Medical Image Analysis System Research Articles

Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challenges

Deep learning techniques have achieved superior performance in computer-aided medical image analysis, yet they are still vulnerable to imperceptible adversarial attacks, resulting in potential misdiagnosis in clinical practice. Oppositely, recent years have also witnessed remarkable progress in defense against these tailored adversarial examples in deep medical diagnosis systems. In this exposition, we present a comprehensive survey on recent advances in adversarial attacks and defenses for medical image analysis with a systematic taxonomy in terms of the application scenario. We also provide a unified framework for different types of adversarial attack and defense methods in the context of medical image analysis. For a fair comparison, we establish a new benchmark for adversarially robust medical diagnosis models obtained by adversarial training under various scenarios. To the best of our knowledge, this is the first survey paper that provides a thorough evaluation of adversarially robust medical diagnosis models. By analyzing qualitative and quantitative results, we conclude this survey with a detailed discussion of current challenges for adversarial attack and defense in medical image analysis systems to shed light on future research directions. Code is available on GitHub.

Developing an explainable diagnosis system utilizing deep learning model: a case study of spontaneous pneumothorax

Objective. The trend in the medical field is towards intelligent detection-based medical diagnostic systems. However, these methods are often seen as ‘black boxes’ due to their lack of interpretability. This situation presents challenges in identifying reasons for misdiagnoses and improving accuracy, which leads to potential risks of misdiagnosis and delayed treatment. Therefore, how to enhance the interpretability of diagnostic models is crucial for improving patient outcomes and reducing treatment delays. So far, only limited researches exist on deep learning-based prediction of spontaneous pneumothorax, a pulmonary disease that affects lung ventilation and venous return. Approach. This study develops an integrated medical image analysis system using explainable deep learning model for image recognition and visualization to achieve an interpretable automatic diagnosis process. Main results. The system achieves an impressive 95.56% accuracy in pneumothorax classification, which emphasizes the significance of the blood vessel penetration defect in clinical judgment. Significance. This would lead to improve model trustworthiness, reduce uncertainty, and accurate diagnosis of various lung diseases, which results in better medical outcomes for patients and better utilization of medical resources. Future research can focus on implementing new deep learning models to detect and diagnose other lung diseases that can enhance the generalizability of this system.

ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image Dataset

Automated medical image analysis systems often require large amounts of training data with high quality labels, which are difficult and time consuming to generate. This paper introduces Radiology Object in COntext version 2 (ROCOv2), a multimodal dataset consisting of radiological images and associated medical concepts and captions extracted from the PMC Open Access subset. It is an updated version of the ROCO dataset published in 2018, and adds 35,705 new images added to PMC since 2018. It further provides manually curated concepts for imaging modalities with additional anatomical and directional concepts for X-rays. The dataset consists of 79,789 images and has been used, with minor modifications, in the concept detection and caption prediction tasks of ImageCLEFmedical Caption 2023. The dataset is suitable for training image annotation models based on image-caption pairs, or for multi-label image classification using Unified Medical Language System (UMLS) concepts provided with each image. In addition, it can serve for pre-training of medical domain models, and evaluation of deep learning models for multi-task learning.

Multimodal Machine Learning in Image-Based and Clinical Biomedicine: Survey and Prospects

Machine learning (ML) applications in medical artificial intelligence (AI) systems have shifted from traditional and statistical methods to increasing application of deep learning models. This survey navigates the current landscape of multimodal ML, focusing on its profound impact on medical image analysis and clinical decision support systems. Emphasizing challenges and innovations in addressing multimodal representation, fusion, translation, alignment, and co-learning, the paper explores the transformative potential of multimodal models for clinical predictions. It also highlights the need for principled assessments and practical implementation of such models, bringing attention to the dynamics between decision support systems and healthcare providers and personnel. Despite advancements, challenges such as data biases and the scarcity of “big data” in many biomedical domains persist. We conclude with a discussion on principled innovation and collaborative efforts to further the mission of seamless integration of multimodal ML models into biomedical practice.

