Complex Medical Images Research Articles

AI-Driven Radiology Report Generation for Traumatic Brain Injuries.

Traumatic brain injuries present significant diagnostic challenges in emergency medicine, where the timely interpretation of medical images is crucial for patient outcomes. In this paper, we propose a novel AI-based approach for automatic radiology report generation tailored to cranial trauma cases. Our model integrates an AC-BiFPN with a Transformer architecture to capture and process complex medical imaging data such as CT and MRI scans. The AC-BiFPN extracts multi-scale features, enabling the detection of intricate anomalies like intracranial hemorrhages, while the Transformer generates coherent, contextually relevant diagnostic reports by modeling long-range dependencies. We evaluate the performance of our model on the RSNA Intracranial Hemorrhage Detection dataset, where it outperforms traditional CNN-based models in both diagnostic accuracy and report generation. This solution not only supports radiologists in high-pressure environments but also provides a powerful educational tool for trainee physicians, offering real-time feedback and enhancing their learning experience. Our findings demonstrate the potential of combining advanced feature extraction with transformer-based text generation to improve clinical decision-making in the diagnosis of traumatic brain injuries.

A Survey on Liver Cancer Detection Using Hyperfusion of CNN and SVM in Machine Learning

Since liver cancer ranks among of the most aggressive renditions of the disease, improving patient outcomes requires early identification. We propose an inventive tactic to liver cancer detection by integrating CNN and SVM. CNNs, known for their powerful feature extraction capabilities, are particularly effective in analysing complex medical images. SVMs, on the other hand, are efficient classifiers that can separate data points in high-dimensional spaces with accuracy. By merging the feature extraction strength of CNN with the classification efficiency of SVM, the proposed model aims to enhance liver cancer detection accuracy and robustness. The experimental results reveal that the fused CNN-SVM model significantly surpasses the performance of standalone CNN and SVM models, achieving a high detection accuracy of 95.2%. This hybrid method offers a promising direction for improving the precision of computer-aided diagnosis systems, contributing to more effective and reliable liver cancer detection methods that can assist healthcare professionals in making timely decisions.

Design of an Optimal Convolutional Neural Network Architecture for MRI Brain Tumor Classification by Exploiting Particle Swarm Optimization

The classification of brain tumors using MRI scans is critical for accurate diagnosis and effective treatment planning, though it poses significant challenges due to the complex and varied characteristics of tumors, including irregular shapes, diverse sizes, and subtle textural differences. Traditional convolutional neural network (CNN) models, whether handcrafted or pretrained, frequently fall short in capturing these intricate details comprehensively. To address this complexity, an automated approach employing Particle Swarm Optimization (PSO) has been applied to create a CNN architecture specifically adapted for MRI-based brain tumor classification. PSO systematically searches for an optimal configuration of architectural parameters—such as the types and numbers of layers, filter quantities and sizes, and neuron numbers in fully connected layers—with the objective of enhancing classification accuracy. This performance-driven method avoids the inefficiencies of manual design and iterative trial and error. Experimental results indicate that the PSO-optimized CNN achieves a classification accuracy of 99.19%, demonstrating significant potential for improving diagnostic precision in complex medical imaging applications and underscoring the value of automated architecture search in advancing critical healthcare technology.

Skin Cancer Detection Using Transfer Learning and Deep Attention Mechanisms.

