RESUMEN

OBJECTIVE: Machine learning has been effective in other areas of medicine, this study aims to investigate this with regards to HNC and identify which algorithm works best to classify malignant patients. DESIGN: An observational cohort study. SETTING: Queen Elizabeth University Hospital. PARTICIPANTS: Patients who were referred via the USOC pathway between January 2019 and May 2021. MAIN OUTCOME MEASURES: Predicting the diagnosis of patients from three categories, benign, potential malignant and malignant, using demographics and symptoms data. RESULTS: The classic statistical method of ordinal logistic regression worked best on the data, achieving an AUC of 0.6697 and balanced accuracy of 0.641. The demographic features describing recreational drug use history and living situation were the most important variables alongside the red flag symptom of a neck lump. CONCLUSION: Further studies should aim to collect larger samples of malignant and pre-malignant patients to improve the class imbalance and increase the performance of the machine learning models.

RESUMEN

According to the WHO (World Health Organization), lung cancer is the leading cause of cancer deaths globally. In the future, more than 2.2 million people will be diagnosed with lung cancer worldwide, making up 11.4% of every primary cause of cancer. Furthermore, lung cancer is expected to be the biggest driver of cancer-related mortality worldwide in 2020, with an estimated 1.8 million fatalities. Statistics on lung cancer rates are not uniform among geographic areas, demographic subgroups, or age groups. The chance of an effective treatment outcome and the likelihood of patient survival can be greatly improved with the early identification of lung cancer. Lung cancer identification in medical pictures like CT scans and MRIs is an area where deep learning (DL) algorithms have shown a lot of potential. This study uses the Hybridized Faster R-CNN (HFRCNN) to identify lung cancer at an early stage. Among the numerous uses for which faster R-CNN has been put to good use is identifying critical entities in medical imagery, such as MRIs and CT scans. Many research investigations in recent years have examined the use of various techniques to detect lung nodules (possible indicators of lung cancer) in scanned images, which may help in the early identification of lung cancer. One such model is HFRCNN, a two-stage, region-based entity detector. It begins by generating a collection of proposed regions, which are subsequently classified and refined with the aid of a convolutional neural network (CNN). A distinct dataset is used in the model's training process, producing valuable outcomes. More than a 97% detection accuracy was achieved with the suggested model, making it far more accurate than several previously announced methods.

RESUMEN

Recently, research using point clouds has been increasing with the development of 3D scanner technology. According to this trend, the demand for high-quality point clouds is increasing, but there is still a problem with the high cost of obtaining high-quality point clouds. Therefore, with the recent remarkable development of deep learning, point cloud up-sampling research, which uses deep learning to generate high-quality point clouds from low-quality point clouds, is one of the fields attracting considerable attention. This paper proposes a new point cloud up-sampling method called Point cloud Up-sampling via Multi-scale Features Attention (PU-MFA). Inspired by prior studies that reported good performance at generating high-quality dense point set using the multi-scale features or attention mechanisms, PU-MFA merges the two through a U-Net structure. In addition, PU-MFA adaptively uses multi-scale features to refine the global features effectively. The PU-MFA was compared with other state-of-the-art methods in various evaluation metrics through various experiments using the PU-GAN dataset, which is a synthetic point cloud dataset, and the KITTI dataset, which is the real-scanned point cloud dataset. In various experimental results, PU-MFA showed superior performance of generating high-quality dense point set in quantitative and qualitative evaluation compared to other state-of-the-art methods, proving the effectiveness of the proposed method. The attention map of PU-MFA was also visualized to show the effect of multi-scale features.

Asunto(s)

RESUMEN

Ningxia wolfberry is the only wolfberry product with medicinal value in China. However, the nutritional elements, active ingredients, and economic value of the wolfberry vary considerably among different origins in Ningxia. It is difficult to determine the origin of wolfberry by traditional methods due to the same variety, similar origins, and external characteristics. In the study, we have for the first time used a multi-task residual fully convolutional network (MRes-FCN) under Bayesian optimized architecture for imaging from visible-near-infrared (Vis-NIR, 400-1000 nm) and near-infrared (NIR-1700 nm) hyperspectral imaging (HSI) technology to establish a classification model for near geographic origin of Ningxia wolfberries (Zhongning, Guyuan, Tongxin, and Huinong). The denoising auto-encoder (DAE) was used to generate augmented data, then principal component analysis (PCA) was combined with gray level co-occurrence matrix (GLCM) to extract the texture features. Finally, three datasets (HSI, DAE, and texture) were added to the multi-task model. The reshaped data were up-sampled using transposed convolution. After data-sparse processing, the backbone network was imported to train the model. The results showed that the MRes-FCN model exhibited excellent performance, with the accuracies of the full spectrum and optimum characteristic spectrum of 95.54% and 96.43%, respectively. This study has demonstrated that the MRes-FCN model based on Bayesian optimization and DAE data augmentation strategy may be used to identify the near geographical origin of wolfberries.

