Tool In Medical Image Analysis Research Articles

Deep Machine Learning for Medical Diagnosis, Application to Lung Cancer Detection: A Review

Deep learning has emerged as a powerful tool for medical image analysis and diagnosis, demonstrating high performance on tasks such as cancer detection. This literature review synthesizes current research on deep learning techniques applied to lung cancer screening and diagnosis. This review summarizes the state-of-the-art in deep learning for lung cancer detection, highlighting key advances, limitations, and future directions. We prioritized studies utilizing major public datasets, such as LIDC, LUNA16, and JSRT, to provide a comprehensive overview of the field. We focus on deep learning architectures, including 2D and 3D convolutional neural networks (CNNs), dual-path networks, Natural Language Processing (NLP) and vision transformers (ViT). Across studies, deep learning models consistently outperformed traditional machine learning techniques in terms of accuracy, sensitivity, and specificity for lung cancer detection in CT scans. This is attributed to the ability of deep learning models to automatically learn discriminative features from medical images and model complex spatial relationships. However, several challenges remain to be addressed before deep learning models can be widely deployed in clinical practice. These include model dependence on training data, generalization across datasets, integration of clinical metadata, and model interpretability. Overall, deep learning demonstrates great potential for lung cancer detection and precision medicine. However, more research is required to rigorously validate models and address risks. This review provides key insights for both computer scientists and clinicians, summarizing progress and future directions for deep learning in medical image analysis.

MSTAC: A Multi-Stage Automated Classification of COVID-19 Chest X-ray Images Using Stacked CNN Models.

This study introduces a Multi-Stage Automated Classification (MSTAC) system for COVID-19 chest X-ray (CXR) images, utilizing stacked Convolutional Neural Network (CNN) models. Suspected COVID-19 patients often undergo CXR imaging, making it valuable for disease classification. The study collected CXR images from public datasets and aimed to differentiate between COVID-19, non-COVID-19, and healthy cases. MSTAC employs two classification stages: the first distinguishes healthy from unhealthy cases, and the second further classifies COVID-19 and non-COVID-19 cases. Compared to a single CNN-Multiclass model, MSTAC demonstrated superior classification performance, achieving 97.30% accuracy and sensitivity. In contrast, the CNN-Multiclass model showed 94.76% accuracy and sensitivity. MSTAC's effectiveness is highlighted in its promising results over the CNN-Multiclass model, suggesting its potential to assist healthcare professionals in efficiently diagnosing COVID-19 cases. The system outperformed similar techniques, emphasizing its accuracy and efficiency in COVID-19 diagnosis. This research underscores MSTAC as a valuable tool in medical image analysis for enhanced disease classification.

Fractal theory analysis of lung CT image recognition technology and its parameters

With the popularity and maturity of medical imaging technology, CT scans, and other medical technologies are increasingly utilized in clinical diagnosis and treatment. In the diagnosis and treatment of pneumonia or lung tumors, clinicians make extensive use of this technology and rely on CT images to assess the progression of disease or the effectiveness of treatment. But the accuracy of visual interpretation is limited, and much of it requires a doctors extensive clinical experience. In order to reduce the workload of doctors and the misdiagnosis rate, fractal theory is considered an important tool in medical image analysis. This paper introduces the fundamental definition of fractal theory, its objectives, and how the two fractal parameters fractal dimension and lacunarity function to facilitate the recognition, and some of their advantages. They strongly reflect the actual tumor development, and highlight the crucial role played by fractal theory in medical treatment.

Deep Learning in Barrett's Esophagus Diagnosis: Current Status and Future Directions.

Barrett's esophagus (BE) represents a pre-malignant condition characterized by abnormal cellular proliferation in the distal esophagus. A timely and accurate diagnosis of BE is imperative to prevent its progression to esophageal adenocarcinoma, a malignancy associated with a significantly reduced survival rate. In this digital age, deep learning (DL) has emerged as a powerful tool for medical image analysis and diagnostic applications, showcasing vast potential across various medical disciplines. In this comprehensive review, we meticulously assess 33 primary studies employing varied DL techniques, predominantly featuring convolutional neural networks (CNNs), for the diagnosis and understanding of BE. Our primary focus revolves around evaluating the current applications of DL in BE diagnosis, encompassing tasks such as image segmentation and classification, as well as their potential impact and implications in real-world clinical settings. While the applications of DL in BE diagnosis exhibit promising results, they are not without challenges, such as dataset issues and the "black box" nature of models. We discuss these challenges in the concluding section. Essentially, while DL holds tremendous potential to revolutionize BE diagnosis, addressing these challenges is paramount to harnessing its full capacity and ensuring its widespread application in clinical practice.

Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review.

Deep learning has become a popular tool for medical image analysis, but the limited availability of training data remains a major challenge, particularly in the medical field where data acquisition can be costly and subject to privacy regulations. Data augmentation techniques offer a solution by artificially increasing the number of training samples, but these techniques often produce limited and unconvincing results. To address this issue, a growing number of studies have proposed the use of deep generative models to generate more realistic and diverse data that conform to the true distribution of the data. In this review, we focus on three types of deep generative models for medical image augmentation: variational autoencoders, generative adversarial networks, and diffusion models. We provide an overview of the current state of the art in each of these models and discuss their potential for use in different downstream tasks in medical imaging, including classification, segmentation, and cross-modal translation. We also evaluate the strengths and limitations of each model and suggest directions for future research in this field. Our goal is to provide a comprehensive review about the use of deep generative models for medical image augmentation and to highlight the potential of these models for improving the performance of deep learning algorithms in medical image analysis.

Application of Deep Learning in Histopathology Images of Breast Cancer: A Review.

With the development of artificial intelligence technology and computer hardware functions, deep learning algorithms have become a powerful auxiliary tool for medical image analysis. This study was an attempt to use statistical methods to analyze studies related to the detection, segmentation, and classification of breast cancer in pathological images. After an analysis of 107 articles on the application of deep learning to pathological images of breast cancer, this study is divided into three directions based on the types of results they report: detection, segmentation, and classification. We introduced and analyzed models that performed well in these three directions and summarized the related work from recent years. Based on the results obtained, the significant ability of deep learning in the application of breast cancer pathological images can be recognized. Furthermore, in the classification and detection of pathological images of breast cancer, the accuracy of deep learning algorithms has surpassed that of pathologists in certain circumstances. Our study provides a comprehensive review of the development of breast cancer pathological imaging-related research and provides reliable recommendations for the structure of deep learning network models in different application scenarios.

Automated identification of human gastrointestinal tract abnormalities based on deep convolutional neural network with endoscopic images

• A specialized DCNN architecture is proposed to accurately classify human gastrointestinal abnormalities. • It is designed with multiple routes, various image resolutions, and several convolutional layers. • HGANet outperforms state-of-the-art algorithms, exhibiting 0.974 MCC for gastrointestinal abnormalities. • It requires less evaluation time, FLOPS, and parameters compared to previous methods. As a powerful analytic tool for medical image analysis, particularly for endoscopic image interpretation, deep convolutional neural network (DCNN) has gained remarkable attention due to its capacity to provide results comparable to or even exceeding those of medical experts. Automated identification of gastrointestinal abnormalities with endoscopic images is a challenging task even for experienced gastroenterologists which could greatly aid medical diagnosis and reduce the time and cost of investigational procedures. Nonetheless, in medical diagnosis, the human gastrointestinal tract findings are manually determined, and greatly depend on the prowess of the gastrointestinal endoscopist. In addition, this evaluation is laborious and onerous, and there is also a high degree of intra- and inter-laboratory discrepancy in the outcomes. With the aim of preventing these issues, a specialized DCNN architecture is proposed to accurately identify human gastrointestinal abnormalities with endoscopic images. It is meticulously designed with multiple routes, various image resolutions and several convolutional layers to improve the efficacy and performance. The results of our proposed deep learning-based method are presented in terms of specificity, recall, area under the receiver operating characteristics (AUROC) and other metrics in Kvasir dataset. The experimental results of the proposed algorithm outdo recent techniques, exhibiting 0.9743 Matthews correlation coefficient (MCC), and can be used to assist gastroenterologists for the classification of gastrointestinal tract abnormalities. Proposed model is also assessed on skewed Kvasir-Capsule dataset to show its genericity. Consequently, this approach offers an innovative and attainable way for accelerating and systematizing the classification of human gastrointestinal abnormalities along with saving time and exertion.

