RESUMEN
Laser speckle contrast imaging (LSCI) is widely used for in vivo real-time detection and analysis of local blood flow microcirculation due to its non-invasive ability and excellent spatial and temporal resolution. However, vascular segmentation of LSCI images still faces a lot of difficulties due to numerous specific noises caused by the complexity of blood microcirculation's structure and irregular vascular aberrations in diseased regions. In addition, the difficulties of LSCI image data annotation have hindered the application of deep learning methods based on supervised learning in the field of LSCI image vascular segmentation. To tackle these difficulties, we propose a robust weakly supervised learning method, which selects the threshold combinations and processing flows instead of labor-intensive annotation work to construct the ground truth of the dataset, and design a deep neural network, FURNet, based on UNet++ and ResNeXt. The model obtained from training achieves high-quality vascular segmentation and captures multi-scene vascular features on both constructed and unknown datasets with good generalization. Furthermore, we intravital verified the availability of this method on a tumor before and after embolization treatment. This work provides a new approach for realizing LSCI vascular segmentation and also makes a new application-level advance in the field of artificial intelligence-assisted disease diagnosis.
Asunto(s)
Inteligencia Artificial , Redes Neurales de la Computación , Rayos Láser , Microcirculación/fisiología , Aprendizaje Automático Supervisado , Procesamiento de Imagen Asistido por Computador/métodosRESUMEN
Osteoporosis is a bone-related disease characterized by decreased bone density and mass, leading to brittle fractures. Osteoporosis assessment from radiographs using a deep learning algorithm has proven a low-cost alternative to the golden standard DXA. Due to the considerable noise and low contrast, automated diagnosis of osteoporosis in X-ray images still poses a significant challenge for traditional diagnostic methods. In this paper, an end-to-end transformer-style network was proposed, termed FCoTNet, to overcome the shortcoming of insufficient fusion of texture information and local features in the traditional CoTNet. To extract complementary geometric representations at each scale of the transformer module, we integrated parallel multi-scale feature extraction architectures in each unit layer of FCoTNet to utilize convolution to aggregate features from different receptive fields. Moreover, in order to extract small-scale texture features which were more critical to the diagnosis of osteoporosis in radiographs, larger fusion weights were assigned to the feature maps with small-size receptive fields. Afterward, the multi-scale global modeling was conducted by self-attention mechanism. The proposed model was first investigated on a private lumbar spine X-ray dataset with the 5-fold cross-validation strategy, obtaining an average accuracy of 78.29 ± 0.93 %, an average sensitivity of 69.72 ± 2.35 %, and an average specificity of 88.92 ± 0.67 % for the multi-classification of normal, osteopenia, and osteoporosis categories. We then conducted a controlled trial with five orthopedic clinicians to evaluate the clinical value of the model. The average clinician's accuracy improved from 61.50 ± 10.79 % unaided to 80.00 ± 5.92 % aided (18.50 % improvement), sensitivity improved from 64.38 ± 8.07 % unaided to 83.31 ± 5.43 % aided (18.93 % improvement), and specificity improved from 80.11 ± 4.72 % unaided to 89.94 ± 3.82 % aided (9.83 % improvement). Meanwhile, the prediction consistency among clinicians significantly improved with the assistance of FCoTNet. Furthermore, the proposed model showed good robustness on an external test dataset. These investigations indicate that the proposed deep learning model achieves state-of-the-art performance for osteoporosis prediction, which substantially improves osteoporosis screening and reduced osteoporosis fractures.
