Background/Objective: The integration of machine learning (ML) and deep learning (DL) has significantly enhanced medical image classification, especially in histopathology, by improving diagnostic accuracy and aiding clinical decision making. However, data privacy concerns and restrictions on sharing patient data limit the development of effective DL models. Federated learning (FL) offers a promising solution by enabling collaborative model training across institutions without exposing sensitive data. This systematic review aims to comprehensively evaluate the current state of FL applications in histopathological image classification by identifying prevailing methodologies, datasets, and performance metrics and highlighting existing challenges and future research directions. Methods: Following PRISMA guidelines, 24 studies published between 2020 and 2025 were analyzed. The literature was retrieved from ScienceDirect, IEEE Xplore, MDPI, Springer Nature Link, PubMed, and arXiv. Eligible studies focused on FL-based deep learning models for histopathology image classification with reported performance metrics. Studies unrelated to FL in histopathology or lacking accessible full texts were excluded. Results: The included studies utilized 10 datasets (8 public, 1 private, and 1 unspecified) and reported classification accuracies ranging from 69.37% to 99.72%. FedAvg was the most commonly used aggregation algorithm (14 studies), followed by FedProx, FedDropoutAvg, and custom approaches. Only two studies reported their FL frameworks (Flower and OpenFL). Frequently employed model architectures included VGG, ResNet, DenseNet, and EfficientNet. Performance was typically evaluated using accuracy, precision, recall, and F1-score. Federated learning demonstrates strong potential for privacy-preserving digital pathology applications. However, key challenges remain, including communication overhead, computational demands, and inconsistent reporting standards. Addressing these issues is essential for broader clinical adoption. Conclusions: Future work should prioritize standardized evaluation protocols, efficient aggregation methods, model personalization, robustness, and interpretability, with validation across multi-institutional clinical environments to fully realize the benefits of FL in histopathological image classification.

Accurate analysis of histopathology images is essential for disease diagnosis and treatment planning. However, the quality of digital pathology slides is often limited by scanner resolution, which can compromise diagnostic precision and patient care. To address this challenge, we conducted a comparative study evaluating four state of the art image enhancement methods: real enhanced super resolution generative adversarial network (Real‐ESRGAN), SwinIR, multi scale image restoration network v2 (MIRNet‐v2) and super resolution CNN (SRCNN). Our assessment focused on both quantitative metrics peak signal to noise ratio (PSNR) and structural similarity index (SSIM) and qualitative visual analysis to evaluate detail preservation. The experimental results revealed that SwinIR achieved the best quantitative performance among all evaluated methods, attaining the highest PSNR (35.81) and SSIM (0.95) for lung images from the LC2500 dataset at a 2 upscaling factor. In contrast, real‐ESRGAN excelled in perceptual quality, preserving finer image details more effectively, though it recorded slightly lower numerical scores (PSNR: 33.53, SSIM: 0.92) on the same dataset. These outcomes highlight essential trade off between perceptual fidelity and reconstruction quality, indicating that the optimal choice of enhancement method may vary depending on clinical or diagnostic priorities. The MIRNetv2 method delivered reasonable performance but ranked below both real‐ESRGAN and SwinIR. Specifically, it achieved PSNR/SSIM scores of 30.67/0.94 on PR‐IHC patches, 32.90/0.95 on lung images, and 31.87/0.95 on colon images, while scoring 29.11 for PR‐IHC images in a separate evaluation. SRCNN demonstrated a balanced performance across datasets, achieving PSNR/SSIM values of 31.45/0.88 for lung images, 30.76/0.87 for PR‐IHC patches, 32.62/0.93 for colon images, and 33.76/0.91 for PR‐IHC. These findings underscore the real ESRGAN as the most effective method for improving the resolution and quality of histopathology images, supporting its potential integration into digital pathology workflows to enhance diagnostic accuracy and patient outcomes.

Accurate classification of otoscopic ear images is crucial for early diagnosis of ear pathologies such as Chronic Otitis Media, Earwax Plug, and Myringosclerosis. In this study, we propose a novel deep learning framework that employs a knowledge distillation strategy, wherein a high-capacity pre-trained teacher model (Vision Transformer or ResNet101) transfers learned representations to a lightweight student CNN model (EfficientNet-B0). The student network is further enhanced through the integration of an Adaptive Channel Attention (ACA) module, which selectively emphasizes informative features via channel-wise recalibration. The multi-scale feature distillation from the teacher improves generalization while the ACA block boosts sensitivity to clinically relevant regions. We validated our method on a publicly available otoscopic image dataset comprising four balanced classes. Our approach achieved an overall accuracy of 98.75%, with class-wise AUC values of 1.000 (CSOM), 1.000 (Earwax Plug), 0.994 (Myringosclerosis), and 0.992 (Normal), and a micro-average AUC of 0.997. Additionally, Grad-CAM analysis confirmed the model’s focus on diagnostically meaningful areas, supporting the interpretability of the predictions. These results demonstrate the effectiveness of our distillation-based ACA-enhanced architecture in otoscopic image classification, with potential to assist clinical decision-making in primary care and telemedicine applications.