2D and 3D CT Radiomic Features Performance Comparison in Characterization of Gastric Cancer: A Multi-Center Study.

Radiomics, an emerging tool for medical image analysis, is potential towards precisely characterizing gastric cancer (GC). Whether using one-slice 2D annotation or whole-volume 3D annotation remains a long-time debate, especially for heterogeneous GC. We comprehensively compared 2D and 3D radiomic features' representation and discrimination capacity regarding GC, via three tasks ( TLNM, lymph node metastasis' prediction; TLVI, lymphovascular invasion's prediction; TpT, pT4 or other pT stages' classification). Four-center 539 GC patients were retrospectively enrolled and divided into the training and validation cohorts. From 2D or 3D regions of interest (ROIs) annotated by radiologists, radiomic features were extracted respectively. Feature selection and model construction procedures were customed for each combination of two modalities (2D or 3D) and three tasks. Subsequently, six machine learning models ( Model2DLNM, Model3DLNM; Model2DLVI, Model3DLVI; Model2DpT, Model3DpT) were derived and evaluated to reflect modalities' performances in characterizing GC. Furthermore, we performed an auxiliary experiment to assess modalities' performances when resampling spacing different. Regarding three tasks, the yielded areas under the curve (AUCs) were: Model2DLNM's 0.712 (95% confidence interval, 0.613-0.811), Model3DLNM's 0.680 (0.584-0.775); Model2DLVI's 0.677 (0.595-0.761), Model3DLVI's 0.615 (0.528-0.703); Model2DpT's 0.840 (0.779-0.901), Model3DpT's 0.813 (0.747-0.879). Moreover, the auxiliary experiment indicated that Models2D are statistically advantageous than Models3D with different resampling spacings. Models constructed with 2D radiomic features revealed comparable performances with those constructed with 3D features in characterizing GC. Our work indicated that time-saving 2D annotation would be the better choice in GC, and provided a related reference to further radiomics-based researches.

Visual Analytics of a Computer-Aided Diagnosis System for Pancreatic Lesions.

Machine learning is a powerful and effective tool for medical image analysis to perform computer-aided diagnosis (CAD). Having great potential in improving the accuracy of a diagnosis, CAD systems are often analyzed in terms of the final accuracy, leading to a limited understanding of the internal decision process, impossibility to gain insights, and ultimately to skepticism from clinicians. We present a visual analytics approach to uncover the decision-making process of a CAD system for classifying pancreatic cystic lesions. This CAD algorithm consists of two distinct components: random forest (RF), which classifies a set of predefined features, including demographic features, and a convolutional neural network (CNN), which analyzes radiological (imaging) features of the lesions. We study the class probabilities generated by the RF and the semantical meaning of the features learned by the CNN. We also use an eye tracker to better understand which radiological features are particularly useful for a radiologist to make a diagnosis and to quantitatively compare with the features that lead the CNN to its final classification decision. Additionally, we evaluate the effects and benefits of supplying the CAD system with a case-based visual aid in a second-reader setting.

Assessment of Deep Learning Methods for Differentiating Autoimmune Disorders in Ultrasound Images.

At present, deep learning becomes an important tool in medical image analysis, with good performance in diagnosing, pattern detection, and segmentation. Ultrasound imaging offers an easy and rapid method to detect and diagnose thyroid disorders. With the help of a computer-aided diagnosis (CAD) system based on deep learning, we have the possibility of real-time and non-invasive diagnosing of thyroidal US images. This paper proposed a study based on deep learning with transfer learning for differentiating the thyroidal ultrasound images using image pixels and diagnosis labels as inputs. We trained, assessed, and compared two pre-trained models (VGG-19 and Inception v3) using a dataset of ultrasound images consisting of 2 types of thyroid ultrasound images: autoimmune and normal. The training dataset consisted of 615 thyroid ultrasound images, from which 415 images were diagnosed as autoimmune, and 200 images as normal. The models were assessed using a dataset of 120 images, from which 80 images were diagnosed as autoimmune, and 40 images diagnosed as normal. The two deep learning models obtained very good results, as follows: the pre-trained VGG-19 model obtained 98.60% for the overall test accuracy with an overall specificity of 98.94% and overall sensitivity of 97.97%, while the Inception v3 model obtained 96.4% for the overall test accuracy with an overall specificity of 95.58% and overall sensitivity of 95.58%

