Image Augmentation Using Fractals for Medical Image Diagnosis

Deep Learning has emerged as a strategic area in medical image diagnosis, with numerous studies exploring automation in this field. However, many existing approaches attempt to fully replace medical professionals by relying exclusively on model predictions. This thesis presents an alternative strategy, proposing Deep Learning architectures designed to support, rather than replace, physicians in diagnostic tasks. Two distinct methodologies are explored to achieve this goal: Content-Based Image Retrieval and eXplainable Artificial Intelligence. Content-Based Image Retrieval system enables physicians to compare complex cases with similar ones from a curated database, enhancing decision-making through feature-based similarities. The eXplainable Artificial Intelligence approach provides visual explanations through heatmaps, indicating the regions of interest detected by the model. The thesis introduces two novel architecturesMulti-Output Classification Autoencoder (MOC-AE) and Multi-Output Classification Variational Autoencoder (MOC-VAE). These models employ multi-objective training to generate rich image descriptors, capturing both pathological and anatomical information. These descriptors are then used to identify visually similar cases in a low-dimensional space. To address the challenge of quantifying visual similarity in Content-Based Image Retrieval, the Sliced Wasserstein distance is proposed, offering a robust metric for comparative diagnosis. Furthermore, the thesis demonstrates the utility of these architectures in generating precise, non-linear explanations for diagnoses, leveraging the factorization process inherent to the models. The simplicity and enhanced performance of the proposed approaches, compared to prior methods, offer a foundation for future research and real-world applications in medical diagnostics using Deep Learning. RESUMEN El Deep Learning ha surgido como un área estratégica en el diagnóstico de imágenes médicas, con numerosos estudios que exploran la automatización en este campo. Sin embargo, muchos enfoques actuales buscan reemplazar por completo a los profesionales médicos basándose únicamente en las predicciones de los modelos. Esta tesis presenta una estrategia alternativa, proponiendo arquitecturas de Deep Learning diseñadas para apoyar, en lugar de reemplazar, a los médicos en tareas diagnósticas. Se exploran dos metodologías distintas para alcanzar este objetivo: Sistemas de Recuperación de Imágenes Basada en Contenido e Inteligencia Artificial Explicable. Los Sistemas de Recuperación de Imágenes Basada en Contenido permiten a los médicos comparar casos complejos con otros similares de una base de datos curada, mejorando la toma de decisiones mediante similitudes basadas en características. El enfoque de la Inteligencia Artificial Explicable proporciona explicaciones visuales a través de mapas de calor, que indican las regiones de interés detectadas por el modelo. La tesis introduce dos arquitecturas novedosas: el Autoencoder de Clasificación Multi-Salida (MOC-AE) y el Autoencoder Variacional de Clasificación Multi-Salida (MOC-VAE). Estos modelos emplean un entrenamiento multiobjetivo para generar descriptores de imágenes enriquecidos que capturan tanto información patológica como anatómica. Estos descriptores se utilizan para identificar casos visualmente similares en un espacio de baja dimensionalidad. Para abordar el desafío de cuantificar la similitud visual en Sistemas de Recuperación de Imágenes Basada en Contenido, se propone la distancia de Wasserstein por secciones, ofreciendo una métrica robusta para el diagnóstico comparativo. Además, la tesis demuestra la utilidad de estas arquitecturas para generar explicaciones precisas y no lineales de los diagnósticos, aprovechando el proceso de factorización inherente a los modelos. La simplicidad y el rendimiento mejorado de los enfoques propuestos, en comparación con métodos anteriores, ofrecen una base sólida para futuras investigaciones y aplicaciones reales en diagnósticos médicos utilizando Deep Learning.

This paper investigates the application of nanometer synthetic materials in medical imaging diagnosis. The main synthesis methods of nanomaterials are described, and nanomaterials are applied to X-ray CT imaging, magnetic resonance imaging, PAT imaging, fluorescence imaging, photoacoustic imaging and PET imaging. The diagnostic results can be obtained by applying spatial filtering to filter operation, medical imaging and the filtering processing of image segmentation. By extracting the medical image texture feature using gray level cooccurrence matrix, studying shallow network features and combining the characteristics of the learning result, a more comprehensive medical imaging diagnosis can be obtained. The experimental results show that the method can reduce the error rate of medical imaging diagnosis and accelerate the efficiency of medical imaging diagnosis.

Given current error rates, this article surveys various approaches and techniques for improved breast lesion diagnosis in medical images, including mammography, ultrasound and magnetic resonance imaging. The author also includes studies that compare human versus computer-aided diagnosis.