Image encryption with leveraging blockchain-based optimal deep learning for Secure Disease Detection and Classification in a smart healthcare environment

<abstract> <p>Blockchain (BC) in healthcare can be used for sharing medical records and secure storage and other confidential data. Deep learning (DL) assists in disease recognition through image analysis, specifically in detecting medical conditions from images. Image encryption ensures the security and privacy of medical images by encrypting the image before sharing or storage. The combination of image encryption, BC, and DL provides an efficient and secure system for medical image analysis and disease detection in healthcare. Therefore, we designed a new BC with an Image Encryption-based Optimal DL for Secure Disease Detection and Classification (BIEODL-SDDC) technique. The presented BIEODL-SDDC technique enables the secure sharing of medical images via encryption and BC technology with a DL-based disease classification process. Furthermore, the medical image encryption process took place using the ElGamal Encryption technique with a giraffe kicking optimization (GKO) algorithm-based key generation process. In addition, BC-based smart contracts (SCs) were used for the secure sharing of medical images. For the disease detection process, the BIEODL-SDDC technique encompassed EfficientNet-B7-CBAM-based feature extraction, Adam optimizer, and a fully connected neural network (FCNN). The experimental validation of the BIEODL-SDDC technique was tested on medical image datasets and the outcome highlighted an enhanced accuracy outcome of 94.81% over other techniques.</p> </abstract>

ASSOCIATION OF MASSETER MUSCLE VOLUME WITH RISK OF OSTEOPOROSIS IN OLDER ADULTS: THE BUNKYO HEALTH STUDY

Abstract Abstract The relationship between bone mineral density (BMD) and oral function has been previously studied. However, the relationship between the masseter muscle, which plays an important role in oral function, and BMD and osteoporosis in older adults has not been investigated. This study investigated the association between masseter muscle volume (MMV) and old age in relation to osteoporosis prevalence and hip joint BMD. Body composition and BMD of 1534 people aged 65–84 years living in Bunkyo-ku, Tokyo, were measured using dual-energy X-ray absorptiometry. MMV was measured using a three-dimensional medical image analysis system. Participants were divided into five groups based on MMV by 20% for each gender (Quintile 1–5: Q1–5, Q1< Q5). Logistic regression models were employed to estimate multivariable-adjusted odds ratios (ORs) for osteoporosis determined by T-score (<−2.5 standard deviation) using the Q5 reference. Subsequently, analysis of covariance was used to investigate the relationship between MMV and BMD. Adjustment for age, body mass index, smoking history, alcohol intake, calcium intake, 25(OH)D, diabetes, and osteoporosis drugs or estrogen. In men, Q1 had higher hip osteoporosis prevalence than Q5 (OR 11.65; 95% confidence interval, 1.48–1.62, p=0.020). Further, hip BMD was significantly higher in Q5 than in Q1 (p=0.001). In women, MMV and old age was not associated with osteoporosis prevalence. However, hip BMD was significantly higher in Q3,4 than in Q1 (p=0.003). Older adults with lower MMV had lower BMD in the hip joint. Additionally, men had higher odds of osteoporosis of the hip joint.

A Comprehensive Review and Analysis of Deep Learning-Based Medical Image Adversarial Attack and Defense

Deep learning approaches have demonstrated great achievements in the field of computer-aided medical image analysis, improving the precision of diagnosis across a range of medical disorders. These developments have not, however, been immune to the appearance of adversarial attacks, creating the possibility of incorrect diagnosis with substantial clinical implications. Concurrently, the field has seen notable advancements in defending against such targeted adversary intrusions in deep medical diagnostic systems. In the context of medical image analysis, this article provides a comprehensive survey of current advancements in adversarial attacks and their accompanying defensive strategies. In addition, a comprehensive conceptual analysis is presented, including several adversarial attacks and defensive strategies designed for the interpretation of medical images. This survey, which draws on qualitative and quantitative findings, concludes with a thorough discussion of the problems with adversarial attack and defensive mechanisms that are unique to medical image analysis systems, opening up new directions for future research. We identified that the main problems with adversarial attack and defense in medical imaging include dataset and labeling, computational resources, robustness against target attacks, evaluation of transferability and adaptability, interpretability and explainability, real-time detection and response, and adversarial attacks in multi-modal fusion. The area of medical imaging adversarial attack and defensive mechanisms might move toward more secure, dependable, and therapeutically useful deep learning systems by filling in these research gaps and following these future objectives.

AI image-based diagnosis systems: how to implement them?

