Explainable AI for Medical Image Analysis: Enhancing Diagnostic Transparency and Clinical Trust

ObjectivePneumothorax is an acute thoracic disease caused by abnormal air collection between the lungs and chest wall. Recently, artificial intelligence (AI), especially deep learning (DL), has been increasingly employed for automating the diagnostic process of pneumothorax. To address the opaqueness often associated with DL models, explainable artificial intelligence (XAI) methods have been introduced to outline regions related to pneumothorax. However, these explanations sometimes diverge from actual lesion areas, highlighting the need for further improvement. MethodWe propose a template-guided approach to incorporate the clinical knowledge of pneumothorax into model explanations generated by XAI methods, thereby enhancing the quality of the explanations. Utilizing one lesion delineation created by radiologists, our approach first generates a template that represents potential areas of pneumothorax occurrence. This template is then superimposed on model explanations to filter out extraneous explanations that fall outside the template’s boundaries. To validate its efficacy, we carried out a comparative analysis of three XAI methods (Saliency Map, Grad-CAM, and Integrated Gradients) with and without our template guidance when explaining two DL models (VGG-19 and ResNet-50) in two real-world datasets (SIIM-ACR and ChestX-Det). ResultsThe proposed approach consistently improved baseline XAI methods across twelve benchmark scenarios built on three XAI methods, two DL models, and two datasets. The average incremental percentages, calculated by the performance improvements over the baseline performance, were 97.8% in Intersection over Union (IoU) and 94.1% in Dice Similarity Coefficient (DSC) when comparing model explanations and ground-truth lesion areas. We further visualized baseline and template-guided model explanations on radiographs to showcase the performance of our approach. ConclusionsIn the context of pneumothorax diagnoses, we proposed a template-guided approach for improving model explanations. Our approach not only aligns model explanations more closely with clinical insights but also exhibits extensibility to other thoracic diseases. We anticipate that our template guidance will forge a novel approach to elucidating AI models by integrating clinical domain expertise.

The growing use of deep learning models in diagnosing medical images has resulted in impressive gains in terms of the accuracy in diagnosis. Still, the lack of transparency in these models tends to increase the resistance of these models in clinical use. This paper will fill the accuracy-interpretability gap by creating explainable deep learning models that do not affect predictive accuracy. An explainability methodology was incorporated into a convolutional neural network (CNN) architecture using the state-of-the-art explainability methods, Gradient-weighted Class Activation Mapping (Grad-CAM), Local Interpretable Model-Agnostic Explanations (LIME), and Integrated Gradients, to visualize model reasoning and locate important diagnostic regions of medical images. Benchmark radiology and histopathology data sets were evaluated experimentally to assess their accuracy and F1-score, interpretability measures, and the level of clinician agreement. The proposed model attained a diagnostic accuracy of 95.8 and an interpretability score of 0.89, which indicates a high similarity of model explanations and expert annotations. Using an explainability tool compared to the control group led to a marked increase in clinical trust and comprehension of model predictions. The results highlight that deep learning systems can be highly diagnostic and, at the same time, produce a transparent decision-making process. The study can be considered significant to developing human-centric artificial intelligence in healthcare as it contributes to accountability, reliability, and interpretability in medical image analysis.

The early and precise diagnosis of breast cancer is one of the most important factors in enhancing survival rates. Despite considerable improvements in screening methods, medical imaging, and treatment approaches, the issue of reliable early detection remains a significant problem due to instability in clinical interpretation and the complexity of diagnostic information. Conventional methods of diagnosis emphasize the analysis of clinical and histopathological information, which are prone to inter-observer error and do not necessarily reveal subtle patterns related to disease progression. Artificial Intelligence has demonstrated enormous potential in alleviating these weaknesses. Ensemble methods, as well as support vector machines and gradient boosting-based algorithms such as XGBoost and LightGBM, have shown excellent results in the analysis of structured clinical data. Simultaneously, deep learning (DL) systems, specifically convolutional neural networks (CNNs), have been demonstrated to be exceptionally successful in medical image analysis such as mammography and histopathology. However, the interpretability of such models remains a major obstacle to their usage in clinical practice. To address this problem, Explainable Artificial Intelligence (XAI) methods, including SHAP, LIME, and Grad-CAM, have been proposed to improve model transparency and contribute significantly to understanding how decisions are made. This paper reviews recent developments in ML, DL, and XAI in relation to breast cancer diagnosis. It examines commonly used datasets, evaluation metrics, and trends, and also reports the most significant issues, including data constraints, lack of interpretability, and challenges in multimodal integration. Moreover, this paper identifies knowledge gaps in existing research and highlights the necessity of developing robust, explainable, and actionable AI-based diagnostic systems.