Background/Objectives: Early and accurate diagnosis of skin cancer improves survival rates; however, dermatologists often struggle with lesion detection due to similar pigmentation. Deep learning and transfer learning models have shown promise in diagnosing skin cancers through image processing. Integrating attention mechanisms (AMs) with deep learning has further enhanced the accuracy of medical image classification. While significant progress has been made, further research is needed to improve the detection accuracy. Previous studies have not explored the integration of attention mechanisms with the pre-trained Xception transfer learning model for binary classification of skin cancer. This study aims to investigate the impact of various attention mechanisms on the Xception model's performance in detecting benign and malignant skin lesions. Methods: We conducted four experiments on the HAM10000 dataset. Three models integrated self-attention (SL), hard attention (HD), and soft attention (SF) mechanisms, while the fourth model used the standard Xception without attention mechanisms. Each mechanism analyzed features from the Xception model uniquely: self-attention examined the input relationships, hard-attention selected elements sparsely, and soft-attention distributed the focus probabilistically. Results: Integrating AMs into the Xception architecture effectively enhanced its performance. The accuracy of the Xception alone was 91.05%. With AMs, the accuracy increased to 94.11% using self-attention, 93.29% with soft attention, and 92.97% with hard attention. Moreover, the proposed models outperformed previous studies in terms of the recall metrics, which are crucial for medical investigations. Conclusions: These findings suggest that AMs can enhance performance in relation to complex medical imaging tasks, potentially supporting earlier diagnosis and improving treatment outcomes.

METHOD FOR INTERPRETING DECISIONS MADE BY DEEP LEARNING MODELS

The use of artificial intelligence (AI) in medical diagnostics opens new opportunities for analyzing complex medical images and optimizing diagnostic processes. One of the key challenges remains the interpretation of results obtained through AI systems, particularly in medical practice, where ensuring transparency and clarity of decision-making is critically important. This study proposes a method for visualizing and interpreting the results of cardiac disease classification based on MRI image analysis using deep learning models. The primary goal of the research is to explain AI-driven decisions in a convenient and understandable format for physicians, contributing to the reduction of subjectivity in clinical practice.During the research, approaches were developed for visualizing key groups of medical indicators, such as heart volumes, ejection fraction, myocardial wall thickness, and volume-to-mass ratios. The study describes numerical metrics commonly used in medical practice. Fifteen key medical metrics were identified and grouped into corresponding categories for effective representation of essential medical indicators. Various visualization forms were utilized to ensure intuitive data presentation: pie charts to demonstrate ratios, the 17-segment myocardial model for analyzing wall thickness, and numerical indicators for accurately displaying volumes and ejection fraction. This approach allows physicians to quickly assess structural changes in the heart and make informed conclusions.The proposed method aims to enhance transparency and trust in AI by providing comprehensible data representation, reducing the risks of subjective interpretation and cognitive biases. The results indicate that using such visualizations can significantly facilitate clinical decision-making, improve diagnostic accuracy, and standardize approaches to medical data analysis.

Enhanced Lung Cancer Prediction via Integrated Multi‐Space Feature Adaptation, Collaborative Alignment and Disentanglement Learning

ABSTRACTLung cancer, marked by the rapid and uncontrolled proliferation of abnormal cells in the lungs, continues to be one of the leading causes of cancer‐related deaths globally. Early and accurate diagnosis is critical for improving patient outcomes. This research presents an enhanced lung cancer prediction model by integrating Adaptation Multiple Spaces Feature and L1‐norm Regularization (AMSF‐L1ELM) with Primitive Generation with Collaborative Relationship Alignment and Feature Disentanglement Learning (PADing). Initially, the AMSF‐L1ELM model was employed to address the challenges of feature alignment and multi‐domain adaptation, achieving a baseline performance with a test accuracy of 83.20%, precision of 83.43%, recall of 83.74%, and an F1‐score of 83.07%. After incorporating PADing, the model exhibited significant improvements, increasing the test accuracy to 98.07%, precision to 98.11%, recall to 98.05%, F1‐score to 98.06%, and achieving a ROC‐AUC of 100%. Cross‐validation results further validated the model's robustness, with an average precision of 99.73%, recall of 99.55%, F1‐score of 99.64%, and accuracy of 99.64% across five folds. The study utilized four distinct datasets covering a range of imaging modalities and diagnostic labels: the Chest CT‐Scan dataset from Kaggle, the NSCLC‐Radiomics‐Interobserver1 dataset from TCIA, the LungCT‐Diagnosis dataset from TCIA, and the IQ‐OTH/NCCD dataset from Kaggle. In total, 4085 images were selected, distributed between source and target domains. These results demonstrate the effectiveness of PADing in improving the model's performance and enhancing lung cancer prediction accuracy across multiple domains in complex medical imaging data.

