Search

Breast cancer (BC) is the leading cause of death among women worldwide. It affects in general women older than 40 years old. Medical images analysis is one of the most promising research areas since it provides facilities for diagnosis and decision-making of several diseases such as BC. This paper conducts a Structured Literature Review (SLR) of the use of Machine Learning (ML) and Image Processing (IP) techniques to deal with BC imaging. A set of 530 papers published between 2000 and August 2019 were selected and analyzed according to ten criteria: year and publication channel, empirical type, research type, medical task, machine learning techniques, datasets used, validation methods, performance measures and image processing techniques which include image pre-processing, segmentation, feature extraction and feature selection. Results showed that diagnosis was the most used medical task and that Deep Learning techniques (DL) were largely used to perform classification. Furthermore, we found out that classification was the most ML objective investigated followed by prediction and clustering. Most of the selected studies used Mammograms as imaging modalities rather than Ultrasound or Magnetic Resonance Imaging with the use of public or private datasets with MIAS as the most frequently investigated public dataset. As for image processing techniques, the majority of the selected studies pre-process their input images by reducing the noise and normalizing the colors, and some of them use segmentation to extract the region of interest with the thresholding method. For feature extraction, we note that researchers extracted the relevant features using classical feature extraction techniques (e.g. Texture features, Shape features, etc.) or DL techniques (e. g. VGG16, VGG19, ResNet, etc.), and finally few papers used feature selection techniques in particular the filter methods. [ABSTRACT FROM AUTHOR]

Lung cancer is considered one of the deadliest diseases in the world. An early and accurate diagnosis aims to promote the detection and characterization of pulmonary nodules, which is of vital importance to increase the patients' survival rates. The mentioned characterization is done through a segmentation process, facing several challenges due to the diversity in nodular shape, size, and texture, as well as the presence of adjacent structures. This paper tackles pulmonary nodule segmentation in computed tomography scans proposing three distinct methodologies. First, a conventional approach which applies the Sliding Band Filter (SBF) to estimate the filter's support points, matching the border coordinates. The remaining approaches are Deep Learning based, using the U-Net and a novel network called SegU-Net to achieve the same goal. Their performance is compared, as this work aims to identify the most promising tool to improve nodule characterization. All methodologies used 2653 nodules from the LIDC database, achieving a Dice score of 0.663, 0.830, and 0.823 for the SBF, U-Net and SegU-Net respectively. This way, the U-Net based models yield more identical results to the ground truth reference annotated by specialists, thus being a more reliable approach for the proposed exercise. The novel network revealed similar scores to the U-Net, while at the same time reducing computational cost and improving memory efficiency. Consequently, such study may contribute to the possible implementation of this model in a decision support system, assisting the physicians in establishing a reliable diagnosis of lung pathologies based on this segmentation task. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to develop an autonomous tracking algorithm based on adaptive fusion kinematics method, the autonomous laparoscope control algorithm and adaptive fusion kinematics method are proposed for semi-autonomous surgery, focus on solving the problems of autonomous laparoscope field of view control for surgical robot system. A novel autonomous tracking algorithm is proposed. To realize more robust tracking, an adaptive fusion kinematics method based on fuzzy logic is proposed, the method adaptive associates the kinematics information of surgical robot system and the laparoscope information. The proposed methods are implemented on the laparoscopic minimally invasive surgical robot system which is developed by our laboratory. Two experiments are carried out, the results indicate that the accurate autonomous field of view control is achieved with the addition of laparoscope information, laparoscopic motion frequency is reduced, the methods can avoid the laparoscope continuous motion and ensure the stability of field of view. The proposed methods improve the intelligence level of surgical robot system. [ABSTRACT FROM AUTHOR]

Marker-based optical tracking systems (OTS) are widely used in clinical image-guided therapy. However, the emergence of ghost markers, which is caused by the mistaken recognition of markers and the incorrect correspondences between marker projections, may lead to tracking failures for these systems. Therefore, this paper proposes a strategy to prevent the emergence of ghost markers by identifying markers based on the features of their projections, finding the correspondences between marker projections based on the geometric information provided by markers, and fast-tracking markers in a 2D image between frames based on the sizes of their projections. Apart from validating its high robustness, the experimental results show that the proposed strategy can accurately recognize markers, correctly identify their correspondences, and meet the requirements of real-time tracking. [ABSTRACT FROM AUTHOR]