Improved Dominance Soft Set Based Decision Rules with Pruning for Leukemia Image Classification

Acute lymphoblastic leukemia is a well-known type of pediatric cancer that affects the blood and bone marrow. If left untreated, it ends in fatal conditions due to its proliferation into the circulation system and other indispensable organs. All over the world, leukemia primarily attacks youngsters and grown-ups. The early diagnosis of leukemia is essential for the recovery of patients, particularly in the case of children. Computational tools for medical image analysis, therefore, have significant use and become the focus of research in medical image processing. The particle swarm optimization algorithm (PSO) is employed to segment the nucleus in the leukemia image. The texture, shape, and color features are extracted from the nucleus. In this article, an improved dominance soft set-based decision rules with pruning (IDSSDRP) algorithm is proposed to predict the blast and non-blast cells of leukemia. This approach proceeds with three distinct phases: (i) improved dominance soft set-based attribute reduction using AND operation in multi-soft set theory, (ii) generation of decision rules using dominance soft set, and (iii) rule pruning. The efficiency of the proposed system is compared with other benchmark classification algorithms. The research outcomes demonstrate that the derived rules efficiently classify cancer and non-cancer cells. Classification metrics are applied along with receiver operating characteristic (ROC) curve analysis to evaluate the efficiency of the proposed framework.

Unsupervised MRI Homogenization: Application to Pediatric Anterior Visual Pathway Segmentation.

Deep learning strategies have become ubiquitous optimization tools for medical image analysis. With the appropriate amount of data, these approaches outperform classic methodologies in a variety of image processing tasks. However, rare diseases and pediatric imaging often lack extensive data. Specially, MRI are uncommon because they require sedation in young children. Moreover, the lack of standardization in MRI protocols introduces a strong variability between different datasets. In this paper, we present a general deep learning architecture for MRI homogenization that also provides the segmentation map of an anatomical region of interest. Homogenization is achieved using an unsupervised architecture based on variational autoencoder with cycle generative adversarial networks, which learns a common space (i.e. a representation of the optimal imaging protocol) using an unpaired image-to-image translation network. The segmentation is simultaneously generated by a supervised learning strategy. We evaluated our method segmenting the challenging anterior visual pathway using three brain T1-weighted MRI datasets (variable protocols and vendors). Our method significantly outperformed a non-homogenized multi-protocol U-Net.

Computer-aided diagnosis of cirrhosis and hepatocellular carcinoma using multi-phase abdomen CT.

High mortality rate due to liver cirrhosis has been reported over the globe in the previous years. Early detection of cirrhosis may help in controlling the disease progression toward hepatocellular carcinoma (HCC). The lack of trained CT radiologists and increased patient population delays the diagnosis and further management. This study proposes a computer-aided diagnosis system for detecting cirrhosis and HCC in a very efficient and less time-consuming approach. Contrast-enhanced CT dataset of 40 patients (n = 40; M:F = 5:3; age = 25-55years) with three groups of subjects: healthy (n = 14), cirrhosis (n = 12) and cirrhosis with HCC (n = 14), were retrospectively analyzed in this study. A novel method for the automatic 3D segmentation of liver using modified region-growing segmentation technique was developed and compared with the state-of-the-art deep learning-based technique. Further, histogram parameters were calculated from segmented CT liver volume for classification between healthy and diseased (cirrhosis and HCC) liver using logistic regression. Multi-phase analysis of CT images was performed to extract 24 temporal features for detecting cirrhosis and HCC liver using support vector machine (SVM). The proposed method produced improved 3D segmentation with Dice coefficient 90% for healthy liver, 86% for cirrhosis and 81% for HCC subjects compared to the deep learning algorithm (healthy: 82%; cirrhosis: 78%; HCC: 70%). Standard deviation and kurtosis were found to be statistically different (p < 0.05) among healthy and diseased liver, and using logistic regression, classification accuracy obtained was 92.5%. For detecting cirrhosis and HCC liver, SVM with RBF kernel obtained highest slice-wise and patient-wise prediction accuracy of 86.9% (precision = 0.93, recall = 0.7) and 80% (precision = 0.86, recall = 0.75), respectively, than that of linear kernel (slice-wise: accuracy = 85.4%, precision = 0.92, recall = 0.67; patient-wise: accuracy = 73.33%, precision = 0.75, recall = 0.75). The proposed computer-aided diagnosis system for detecting cirrhosis and hepatocellular carcinoma (HCC) showed promising results and can be used as effective screening tool in medical image analysis.