Artificial intelligence (AI) is starting to be widely used in the medical field and has great potential benefits to help doctors and patients. However, it also raises new challenges and problems. This paper analyzed the existing capacities of AI to make a diagnosis and assessed the legal consequences. We present AI medical image analysis systems developed in Belarus. International practice on how AI-systems are implemented in medicine is analyzed. Russian experience in developing standards to test and use AI systems in hospitals is described. Finally, the paper put forward some suggestions on how to improve the legal framework of AI systems using in medicine.

The evaluation of IgG4 and IgG expression in cutaneous Rosai-Dorfman disease

ObjectiveThe authors investigated the expression of IgG4 and IgG in cutaneous Rosai-Dorfman Disease (CRDD) to further improve the understanding of this disease. MethodsThe authors retrospectively reviewed the clinicopathological features of 23 CRDD patients. The authors diagnosed CRDD by the presence of emperipolesis and immunohistochemical (IHC) staining of histiocytes consisting of S-100(+)/CD68(+)/CD1a(-) cells. The expressions of IgG and IgG4 in cutaneous specimens were assessed by IHC (EnVision) and quantitatively calculated by a medical image analysis system. ResultsAll 23 patients, including 14 males and 9 females, were confirmed to have CRDD. Their ages ranged from 17 to 68 years (mean 47.91 ± 14.16). The most frequently affected skin regions were the face, followed by the trunk, ears, neck, limbs, and genitals. In 16 of these cases, the disease presented as a single lesion. IHC staining of sections showed that IgG was positive (≥ 10 cells/High-Power Field [HPF]) in 22 cases, while IgG4 was positive (≥ 10 cells/HPF) in 18 cases. Moreover, the IgG4/IgG proportion ranged from 1.7% to 85.7% (mean 29.50 ± 24.67%, median 18.4%) in the 18 cases. Study limitationsIn the majority of studies, as well as in the current study, the design. RDD is a rare disease, so the sample size is small. In the next studies to come, the authors will expand the sample for multi-center verification and in-depth study. ConclusionThe positive rates of IgG4 and IgG and the IgG4/IgG ratio assessed through IHC staining may be important in understanding the pathogenesis of CRDD.

A new AI assisted medical molecular image diagnostic model

In recent times, ML algorithms that plays a significant role right from drug discovery to clinical decision making. The recent advances in DL technologies contribute towards improved performance for carrying out computer aided medical image analysis and disease diagnosis. The key benefit of AI in processing of medical big data offers spectacular insights into the hierarchal relationships that exist among data which can be algorithmically explored thus replacing the tedious manual processes to extract and localize specific areas of interests in medical images thus considerably changing the way medicine has been practiced so far. In bio medical related clinical applications, there is a constant demand pertaining the research and development with respect to deploying AI as a mainstream tool to perform several medical imaging activities like analysis, diagnosis, segmentation as well as classification. The increased usage of electronic health records and medical images being its integral component the need for appropriate and efficient AI assisted medical image analysis system that takes care of accurate and automated decision making could be of great help to radiologists and medical practitioners. Molecular image analysis is a dynamic field that makes use of ML and DL algorithms that utilizes labeled and structured information which also proves to be helpful to the patients as they serve as an initial interface before further diagnosis and treatments. Thus our research aims to offer a novel and efficient AI based medical analysis system that can assist clinical practitioners to focus on enhancing the disease diagnosis through DL based medical image analysis and decision making. In addition, we also address specific challenges related to disease diagnosis and propose novel GAN model for improved diagnosis and implementation. Our proposed technique can also be generalized to generate synthetic data for further issues related to molecular image analysis in the field of medicine and help towards building a better disease diagnosis model.

Deceptive Tricks in Artificial Intelligence: Adversarial Attacks in Ophthalmology.