Background:Brain tumors represent a diverse group of central nervous system neoplasms that require precise diagnosis and characterization for effective treatment. Advances in neuroimaging have improved the detection of these tumors; however, conventional interpretation methods remain time-intensive and subject to variability. Artificial intelligence (AI), particularly through machine learning and deep learning, has emerged as a powerful tool in neuro-oncological imaging, offering automation, consistency, and enhanced diagnostic performance. Objective:This review aims to provide a comprehensive overview of AI-assisted imaging tools used in the detection and characterization of brain tumors. It highlights key AI technologies, their clinical applications, performance compared to human experts, and the emerging trends shaping the future of AI in neuro-oncology. Methods:A narrative review was conducted of recent peer-reviewed studies focused on the application of AI in brain tumor imaging. Emphasis was placed on machine learning and deep learning models used for tumor segmentation, histopathologic and molecular subtype prediction, prognostic modeling, and treatment response monitoring. Technical challenges, ethical concerns, and regulatory considerations were also examined. Results:AI models have demonstrated high accuracy in tasks such as tumor segmentation, classification of tumor types and grades, non-invasive prediction of molecular markers (e.g., IDH mutation, MGMT methylation), and survival prediction. Emerging techniques such as federated learning, multimodal data integration, and explainable AI are addressing key limitations, including data privacy, generalizability, and clinical trust. Conclusion:AI-assisted imaging holds considerable promise in improving the accuracy, speed, and personalization of brain tumor diagnosis and management. For widespread clinical adoption, future efforts should focus on multi-institutional collaboration, prospective validation, regulatory alignment, and clinician education. With continued advancement, AI can become a valuable adjunct in the neuro-oncology diagnostic arsenal, ultimately contributing to better patient outcomes.

This study addresses the critical challenge of detecting brain tumors using MRI images, a pivotal task in medical diagnostics that demands high accuracy and interpretability. While deep learning has shown remarkable success in medical image analysis, there remains a substantial need for models that are not only accurate but also interpretable to healthcare professionals. The existing methodologies, predominantly deep learning-based, often act as black boxes, providing little insight into their decision-making process. This research introduces an integrated approach using ResNet50, a deep learning model, combined with Gradient-weighted Class Activation Mapping (Grad-CAM) to offer a transparent and explainable framework for brain tumor detection. We employed a dataset of MRI images, enhanced through data augmentation, to train and validate our model. The results demonstrate a significant improvement in model performance, with a testing accuracy of 98.52% and precision-recall metrics exceeding 98%, showcasing the model’s effectiveness in distinguishing tumor presence. The application of Grad-CAM provides insightful visual explanations, illustrating the model’s focus areas in making predictions. This fusion of high accuracy and explainability holds profound implications for medical diagnostics, offering a pathway towards more reliable and interpretable brain tumor detection tools.

Deep learning has attracted great attention in the medical imaging community as a promising solution for automated, fast and accurate medical image analysis, which is mandatory for quality healthcare. Convolutional neural networks and its variants have become the most preferred and widely used deep learning models in medical image analysis. In this paper, concise overviews of the modern deep learning models applied in medical image analysis are provided and the key tasks performed by deep learning models, i.e. classification, segmentation, retrieval, detection, and registration are reviewed in detail. Some recent researches have shown that deep learning models can outperform medical experts in certain tasks. With the significant breakthroughs made by deep learning methods, it is expected that patients will soon be able to safely and conveniently interact with AI-based medical systems and such intelligent systems will actually improve patient healthcare. There are various complexities and challenges involved in deep learning-based medical image analysis, such as limited datasets. But researchers are actively working in this area to mitigate these challenges and further improve health care with AI.

