Search

Breast cancer ranks first among cancers affecting women’s health. Our work aims to realize the intelligence of the medical ultrasound equipment with limited computational capability, which is used for the assistant detection of breast lesions. We embed the high-computational deep learning algorithm into the medical ultrasound equipment with limited computational capability by two techniques: (1) lightweight neural network: considering the limited computational capability of ultrasound equipment, a lightweight neural network is designed, which greatly reduces the amount of calculation. And we use the technique of knowledge distillation to train the low-precision network helped with the high-precision network; (2) asynchronous calculations: consider four frames of ultrasound images as a group; the image of the first frame of each group is used as the input of the network, and the result is respectively fused with the images of the fourth to seventh frames. An amount of computation of 30 GFLO/frame is required for the proposed lightweight neural network, about 1/6 of that of the large high-precision network. After trained from scratch using the knowledge distillation technique, the detection performance of the lightweight neural network (sensitivity = 89.25%, specificity = 96.33%, the average precision [AP] = 0.85) is close to that of the high-precision network (sensitivity = 98.3%, specificity = 88.33%, AP = 0.91). By asynchronous calculation, we achieve real-time automatic detection of 24 fps (frames per second) on the ultrasound equipment. Our work proposes a method to realize the intelligence of the low-computation-power ultrasonic equipment, and successfully achieves the real-time assistant detection of breast lesions. The significance of the study is as follows: (1) The proposed method is of practical significance in assisting doctors to detect breast lesions; (2) our method provides some practical and theoretical support for the development and engineering of intelligent equipment based on artificial intelligence algorithms.

Breast cancer has become the biggest threat to female health. Ultrasonic diagnosis of breast cancer based on artificial intelligence is basically a classification of benign and malignant tumors, which does not meet clinical demand. Besides, the current target detection method performs poorly in detecting small lesions, while it is clinically required to detect nodules below 2 mm. The objective of this study is to (a) propose a diagnostic method based on Breast Imaging Reporting and Data System (BI-RADS) and (b) increase its detectability of small lesions. We modified the framework of Faster R-CNN (Faster Region-based Convolutional Neural Network) by introducing multi-scale feature extraction and multi-resolution candidate bound extraction into the network. Then, it was trained using 852 images of BI-RADS C2, 739 images of C3, and 1662 images of malignancy (BI-RADS 4a/4b/4c/5/6). We compared our model with unmodified Faster R-CNN and YOLO v3 (You Only Look Once v3). The mean average precision (mAP) is significantly increased to 0.913, while its average detection speed is slightly declined to 4.11 FPS (frames per second). Meanwhile, its detectivity of small lesions is effectively improved. Moreover, we also tentatively applied our model on video sequences and got satisfactory results. We modified Faster R-CNN and trained it partly based on BI-RADS. Its detectability of lesions, as well as small nodules, was significantly improved. In view of wide coverage of dataset and satisfactory test results, our method can basically meet clinical needs.

Whale optimization algorithm, as a relatively novel swarm-based intelligence optimization algorithm, has been extensively utilized in numerous scientific and engineering fields. The intent of this work was to devise a modified WOA based on multi-strategy, named MSWOA, to address somewhat deficiencies of the original WOA, such as converging slowly, stagnating at local minima and poor stability. First, a tent map function is adopted to optimize the distribution of the initial population in problem domain. Second, new iteration-based update strategies of convergence factor and inertia weight are constructed to regulate the balance between global and local search capabilities and improve the optimization ability. Additionally, an optimal feedback strategy is presented in the search for prey stage to enhance the global search ability. Numerical experimental results based on 24 test benchmark functions reveal that the proposed MSWOA significantly improves the standard WOA in terms of solution accuracy and convergence speed, and outperforms the comparison algorithms. Furthermore, the results show that the inertia weight strategy has the greatest effect on the performance of basic WOA performance, followed by the convergence factor, and then the optimal feedback strategy.

Studies of non-invasive glucose measurement with optical coherence tomography (OCT) in tissue-simulating phantoms and biological tissues show that glucose has an effect on the OCT signal slope. Choosing an efficient fitting range to calculate the OCT signal slope is important because it helps to improve the precision of glucose measurement. In this paper, we study the problem in two ways: (1) scattering-induced change of OCT signal slope versus depth in intralipid suspensions with different concentrations based on Monte Carlo (MC) simulations and experiments and (2) efficient fitting range for glucose measurement in 3% and 10% intralipid. The results show that the OCT signal slope expresses a contrary change with scattering coefficient below a certain depth in high intralipid concentrations, so that there is an effective fitting depth. With an efficient fitting range from 100 μm to the effective fitting depth, the precision of glucose measurement can be 4.4 mM for 10% intralipid and 2.2 mM for 3% intralipid.

Nonnegative Matrix Factorization (NMF) is a powerful tool for gene expression data analysis as it reduces thousands of genes to a few compact metagenes, especially in clustering gene expression samples for cancer class discovery. Enhancing sparseness of the factorisation can find only a few dominantly coexpressed metagenes and improve the clustering effectiveness. Sparse p-norm (p > 1) Nonnegative Matrix Factorization (sp-NMF) is a more sparse representation method using high order norm to normalise the decomposed components. In this paper, we investigate the benefit of high order normalisation for clustering cancer-related gene expression samples. Experimental results demonstrate that sp-NMF leads to robust and effective clustering in both automatically determining the cluster number, and achieving high accuracy.