic resonance imaging (MRI), deep learning, and multichannel image analysis for predicting MSI and Ki-67 status. A retrospective study included 156 EC patients who were subsequently categorized into MSI and Ki-67 groups. The hybrid radiomics model (HMRadSum) was developed by extracting quantitative imaging features and deep learning features from multiparametric MRI using emerging attention mechanism. Tumor markers were subsequently predicted utilizing an XGBoost classifier. Model performance and interpretability were evaluated using standard classification metrics, Gradient-weighted Class Activation Mapping (Grad-CAM), and SHapley Additive exPlanations (SHAP) techniques. For the MSI prediction task, the HMRadSum model achieved area-under-curve (AUC) value of 0.945 (95% CI 0.862-1.000) and accuracy of 0.889. For the Ki-67 prediction task, the AUC and accuracy of HMRadSum model was 0.888 (95% CI 0.743-1.000) and 0.810. This hybrid radiomics model effectively extracted features associated with EC gene expression, providing potential clinical implications for personalized diagnosis, treatment, and treatment strategy optimization.

Evolution of artificial intelligence in healthcare: a 30-year bibliometric study

Introduction

In recent years, the development of artificial intelligence (AI) technologies, including machine learning, deep learning, and large language models, has significantly supported clinical work. Concurrently, the integration of artificial intelligence with the medical field has garnered increasing attention from medical experts. This study undertakes a dynamic and longitudinal bibliometric analysis of AI publications within the healthcare sector over the past three decades to investigate the current status and trends of the fusion between medicine and artificial intelligence.

Methods

Following a search on the Web of Science, researchers retrieved all reviews and original articles concerning artificial intelligence in healthcare published between January 1993 and December 2023. The analysis employed Bibliometrix, Biblioshiny, and Microsoft Excel, incorporating the bibliometrix R package for data mining and analysis, and visualized the observed trends in bibliometrics.

Results

A total of 22,950 documents were collected in this study. From 1993 to 2023, there was a discernible upward trajectory in scientific output within bibliometrics. The United States and China emerged as primary contributors to medical artificial intelligence research, with Harvard University leading in publication volume among institutions. Notably, the rapid expansion of emerging topics such as COVID-19 and new drug discovery in recent years is noteworthy. Furthermore, the top five most cited papers in 2023 were all pertinent to the theme of ChatGPT.

Conclusion

This study reveals a sustained explosive growth trend in AI technologies within the healthcare sector in recent years, with increasingly profound applications in medicine. Additionally, medical artificial intelligence research is dynamically evolving with the advent of new technologies. Moving forward, concerted efforts to bolster international collaboration and enhance comprehension and utilization of AI technologies are imperative for fostering novel innovations in healthcare.

Mitophagy in gynecological malignancies: roles, advances, and therapeutic potential

Mitophagy is a process in which impaired or dysfunctional mitochondria are selectively eliminated through the autophagy mechanism to maintain mitochondrial quality control and cellular homeostasis. Based on specific target signals, several mitophagy processes have been identified. Defects in mitophagy are associated with various pathological conditions, including neurodegenerative disorders, cardiovascular diseases, metabolic diseases, and cancer. Mitophagy has been shown to play a critical role in the pathogenesis of gynecological malignancies and the development of drug resistance. In this review, we have summarized and discussed the role and recent advances in understanding the therapeutic potential of mitophagy in the development of gynecological malignancies. Therefore, the valuable insights provided in this review may serve as a basis for further studies that contribute to the development of novel treatment strategies and improved patient outcomes.

Lymph node assessment in cervical cancer: current approaches

Cervical cancer (CC) is the fourth most common neoplasia in women worldwide. Although early-stage CC is often curable, 40 to 50% of patients are diagnosed at a locally advanced stage. Metastatic disease accounts for the principal cause of death. Lymph node (LN) status is a major factor impacting treatment options and prognosis. Historically, CC was staged based only on clinical findings. However, in 2018, imaging modalities and/or pathological findings were included in the International Federation of Gynecology and Obstetrics (FIGO) staging classification. In the last decades, LN status assessment has evolved considerably. Full pelvic lymphadenectomy used to be the only way to determine LN status. Currently, several options exist: surgery with full lymphadenectomy, sentinel lymph node (SLN) biopsy or imaging modalities such as computed tomography (CT), magnetic resonance imaging (MRI) and positron emission tomography (PET). Regarding surgery, the SLN biopsy technique has become a standard procedure in cases of CC, with indocyanine green (ICG) being the preferred dye. Pelvic MRI is a valuable imaging technique modality for the evaluation of pelvic LNs. In locally advanced or in early-stage disease with suspicious LNs on CT scans or MRI, PET/CT is recommended for assessment of nodal and distant status. The best strategy for LN assessment remains a highly controversial topic in the literature. In this article, we aim to review and compare the advantages and limitations of each modality, i.e. imaging or surgical (lymphadenectomy or SLN biopsy) approaches.