MediLite3DNet: A lightweight network for segmentation of nasopharyngeal airways.

The precise segmentation and three-dimensional reconstruction of the nasopharyngeal airway are crucial for the diagnosis and treatment of adenoid hypertrophy in children. However, traditional methods face challenges such as information loss and low computational efficiency when addressing this task. To overcome these issues, this paper introduces an innovative lightweight 3D medical image segmentation network-MediLite3DNet. The core of this network is the Parallel Multi-Scale High-Resolution Network (PMHNet), which effectively retains detailed features of the airway and optimizes the fusion of multi-scale features through its parallel structure. In response to the complexity of existing networks and their reliance on vast amounts of training data, this paper presents an efficient Hierarchical Decoupled Convolution Module (EHDC) to reduce computational costs while maintaining efficient feature extraction capabilities. Furthermore, to enhance the accuracy of segmentation, a lightweight Channel and Spatial Attention Mechanism (LCSA) is proposed. This mechanism identifies and emphasizes key channels and spatial features, improving the processing of complex medical images while controlling the increase in the number of parameters. Experiments conducted on a clinical CT dataset demonstrate the network's exceptional performance, with a Dice coefficient of 97.42%, sensitivity of 98.69%, and Jaccard index of 95%. Maintaining high precision, the model has a parameter count of only 0.227M and a floating-point operation count (FLOPs) of 24.526G, proving its computational efficiency. The significance of this study is that it provides a highly efficient and accurate diagnostic tool for children with adenoid hypertrophy. Additionally, with the innovative MediLite3DNet design, it brings a new lightweight solution to the domain of medical image segmentation.

MMAformer: Multiscale Modality-Aware Transformer for Medical Image Segmentation

The segmentation of medical images, particularly for brain tumors, is essential for clinical diagnosis and treatment planning. In this study, we proposed MMAformer, a Multiscale Modality-Aware Transformer model, which is designed for segmenting brain tumors by utilizing multimodality magnetic resonance imaging (MRI). Complementary information between different sequences helps the model delineate tumor boundaries and distinguish different tumor tissues. To enable the model to acquire the complementary information between related sequences, MMAformer employs a multistage encoder, which uses a cross-modal downsampling (CMD) block for learning and integrating the complementary information between sequences at different scales. In order to effectively fuse the various information extracted by the encoder, the Multimodal Gated Aggregation (MGA) block combines the dual attention mechanism and multi-gated clustering to effectively fuse the spatial, channel, and modal features of different MRI sequences. In the comparison experiments on the BraTS2020 and BraTS2021 datasets, the average Dice score of MMAformer reached 86.3% and 91.53%, respectively, indicating that MMAformer surpasses the current state-of-the-art approaches. MMAformer’s innovative architecture, which effectively captures and integrates multimodal information at various scales, offers a promising solution for tackling complex medical image segmentation challenges.

Enhanced Semi-Supervised Medical Image Classification Based on Dynamic Sample Reweighting and Pseudo-Label Guided Contrastive Learning (DSRPGC)

In semi-supervised learning (SSL) for medical image classification, model performance is often hindered by the scarcity of labeled data and the complexity of unlabeled data. This paper proposes an enhanced SSL approach to address these challenges by effectively utilizing unlabeled data through a combination of pseudo-labeling and contrastive learning. The key contribution of our method is the introduction of a Dynamic Sample Reweighting strategy to select reliable unlabeled samples, thereby improving the model’s utilization of unlabeled data. Additionally, we incorporate multiple data augmentation strategies based on the Mean Teacher (MT) model to ensure consistent outputs across different perturbations. To better capture and integrate multi-scale features, we propose a novel feature fusion network, the Medical Multi-scale Feature Fusion Network (MedFuseNet), which enhances the model’s ability to classify complex medical images. Finally, we introduce a pseudo-label guided contrastive learning (PGC) loss function that improves intra-class compactness and inter-class separability of the model’s feature representations. Extensive experiments on three public medical image datasets demonstrate that our method outperforms existing SSL approaches, achieving 93.16% accuracy on the ISIC2018 dataset using only 20% labeled data, highlighting the potential of our approach to advance medical image classification under limited supervision.