Nanotechnology is an alternative material manufacturing technology, and the research field involves a broad field of modern technology, especially in the field of high‐end manufacturing. Nanotechnology is a technique for studying the properties and applications of materials with structural dimensions in the range of 1 nanometer to 100 nanometers. Medical imaging refers to the technology and processing process of obtaining internal tissue images of the human body or a certain part of the human body in a noninvasive way for medical treatment or medical research; the acquired image can be further processed to restore the original image that was not clear enough to highlight some characteristic information in the image. The appearance of medical imaging has promoted the development of the medical field. The purpose of this paper is to study the application of nanoscale microparticle technology in medical imaging diagnosis and treatment. It is expected that the combination of nanotechnology and medical imaging will improve the accuracy of medical imaging diagnosis. This paper mainly introduces the general methods and technologies of technical development of medical imaging instruments and briefly shows the process of data and image analysis. The experimental results in this paper show that when other conditions remain unchanged, the image quality will change when the quality factor of the image changes. When the image quality is 60%, the image transmission rate is about 5.5FPS, which is relatively stable and can be used in the medical field.

Classification problems are increasing in various important applications such as text categorization, images, medical imaging diagnosis and bimolecular analysis etc. due to large amount of attribute set. Feature extraction methods in case of large dataset play an important role to reduce the irrelevant feature and thereby increases the performance of classifier algorithm. There exist various methods based on machine learning for text and image classification. These approaches are utilized for dimensionality reduction which aims to filter less informative and outlier data. Therefore, these approaches provide compact representation and computationally better tractable accuracy. At the same time, these methods can be challenging if the search space is doubled multiple time. To optimize such challenges, a hybrid approach is suggested in this paper. The proposed approach uses differential evolution (DE) for feature selection with naïve bayes (NB) and support vector machine (SVM) classifiers to enhance the performance of selected classifier. The results are verified using text and image data which reflects improved accuracy compared with other conventional techniques. A 25 benchmark datasets (UCI) from different domains are considered to test the proposed algorithms. A comparative study between proposed hybrid classification algorithms are presented in this work. Finally, the experimental result shows that the differential evolution with NB classifier outperforms and produces better estimation of probability terms. The proposed technique in terms of computational time is also feasible.

Objectives: The research aims to develop the segmentation model to identify the deformity in the medical images as accurately as possible and plan for better medical treatment. The study is extended to identify the disease before its appearance in the human body through human aura images to support aura imaging in medical diagnosis. Methods: The study used a brain image from the UCI data set and Aura images from the Biowell data set to identify the disease. The segmentation model Bivariate Gaussian Mixture Model (B.G.M.M) was developed. Model parameters are derived using the Expectation Maximization (E.M) Algorithm. The Grasshopper optimization Algorithm (G.O.A) extracts optimal features from the images. The chosen feature is fed as input to the classification model B.G.M.M. Segmentation accuracy is measured using the quality metrics. Findings: The developed approach shows 97% accuracy in identifying the damaged tissues in MRI images and high-intensity energy zones in the aura images, indicating the potential for deformities. Novelty: This study significantly contributes to the field by offering novel solutions for precise and comprehensive image analysis in medical and aura imaging contexts. Keywords: G.O.A, segmentation, G.M.M, E.M, quality metrics, deformity identification, Hue and saturation

Deep Learning applications have recently emerged for processing and analyzing medical image content. DICOM files are the raw data or the input data for Deep Learning (DL) models used to achieve various tasks such as segmentation, classification, and detection in medical diagnosis. However, such files cannot be used as specific devices produce them; they need multiple pre-processing actions due to the complexity of the problem definition when designing a DL model for medical image research. This paper introduces the innovative PreProcMed framework for data curation, medical image processing, and feature exploration. PreProcMed framework, a pioneering solution, has innovative features chained in an automated workflow using only Python technology, namely i). a new approach in data curation by automated de-identification and anonymization with the option of ii). Selection of the required MRI sequence for the DL model, followed by iii). automated conversion of 2D images in 3D volumes that are easy to use in segmentation models and fully iv). integrates annotation tools like ITKSnap and visualization tools like 3D Slicer. PreProcMed is a modular and flexible framework ready to be modified and adapted according to DL models used for medical imaging research.