Machine-learning diagnostic models for ovarian tumors

Purpose

To create a diagnostic framework for clinical behavior and pathological tissue prognosis in ovarian cancer by using machine-learning (ML) methods based on multiple biomarkers.

Experimental design

Overall, 713 patients with ovarian tumors at Sun Yat Sen Memorial Hospital were randomized into training and test cohorts. Four supervised ML classifiers, namely Support Vector Machine, Random Forest, k-nearest neighbor, and logistic regression were used to derive diagnostic and prognostic information from 10 parameters commonly available from pretreatment peripheral blood tests and age. The best prediction model was selected and validated by comparing the accuracy and the area under the ROC curve of each prediction model and by applying the external data of Guangdong Maternal and Child Health Center.

Results

ML techniques were superior to conventional regression-based analyses in predicting multiple clinical parameters pertaining to ovarian tumor. Ensemble methods combining weak decision trees and RF showed the best reference in diagnosis, especially for malignant ovarian cancer. The values for the highest accuracy and area under the ROC curve for malignant ovarian cancer from benign or borderline ovarian tumors with RF were 99.82 % and 0.86 (micro-average ROC curve), respectively. The greatest accuracy and AUC for the diagnosis of pathological tissue with logistic regression curve were 78.0 % and 0.95 (micro-average ROC curve), respectively. In external validation, the random forest prediction model had an accuracy of 0.789 for applying data from external centers to verify tumor benignity and malignancy, and the logistic regression model had an accuracy of 0.719 for predicting the nature of the tumor.

Conclusions

An ovarian tumor can be diagnosed and characterized before initial treatment via ML systems to provide critical diagnostic and prognostic information. The use of predictive algorithms can facilitate customized treatment options with patient preprocessing stratification.

Global burden of gynaecological cancers in 2022 and projections to 2050

Background

The incidence and mortality of gynaecological cancers can significantly impact women's quality of life and increase the health care burden for organisations globally. The objective of this study was to evaluate global inequalities in the incidence and mortality of gynaecological cancers in 2022, based on The Global Cancer Observatory (GLOBOCAN) 2022 estimates. The future burden of gynaecological cancers (GCs) in 2050 was also projected.

Methods

Data regarding to the total cases and deaths related to gynaecological cancer, as well as cases and deaths pertaining to different subtypes of GCs, gathered from the GLOBOCAN database for the year 2022. Predictions for the number of cases and deaths in the year 2050 were derived from global demographic projections, categorised by world region and Human Development Index (HDI).

Results

In 2022, there were 1 473 427 new cases of GCs and 680 372 deaths. The incidence of gynecological cancer reached 30.3 per 100 000, and the mortality rate hit 13.2 per 100 000. The age-standardised incidence of GCs in Eastern Africa is higher than 50 per 100 000, whereas the age-standardised incidence in Northern Africa is 17.1 per 100 000. The highest mortality rates were found in East Africa (ASMR (age-standardised mortality rates) of 35.3 per 100 000) and the lowest in Australia and New Zealand (ASMR of 8.1 per 100 000). These are related to the endemic areas of HIV and HPV. Very High HDI countries had the highest incidence of GCs, with ASIR (age-standardised incidence rates) of 34.8 per 100 000, and low HDI countries had the second highest incidence rate, with an ASIR of 33.0 per 100 000. Eswatini had the highest incidence and mortality (105.4 per 100 000; 71.1 per 100 000) and Yemen the lowest (5.8 per 100 000; 4.4 per 100 000). If the current trends in morbidity and mortality are maintained, number of new cases and deaths from female reproductive tract tumours is projected to increase over the next two decades.

Conclusions

In 2022, gynaecological cancers accounted for 1 473 427 new cases and 680 372 deaths globally, with significant regional disparities in incidence and mortality rates. The highest rates were observed in Eastern Africa and countries with very high and low HDI, with Eswatini recording the most severe statistics. If current trends continue, the number of new cases and deaths from gynaecological cancers is expected to rise over the next two decades, highlighting the urgent need for effective interventions.

Screening and Early Diagnosis in Gynecological Cancers

Cervical (CC), endometrial (EC), and ovarian (OC) cancers are the pathologies with the highest incidences among gynecological tumors, with such high morbidity and mortality values that they are considered significant public health problems [...].