A note on the marker-based watershed method for X-ray image segmentation

Comparative analysis of active contour and convolutional neural network in rapid left-ventricle volume quantification using echocardiographic imaging

In cardiology, ultrasound is often used to diagnose heart disease associated with myocardial infarction. This study aims to develop robust segmentation techniques for segmenting the left ventricle (LV) in ultrasound images to check myocardium movement during heartbeat. The proposed technique utilizes machine learning (ML) techniques such as the active contour (AC) and convolutional neural networks (CNNs) for segmentation. Medical experts determine the consistency between the proposed ML approach, which is a state-of-the-art deep learning method, and the manual segmentation approach. These methods are compared in terms of performance indicators such as the ventricular area (VA), ventricular maximum diameter (VMXD), ventricular minimum diameter (VMID), and ventricular long axis angle (AVLA) measurements. Furthermore, the Dice similarity coefficient, Jaccard index, and Hausdorff distance are measured to estimate the agreement of the LV segmented results between the automatic and visual approaches. The obtained results indicate that the proposed techniques for LV segmentation are useful and practical. There is no significant difference between the use of AC and CNN in image segmentation; however, the AC method could obtain comparable accuracy as the CNN method using less training data and less run-time.

Thermal Infrared Pedestrian Segmentation Based on Conditional GAN

A novel thermal infrared pedestrian segmentation algorithm based on conditional generative adversarial network (IPS-cGAN) is proposed for intelligent vehicular applications. The convolution backbone architecture of the generator is based on the improved U-Net with residual blocks for well utilizing regional semantic information. Moreover, cross entropy loss for segmentation is introduced as the condition for the generator. SandwichNet, a novel convolutional network with symmetrical input, is proposed as the discriminator for real-fake segmented images. Based on the c-GAN framework, good segmentation performance could be achieved for thermal infrared pedestrians. Compared to some supervised and unsupervised segmentation algorithms, the proposed algorithm achieves higher accuracy with better robustness, especially for complex scenes.

A novel expert system for objective masticatory efficiency assessment

Most of the tools and diagnosis models of Masticatory Efficiency (ME) are not well documented or severely limited to simple image processing approaches. This study presents a novel expert system for ME assessment based on automatic recognition of mixture patterns of masticated two-coloured chewing gums using a combination of computational intelligence and image processing techniques. The hypotheses tested were that the proposed system could accurately relate specimens to the number of chewing cycles, and that it could identify differences between the mixture patterns of edentulous individuals prior and after complete denture treatment. This study enrolled 80 fully-dentate adults (41 females and 39 males, 25 ± 5 years of age) as the reference population; and 40 edentulous adults (21 females and 19 males, 72 ± 8.9 years of age) for the testing group. The system was calibrated using the features extracted from 400 samples covering 0, 10, 15, and 20 chewing cycles. The calibrated system was used to automatically analyse and classify a set of 160 specimens retrieved from individuals in the testing group in two appointments. The ME was then computed as the predicted number of chewing strokes that a healthy reference individual would need to achieve a similar degree of mixture measured against the real number of cycles applied to the specimen. The trained classifier obtained a Mathews Correlation Coefficient score of 0.97. ME measurements showed almost perfect agreement considering pre- and post-treatment appointments separately (κ ≥ 0.95). Wilcoxon signed-rank test showed that a complete denture treatment for edentulous patients elicited a statistically significant increase in the ME measurements (Z = -2.31, p < 0.01). We conclude that the proposed expert system proved able and reliable to accurately identify patterns in mixture and provided useful ME measurements.

Femur segmentation in DXA imaging using a machine learning decision tree

BACKGROUND

Accurate measurement of bone mineral density (BMD) in dual-energy X-ray absorptiometry (DXA) is essential for proper diagnosis of osteoporosis. Calculation of BMD requires precise bone segmentation and subtraction of soft tissue absorption. Femur segmentation remains a challenge as many existing methods fail to correctly distinguish femur from soft tissue. Reasons for this failure include low contrast and noise in DXA images, bone shape variability, and inconsistent X-ray beam penetration and attenuation, which cause shadowing effects and person-to-person variation.

OBJECTIVE

To present a new method namely, a Pixel Label Decision Tree (PLDT), and test whether it can achieve higher accurate performance in femur segmentation in DXA imaging.

METHODS

PLDT involves mainly feature extraction and selection. Unlike photographic images, X-ray images include features on the surface and inside an object. In order to reveal hidden patterns in DXA images, PLDT generates seven new feature maps from existing high energy (HE) and low energy (LE) X-ray features and determines the best feature set for the model. The performance of PLDT in femur segmentation is compared with that of three widely used medical image segmentation algorithms, the Global Threshold (GT), Region Growing Threshold (RGT), and artificial neural networks (ANN).

RESULTS

PLDT achieved a higher accuracy of femur segmentation in DXA imaging (91.4%) than either GT (68.4%), RGT (76%) or ANN (84.4%).

CONCLUSIONS

The study demonstrated that PLDT outperformed other conventional segmentation techniques in segmenting DXA images. Improved segmentation should help accurate computation of BMD which later improves clinical diagnosis of osteoporosis.

Endoscopic Image Classification and Retrieval using Clustered Convolutional Features

With the growing use of minimally invasive surgical procedures, endoscopic video archives are growing at a rapid pace. Efficient access to relevant content in such huge multimedia archives require compact and discriminative visual features for indexing and matching. In this paper, we present an effective method to represent images using salient convolutional features. Convolutional kernels from the first layer of a pre-trained convolutional neural network (CNN) are analyzed and clustered into multiple distinct groups, based on their sensitivity to colors and textures. Dominant features detected by each cluster are collected into a single, layout-preserving feature map using a spatial maximal activator pooling (SMAP) approach. A moving window based structured pooling method then captures spatial layout features and global shape information from the aggregated feature map to populate feature histograms. Finally, individual histograms for each cluster are combined into a single comprehensive feature histogram. Clustering convolutional feature space allow extraction of color and texture features of varying strengths. Further, the SMAP approach enable us to select dominant discriminative features. The proposed features are compact and capable of conveniently outperforming several existing features extraction approaches in retrieval and classification tasks on endoscopy images dataset.