Decoding the black box: Explainable AI (XAI) for cancer diagnosis, prognosis, and treatment planning-A state-of-the art systematic review

International Journal of Medical Informatics, Journal Year: 2024, Volume and Issue: 193, P. 105689 - 105689

Published: Nov. 4, 2024

Language: Английский

---

An amalgamation of deep neural networks optimized with Salp swarm algorithm for cervical cancer detection

Computers & Electrical Engineering, Journal Year: 2025, Volume and Issue: 123, P. 110106 - 110106

Published: Jan. 28, 2025

Language: Английский

---

Brain tumor detection and classification in MRI using hybrid ViT and GRU model with explainable AI in Southern Bangladesh

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

Published: Oct. 1, 2024

Language: Английский

---

Convolutional Block Attention Module and Parallel Branch Architectures for Cervical Cell Classification

International Journal of Imaging Systems and Technology, Journal Year: 2025, Volume and Issue: 35(2)

Published: Feb. 18, 2025

ABSTRACT Cervical cancer persists as a significant global health concern, underscoring the vital importance of early detection for effective treatment and enhanced patient outcomes. While traditional Pap smear tests remain an invaluable diagnostic tool, they are inherently time‐consuming susceptible to human error. This study introduces innovative approach that employs convolutional neural networks (CNN) enhance accuracy efficiency cervical cell classification. The proposed model incorporates Convolutional Block Attention Module (CBAM) parallel branch architectures, which facilitate feature extraction by focusing on crucial spatial channel information. process entails identification utilization most pertinent elements within image purpose was meticulously assessed SIPaKMeD dataset, attaining exceptional degree (92.82%), surpassed performance CNN models. incorporation sophisticated attention mechanisms enables not only accurately classify images but also interpretability emphasizing regions images. highlights transformative potential cutting‐edge deep learning techniques in medical analysis, particularly screening, providing powerful tool support pathologists accurate diagnosis. Future work will explore additional extend application this architecture other imaging tasks, further enhancing its clinical utility impact

Language: Английский

---

Diagnosis of Cervical Cancer Based on a Hybrid Strategy with CTGAN

Electronics, Journal Year: 2025, Volume and Issue: 14(6), P. 1140 - 1140

Published: March 14, 2025

Cervical cancer remains a significant global public health challenge, particularly in low- and middle-income countries where invasive diagnostic methods are underutilized due to limited medical resources. Machine learning has provided new pathway address this but existing machine prediction face three major challenges: feature redundancy, class imbalance, sample scarcity. To these issues, study proposes hybrid data processing strategy with Conditional Tabular Generative Adversarial Networks (CTGAN) construct more accurate efficient auxiliary model for cervical cancer. The first employs the Minimal Redundancy Maximal Relevance (mRMR) algorithm XGBoost-based Recursive Feature Elimination (RFE) secondary screening. Subsequently, SMOTE-ENN combination sampling method is applied handle extreme CTGAN utilized augment dataset, thereby mitigating Experimental validation on Risk Factors of Cancer (RFCC) dataset from Venezuelan hospital demonstrates that, after proposed strategy, Logistic Regression (LR) achieves best overall results, accuracy, precision, recall, F1-score reaching 99.00%, 99.28%, 98.77%, 99.02%, respectively, outperforming methods.

Language: Английский

---

Interpretable artificial intelligence (AI) for cervical cancer risk analysis leveraging stacking ensemble and expert knowledge

Digital Health, Journal Year: 2025, Volume and Issue: 11

Published: March 1, 2025

Objectives This study develops a machine learning (ML)-based cervical cancer prediction system emphasizing explainability. A hybrid feature selection method is proposed to enhance predictive accuracy and stability, alongside evaluation of multiple classification algorithms. The integration explainable artificial intelligence (XAI) techniques ensures transparency interpretability in model decisions. Methods approach combining correlation-based recursive elimination introduced. An ensemble integrating random forest, extreme gradient boosting, logistic regression compared against eight classical ML Generative methods, such as variational autoencoders generative teaching networks, were evaluated but showed suboptimal performance. research integrates global local XAI techniques, including individual contributions tree-based explanations, interpret effects data balancing on performance are examined stabilize precision, recall, F1 scores. Classical models without preprocessing achieve 95-96% exhibit instability. Results strategies significantly creating robust model. achieves 98% with an area under the curve 99.50%, outperforming other models. Domain experts validate critical contributing features, confirming practical relevance. Incorporating domain knowledge increases transparency, making predictions interpretable trustworthy for clinical use. Conclusion Hybrid combined substantially improves reliability. supporting trustworthiness, demonstrating significant potential decision-making.

Language: Английский

---

A hybrid learning network with progressive resizing and PCA for diagnosis of cervical cancer on WSI slides

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 14, 2025

Language: Английский

---

Navigating Explainable Ai in Healthcare: A Taxonomic Guide for Clinical Decision Support Systems

Published: Jan. 1, 2025

Language: Английский

---

A precise machine learning model: Detecting cervical cancer using feature selection and explainable AI

Journal of Pathology Informatics, Journal Year: 2024, Volume and Issue: 15, P. 100398 - 100398

Published: Sept. 27, 2024

Language: Английский

---

An Electrocardiogram Signal Classification Using a Hybrid Machine Learning and Deep Learning Approach

Healthcare Analytics, Journal Year: 2024, Volume and Issue: 6, P. 100366 - 100366

Published: Oct. 9, 2024

Language: Английский

---