Medical Image Segmentation

Medical image segmentation is a critical component in the development of computer-aided diagnosis and treatment planning systems. This paper provides a comprehensive survey of recent advances in segmentation techniques applied to various imaging modalities, including Magnetic Resonance Imaging (MRI). Traditional methods such as thresholding, region-growing, and active contours are reviewed alongside contemporary machine learning-based approaches, particularly deep learning models. The survey emphasizes the growing dominance of convolutional neural networks (CNNs) and their variants, including U-Net and Fully Convolutional Networks (FCNs), which have shown remarkable success in handling complex medical imaging challenges. Additionally, the paper discusses hybrid methods that combine classical techniques with artificial intelligence to improve accuracy and robustness in segmentation tasks. Key challenges such as class imbalance, boundary delineation, and computational efficiency are also highlighted. Future directions, including the integration of multi-modal data and advancements in self-supervised learning, are explored as potential solutions to overcome current limitations in medical image segmentation.

Performance of Multimodal Artificial Intelligence Chatbots Evaluated on Clinical Oncology Cases

Multimodal artificial intelligence (AI) chatbots can process complex medical image and text-based information that may improve their accuracy as a clinical diagnostic and management tool compared with unimodal, text-only AI chatbots. However, the difference in medical accuracy of multimodal and text-only chatbots in addressing questions about clinical oncology cases remains to be tested. To evaluate the utility of prompt engineering (zero-shot chain-of-thought) and compare the competency of multimodal and unimodal AI chatbots to generate medically accurate responses to questions about clinical oncology cases. This cross-sectional study benchmarked the medical accuracy of multiple-choice and free-text responses generated by AI chatbots in response to 79 questions about clinical oncology cases with images. A unique set of 79 clinical oncology cases from JAMA Network Learning accessed on April 2, 2024, was posed to 10 AI chatbots. The primary outcome was medical accuracy evaluated by the number of correct responses by each AI chatbot. Multiple-choice responses were marked as correct based on the ground-truth, correct answer. Free-text responses were rated by a team of oncology specialists in duplicate and marked as correct based on consensus or resolved by a review of a third oncology specialist. This study evaluated 10 chatbots, including 3 multimodal and 7 unimodal chatbots. On the multiple-choice evaluation, the top-performing chatbot was chatbot 10 (57 of 79 [72.15%]), followed by the multimodal chatbot 2 (56 of 79 [70.89%]) and chatbot 5 (54 of 79 [68.35%]). On the free-text evaluation, the top-performing chatbots were chatbot 5, chatbot 7, and the multimodal chatbot 2 (30 of 79 [37.97%]), followed by chatbot 10 (29 of 79 [36.71%]) and chatbot 8 and the multimodal chatbot 3 (25 of 79 [31.65%]). The accuracy of multimodal chatbots decreased when tested on cases with multiple images compared with questions with single images. Nine out of 10 chatbots, including all 3 multimodal chatbots, demonstrated decreased accuracy of their free-text responses compared with multiple-choice responses to questions about cancer cases. In this cross-sectional study of chatbot accuracy tested on clinical oncology cases, multimodal chatbots were not consistently more accurate than unimodal chatbots. These results suggest that further research is required to optimize multimodal chatbots to make more use of information from images to improve oncology-specific medical accuracy and reliability.

