Vision based Techniques for Image Classification: A Survey

Medical imaging is becoming indispensable for patients' healthcare. Machine learning plays an essential role in the medical imaging field, including computer-aided diagnosis, image segmentation, image registration, image fusion, image-guided therapy, image annotation, and image database retrieval. With advances in medical imaging, new imaging modalities and methodologies such as cone-beam/multislice CT, 3D ultrasound imaging, tomosynthesis, diffusion-weighted magnetic resonance imaging (MRI), positron-emission tomography (PET)/CT, electrical impedance tomography, and diffuse optical tomography, new machine-learning algorithms/applications are demanded in the medical imaging field. Because of large variations and complexityit is generally difficult to derive analytic solutions or simple equations to represent objects such as lesions and anatomy in medical images. Therefore, tasks in medical imaging require “learning from examples” for accurate representation of data and prior knowledge. Because of its essential needs, machine learning in medical imaging is one of the most promising, growing fields. The main aim of this special issue is to help advance the scientific research within the broad field of machine learning in medical imaging. The special issue was planned in conjunction with the International Workshop on Machine Learning in Medical Imaging (MLMI 2010) [1], which was the first workshop on this topic, held at the 13th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2010) in September, 2010, in Beijing, China. This special issue is one in a series of special issues of journals on this topic [2]; it focuses on major trends and challenges in this area, and it presents work aimed at identifying new cutting-edge techniques and their use in medical imaging. The quality level of the submissions for this special issue was very high. A total of 17 papers were submitted to this issue in response to the call for papers. Based on a rigorous review process, 10 papers (59%) were accepted for publication in the special issue. The special issue starts by a review of studies on a class of machine-learning techniques, called pixel/voxel-based machine learning, in medical imaging by K. Suzuki. A series of medical imaging applications of machine-learning techniques are presented. A large variety of applications are well represented here, including organ modeling by D. Wang et al. and X. Qiao and Y.-W. Chen, brain function estimation by V. Michel et al., image reconstruction by H. Shouno et al., lesion classification by P. Wighton et al., modality classification by X.-H. Han and Y.-W. Chen, lesion segmentation by M. Zortea et al., organ segmentation by S. Alzubi et al., and visualization of molecular signals by F. Mattoli et al. Also, the issue covers various biomedical imaging modalities, including MRI by D. Wang et al., CT by X. Qiao and Y.-W. Chen and H. Shouno et al., functional MRI by V. Michel et al., dermoscopy by P. Wighton et al. and M. Zortea et al., scintigraphy by X.-H. Han and Y.-W. Chen, ultrasound imaging by X.-H. Han and Y.-W. Chen, radiography by X.-H. Han and Y.-W. Chen, MR angiography by S. Alzubi et al., and microscopy by F. Mattoli et al. as well as a variety of organs, including the kidneys by D. Wang et al., liver by X. Qiao and Y.-W. Chen, brain by V. Michel et al. and F. Mattoli et al., chest by S. Alzubi et al., skin by P. Wighton et al. and M. Zortea et al., and heart by F. Mattoli et al. Various machine-learning techniques were developed/used to solve the respective problems, including structured dictionary learning by D. Wang et al., generalized N-dimensional principal component analysis by X. Qiao et al., multiclass sparse Bayesian regression by V. Michel et al., Bayesian hyperparameter inference by H. Shouno et al., supervised learning of probabilistic models based on maximum aposteriori estimation and conditional random fields by P. Wighton et al., joint kernel equal contribution in support vector classification by X.-H. Han and Y.-W. Chen, and iterative hybrid classification by M. Zortea et al. We are grateful to all authors for their excellent contributions to this special issue and to all reviewers for their reviews and constructive suggestions. We hope that this special issue will inspire further ideas for creative research, advance the field of machine learning in medical imaging, and facilitate the translation of the research from bench to bedside. Kenji Suzuki Pingkun Yan Fei Wang Dinggang Shen

The use of machine learning (ML) has been increasing rapidly in the medical imaging field, including computer-aided diagnosis (CAD), radiomics, and medical image analysis. Recently, an ML area called deep learning emerged in the computer vision field and became very popular in many fields. It started from an event in late 2012, when a deep-learning approach based on a convolutional neural network (CNN) won an overwhelming victory in the best-known worldwide computer vision competition, ImageNet Classification. Since then, researchers in virtually all fields, including medical imaging, have started actively participating in the explosively growing field of deep learning. In this paper, the area of deep learning in medical imaging is overviewed, including (1) what was changed in machine learning before and after the introduction of deep learning, (2) what is the source of the power of deep learning, (3) two major deep-learning models: a massive-training artificial neural network (MTANN) and a convolutional neural network (CNN), (4) similarities and differences between the two models, and (5) their applications to medical imaging. This review shows that ML with feature input (or feature-based ML) was dominant before the introduction of deep learning, and that the major and essential difference between ML before and after deep learning is the learning of image data directly without object segmentation or feature extraction; thus, it is the source of the power of deep learning, although the depth of the model is an important attribute. The class of ML with image input (or image-based ML) including deep learning has a long history, but recently gained popularity due to the use of the new terminology, deep learning. There are two major models in this class of ML in medical imaging, MTANN and CNN, which have similarities as well as several differences. In our experience, MTANNs were substantially more efficient in their development, had a higher performance, and required a lesser number of training cases than did CNNs. "Deep learning", or ML with image input, in medical imaging is an explosively growing, promising field. It is expected that ML with image input will be the mainstream area in the field of medical imaging in the next few decades.