Retinal blood vessels are the source to provide oxygen and nutrition to retina and any change in the normal structure may lead to different retinal abnormalities. Automated detection of vascular structure is very important while designing a computer aided diagnostic system for retinal diseases. Most popular methods for vessel segmentation are based on matched filters and Gabor wavelets which give good response against blood vessels. One major drawback in these techniques is that they also give strong response for lesion (exudates, hemorrhages) boundaries which give rise to false vessels. These false vessels may lead to incorrect detection of vascular changes. In this paper, we propose a new hybrid feature set along with new classification technique for accurate detection of blood vessels. The main motivation is to lower the false positives especially from retinal images with severe disease level. A novel region based hybrid feature set is presented for proper discrimination between true and false vessels. A new modified m-mediods based classification is also presented which uses most discriminating features to categorize vessel regions into true and false vessels. The evaluation of proposed system is done thoroughly on publicly available databases along with a locally gathered database with images of advanced level of retinal diseases. The results demonstrate the validity of the proposed system as compared to existing state of the art techniques. [ABSTRACT FROM AUTHOR]

CVD (cardiovascular disease) is one of the biggest threats to human beings nowadays. An early and quantitative diagnosis of CVD is important in extending lifespan and improving people's life quality. Coronary artery stenosis can prevent CVD. To diagnose the degree of stenosis, the inner diameter of coronary artery needs to be measured. To achieve such measurement, the coronary artery is segmented by using a method that is based on morphology and the continuity between computed tomography image slices. A centerline extraction method based on mechanical simulation is proposed. This centerline extraction method can figure out a basic framework of the coronary artery by simulating pixel dots of the artery image into mass points. Such mass points have tensile forces, with which the outer pixel dots can be drawn to the center. Subsequently, the centerline of the coronary artery can be outlined by using the local line-fitting method. Finally, the nearest point method is adopted to measure the inner diameter. Experimental results showed that the methods proposed in this paper can precisely extract the centerline of the coronary artery and can accurately measure its inner diameter, thereby providing a basis for quantitative diagnosis of coronary artery stenosis. [ABSTRACT FROM AUTHOR]

Heart failure with preserved ejection fraction (HFpEF) is a complex and heterogeneous clinical syndrome. For the purpose of assisting HFpEF diagnosis, a non-invasive method using extreme learning machine and heart sound (HS) characteristics was provided in this paper. Firstly, the improved wavelet denoising method was used for signal preprocessing. Then, the logistic regression based hidden semi-Markov model algorithm was utilized to locate the boundary of the first HS and the second HS, therefore, the ratio of diastolic to systolic duration can be calculated. Eleven features were extracted based on multifractal detrended fluctuation analysis to analyze the differences of multifractal behavior of HS between healthy people and HFpEF patients. Afterwards, the statistical analysis was implemented on the extracted HS characteristics to generate the diagnostic feature set. Finally, the extreme learning machine was applied for HFpEF identification by the comparison of performances with support vector machine. The result shows an accuracy of 96.32%, a sensitivity of 95.48% and a specificity of 97.10%, which demonstrates the effectiveness of HS for HFpEF diagnosis. [ABSTRACT FROM AUTHOR]

Skeletal bone age assessment is a widely used standard procedure in both disease detection and growth prediction for children in endocrinology. Conventional manual assessment methods mainly rely on personal experience in observing X-ray images of left hand and wrist to calculate bone age, which show some intrinsic limitations from low efficiency to unstable accuracy. To address these problems, some automated methods based on image processing or machine learning have been proposed, while their performances are not satisfying enough yet in assessment accuracy. Motivated by the remarkable success of deep learning (DL) techniques in the fields of image classification and speech recognition, we develop a deep automated skeletal bone age assessment model based on convolutional neural networks (CNNs) and support vector regression (SVR) using multiple kernel learning (MKL) algorithm to process heterogeneous features in this paper. This deep framework has been constructed, not only exploring the X-ray images of hand and twist but also some other heterogeneous information like race and gender. The experiment results prove its better performance with higher bone age assessment accuracy on two different data sets compared with the state of the art, indicating that the fused heterogeneous features provide a better description of the degree of bones' maturation. [ABSTRACT FROM AUTHOR]

Maculopathy is the group of diseases that affects central vision of a person and they are often associated with diabetes. Many researchers reported automated diagnosis of maculopathy from optical coherence tomography (OCT) images. However, to the best of our knowledge there is no literature that presents a complete 3D suite for the extraction as well as diagnosis of macula. Therefore, this paper presents a multilayered convolutional neural networks (CNN) structure tensor Delaunay triangulation and morphing based fully autonomous system that extracts up to nine retinal and choroidal layers along with the macular fluids. Furthermore, the proposed system utilizes the extracted retinal information for the automated diagnosis of maculopathy as well as for the robust reconstruction of 3D macula of retina. The proposed system has been validated on 41,921 retinal OCT scans acquired from different OCT machines and it significantly outperformed existing state of the art solutions by achieving the mean accuracy of 95.27% for extracting retinal and choroidal layers, mean dice coefficient of 0.90 for extracting fluid pathology and the overall accuracy of 96.07% for maculopathy diagnosis. To the best of our knowledge, the proposed framework is first of its kind that provides a fully automated and complete 3D integrated solution for the extraction of candidate macula along with its fully automated diagnosis against different macular syndromes. [ABSTRACT FROM AUTHOR]