A comprehensive review of deep learning for medical image segmentation

Medical image segmentation provides detailed mappings of regions of interest, facilitating precise identification of critical areas and greatly aiding in the diagnosis, treatment, and understanding of diverse medical conditions. However, conventional techniques frequently rely on hand-crafted feature-based approaches, posing challenges when dealing with complex medical images, leading to issues such as low accuracy and sensitivity to noise. Recent years have seen substantial research focused on the effectiveness of deep learning models for segmenting medical images. In this study, we present a comprehensive review of the various deep learning-based approaches for medical image segmentation and provide a detailed analysis of their contributions to the domain. These methods can be broadly categorized into five groups: CNN-based methods, Transformer-based methods, Mamba-based methods, semi-supervised learning methods, and weakly supervised learning methods. Convolutional Neural Networks (CNNs), with their efficient feature self-learning, have driven major advances in medical image segmentation. Subsequently, Transformers, leveraging self-attention mechanisms, have achieved performance on par with or surpassing Convolutional Neural Networks. Mamba-based methods, as a novel selective state-space model, are emerging as a promising direction. Furthermore, due to the limited availability of annotated medical images, research in weakly supervised and semi-supervised learning continues to evolve. This review covers common evaluation methods, datasets, and deep learning applications in diagnosing and treating skin lesions, hippocampus, tumors, and polyps. Finally, we identify key challenges such as limited data, diverse modalities, noise, and clinical applicability, and propose future research in zero-shot segmentation, transfer learning, and multi-modal techniques to advance the development of medical image segmentation technology.

Advances in Medical Image Segmentation: A Comprehensive Review of Traditional, Deep Learning and Hybrid Approaches.

Medical image segmentation plays a critical role in accurate diagnosis and treatment planning, enabling precise analysis across a wide range of clinical tasks. This review begins by offering a comprehensive overview of traditional segmentation techniques, including thresholding, edge-based methods, region-based approaches, clustering, and graph-based segmentation. While these methods are computationally efficient and interpretable, they often face significant challenges when applied to complex, noisy, or variable medical images. The central focus of this review is the transformative impact of deep learning on medical image segmentation. We delve into prominent deep learning architectures such as Convolutional Neural Networks (CNNs), Fully Convolutional Networks (FCNs), U-Net, Recurrent Neural Networks (RNNs), Adversarial Networks (GANs), and Autoencoders (AEs). Each architecture is analyzed in terms of its structural foundation and specific application to medical image segmentation, illustrating how these models have enhanced segmentation accuracy across various clinical contexts. Finally, the review examines the integration of deep learning with traditional segmentation methods, addressing the limitations of both approaches. These hybrid strategies offer improved segmentation performance, particularly in challenging scenarios involving weak edges, noise, or inconsistent intensities. By synthesizing recent advancements, this review provides a detailed resource for researchers and practitioners, offering valuable insights into the current landscape and future directions of medical image segmentation.

Computationally optimized brain tumor classification using attention based GoogLeNet-style CNN

Early detection of diseases is a crucial step towards patient healthcare and recovery, especially, for low survival rate diseases like brain cancer. In recent years, deep learning models such as convolutional neural networks (CNNs) have been widely utilized for medical image classification owing to their proficiency in extracting local features. However, accurate classification of complex medical images necessitates capturing local and global features. This paper focuses on the classification of the three most prominent kinds of brain tumors, namely, glioma, meningioma and pituitary tumor, with the proposed CNN based on the structure of GoogLeNet. The proposed model uses an attention-based inception module (ABIM) embedded with attention mechanism of spatial attention and efficient channel attention. Attention helps CNN focus on features with more distinguishing power and ignores irrelevant features while the inception approach aids in extracting multiscale local features. ABIM incorporates attention with inception to generate better feature representation. The model training and testing are done on a publicly accessible Figshare dataset with 3064 brain MRI samples. The dataset comprises 1426, 708, and 930 MRI samples of glioma, meningioma, and pituitary tumors, respectively. In a five-fold cross-validation experiment, the proposed model achieved an average accuracy of 97.97% for glioma, 94.76% for meningioma, and 99.22% for pituitary tumors. The proposed CNN model surpasses existing models with an overall accuracy of 97.62%, while utilizing fewer parameters than its base model, GoogLeNet. The model is also evaluated on datasets from the Kaggle and Harvard medical repositories, and showed promising results in distinguishing between different tumor classes, and normal brain MRIs. These results demonstrate that our model not only outperforms other existing models in terms of accuracy but also has comparatively lower computational complexity, providing a robust tool to support healthcare professionals.