The radiographer`s profession holds a significant place among the healthcare professionals in Bulgaria. Applying the medical imaging methods and techniques, performing the nuclear medicine tests and the radiotherapy procedures would be unthinkable without the participation of highly competent radiographers. The introduction of new high-tech equipment and technologies as well as of diagnosing and treating methods pose new challenges to the radiographers who now have to adopt new knowledge and skills and to perfect their competences in order to respond to the challenges of modern healthcare. This study aims at establishing the attitudes and tendency of practicing radiographers towards expanding their professional competences in their field of practice. Documentary, sociological and statistical methods have been used. Sources related to the topic have been researched. The study presents the opinion of 182 radiographers practicing in the North-Eastern region of Bulgaria regarding the attitudes and the tendency to expand the professional competences of radiographers. The interviewees have been distributed as follows: 137 radiographers (75.27%) practicing in the field of medical imaging, 42 (23.08%) – in radiotherapy and 3 (1.65%) in the field of nuclear medicine. The data has been processed mathematically and statistically and the results have been presented as graphs. The study showed that the radiographers from all three fields of practice and within the age group 22-40 years (professional experience up to 15 years) are more willing to expand their professional competences in the field of practice but after additional training compared to the age group 40-60 years (professional experience more than 15 years) who consider the competence they already possess allows them to perform the assigned tasks and that adopting new competences would increase their work load. The data obtained from the study in terms of the field of practice is quite interesting. The radiographers practicing in the field of radiotherapy are more willing to adopt new competences compared to those practicing in the field of medical imaging and nuclear medicine. This is due to some extent to the fact that radiographers working in the field of medical imaging have to deal with more work load, often in emergency situations and this would make difficult assuming new responsibilities.

Background: Application and development of the artificial intelligence technology have generated a profound impact in the field of medical imaging. It helps medical personnel to make an early and more accurate diagnosis. Recently, the deep convolution neural network is emerging as a principal machine learning method in computer vision and has received significant attention in medical imaging. Key Message: In this paper, we will review recent advances in artificial intelligence, machine learning, and deep convolution neural network, focusing on their applications in medical image processing. To illustrate with a concrete example, we discuss in detail the architecture of a convolution neural network through visualization to help understand its internal working mechanism. Summary: This review discusses several open questions, current trends, and critical challenges faced by medical image processing and artificial intelligence technology.

Statistical techniques for digital pre-processing of computed tomography medical images: A current review

Automated classification of magnetic resonance brain images (MRIs) is a hot topic in the field of medical and biomedical imaging. Various methods have been suggested recently to improve this technology. In this paper, to reduce the complexity involved in the medical images and to ameliorate the classification of MRIs, a novel 3D magnetic resonance (MR) brain image classifier using kernel principal component analysis (KPCA) and support vector machines (SVMs) is proposed. Experiments are carried out using A deep multiple kernel SVM (DMK-SVM) and a regular SVM. An algorithm entitled SVM–KPCA is put forward. Its main task is to classify a brain MRI as a normal brain image or as a pathological brain image. This algorithm, firstly, adopts the discrete wavelet transform technique to extract features from images. Secondly, KPCA is applied to decrease the dimensionality of features. SVM is then applied to the reduced data. A K-fold cross-validation strategy is used to avoid overfitting and to ameliorate the generalization of the SVM–KPCA algorithm. Three databases are used to validate the suggested SVM–KPCA method. Three conclusions are obtained from this work. First, KPCA is highly efficient in increasing the classifier’s performance compared with similar algorithms working on the proposed database. Second, the SVM–KPCA algorithm performs well in differentiating between two classes of medical images. Third, the approach is robust and might be utilized for other MRIs. This proposes a significant role for computer aided diagnosis analysis systems used for clinical practice.

Not-so-supervised: A survey of semi-supervised, multi-instance, and transfer learning in medical image analysis.