RESUMEN

The determination of a tailored anti-drug antibody (ADA) testing strategy is based on the immunogenicity risk assessment to allow a correlation of ADAs with changes to pharmacokinetics, efficacy, and safety. The clinical impact of ADA formation refines the immunogenicity risk assessment and defines appropriate risk mitigation strategies. Health agencies request for high-risk biotherapeutics to extend ADA monitoring for patients that developed an ADA response to the drug until ADAs return to baseline levels. However, there is no common understanding in which cases an extension of ADA follow-up sampling beyond the end of study (EOS) defined in the clinical study protocol is required. Here, the Immunogenicity Strategy Working Group of the European Immunogenicity Platform (EIP) provides recommendations on requirements for an extension of ADA follow-up sampling in clinical studies where there is a high risk of serious consequences from ADAs. The importance of ADA evaluation during a treatment-free period is recognized but the decision whether to extend ADA monitoring at a predefined EOS should be based on evaluation of ADA data in the context of corresponding clinical signals. If the clinical data set shows that safety consequences are minor, mitigated, or resolved, further ADA monitoring may not be required despite potentially detectable ADAs above baseline. Extended ADA monitoring should be centered on individual patient benefit.

Asunto(s)

RESUMEN

At present, the one-stage detector based on the lightweight model can achieve real-time speed, but the detection performance is challenging. To enhance the discriminability and robustness of the model extraction features and improve the detector's detection performance for small objects, we propose two modules in this work. First, we propose a receptive field enhancement method, referred to as adaptive receptive field fusion (ARFF). It enhances the model's feature representation ability by adaptively learning the fusion weights of different receptive field branches in the receptive field module. Then, we propose an enhanced up-sampling (EU) module to reduce the information loss caused by up-sampling on the feature map. Finally, we assemble ARFF and EU modules on top of YOLO v3 to build a real-time, high-precision and lightweight object detection system referred to as the ARFF-EU network. We achieve a state-of-the-art speed and accuracy trade-off on both the Pascal VOC and MS COCO data sets, reporting 83.6% AP at 37.5 FPS and 42.5% AP at 33.7 FPS, respectively. The experimental results show that our proposed ARFF and EU modules improve the detection performance of the ARFF-EU network and achieve the development of advanced, very deep detectors while maintaining real-time speed.

RESUMEN

A high-resolution display panel comes to practical use, but the resolution of the indicated contents does not change. The up-sampling processing is applied to indication of the low-resolution contents. In the up-sampling process, the super resolution enables an up-sampling process which estimates information of high frequency components lost by sampling while analyzing input images is noticed. In this paper, we aimed at reconstructing an image of normal resolution in which the influence of statistical noise is reduced by applying super resolution after down-sampling processing is applied to positron emission tomography (PET) image with many statistical noises. To evaluate the noise reduction effect, we compared it with the Gaussian filter which is frequently used to reduce the influence of the statistical noise of the PET image. A 3D Hoffman brain phantom was used to evaluate objectively by peak signal-to-noise ratio and power spectral density. The objective index of the PET image applying super resolution is positive results, suggesting the possibility of being useful as compared with the conventional method.