The artificial intelligence (AI) systems used for diagnosing ophthalmic diseases have significantly progressed in recent years. The diagnosis of difficult eye conditions, such as cataracts, diabetic retinopathy, age-related macular degeneration, glaucoma, and retinopathy of prematurity, has become significantly less complicated as a result of the development of AI algorithms, which are currently on par with ophthalmologists in terms of their level of effectiveness. However, in the context of building AI systems for medical applications such as identifying eye diseases, addressing the challenges of safety and trustworthiness is paramount, including the emerging threat of adversarial attacks. Research has increasingly focused on understanding and mitigating these attacks, with numerous articles discussing this topic in recent years. As a starting point for our discussion, we used the paper by Ma et al. "Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems". A literature review was performed for this study, which included a thorough search of open-access research papers using online sources (PubMed and Google). The research provides examples of unique attack strategies for medical images. Unfortunately, unique algorithms for attacks on the various ophthalmic image types have yet to be developed. It is a task that needs to be performed. As a result, it is necessary to build algorithms that validate the computation and explain the findings of artificial intelligence models. In this article, we focus on adversarial attacks, one of the most well-known attack methods, which provide evidence (i.e., adversarial examples) of the lack of resilience of decision models that do not include provable guarantees. Adversarial attacks have the potential to provide inaccurate findings in deep learning systems and can have catastrophic effects in the healthcare industry, such as healthcare financing fraud and wrong diagnosis.

Shuffled Shepherd Deer Hunting Optimization based Deep Neural Network for Breast Cancer Classification using Breast Histopathology Images

Accurate classification of breast cancer from the histopathology images poses a difficult task because of various benign breast tissue proliferative lesions and heterogeneity of abnormal cell growth. Various breast cancer classification methods are adopted in recent decades to categorize the breast cancer from histopathology images, but generating accurate classification result poses a complex task in medical image analysis system. Therefore, an accurate breast cancer classification method named Shuffled Shepherd Deer Hunting Optimization-based Deep Neural Network (SSDHO-based DNN) is designed for classifying the breast tumor images into six different classes, like non-tubule, non-tumor nuclei, tubule, apoptosis, tumor nuclei, and mitosis. The proposed algorithm named SSDHO is modelled by merging the Shuffled Shepherd Optimization Algorithm (SSOA) and Deer Hunting Optimization Algorithm (DHOA). Here, the feature, like statistical features, shape features and Convolutional Neural Network (CNN) features are effectively mined from the segmented blood cells such that these extracted features make the classification process more effective using DNN. By employing DNN, the breast cancer classification process is achieved more efficiently with their associated hidden neurons and generates the classification result more accurately. The devised approach obtained maximum results in terms of accuracy, precision, sensitivity, and specificity by acquiring the values of 0.9561, 0.8232, 0.7903, and 0.9426, respectively.

Generative Artificial Intelligence-based Diagnostic Algorithms in Patient Data Processing, in Medical Image Analysis Systems, and in Healthcare Risk Assessment

Generative Artificial Intelligence-based Diagnostic Algorithms in Patient Data Processing, in Medical Image Analysis Systems, and in Healthcare Risk Assessment

Enhanced Tunicate Swarm Optimization with Transfer Learning Enabled Medical Image Analysis System

Enhanced Tunicate Swarm Optimization with Transfer Learning Enabled Medical Image Analysis System

Ensembling to Leverage the Interpretability of Medical Image Analysis Systems

Ensembling to Leverage the Interpretability of Medical Image Analysis Systems

Machine Learning Approaches in Developing Expert System for Medical Image Analysis with respect to THR: From Detection to Diagnosis

Machine Learning Approaches in Developing Expert System for Medical Image Analysis with respect to THR: From Detection to Diagnosis

OPTIMIZED DEEP NEURAL NETWORKS ARCHITECTURE MODEL FOR BREAST CANCER DIAGNOSIS

Breast cancer has increasingly claimed the lives of women. Oncologists use digital mammograms as a viable source to detect breast cancer and classify it into benign and malignant based on the severity. The performance of the traditional methods on breast cancer detection could not be improved beyond a certain point due to the limitations and scope of computing. Moreover, the constrained scope of image processing techniques in developing automated breast cancer detection systems has motivated the researchers to shift their focus towards Artificial Intelligence based models. The Neural Networks (NN) have exhibited greater scope for the development of automated medical image analysis systems with the highest degree of accuracy. As NN model enables the automated system to understand the feature of problem-solving without being explicitly programmed. The optimization for NN offers an additional payoff on accuracy, computational complexity, and time. As the scope and suitability of optimization methods are data-dependent, the choice of selection of an appropriate optimization method itself is emerging as a prominent domain of research. In this paper, Deep Neural Networks (DNN) with different optimizers and Learning rates were designed for the prediction of breast cancer and its classification. Comparative performance analysis of five distinct first-order gradient-based optimization techniques, namely, Adaptive Gradient (Adagrad), Root Mean Square Propagation (RMSProp), Adaptive Delta (Adadelta), Adaptive Moment Estimation (Adam), and Stochastic Gradient Descent (SGD), is carried out to make predictions on the classification of breast cancer masses. For this purpose, the Mammographic Mass dataset was chosen for experimentation. The parameters determined for experiments were chosen on the number of hidden layers and learning rate along with hyperparameter tuning. The impacts of those optimizers were tested on the NN with One Hidden Layer (NN1HL), DNN with Three Hidden Layers (DNN4HL), and DNN with Eight Hidden Layers (DNN8HL). The experimental results showed that DNN8HL-Adam (DNN8HL-AM) had produced the highest accuracy of 91% among its counterparts. This research endorsed that the incorporation of optimizers in DNN contributes to an increased accuracy and optimized architecture for automated system development using neural networks.