Brain Tumor Detection and Classification using YOLOv10 and AI Chatbot Using LLMs

The integration of advanced medical imaging techniques and artificial intelligence (AI) has greatly improved the early detection and diagnosis of brain tumors. This paper introduces a novel system for brain tumor detection and classification using the YOLOv10 (You Only Look Once) model, enhanced by an AI chatbot powered by Large Language Models (LLMs). Leveraging the real-time object detection capabilities of YOLOv10, the system accurately classifies brain tumors from MRI images into four categories: Glioma, Meningioma, Pituitary, and No Tumor. This deep learning-based approach ensures swift and precise analysis of complex medical images. In addition, an AI chatbot is integrated to provide seamless interaction and information retrieval for both patients and healthcare professionals. Utilizing LLMs, the chatbot offers advanced conversational abilities, delivering detailed explanations about tumor types, potential treatments, and further medical advice based on the detected tumor characteristics. This dual-system approach aims to enhance diagnostic accuracy while providing real-time, accessible support, ultimately improving decision-making for medical practitioners and enhancing patient outcomes. The proposed system exemplifies the synergy between cutting-edge AI technologies and medical diagnostics, showcasing the potential to revolutionize patient care.

Advancing Medical Image Analysis: The Role of Adaptive Optimization Techniques in Enhancing COVID-19 Detection, Lung Infection, and Tumor Segmentation

Artificial intelligence (AI) holds significant potential to revolutionize healthcare by improving clinical practices and patient outcomes. This research explores the integration of AI in healthcare, focusing on methodologies such as machine learning, natural language processing, and computer vision, which enable the extraction of valuable insights from complex medical imaging and clinical data. Through a comprehensive literature review, the study highlights AI’s practical applications in diagnostics, treatment planning, and predicting patient outcomes. Additionally, ethical issues, data privacy, and legal frameworks are examined, emphasizing the importance of responsible AI usage in healthcare. The findings demonstrate AI’s ability to enhance diagnostic accuracy, streamline administrative tasks, and optimize resource allocation, leading to personalized treatments and more efficient healthcare management. However, challenges remain, including data quality, algorithm transparency, and ethical concerns, which must be addressed to ensure safe and effective AI deployment. Continued research, collaboration between healthcare professionals and AI experts, and the development of robust regulatory frameworks are essential for maximizing AI’s benefits while minimizing risks. This research underscores the transformative potential of AI in healthcare and stresses the need for a multidisciplinary approach to address the ethical and regulatory complexities involved in its widespread adoption

Developing Role of Artificial Intelligence in Radiology in the UK

Artificial intelligence (AI) is revolutionising radiological diagnosis in the UK, promising to enhance the accuracy, efficiency, and accessibility of healthcare. The integration of AI into radiology is particularly timely, as the National Health Service (NHS) faces increasing demand for imaging services, coupled with a shortage of radiologists. AI technologies, including deep learning algorithms and machine learning systems, are being developed to assist in interpreting complex medical images such as X-rays, CT scans, and MRIs. One of the key benefits of AI in radiology is its ability to quickly and accurately detect abnormalities. For instance, AI algorithms can identify early signs of diseases like cancer, strokes, and fractures, often with a precision that rivals or exceeds human expertise. This has the potential to significantly reduce diagnostic errors, expedite treatment plans, and improve patient outcomes. For example, AI tools are already in use in the UK to flag lung nodules on CT scans, assisting radiologists in early cancer detection. AI also offers efficiency gains. By automating routine tasks, such as identifying normal scans or prioritizing urgent cases, AI can help streamline workflows, reduce waiting times, and alleviate the burden on overworked radiologists. This is critical, as delays in diagnosis can have serious consequences for patient care. However, the widespread adoption of AI in radiology is not without challenges. Concerns about data privacy, algorithmic transparency, and the potential for over-reliance on AI must be carefully managed. It is crucial to strike a balance where AI complements, rather than replaces, the expertise of radiologists. Ultimately, AI's role in radiological diagnosis in the UK is poised to grow, offering a future where healthcare is not only faster and more accurate but also more equitable for patients across the country.