Asunto(s)

RESUMEN

BACKGROUND: Efficient computational recognition and segmentation of target organ from medical images are foundational in diagnosis and treatment, especially about pancreas cancer. In practice, the diversity in appearance of pancreas and organs in abdomen, makes detailed texture information of objects important in segmentation algorithm. According to our observations, however, the structures of previous networks, such as the Richer Feature Convolutional Network (RCF), are too coarse to segment the object (pancreas) accurately, especially the edge. METHOD: In this paper, we extend the RCF, proposed to the field of edge detection, for the challenging pancreas segmentation, and put forward a novel pancreas segmentation network. By employing multi-layer up-sampling structure replacing the simple up-sampling operation in all stages, the proposed network fully considers the multi-scale detailed contexture information of object (pancreas) to perform per-pixel segmentation. Additionally, using the CT scans, we supply and train our network, thus get an effective pipeline. RESULT: Working with our pipeline with multi-layer up-sampling model, we achieve better performance than RCF in the task of single object (pancreas) segmentation. Besides, combining with multi scale input, we achieve the 76.36% DSC (Dice Similarity Coefficient) value in testing data. CONCLUSION: The results of our experiments show that our advanced model works better than previous networks in our dataset. On the other words, it has better ability in catching detailed contexture information. Therefore, our new single object segmentation model has practical meaning in computational automatic diagnosis.

Asunto(s)

RESUMEN

Purpose: Magnetic resonance spectroscopic imaging (MRSI) provides complementary information to conventional magnetic resonance imaging. Acquiring high resolution MRSI is time consuming and requires complex reconstruction techniques. Methods: In this paper, a patch-based super-resolution method is presented to increase the spatial resolution of metabolite maps computed from MRSI. The proposed method uses high resolution anatomical MR images (T1-weighted and Fluid-attenuated inversion recovery) to regularize the super-resolution process. The accuracy of the method is validated against conventional interpolation techniques using a phantom, as well as simulated and in vivo acquired human brain images of multiple sclerosis subjects. Results: The method preserves tissue contrast and structural information, and matches well with the trend of acquired high resolution MRSI. Conclusions: These results suggest that the method has potential for clinically relevant neuroimaging applications.

RESUMEN

BACKGROUND AND PURPOSE: Diffusion MRI tractography enables to investigate white matter pathways noninvasively by reconstructing estimated fiber pathways. However, such tractograms remain biased and nonquantitative. Several techniques have been proposed to reestablish the link between tractography and tissue microstructure by modeling the diffusion signal or fiber orientation distribution (FOD) with the given tractogram and optimizing each fiber or compartment contribution according to the diffusion signal or FOD. Nevertheless, deriving a reliable quantification of connectivity strength between different brain areas is still a challenge. Moreover, evaluating the quality of a tractogram and measuring the possible error sources contained in a specific reconstructed fiber bundle also remains difficult. Lastly, all of these optimization techniques fail if specific fiber populations within a tractogram are underrepresented, for example, due to algorithmic constraints, anatomical properties, fiber geometry or seeding patterns. METHODS: In this work, we propose an approach which enables the inspection of the quality of a tractogram optimization by evaluating the residual error signal and its FOD representation. The automated fiber quantification (AFQ) is applied, whereby the framework is extended to reflect not only scalar diffusion metrics along a fiber bundle, but also directionally dependent FOD amplitudes along and perpendicular to the fiber direction. Furthermore, we also present an up-sampling procedure to increase the number of streamlines of a given fiber population. The introduced error metrics and fiber up-sampling method are tested and evaluated on single-shell diffusion data sets of 16 healthy volunteers. RESULTS AND CONCLUSION: Analyzing the introduced error measures on specific fiber bundles shows a considerable improvement in applying the up-sampling method. Additionally, the error metrics provide a useful tool to spot and identify potential error sources in tractograms.

Asunto(s)

RESUMEN

Accurate acoustic source localization at a low sampling rate (less than 10 kHz) is still a challenging problem for small portable systems, especially for a multitasking micro-embedded system. A modification of the generalized cross-correlation (GCC) method with the up-sampling (US) theory is proposed and defined as the US-GCC method, which can improve the accuracy of the time delay of arrival (TDOA) and source location at a low sampling rate. In this work, through the US operation, an input signal with a certain sampling rate can be converted into another signal with a higher frequency. Furthermore, the optimal interpolation factor for the US operation is derived according to localization computation time and the standard deviation (SD) of target location estimations. On the one hand, simulation results show that absolute errors of the source locations based on the US-GCC method with an interpolation factor of 15 are approximately from 1/15- to 1/12-times those based on the GCC method, when the initial same sampling rates of both methods are 8 kHz. On the other hand, a simple and small portable passive acoustic source localization platform composed of a five-element cross microphone array has been designed and set up in this paper. The experiments on the established platform, which accurately locates a three-dimensional (3D) near-field target at a low sampling rate demonstrate that the proposed method is workable.