Efficient Segmentation of a Breast in B-Mode Ultrasound Tomography Using Three-Dimensional GrabCut (GC3D)

Estimation of drinking water volume of laboratory animals based on image processing

This paper describes an image processing-based technique used to measure the volume of residual water in the drinking water bottle for the laboratory mouse. This technique uses a camera to capture the bottle's image and then processes the image to calculate the volume of water in the bottle. Firstly, the Grabcut method separates the foreground and background to avoid the influence of background on image feature extraction. Then Canny operator was used to detect the edge of the water bottle and the edge of the liquid surface. The cumulative probability Hough detection identified the water bottle edge line segment and the liquid surface line segment from the edge image. Finally, the spatial coordinate system is constructed, and the length of each line segment on the water bottle is calculated by using plane analytical geometry. Then the volume of water is calculated. By comparing image processing time, the pixel number of liquid level, and other indexes, the optimal illuminance and water bottle color were obtained. The experimental results show that the average deviation rate of this method is less than 5%, which significantly improves the accuracy and efficiency of measurement compared with traditional manual measurement.

Accurate breast cancer diagnosis using a stable feature ranking algorithm

BACKGROUND

Breast cancer (BC) is one of the most common cancers among women. Since diverse features can be collected, how to stably select the powerful ones for accurate BC diagnosis remains challenging.

METHODS

A hybrid framework is designed for successively investigating both feature ranking (FR) stability and cancer diagnosis effectiveness. Specifically, on 4 BC datasets (BCDR-F03, WDBC, GSE10810 and GSE15852), the stability of 23 FR algorithms is evaluated via an advanced estimator (S), and the predictive power of the stable feature ranks is further tested by using different machine learning classifiers.

RESULTS

Experimental results identify 3 algorithms achieving good stability ([Formula: see text]) on the four datasets and generalized Fisher score (GFS) leading to state-of-the-art performance. Moreover, GFS ranks suggest that shape features are crucial in BC image analysis (BCDR-F03 and WDBC) and that using a few genes can well differentiate benign and malignant tumor cases (GSE10810 and GSE15852).

CONCLUSIONS

The proposed framework recognizes a stable FR algorithm for accurate BC diagnosis. Stable and effective features could deepen the understanding of BC diagnosis and related decision-making applications.

A Signal Domain Object Segmentation Method for Ultrasound and Photoacoustic Computed Tomography

Image segmentation is important in improving the diagnostic capability of ultrasound computed tomography (USCT) and photoacoustic computed tomography (PACT), as it can be included in the image reconstruction process to improve image quality and quantification abilities. Segmenting the imaged object out of the background using image domain methods is easily complicated by low contrast, noise, and artifacts in the reconstructed image. Here, we introduce a new signal domain object segmentation method for USCT and PACT which does not require image reconstruction beforehand and is automatic, robust, computationally efficient, accurate, and straightforward. We first establish the relationship between the time-of-flight of the received first arrival waves and the object's boundary which is described by ellipse equations. Then, we show that the ellipses are tangent to the boundary. By looking for tangent points on the common tangent of neighboring ellipses, the boundary can be approximated with high fidelity. Imaging experiments of human fingers and mice cross-sections showed that our method provided equivalent or better segmentations than the optimal ones by active contours. In summary, our method greatly reduces the overall complexity of object segmentation and shows great potential in eliminating user dependency without sacrificing segmentation accuracy. The method can be further seamlessly incorporated into algorithms for other processing purposes in USCT and PACT, such as high-quality image reconstruction.

Research on High-Efficiency Transmission Characteristics of Multi-Channel Breast Ultrasound Signals Based on Graphene Structure

In breast ultrasound CT imaging, the ultrasound signals received by high-density CMUT cylindrical array have problems of low transmission efficiency, susceptibility to interference from other signals, and an inability to achieve efficient acquisition. Therefore, to overcome these problems, based on acoustic metamaterials and graphene structure, an efficient transmission model of the multi-channel breast ultrasonic signals was designed, and a finite element simulation experiment was conducted. Research showed that the separation of ultrasonic signals could be achieved by the model designed in this article. The anti-interference ability in the ultrasonic signal acquisition process was effectively improved by the good multi-channel directional transmission and the sound wave local enhancement effect, which improved the sound wave transmission efficiency. In addition, the acoustic signals could be effectively transmitted from 80 kHz to 4000 kHz, realizing broadband transmission. Based on the flexibility of the design of the phononic crystal structure, phase adjustment could be achieved in a wide frequency range by changing the parameters of the primary cell structure. This enabled the CMUT cylindrical array to obtain better directivity characteristics, laying the foundation for high-quality breast ultrasound imaging.

