QUANTIFYING EXPLAINABLE AI METHODS IN MEDICAL DIAGNOSIS: A STUDY IN SKIN CANCER DOI Creative Commons

Hardik Sangwan

medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Дек. 10, 2024

Abstract Deep learning models have shown substantial promise in assisting medical diagnosis, offering the potential to improve patient outcomes and reduce clinician workloads. However, widespread adoption of these clinical practice has been hindered by concerns surrounding their trustworthiness, transparency, interpretability. Addressing challenges requires not only development explainable AI (xAI) techniques but also quantitative metrics evaluate effectiveness. This study presents a comprehensive framework for training, explaining, quantitatively assessing deep skin cancer diagnosis. Leveraging HAM10000 dataset seven diagnostic lesion categories, multiple convolutional neural network architectures—including custom CNNs, DenseNet, MobileNet, ResNet—were trained optimized using augmentation, oversampling, hyperparameter tuning. Following model explainability such as SHAP, LIME, Integrated Gradients were deployed generate post hoc explanations. Critically, primary contribution this work is evaluation explanation methods related faithfulness, robustness, complexity. All code, models, results are publicly available, providing reproducible pathway toward more trustworthy, tools.

Язык: Английский

Medical Image Classifications Using Convolutional Neural Networks: A Survey of Current Methods and Statistical Modeling of the Literature DOI Creative Commons

Foziya Ahmed Mohammed,

Kula Kekeba Tune, Beakal Gizachew Assefa

и другие.

Machine Learning and Knowledge Extraction, Год журнала: 2024, Номер 6(1), С. 699 - 736

Опубликована: Март 21, 2024

In this review, we compiled convolutional neural network (CNN) methods which have the potential to automate manual, costly and error-prone processing of medical images. We attempted provide a thorough survey improved architectures, popular frameworks, activation functions, ensemble techniques, hyperparameter optimizations, performance metrics, relevant datasets data preprocessing strategies that can be used design robust CNN models. also machine learning algorithms for statistical modeling current literature uncover latent topics, method gaps, prevalent themes future advancements. The results indicate temporal shift in favor designs, such as from use architecture CNN-transformer hybrid. insights point surge practitioners into imaging field, partly driven by COVID-19 challenge, catalyzed detecting diagnosing pathological conditions. This phenomenon likely contributed sharp increase number publications on CNNs imaging, both during after pandemic. Overall, existing has certain gaps scope with respect optimization architectures specifically imaging. Additionally, there is lack post hoc explainability models slow progress adopting low-resource review ends list open research questions been identified through recommendations potentially help set up more robust, reproducible experiments

Язык: Английский

Процитировано

14
Multi-scale feature fusion of deep convolutional neural networks on cancerous tumor detection and classification using biomedical images DOI Creative Commons
U. M. Prakash, S. Iniyan, Ashit Kumar Dutta

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Янв. 7, 2025

In the present scenario, cancerous tumours are common in humans due to major changes nearby environments. Skin cancer is a considerable disease detected among people. This uncontrolled evolution of atypical skin cells. It occurs when DNA injury cells, or genetic defect, leads an increase quickly and establishes malignant tumors. However, rare instances, many types occur from tempted by infrared light affecting worldwide health problem, so accurate appropriate diagnosis needed for efficient treatment. Current developments medical technology, like smart recognition analysis utilizing machine learning (ML) deep (DL) techniques, have transformed treatment these conditions. These approaches will be highly effective biomedical imaging. study develops Multi-scale Feature Fusion Deep Convolutional Neural Networks on Cancerous Tumor Detection Classification (MFFDCNN-CTDC) model. The main aim MFFDCNN-CTDC model detect classify using To eliminate unwanted noise, method initially utilizes sobel filter (SF) image preprocessing stage. For segmentation process, Unet3+ employed, providing precise localization tumour regions. Next, incorporates multi-scale feature fusion combining ResNet50 EfficientNet architectures, capitalizing their complementary strengths extraction varying depths scales input images. convolutional autoencoder (CAE) utilized classification method. Finally, parameter tuning process performed through hybrid fireworks whale optimization algorithm (FWWOA) enhance performance CAE A wide range experiments authorize approach. experimental validation approach exhibited superior accuracy value 98.78% 99.02% over existing techniques under ISIC 2017 HAM10000 datasets.

Язык: Английский

Процитировано

2
WCFormer: An interpretable deep learning framework for heart sound signal analysis and automated diagnosis of cardiovascular diseases DOI

Suiyan Wang,

Junhui Hu,

Yanwei Du

и другие.

Expert Systems with Applications, Год журнала: 2025, Номер unknown, С. 127238 - 127238

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

2
Belt Conveyor Idlers Fault Detection Using Acoustic Analysis and Deep Learning Algorithm with the YAMNet Pretrained Network DOI
Fahad Alharbi, Suhuai Luo, Sipei Zhao

и другие.