Efficient skin lesion segmentation with boundary distillation.

Medical image segmentation models are commonly known for their complex structures, which often render them impractical for use on edge computing devices and compromising efficiency in the segmentation process. In light of this, the industry has proposed the adoption of knowledge distillation techniques. Nevertheless, the vast majority of existing knowledge distillation methods are focused on the classification tasks of skin diseases. Specifically, for the segmentation tasks of dermoscopy lesion images, these knowledge distillation methods fail to fully recognize the importance of features in the boundary regions of lesions within medical images, lacking boundary awareness for skin lesions. This paper introduces pioneering medical image knowledge distillation architecture. The aim of this method is to facilitate the efficient transfer of knowledge from existing complex medical image segmentation networks to a more simplified student network. Initially, a masked boundary feature (MBF) distillation module is designed. By applying random masking to the periphery of skin lesions, the MBF distillation module obliges the student network to reproduce the comprehensive features of the teacher network. This process, in turn, augments the representational capabilities of the student network. Building on the MBF distillation module, this paper employs a cascaded combination approach to integrate the MBF distillation module into a multi-head boundary feature (M2BF) distillation module, further strengthening the student network's feature learning ability and enhancing the overall image segmentation performance of the distillation model. This method has been experimentally validated on the public datasets ISIC-2016 and PH2, with results showing significant performance improvements in the student network. Our findings highlight the practical utility of the lightweight network distilled using our approach, particularly in scenarios demanding high operational speed and minimal storage usage. This research offers promising prospects for practical applications in the realm of medical image segmentation.

Semi-supervised lung adenocarcinoma histopathology image classification based on multi-teacher knowledge distillation.

In this study, we propose a semi-supervised learning scheme using a patch-based deep learning framework to tackle the challenge of high-precision classification of seven lung tumor growth patterns, despite having a small amount of labeled data in whole slide images (WSIs). This scheme aims to enhance generalization ability with limited data and reduce dependence on large amounts of labeled data. It effectively addresses the common challenge of high demand for labeled data in medical image analysis.

Approach. To address these challenges, the study employs a semi-supervised learning approach enhanced by a dynamic confidence threshold mechanism. This mechanism adjusts based on the quantity and quality of pseudo labels generated. This dynamic thresholding mechanism helps avoid the imbalance of pseudo-label categories and the low number of pseudo-labels that may result from a higher fixed threshold. Furthermore, the research introduces a multi-teacher knowledge distillation technique. This technique adaptively weights predictions from multiple teacher models to transfer reliable knowledge and safeguard student models from low-quality teacher predictions.

Main results. The framework underwent rigorous training and evaluation using a dataset of 150 WSIs, each representing one of the seven growth patterns. The experimental results demonstrate that the framework is highly accurate in classifying lung tumor growth patterns in histopathology images. Notably, the performance of the framework is comparable to that of fully supervised models and human pathologists. In addition, the framework's evaluation metrics on a publicly available dataset are higher than those of previous studies, indicating good generalizability.

Significance. This research demonstrates that a semi-supervised learning approach can achieve results comparable to fully supervised models and expert pathologists, thus opening new possibilities for efficient and cost-effective medical images analysis. The implementation of dynamic confidence thresholding and multi-teacher knowledge distillation techniques represents a significant advancement in applying deep learning to complex medical image analysis tasks. This advancement could lead to faster and more accurate diagnoses, ultimately improving patient outcomes and fostering the overall progress of healthcare technology.&#xD.

HMedCaps: a new hybrid capsule network architecture for complex medical images

HMedCaps: a new hybrid capsule network architecture for complex medical images