<p>The article analyzes the basic methods and algorithms of mathematical processing of medical images as objects of computer mathematics. The presented methods and computer algorithms of mathematics relevant and may find application in the field of medical imaging - automated processing of images; as a tool for measurement and determination the optical parameters; identification and formation of medical images database.</p><p>Methods and computer algorithms presented in the article & based on Wolfram Mathematica are also relevant to the problem of modern medical education. As an example of Wolfram Mathematica may be considered appropriate demonstration, such as recognition of special radiographs and morphological imaging. These methods are used to improve the diagnostic significance and value of medical (clinical) research and can serve as an educational interactive demonstration.</p><p>Implementation submitted individual methods and algorithms of computer Wolfram Mathematics contributes, in general, the optimization process of practical processing and presentation of medical images.</p>

In recent years, there has been a noticeable increase in the incidence of thyroid diseases, posing severe challenges to the traditional diagnosis and treatment methods. As a result, artificial intelligence technology has emerged as a valuable tool in the field of thyroid medical imaging, offering substantial support for auxiliary diagnosis and treatment in the future. In this paper, the application of artificial intelligence in the field of thyroid medical imaging is divided into three parts: image segmentation and texture analysis, benign and malignant diagnosis of thyroid gland, and postoperative analysis and prediction of thyroid conditions. Through an examination of recent research datasets and an analysis of the medical imaging process, this paper investigates the application of various algorithm models in these three areas and provides a comprehensive overview of the latest research trends. Furthermore, some certain directions for future research are also provided in this work.

The fields of medical imaging and medical imaging instrumentation are increasingly important. The state-of-the-art continues to advance at a very rapid pace. In fact, various medical imaging modalities are under development at the National Synchrotron Light Source (such as MECT and Transvenous Angiography.) It is important to understand how these techniques compare with today`s more conventional imaging modalities. The purpose of this report is to provide some basic information about the various medical imaging technologies currently in use and their potential developments as a basis for this comparison. This report is by no means an in-depth study of the physics and instrumentation of the various imaging modalities; instead, it is an attempt to provide an explanation of the physical bases of these techniques and their principal clinical and research capabilities.

Support Vector Machine (SVM) has become a popular method in machine learning in recent years. SVM is widely used as a tool in many classifiction areas. The selection optimum values of the parameters (model selection) for SVM is an important step in SVM design. This paper presents the results of research and testing method Particle Swarm Optimization (PSO) in selecting the parameters for SVM. Here we focus on the selection parameter γ of the RBF function and soft margin parameter C of SVM for classification problems. In this paper we propose a Particle Swarm Optimization variation model which combine the cognition-only model with the social-only model and use randomised low discrepancy sequences for initialising particle swarms. We then evaluate the suggested strategies with a series of experiments on 6 benchmark datasets. Experimental results demonstrate the model we proposed better than grid search and full PSO-SVM model.

We develop two different techniques to study volume mapping problem in Computer Graphics and Medical Imaging fields.The first one is to find a harmonic map from a 3 manifold to a 3D solid sphere and the second is a sphere carving algorithm which calculates the simplicial decomposition of volume adapted to surfaces.We derive the 3D harmonic energy equation and it can be easily extended to higher dimensions.We use a textrehedral mesh to represent the volume data.We demonstrate our method on various solid 3D models.We suggest that 3D harmonic mapping of volume can provide a canonical coordinate system for feature identification and registration for computer animation and medical imaging.

The shape of red blood cells (RBCs) contributes to clinical diagnoses of blood diseases. The field of medical imaging has become more important because of the increasing need for automated and efficient diagnoses within a short period of time. Imaging technique plays an important role in RBC research for hematology. Classification is an important component of the retrieval system which allows one to distinguish between normal RBCs and abnormal RBCs which indicate anemia. In this paper, image processing techniques that use the optimization segmentation and mean filter play an important role in obtaining the geometric, texture and color features related to RBC images by using a photo imaging microscope. The support vector machine, which is an advanced kernel-based technique, is used to classify RBC data as either normal or abnormal, the proposed classifier algorithm achieved very good accuracy rates with validation measure of sensitivity, specificity and Kappa to be 100%, 0.998% and 0.9944 respectively.

Generative AI is an expanding domain that employs machine learning models to generate novel data that closely mimic pre existing data. ChatGPT and DALL-E can be customized for specific applications and are expected to transform healthcare, education, and communication. Generative Adversarial Networks (GANs) that can generate synthetic medical images closely mimicking actual patient data may substantially enhance machine learning model training datasets. They also translate medical images from one modality to another, improve medical imaging resolution, reduce radiation exposure, and boost image quality and detail. Despite their challenges, GANs have great potential in the field of medical imaging. The key obstacles are the need for Graphic Processing Units (GPUs) and computing resources to train GANs and the lack of established standards for generating synthetic images. Incorrectly labeled data for training other machine learning models can reduce performance, making ground-truth data labeling for healthcare AI more difficult. Generative AI is revolutionizing healthcare imaging, simplifying diagnosis, and propelling healthcare research and practice to new frontiers. Ensuring the reliability and safety of generated images in medical applications requires addressing ethical considerations and validating data.

Surgery of complex craniofacial defects: A single-step AM-based methodology