Brain tumour classification is among the most challenging tasks in medical image analysis. The purpose of brain tumour classification is to produce a precise delineation of tumour areas. Successful early detection of brain tumours is essential to enhancing treatment outcomes and thus improving patient survival. Over the last several decades, many researchers have contributed significantly to the field of brain tumour classification. The level of user supervision and computing efficiency have both been factors in the clinical acceptability of classification systems. However, due to a lack of collaboration between doctors and researchers, practical applications are still limited, and clinicians still rely on manual tumour estimates. This research presents a comprehensive review of recent brain tumour classification methods. The purpose of this survey is to conduct an evaluation of 70 papers that deal with the classification of brain tumours. This survey includes a systematic analysis based on performance levels and related maximum achievements for each contribution. In addition, the chronological review and numerous implemented tools used in the evaluated works are examined. Finally, the survey highlights a number of research issues and flaws that researchers may find helpful in developing prospective studies on brain tumour classification.

Skin diseases impact millions of people around the world and pose a severe risk to public health. These diseases have a wide range of effects on the skin’s structure, functionality, and appearance. Identifying and predicting skin diseases are laborious processes that require a complete physical examination, a review of the patient’s medical history, and proper laboratory diagnostic testing. Additionally, it necessitates a significant number of histological and clinical characteristics for examination and subsequent treatment. As a disease’s complexity and quantity of features grow, identifying and predicting it becomes more challenging. This research proposes a deep learning (DL) model utilizing transfer learning (TL) to quickly identify skin diseases like chickenpox, measles, and monkeypox. A pre-trained VGG16 is used for transfer learning. The VGG16 can identify and predict diseases more quickly by learning symptom patterns. Images of the skin from the four classes of chickenpox, measles, monkeypox, and normal are included in the dataset. The dataset is separated into training and testing. The experimental results performed on the dataset demonstrate that the VGG16 model can identify and predict skin diseases with 93.29% testing accuracy. However, the VGG16 model does not explain why and how the system operates because deep learning models are black boxes. Deep learning models’ opacity stands in the way of their widespread application in the healthcare sector. In order to make this a valuable system for the health sector, this article employs layer-wise relevance propagation (LRP) to determine the relevance scores of each input. The identified symptoms provide valuable insights that could support timely diagnosis and treatment decisions for skin diseases.

Over the past five years, artificial intelligence (AI) has introduced new models and methods for addressing the challenges associated with the broader adoption of AI models and systems in medicine. This paper reviews recent advances in AI for medical image and video analysis, outlines emerging paradigms, highlights pathways for successful clinical translation, and provides recommendations for future work. Hybrid Convolutional Neural Network (CNN) Transformer architectures now deliver state-of-the-art results in segmentation, classification, reconstruction, synthesis, and registration. Foundation and generative AI models enable the use of transfer learning to smaller datasets with limited ground truth. Federated learning supports privacy-preserving collaboration across institutions. Explainable and trustworthy AI approaches have become essential to foster clinician trust, ensure regulatory compliance, and facilitate ethical deployment. Together, these developments pave the way for integrating AI into radiology, pathology, and wider healthcare workflows.

The growing reliance on opaque deep learning models in critical domains has intensified the demand for transparency, accountability, and interpretability of artificial intelligence systems. Explainable Artificial Intelligence (XAI) seeks to address this through methods that clarify how models make predictions, fostering informed oversight and trust. This review synthesizes foundational concepts in XAI, distinguishing interpretability from explainability and contrasting intrinsic with post-hoc methods, as well as local with global explanations. It surveys major techniques such as feature attribution, gradient-based methods, surrogate models, counterfactual reasoning, and inherently interpretable architectures alongside widely used tools, frameworks, and evaluation metrics, including fidelity, human interpretability, robustness, and efficiency. Applications in healthcare, finance, law, and autonomous systems are discussed, highlighting domain-specific interpretability needs. Persistent challenges, including inconsistent terminology, subjective evaluation, and adversarial vulnerabilities, are examined. The review concludes with emerging directions in human-centered, real-time, and multimodal explanations, aiming to guide the design of XAI systems that are both technically sound and aligned with societal expectations.