Non-negative subspace feature representation for few-shot learning in medical imaging

The convergence of ConvNeXt architecture and classification tasks highlights an auspicious direction in modern computer vision. This review systematically analyzes how ConvNeXt transforms these challenges by examining its implementation from 2020 to 2025. This paper investigates four primary domains where ConvNeXt has demonstrated remarkable potential: medical imaging and diagnosis, general computer vision, fine-level image classification, and defect inspection. Analysis reveals significant performance improvements resulting from these ConvNeXt applications: Data augmentation methods consistently improve Bleu-1 detection metrics and F1-score on scarce datasets. SE (Squeeze-and-Excitation), CA (Channel Attention), and CBAM (Convolutional Block Attention Module) in the ConvNeXt model result in improved performance. ConvNeXt has produced outstanding performance, achieving 99.5% accuracy in medical imaging and brain tumor diagnosis classification. Collectively, these findings demonstrate how ConvNeXt, integrated with modern classification capabilities, continues to advance rapidly. Despite this progress, the ongoing challenge of training stability remains. By critically analyzing these advances and limitations, this paper provides important insights into the current state and potential future development of ConvNext-based classification systems.

Machine Learning, a subtype of AI, enables computers to mimic human behavior without explicit programming. Machine learning models aren't used very often in diagnostic imaging because there isn't enough knowledge and resources to do so. Hence, this study aims to apply automated machine learning to the diagnosis of medical images to make machine learning more accessible to non-experts. In this study, a dataset containing 2313 images each of covid-19, pneumonia and normal chest x-rays were selected and divided into testing, training, and validation datasets. The AutoGluon library was used to train and produce a model that would classify an input image and infer the probable diagnosis from the diseases it was trained upon. This study can prove that applying hyperparameter optimization and neural architecture search is able to produce high accuracy models for medical image diagnosis.

Deep learning has revolutionized the detection of diseases and is helping the healthcare sector break barriers in terms of accuracy and robustness to achieve efficient and robust computer-aided diagnostic systems. The application of deep learning techniques empowers automated AI-based utilities requiring minimal human supervision to perform any task related to medical diagnosis of fractures, tumors, and internal hemorrhage; preoperative planning; intra-operative guidance, etc. However, deep learning faces some major threats to the flourishing healthcare domain. This paper traverses the major challenges that the deep learning community of researchers and engineers faces, particularly in medical image diagnosis, like the unavailability of balanced annotated medical image data, adversarial attacks faced by deep neural networks and architectures due to noisy medical image data, a lack of trustability among users and patients, and ethical and privacy issues related to medical data. This study explores the possibilities of AI autonomy in healthcare by overcoming the concerns about trust that society has in autonomous intelligent systems.

Area under the curve may hide poor generalisation to external datasets

Colorectal cancer has a high incidence rate in all countries around the world, and the survival rate of patients is improved by early detection. With the development of object detection technology based on deep learning, computer-aided diagnosis of colonoscopy medical images becomes a reality, which can effectively reduce the occurrence of missed diagnosis and misdiagnosis. In medical image recognition, the assumption that training samples follow independent identical distribution (IID) is the key to the high accuracy of deep learning. However, the classification of medical images is unbalanced in most cases. This paper proposes a new loss function named the double-balanced loss function for the deep learning model, to improve the impact of datasets on classification accuracy. It introduces the effects of sample size and sample difficulty to the loss calculation and deals with both sample size imbalance and sample difficulty imbalance. And it combines with deep learning to build the medical diagnosis model for colorectal cancer. Experimentally verified by three colorectal white-light endoscopic image datasets, the double-balanced loss function proposed in this paper has better performance on the imbalance classification problem of colorectal medical images.

Cardiovascular medical image and analysis based on 3D vision: A comprehensive survey

Accurate medical image diagnosis is essential in clinical practice and places high demands on the diagnostic skills of imaging professionals. However, a significant shortage of radiologists highlights the gap between supply and demand, leading to the importance of education. Traditional education has largely neglected the development of visual perception skills, which play a critical role in lesion detection. This study aims to investigate visual training methods that can effectively enhance learners’ perceptual abilities in medical image interpretation through a pre-post experiment. In the experiment, the participants of intervention groups underwent intensive training targeting uncovered visual areas under central or peripheral vision occlusion conditions. The result showed that peripheral vision training significantly improved participants’ diagnostic mean accuracy (from 59.5 to 68.0%, p < 0.001), mean sensitivity (from 69.0 to 79.5%, p < 0.001), mean positive predictive value (from 65.6 to 82.9%, p < 0.001), and reduced mean task time (from 1163.4s to 877.3s, p < 0.001). However, neither peripheral nor central vision training significantly improved specificity and negative predictive value, which were metrics of negative diagnostic ability. Consequently, enhancing peripheral vision perception helped to reduce missed diagnoses, but with limited impact on reducing misdiagnosis. The peripheral training enhanced the effectiveness of medical image diagnosis education to provide competent professionals in the field.