To Align Multimodal Lumbar Spine Images via Bending Energy Constrained Normalized Mutual Information

To align multimodal images is important for information fusion, clinical diagnosis, treatment planning, and delivery, while few methods have been dedicated to matching computerized tomography (CT) and magnetic resonance (MR) images of lumbar spine. This study proposes a coarse-to-fine registration framework to address this issue. Firstly, a pair of CT-MR images are rigidly aligned for global positioning. Then, a bending energy term is penalized into the normalized mutual information for the local deformation of soft tissues. In the end, the framework is validated on 40 pairs of CT-MR images from our in-house collection and 15 image pairs from the SpineWeb database. Experimental results show high overlapping ratio (in-house collection, vertebrae 0.97 ± 0.02, blood vessel 0.88 ± 0.07; SpineWeb, vertebrae 0.95 ± 0.03, blood vessel 0.93 ± 0.10) and low target registration error (in-house collection, ≤2.00 ± 0.62 mm; SpineWeb, ≤2.37 ± 0.76 mm) are achieved. The proposed framework concerns both the incompressibility of bone structures and the nonrigid deformation of soft tissues. It enables accurate CT-MR registration of lumbar spine images and facilitates image fusion, spine disease diagnosis, and interventional treatment delivery.

One View Per City for Buildings Segmentation in Remote-Sensing Images via Fully Convolutional Networks: A Proof-of-Concept Study

The segmentation of buildings in remote-sensing (RS) images plays an important role in monitoring landscape changes. Quantification of these changes can be used to balance economic and environmental benefits and most importantly, to support the sustainable urban development. Deep learning has been upgrading the techniques for RS image analysis. However, it requires a large-scale data set for hyper-parameter optimization. To address this issue, the concept of “one view per city” is proposed and it explores the use of one RS image for parameter settings with the purpose of handling the rest images of the same city by the trained model. The proposal of this concept comes from the observation that buildings of a same city in single-source RS images demonstrate similar intensity distributions. To verify the feasibility, a proof-of-concept study is conducted and five fully convolutional networks are evaluated on five cities in the Inria Aerial Image Labeling database. Experimental results suggest that the concept can be explored to decrease the number of images for model training and it enables us to achieve competitive performance in buildings segmentation with decreased time consumption. Based on model optimization and universal image representation, it is full of potential to improve the segmentation performance, to enhance the generalization capacity, and to extend the application of the concept in RS image analysis.

A Novel Bio-Inspired Method for Early Diagnosis of Breast Cancer through Mammographic Image Analysis

Breast cancer is a current problem that causes the death of many women. In this work, we test meta-heuristics applied to the segmentation of mammographic images. Traditionally, the application of these algorithms has a direct relationship with optimization problems; however, in this study, its implementation is oriented to the segmentation of mammograms using the Dunn index as an optimization function, and the grey levels to represent each individual. The update of grey levels during the process results in the maximization of the Dunn’s index function; the higher the index, the better the segmentation will be. The results showed a lower error rate using these meta-heuristics for segmentation compared to a well-adopted classical approach known as the Otsu method.

A Technical Review of Convolutional Neural Network-Based Mammographic Breast Cancer Diagnosis

This study reviews the technique of convolutional neural network (CNN) applied in a specific field of mammographic breast cancer diagnosis (MBCD). It aims to provide several clues on how to use CNN for related tasks. MBCD is a long-standing problem, and massive computer-aided diagnosis models have been proposed. The models of CNN-based MBCD can be broadly categorized into three groups. One is to design shallow or to modify existing models to decrease the time cost as well as the number of instances for training; another is to make the best use of a pretrained CNN by transfer learning and fine-tuning; the third is to take advantage of CNN models for feature extraction, and the differentiation of malignant lesions from benign ones is fulfilled by using machine learning classifiers. This study enrolls peer-reviewed journal publications and presents technical details and pros and cons of each model. Furthermore, the findings, challenges and limitations are summarized and some clues on the future work are also given. Conclusively, CNN-based MBCD is at its early stage, and there is still a long way ahead in achieving the ultimate goal of using deep learning tools to facilitate clinical practice. This review benefits scientific researchers, industrial engineers, and those who are devoted to intelligent cancer diagnosis.