With the rise of deep learning, medical image analysis has undergone fundamental change, presenting new possibilities to physicians in terms of achieving higher accuracy more efficiently, and greater automation in disease diagnosis and prognosis. In this paper, we discuss recent progress in utilizing deep learning techniques such as convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), and transformer-based model for medical image analysis. Image classification, segmentation, and anomaly detection in modalities such MRI, CT, Xray, and ultrasound have been strongly improved by these architectures. Yet, such progress brings challenges, namely scarcity of sufficient data, interpretability of models, computational intensity, and robust generalization to diverse clinical datasets. At the same time regulatory concerns and ethical questions on the use of AI diagnostics are still constraining large scale adoption. This paper provides a comprehensive review of state-of-the art deep learning models in medical imaging, reviews the current limitations, and envisions future research directions in federated learning, explainable AI, and quantum enhanced deep learning. Such insights are intended to guide researchers and clinicians in the optimization of AI driven medical image analysis for optimized patient care and clinical decision making.

Brain tumors are abnormal growth of cells which are very serious issue, and the early diagnosis is the main factor for the enhancement of the patients' situation. The traditional methods of brain tumor detection and classification are usually time-consuming, and often the human error is involved. Also, they cannot at all accurately classify the different types of tumors. The deep learning models mainly CNNs have been the main factors for the significant transformation of the medical image analysis. CNNs are applied to automatically extract the complex features from MRI images which make it possible to get the advantages of the exact identification of the tumor boundaries and the slight variations that can be ignored by human. This work investigates the use of transfer learning technique to improve the accuracy of CNN models for brain tumor detection and classification. We tested VGG16 and ResNet50 models on 4000 MRI images with tumor and no-tumor. Both scratch and pre-trained models were used. Results show that pre-trained VGG16 and ResNet50 achieved 99.44% and 99.55% accuracy while scratch models achieved 59.64% and 96.02% accuracy respectively. This result proves the power of transfer learning technique in deep learning models especially CNNs for brain tumor detection and classification.

While deep learning (DL) models have shown promise in breast cancer diagnosis using digital breast tomosynthesis (DBT) images, the impact of varying matrix sizes and image interpolation methods on diagnostic accuracy remains unclear. Understanding these effects is essential to optimize preprocessing steps for DL models, which can lead to more efficient training processes, improved diagnostic accuracy, and better utilization of computational resources. Our institutional review board approved this retrospective study and waived the requirement for informed consent from the patients. In this study, 499 patients (29-90 years old, mean age 50.5 years) who underwent breast tomosynthesis were included. We performed downsampling to 256 × 256, 128 × 128, 64 × 64, and 32 × 32 using five image interpolation methods: Nearest (NN), Bilinear (BL), Bicubic (BC), Hamming (HM), and Lanczos (LC). The diagnostic accuracy of the DL model was assessed by mean AUC with its 95% confidence interval (CI). DL models with downsampled images to 256 × 256 pixels using the LC interpolation method showed a significantly lower AUC than the original 512 × 512 pixels model. This decrease was also observed with the 128 × 128 pixels DL models using HM and LC methods. All interpolation methods showed a significant decrease in AUC for the 64 × 64 and 32 × 32 pixels DL models. Our results highlight the significant impact of downsampling size and interpolation methods on the diagnostic performance of DL models. Understanding these effects is essential for optimizing preprocessing steps, which can enhance the accuracy and reliability of breast cancer diagnosis using DBT images.

Abstract: Deep learning models have demonstrated remarkable capabilities across various domains, but their inherent complexity often leads to challenges in understanding and interpreting their decisions. The demand for transparent and interpretable artificial intelligence (AI) systems is particularly crucial in fields such as healthcare, finance, and autonomous systems. This research paper presents a comprehensive study on the application of Explainable AI (XAI) techniques to enhance transparency and interpretability in deep learning models. Keywords: Explainable AI (XAI), artificial intelligence (AI).

Deep learning of endoscopic features for the assessment of neoadjuvant therapy response in locally advanced rectal cancer.