Fractional Calculus and Fuzzy Rule Based Filter for Despeckling the Medical Images

Medical ultrasound imaging plays an important role in diagnosis of various complicated disorders. But, these ultrasound images are intrinsically degraded with speckle noise which harshly affects the image visual qualities and essential particulars. Hence, denoising is an unavoidable process in medical image processing. In this paper, a new despeckling technique is presented for denoising the medical ultrasound images by employing fuzzy technique on co-efficient of variation and fractional order integration filter. The proposed technique has two steps. During first step, the noisy image pixels are classified into three regions by using fuzzy technique on co-efficient of variation and consequently, the proposed technique adaptively employs appropriate filters on the grouped pixels to reduce noise in the ultrasound image. In the second step, to obtain an effective denoising image, the fractional order integration filter is applied on the resulting image of step 1. The performance of the proposed technique is tested on various medical images in terms of Peak signal to noise ratio and speckle suppression index quality measures. Experimental results reveal that the proposed despeckling technique can efficiently reduce the speckle noise, protect the edges and preserves any other important structural details of an image. It is suggested that the proposed technique is employed as a preprocessing tool for medical image analysis and diagnosis.

Bruker2nifti: Magnetic Resonance Images converter from Bruker ParaVision to Nifti format

In clinical and pre-clinical research involving medical images, the first step following a Magnetic Resonance Imaging dataset acquisition, usually entails the conversion of image data from the native scanner format to a format suitable for the intended analysis. The proprietary [Bruker ParaVision](https://www.bruker.com/products/mr/preclinical-mri/software/service-support.html) software currently does not provide the tools for conversion of the data to suitable and open formats for research, such as nifti [@cox2004sort], for which most of the available tools for medical image analysis are implemented. For this purpose we have designed and developed [bruker2nifti](https://github.com/SebastianoF/bruker2nifti), a pip-installable Python tool provided with a Graphical User Interface to convert from the native MRI Bruker format to the nifti format, without any intermediate step through the DICOM standard formats [@Mildenberger2002]. Bruker2nifti is intended to be a tool to access the data structure and to parse all parameter files of the Bruker ParaVision format into python dictionaries, to select the relevant information to fill the Nifti header and data volume. Lastly it is meant to be a starting point where to integrate possible future variations in Bruker hardware and ParaVision software future releases.

Multi-Atlas Segmentation Using Partially Annotated Data: Methods and Annotation Strategies

Multi-atlas segmentation is a widely used tool in medical image analysis, providing robust and accurate results by learning from annotated atlas datasets. However, the availability of fully annotated atlas images for training is limited due to the time required for the labelling task. Segmentation methods requiring only a proportion of each atlas image to be labelled could therefore reduce the workload on expert raters tasked with annotating atlas images. To address this issue, we first re-examine the labelling problem common in many existing approaches and formulate its solution in terms of a Markov Random Field energy minimisation problem on a graph connecting atlases and the target image. This provides a unifying framework for multi-atlas segmentation. We then show how modifications in the graph configuration of the proposed framework enable the use of partially annotated atlas images and investigate different partial annotation strategies. The proposed method was evaluated on two Magnetic Resonance Imaging (MRI) datasets for hippocampal and cardiac segmentation. Experiments were performed aimed at (1) recreating existing segmentation techniques with the proposed framework and (2) demonstrating the potential of employing sparsely annotated atlas data for multi-atlas segmentation.