Comparison Between Median Filter and Wiener Filter to Get High Accuracy for Blood Vessel Image Extraction

With today's advancing technology, support of developing hardware and software systems, the developments in the field of medicine have increased considerably. In particular, medical image analysis and processing systems have taken a considerable lead. The development of an automatic system could provide great convenience for doctors and practitioners in the field. The image processing techniques proposed in this study can contribute to more effective analysis and more accurate diagnosis, regardless of the individual levels of experience of the users or particular situations and conditions such as fatigue or image quality. This paper presents a robust method for retinal blood vessel segmentation and some automatic algorithms for analyzing the vessel network and pixel classification into vessel and non-vessel .The aim of the work extraction or segmentation of retinal blood vessels used computer vision and image processing for getting high accuracy (comparison with manual) .Also We used the preprocessing techniques for enhancement of the image .And used two types of filter for comparing result to get best scenario. Also for simulation result we used the matlab and implement on DRIVE database.

Enhancing adversarial defense for medical image analysis systems with pruning and attention mechanism.

Deep learning has achieved impressive performance across a variety of tasks, including medical image processing. However, recent research has shown that deep neural networks (DNNs) are susceptible to small adversarial perturbations in the image, which raise safety concerns about the deployment of these systems in clinical settings. To improve the defense of the medical imaging system against adversarial examples, we propose a new model-based defense framework for medical image DNNs model equipped with pruning and attention mechanism module based on the analysis of the reason why existing medical image DNNs models are vulnerable to attacks from adversarial examples is that complex biological texture of medical imaging and overparameterized medical image DNNs model. Three benchmark medical image datasets have verified the effectiveness of our method in improving the robustness of medical image DNNs models. In the chest X-ray datasets, our defending method can even achieve up 77.18% defense rate for projected gradient descent attack and 69.49% defense rate for DeepFool attack. And through ablation experiments on the pruning module and the attention mechanism module, it is verified that the use of pruning and attention mechanism can effectively improve the robustness of the medical image DNNs model. Compared with the existing model-based defense methods proposed for natural images, our defense method is more suitable for medical images. Our method can be a general strategy to approach the design of more explainable and secure medical deep learning systems, and can be widely used in various medical image tasks to improve the robustness of medical models.

Deep ensemble learning for skin lesions classification with convolutional neural network

One type of skin cancer that is considered a malignant tumor is melanoma. Such a dangerous disease can cause a lot of death in the world. The early detection of skin lesions becomes an important task in cancer diagnosis, therefore the patient survival can be improved. Recently, a machine learning paradigm emerged known as deep learning (DL) utilized for skin lesions classification. However, in some previous studies by using seven class images diagnostic of skin lesions classification based on a single DL approach with CNNs architecture not produce a satisfying performance. The DL approach allows the development of a medical image analysis system that can utilize an extraordinary network for improving the performance, such as the deep convolutional neural networks (DCNNs) method. In this study, we propose an ensemble learning approach that combines three DCNNs architectures such as Inception V3, Inception ResNet V2 and DenseNet 201 for improving the performance in terms of accuracy, sensitivity, specificity, precision, and F1-score. Seven classes of dermoscopy image categories of skin lesions is utilized with 10015 dermoscopy images from well known the HAM10000 dataset. As found in the results with proposed model ensemble learning architecture produce good classification performance with 97.23% accuracy, 90.12% sensitivity, 97.73% specificity, 82.01% precision, and 85.01% F1-Score. This method gives promising results in classifying skin lesions for cancer diagnosis.