Multi-Perspective Ultrasound Imaging Technology of the Breast with Cylindrical Motion of Linear Arrays

In this paper, we propose a multi-perspective ultrasound imaging technology with the cylindrical motion of four piezoelectric micromachined ultrasonic transducer (PMUT) rotatable linear arrays. The transducer is configured in a cross shape vertically on the circle with the length of the arrays parallel to the z axis, roughly perpendicular to the chest wall. The transducers surrounded the breast, which achieves non-invasive detection. The electric rotary table drives the PMUT to perform cylindrical scanning. A breast model with a 2 cm mass in the center and six 1-cm superficial masses were used for the experimental analysis. The detection was carried out in a water tank and the working temperature was constant at 32 °C. The breast volume data were acquired by rotating the probe 90° with a 2° interval, which were 256 × 180 A-scan lines. The optimized segmented dynamic focusing technology was used to improve the image quality and data reconstruction was performed. A total of 256 A-scan lines at a constant angle were recombined and 180 A-scan lines were recombined according to the nth element as a dataset, respectively. Combined with ultrasound imaging algorithms, multi-perspective ultrasound imaging was realized including vertical slices, horizontal slices and 3D imaging. The seven masses were detected and the absolute error of the size was approximately 1 mm where even the image of the injection pinhole could be seen. Furthermore, the breast boundary could be seen clearly from the chest wall to the nipple, so the location of the masses was easier to confirm. Therefore, the validity and feasibility of the data reconstruction method and imaging algorithm were verified. It will be beneficial for doctors to be able to comprehensively observe the pathological tissue.

A consistency evaluation of signal-to-noise ratio in the quality assessment of human brain magnetic resonance images

Background

Quality assessment of medical images is highly related to the quality assurance, image interpretation and decision making. As to magnetic resonance (MR) images, signal-to-noise ratio (SNR) is routinely used as a quality indicator, while little knowledge is known of its consistency regarding different observers.

Methods

In total, 192, 88, 76 and 55 brain images are acquired using T₂^*, T₁, T₂ and contrast-enhanced T₁ (T₁C) weighted MR imaging sequences, respectively. To each imaging protocol, the consistency of SNR measurement is verified between and within two observers, and white matter (WM) and cerebral spinal fluid (CSF) are alternately used as the tissue region of interest (TOI) for SNR measurement. The procedure is repeated on another day within 30 days. At first, overlapped voxels in TOIs are quantified with Dice index. Then, test-retest reliability is assessed in terms of intra-class correlation coefficient (ICC). After that, four models (BIQI, BLIINDS-II, BRISQUE and NIQE) primarily used for the quality assessment of natural images are borrowed to predict the quality of MR images. And in the end, the correlation between SNR values and predicted results is analyzed.

Results

To the same TOI in each MR imaging sequence, less than 6% voxels are overlapped between manual delineations. In the quality estimation of MR images, statistical analysis indicates no significant difference between observers (Wilcoxon rank sum test, p_w ≥ 0.11; paired-sample t test, p_p ≥ 0.26), and good to very good intra- and inter-observer reliability are found (ICC, p_icc ≥ 0.74). Furthermore, Pearson correlation coefficient (r_p) suggests that SNR_wm correlates strongly with BIQI, BLIINDS-II and BRISQUE in T₂^* (r_p ≥ 0.78), BRISQUE and NIQE in T₁ (r_p ≥ 0.77), BLIINDS-II in T₂ (r_p ≥ 0.68) and BRISQUE and NIQE in T₁C (r_p ≥ 0.62) weighted MR images, while SNR_csf correlates strongly with BLIINDS-II in T₂^* (r_p ≥ 0.63) and in T₂ (r_p ≥ 0.64) weighted MR images.

Conclusions

The consistency of SNR measurement is validated regarding various observers and MR imaging protocols. When SNR measurement performs as the quality indicator of MR images, BRISQUE and BLIINDS-II can be conditionally used for the automated quality estimation of human brain MR images.

The Application of an Ultrasound Tomography Algorithm in a Novel Ring 3D Ultrasound Imaging System

Currently, breast cancer is one of the most common cancers in women all over the world. A novel 3D breast ultrasound imaging ring system using the linear array transducer is proposed to decrease costs, reduce processing difficulties, and improve patient comfort as compared to modern day breast screening systems. The 1 × 128 Piezoelectric Micromachined Ultrasonic Transducer (PMUT) linear array is placed 90 degrees cross-vertically. The transducer surrounds the mammary gland, which allows for non-contact detection. Once the experimental platform is built, the breast model is placed through the electric rotary table opening and into a water tank that is at a constant temperature of 32 °C. The electric rotary table performs a 360° scan either automatically or mechanically. Pulse echo signals are captured through a circular scanning method at discrete angles. Subsequently, an ultrasonic tomography algorithm is designed, and a horizontal slice imaging is realized. The experimental results indicate that the preliminary detection of mass is realized by using this ring system. Circular scanning imaging is obtained by using a rotatable linear array instead of a cylindrical array, which allows the size and location of the mass to be recognized. The resolution of breast imaging is improved through the adjustment of the angle interval (>0.05°) and multiple slices are gained through different transducer array elements (1 × 128). These results validate the feasibility of the system design as well as the algorithm, and encourage us to implement our concept with a clinical study in the future.