IEEE Sensors Journal, Год журнала: 2024, Номер 24(19), С. 31379 - 31394

Опубликована: Авг. 16, 2024

Язык: Английский

Процитировано

5
Deep learning‐based magnetic resonance imaging analysis for chronic cerebral hypoperfusion risk DOI Creative Commons
Meiyi Yang,

Lili Yang,

Qi Zhang

и другие.

Medical Physics, Год журнала: 2024, Номер 51(8), С. 5270 - 5282

Опубликована: Май 31, 2024

Abstract Background Chronic cerebral hypoperfusion (CCH) is a frequently encountered clinical condition that poses diagnostic challenge due to its nonspecific symptoms. Purpose To enhance the diagnosis of CCH and non‐CCH through Magnetic Resonance Imaging (MRI), offering support in decision‐making recommendations ultimately elevate accuracy optimize patient treatment outcomes. Methods In retrospective research, we collected 204 routine brain magnetic resonance imaging (MRI) from March 1 September 10 2022, as training testing cohorts. And validation cohort with 108 samples was November 14 2022 August 4 2023. MRI sequences were processed obtain T1‐weighted (T1WI) T2‐weighted (T2WI) sequence images for each patient. We propose CCH‐Network (CCHNet), an end‐to‐end deep learning model, integrating convolution Transformer modules capture local global structural information. Our novel adversarial method improves feature knowledge capture, enhancing both generalization ability efficiency predicting risk. assessed classification performance proposed model CCHNet by comparing it existing state‐of‐the‐art algorithms, including ResNet34, DenseNet121, VGG16, Convnext, ViT, Coat, TransFG. better validate performance, compared results eight neurologists evaluate their consistency. Results achieved AUC 91.6% (95% CI: 86.8–99.1), (ACC) 85.0% 75.6–95.2). It demonstrated sensitivity (SE) 80.0% 71.6–95.6) specificity (SP) 90.0% 82.3–97.8) cohort. cohort, 86.0% 80.3–93.0), ACC 84.2% 70.2–93.6), SE 83.3% 68.3–95.5), SP 84.7% 70.3–96.8). Conclusions The improved high SP, providing promising CCH.

Язык: Английский

Процитировано

4
An Explainable Contrastive-based Dilated Convolutional Network with Transformer for pediatric pneumonia detection DOI
Chandravardhan Singh Raghaw, Parth Shirish Bhore,

Mohammad Zia Ur Rehman

и другие.

Applied Soft Computing, Год журнала: 2024, Номер 167, С. 112258 - 112258

Опубликована: Сен. 19, 2024

Язык: Английский

Процитировано

3
Navigating Uncertainty: A User-Perspective Survey of Trustworthiness of AI in Healthcare DOI Open Access
Jaya Ojha, Oriana Presacan, Pedro G. Lind

и другие.

ACM Transactions on Computing for Healthcare, Год журнала: 2025, Номер unknown

Опубликована: Фев. 4, 2025

This paper offers an extensive survey of one the fundamental aspects trustworthiness Artificial Intelligence (AI) in healthcare, namely uncertainty, focusing on large panoply recent studies addressing connection between AI, and healthcare. The concept uncertainty is a recurring theme across multiple disciplines, with varying focuses approaches. Here, we focus diverse nature medical applications, emphasizing importance quantifying model predictions its advantages specific clinical settings. Questions that emerge this context range from guidelines for AI integration healthcare domain to ethical deliberations their compatibility cutting-edge research. Together description main works context, also discuss that, as medicine evolves introduces novel sources there need more versatile quantification methods be developed collaboratively by researchers professionals. Finally, acknowledge limitations current different facets within domain. In particular, identify relative paucity approaches user’s perception accordingly trustworthiness.

Язык: Английский

Процитировано

0
Revolutionizing biological digital twins: Integrating internet of bio-nano things, convolutional neural networks, and federated learning DOI Creative Commons
Mohammad Jamshidi, Dinh Thai Hoang, Diep N. Nguyen

и другие.

Computers in Biology and Medicine, Год журнала: 2025, Номер 189, С. 109970 - 109970

Опубликована: Март 17, 2025

Язык: Английский

Процитировано

0
A novel hybrid feature fusion approach using handcrafted features with transfer learning model for enhanced skin cancer classification DOI

B Soundarya,

C. Poongodi

Computers in Biology and Medicine, Год журнала: 2025, Номер 190, С. 110104 - 110104

Опубликована: Апрель 2, 2025

Язык: Английский

Процитировано

0
Comparative Study on Adaptable Intelligent Frost Recognition Method for Air-source Heat Pump and Cold Chain Based on Image Texture Features under Complex Lighting Conditions DOI
Yingjie Xu, Hengrui Zhang, Kai Wu

и другие.

International Journal of Refrigeration, Год журнала: 2025, Номер unknown

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0