Artificial Intelligence for Ovarian Cancer Detection with Medical Images: A Review of the Last Decade (2013–2023)

Archives of Computational Methods in Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: March 17, 2025

Language: Английский

---

Explainable AI-based feature importance analysis for ovarian cancer classification with ensemble methods

Frontiers in Public Health, Journal Year: 2025, Volume and Issue: 13

Published: March 26, 2025

Introduction Ovarian Cancer (OC) is one of the leading causes cancer deaths among women. Despite recent advances in medical field, such as surgery, chemotherapy, and radiotherapy interventions, there are only marginal improvements diagnosis OC using clinical parameters, symptoms very non-specific at early stage. Owing to computational algorithms, ensemble machine learning, it now possible identify complex patterns parameters. However, these do not provide deeper insights into prediction diagnosis. Explainable artificial intelligence (XAI) models, LIME SHAP Kernels, can decision-making process thus increasing their applicability. Methods The main aim this study design a computer-aided diagnostic system that accurately classifies detects ovarian cancer. To achieve objective, three-stage model game-theoretic approach based on values were built evaluate visualize results, analyzing important features responsible for prediction. Results Discussion results demonstrate efficacy proposed with an accuracy 98.66%. model’s consistency advantages compared single classifiers. validated conventional statistical methods p -test Cohen’s d highlight method. further validate ranking features, we -values top five bottom features. AI-based method detection, diagnosis, prognosis multi-modal real-life data, which mimics move clinician demonstration high performance. strategy lead reliable, accurate, consistent AI solutions detection management higher patient experience outcomes low cost, morbidity, mortality. This be beneficial millions women living resource-constrained challenging economies.

Language: Английский

---

Improving Ovarian Cancer Subtyping with Computer Vision Models on Tiled Histopathological Images

Deleted Journal, Journal Year: 2025, Volume and Issue: unknown

Published: May 20, 2025

Ovarian cancer remains one of the most challenging cancers to diagnose due its non-specific symptoms, lack reliable screening tests, and complexity detecting abnormalities. Accurate subtype classification is crucial for personalised treatment improved patient outcomes. In this study, we developed a machine learning pipeline fine-tuning pre-trained computer vision models classify ovarian subtypes from whole slide images (WSI). Using targeted tissue masks necrosis, stroma, tumour regions as proof concept, demonstrated efficacy tiling masked transform complex detection-then-classification problem into simpler task. Our method achieved high accuracy in tile-level classification, with subsequent extension via majority voting on tiled images. Precision exceeds 90% across subtypes, which highlights potential scalable, automated systems assist diagnostics. These findings contribute broader field computational pathology, paving way enhanced diagnostic consistency accessibility clinical settings.

Language: Английский

---

A deep learning approach for ovarian cancer detection and classification based on fuzzy deep learning

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Nov. 2, 2024

Different oncologists make their own decisions about the detection and classification of type ovarian cancer from histopathological whole slide images. However, it is necessary to have an automated system that more accurate standardized for decision-making, which essential early cancer. To help doctors, proposed. This model starts by extracting main features histopathology images based on ResNet-50 detect classify Then, recursive feature elimination a decision tree introduced remove unnecessary extracted during extraction process. Adam optimizers were implemented optimize network's weights training data. Finally, advantages combining deep learning fuzzy logic are combined The dataset consists 288 hematoxylin eosin (H&E) stained slides with clinical information 78 patients. H&E-stained Whole Slide Images (WSIs), including 162 effective 126 invalid WSIs obtained different tissue blocks post-treatment specimens. Experimental results can diagnose potential accuracy 98.99%, sensitivity 99%, specificity 98.96%, F1-score 98.99%. show promising indicating using deep-learning classifiers predicting

Language: Английский

---

Optimizing Deep Learning Models for Ovarian Cancer Subtype Classification: A Systematic Evaluation of Architectures and Data Augmentation Strategies

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: May 7, 2025

Ovarian cancer is a leading cause of cancer-related mortality among women, and accurate classification its subtypes critical for effective treatment planning. This study systematically investigates the impact different network architectures data augmentation strategies on ovarian subtype classification. We evaluate two baseline models (VGG ViT) propose an efficient hybrid model that integrates convolutional self-attention mechanisms to balance local feature extraction global context modeling. Furthermore, we conduct comprehensive assessment various techniques, including geometric, color, spatial transformations, determine their effects generalization. Additionally, compare pre-trained non-pre-trained analyze benefits transfer learning in this domain. To enhance interpretability, utilize Grad-CAM visualizations examine decision-making processes models. Our findings reveal while ViT exhibits superior generalization capabilities with pre-training, VGG remains competitive even without pre-training due strong inductive biases. Among tested strategies, geometric transformations significantly improve performance, whereas color-based augmentations show limited or degrade performance. The proposed achieves comparable accuracy maintaining smaller parameter scale faster training efficiency. In conclusion, provides key insights into selection techniques pathological image design framework offers interpretable approach classification, potential applications broader medical imaging tasks.