Discontinuity Preserving Image Registration through Motion Segmentation: A Primal-Dual Approach.

Image registration is a powerful tool in medical image analysis and facilitates the clinical routine in several aspects. There are many well established elastic registration methods, but none of them can so far preserve discontinuities in the displacement field. These discontinuities appear in particular at organ boundaries during the breathing induced organ motion. In this paper, we exploit the fact that motion segmentation could play a guiding role during discontinuity preserving registration. The motion segmentation is embedded in a continuous cut framework guaranteeing convexity for motion segmentation. Furthermore we show that a primal-dual method can be used to estimate a solution to this challenging variational problem. Experimental results are presented for MR images with apparent breathing induced sliding motion of the liver along the abdominal wall.

An improved medical image enhancement scheme using Type II fuzzy set

A contrast enhancement of medical images using Type II fuzzy set theory is suggested. Fuzzy set theory considers uncertainty in the form of membership function but to have better information on uncertainty on the membership function, Type II fuzzy set is considered. Type II fuzzy set considers fuzziness in the membership function. Hamacher T co norm is used as an aggregation operator to form a new membership function using the upper and lower membership function of Type II fuzzy set. The image with the new membership function is an enhanced image. As medical images contain lot of uncertainties, Type II fuzzy set may be a good tool for medical image analysis. To show the effectiveness of the proposed method, the results are compared with fuzzy, intuitionistic fuzzy, and existing Type II fuzzy methods. Experiments on several images show that the proposed Type II fuzzy method performs better than the existing methods. To show the advantage of the proposed enhancement method, detection or extraction of abnormal lesions or blood vessels has been carried out on enhanced images of all the methods. It is observed that the segmented results on the proposed enhanced images are better.

Using image segmentation for evaluating 3D statistical shape models built with groupwise correspondence optimization

Statistical shape models (SSMs) are a well-established tool in medical image analysis. The most challenging part of SSM construction, which cannot be solved trivially in 3D, is the establishment of corresponding points, so-called landmarks. A popular approach for solving the correspondence problem is to minimize a groupwise objective function using the optimization by re-parameterization approach. To this end, several objective functions, optimization strategies and re-parameterization functions have been proposed. While previous evaluation studies focused mainly on the objective function, we provide a detailed evaluation of different correspondence methods, objective functions, re-parameterization, and optimization strategies. Moreover and contrary to previous works, we use distance measures that compare landmark shape vectors to the original input shapes, thus adequately accounting for correspondences which undersample certain regions of the input shapes. Additionally, we segment binary expert segmentations to benchmark SSMs constructed from different correspondences. This new evaluation technique overcomes limitations of the correspondence based evaluation and allows for directly quantifying the influence of the correspondence on the expected segmentation accuracy. From our evaluation results we identify pitfalls of the current approach and derive practical recommendations for implementing a groupwise optimization pipeline.

MRF-Based Deformable Registration and Ventilation Estimation of Lung CT

Deformable image registration is an important tool in medical image analysis. In the case of lung computed tomography (CT) registration there are three major challenges: large motion of small features, sliding motions between organs, and changing image contrast due to compression. Recently, Markov random field (MRF)-based discrete optimization strategies have been proposed to overcome problems involved with continuous optimization for registration, in particular its susceptibility to local minima. However, to date the simplifications made to obtain tractable computational complexity reduced the registration accuracy. We address these challenges and preserve the potentially higher quality of discrete approaches with three novel contributions. First, we use an image-derived minimum spanning tree as a simplified graph structure, which copes well with the complex sliding motion and allows us to find the global optimum very efficiently. Second, a stochastic sampling approach for the similarity cost between images is introduced within a symmetric, diffeomorphic B-spline transformation model with diffusion regularization. The complexity is reduced by orders of magnitude and enables the minimization of much larger label spaces. In addition to the geometric transform labels, hyper-labels are introduced, which represent local intensity variations in this task, and allow for the direct estimation of lung ventilation. We validate the improvements in accuracy and performance on exhale-inhale CT volume pairs using a large number of expert landmarks.