Language: Английский

---

Transforming women's health, empowerment, and gender equality with digital health: evidence-based policy and practice

The Lancet Digital Health, Journal Year: 2025, Volume and Issue: unknown

Published: May 1, 2025

Language: Английский

---

Improved Prediction of Ovarian Cancer Using Ensemble Classifier and Shaply Explainable AI

Cancers, Journal Year: 2023, Volume and Issue: 15(24), P. 5793 - 5793

Published: Dec. 11, 2023

The importance of detecting and preventing ovarian cancer is utmost significance for women's overall health wellness. Referred to as the "silent killer," exhibits inconspicuous symptoms during its initial phases, posing a challenge timely identification. Identification advanced stages significantly diminishes likelihood effective treatment survival. Regular screenings, such pelvic exams, ultrasound, blood tests specific biomarkers, are essential tools disease in early, more treatable stages. This research makes use Soochow University dataset, containing 50 features accurate detection cancer. proposed predictive model stacked ensemble model, merging strengths bagging boosting classifiers, aims enhance accuracy reliability. combination harnesses benefits variance reduction improved generalization, contributing superior prediction outcomes. gives 96.87% accuracy, which currently highest result obtained on this dataset so far using all features. Moreover, outcomes elucidated utilizing explainable artificial intelligence method referred SHAPly. excellence suggested demonstrated through comparison performance with that other cutting-edge models.

Language: Английский

---

Preoperative Molecular Subtype Classification Prediction of Ovarian Cancer Based on Multi-Parametric Magnetic Resonance Imaging Multi-Sequence Feature Fusion Network

Bioengineering, Journal Year: 2024, Volume and Issue: 11(5), P. 472 - 472

Published: May 9, 2024

In the study of deep learning classification medical images, models are applied to analyze aiming achieve goals assisting diagnosis and preoperative assessment. Currently, most research classifies predicts normal cancer cells by inputting single-parameter images into trained models. However, for ovarian (OC), identifying its different subtypes is crucial predicting disease prognosis. particular, need distinguish high-grade serous carcinoma from clear cell preoperatively through non-invasive means has not been fully addressed. This proposes a (DL) method based on fusion multi-parametric magnetic resonance imaging (mpMRI) data, aimed at improving accuracy subtype classification. By constructing new network architecture that integrates various sequence features, this achieves high-precision prediction typing carcinoma, achieving an AUC 91.62% AP 95.13% in subtypes.

Language: Английский

---

Deep fine-KNN classification of ovarian cancer subtypes using efficientNet-B0 extracted features: a comprehensive analysis

Journal of Cancer Research and Clinical Oncology, Journal Year: 2024, Volume and Issue: 150(7)

Published: July 25, 2024

This study presents a robust approach for the classification of ovarian cancer subtypes through integration deep learning and k-nearest neighbor (KNN) methods. The proposed model leverages powerful feature extraction capabilities EfficientNet-B0, utilizing its features subsequent fine-grained using fine-KNN approach. UBC-OCEAN dataset, encompassing histopathological images five distinct subtypes, namely, high-grade serous carcinoma (HGSC), clear-cell (CC), endometrioid (EC), low-grade (LGSC), mucinous (MC), served as foundation our investigation. With dataset comprising 725 images, divided into 80% training 20% testing, exhibits exceptional performance. Both validation testing phases achieved 100% accuracy, underscoring efficacy methodology. In addition, area under curve (AUC), key metric evaluating model's discriminative ability, demonstrated high performance across various with AUC values 0.94, 0.78, 0.69, 0.92, 0.94 MC. Furthermore, positive likelihood ratios (LR

Language: Английский

---

Enhanced ovarian cancer survival prediction using temporal analysis and graph neural networks

BMC Medical Informatics and Decision Making, Journal Year: 2024, Volume and Issue: 24(1)

Published: Oct. 10, 2024

Ovarian cancer is a formidable health challenge that demands accurate and timely survival predictions to guide clinical interventions. Existing methods, while commendable, suffer from limitations in harnessing the temporal evolution of patient data capturing intricate interdependencies among different elements. In this paper, we present novel methodology which combines Temporal Analysis Graph Neural Networks (GNNs) significantly enhance ovarian rate predictions. The shortcomings current processes originate their disability correctly seize complex interactions amongst diverse scientific information units addition dynamic modifications arise affected person`s nation over time. By combining evaluation GNNs, our cautioned approach overcomes those drawbacks and, whilst as compared preceding yields noteworthy 8.3% benefit precision, 4.9% more accuracy, 5.5% advantageous recall, considerable 2.9% reduction prediction latency. Our method's factor uses longitudinal person perceive good-sized styles tendencies offer precious insights into direction cancer. Through combination robust framework able shoot complicated exclusive capabilities data, permitting version realize diffused dependencies would affect results. paintings have tremendous implications for practice. Prompt correct estimation price most cancers allows experts customize remedy regimens, manipulate assets efficiently, provide individualized care patients. Additionally, interpretability version`s promotes collaborative method via way means strengthening agreement employees AI-driven selection help system. proposed not only outperforms existing methods but also has possible develop treatment by providing clinicians through reliable tool informed decision-making. fusion Networks, conduit gap data-driven practice, proposing capable opportunity refining outcomes management operations.

Language: Английский

---