Asunto(s)
Vértebras Lumbares , Osteoporosis , Humanos , Rayos X , Vértebras Lumbares/diagnóstico por imagen , Osteoporosis/diagnóstico por imagen , AlgoritmosRESUMEN
Diabetic retinopathy (DR) will cause blindness if the detection and treatment are not carried out in the early stages. To create an effective treatment strategy, the severity of the disease must first be divided into referral-warranted diabetic retinopathy (RWDR) and non-referral diabetic retinopathy (NRDR). However, there are usually no sufficient fundus examinations due to lack of professional service in the communities, particularly in the developing countries. In this study, we introduce UGAN_Resnet_CBAM (URNet; UGAN is a generative adversarial network that uses Unet for feature extraction), a two-stage end-to-end deep learning technique for the automatic detection of diabetic retinopathy. The characteristics of DDR fundus data set were used to design an adaptive image preprocessing module in the first stage. Gradient-weighted Class Activation Mapping (Grad-CAM) and t-distribution and stochastic neighbor embedding (t-SNE) were used as the evaluation indices to analyze the preprocessing results. In the second stage, we enhanced the performance of the Resnet50 network by integrating the convolutional block attention module (CBAM). The outcomes demonstrate that our proposed solution outperformed other current structures, achieving 94.5% and 94.4% precisions, and 96.2% and 91.9% recall for NRDR and RWDR, respectively.
Asunto(s)
Aprendizaje Profundo , Diabetes Mellitus , Retinopatía Diabética , Humanos , Retinopatía Diabética/diagnóstico , Fondo de OjoRESUMEN
Objective.The goal of this study is to develop a robust semi-weakly supervised learning strategy for vessel segmentation in laser speckle contrast imaging (LSCI), addressing the challenges associated with the low signal-to-noise ratio, small vessel size, and irregular vascular aberration in diseased regions, while improving the performance and robustness of the segmentation method.Approach.For the training dataset, the healthy vascular images denoted as normal-vessel samples were manually labeled, while the diseased LSCI images involving tumor or embolism were denoted as abnormal-vessel samples and annotated as pseudo labels by the traditional semantic segmentation methods. In the training phase, the pseudo labels were constantly updated to improve the segmentation accuracy based on DeepLabv3+. Objective evaluation was conducted on the normal-vessel test set, while subjective evaluation was performed on the abnormal-vessel test set.Main results.The proposed method achieved an IOU of 0.8671, a Dice of 0.9288, and a mean relative percentage difference (mRPD) with supervised learning of 0.5% in the objective evaluation. In the subjective evaluation, our method significantly outperformed other methods in main vessel segmentation, tiny vessel segmentation, and blood vessel connection. Additionally, our method exhibited robustness when abnormal-vessel style noise was added to normal-vessel samples using a style translation network.Significance.The proposed semi-weakly supervised learning strategy demonstrates high efficiency and excellent robustness for vascular segmentation in LSCI, providing a potential tool for assessing the morphological and structural features of vessels in clinical applications.
Asunto(s)
Procesamiento de Imagen Asistido por Computador , Aprendizaje Automático Supervisado , Procesamiento de Imagen Asistido por Computador/métodos , Relación Señal-RuidoRESUMEN
OBJECTIVES: To differentiate the primary small-cell lung cancer (SCLC) and non-small-cell lung cancer (NSCLC) for patients with brain metastases (BMs) based on a deep learning (DL) model using contrast-enhanced magnetic resonance imaging (MRI) T1 weighted (T1CE) images. METHODS: Out of 711 patients with BMs of lung cancer origin (SCLC 232, NSCLC 479), the MRI datasets of 192 patients (lesions' widths and heights > 30 pixels) with BMs from lung cancer (73 SCLC and 119 NSCLC) confirmed pathologically were enrolled, retrospectively. A typical convolutional neural network ResNet18 was applied for the automatic classification of BMs lesions from lung cancer based on T1CE images, with training and testing groups randomized per patient to eliminate learning bias. A 5-fold cross-validation was performed to evaluate the classification of the model. The receiver operating characteristic (ROC) curve, accuracy, precision, recall and f1 score were calculated. RESULTS: For a 5-fold cross-validation test, the DL model achieved AUCs of 0.8019 and 0.8024 for SCLC and NSCLC patients with BMs, respectively, and a mean overall accuracy of 0.7515±0.04. The DL model performed well in differentiating the primary SCLC and NSCLC with BMs. CONCLUSION: The proposed DL model is feasible and effective in differentiating the pathological subtypes of SCLC and NSCLC causing BMs, which may be used as a new tool for oncologists to diagnose noninvasively BMs and guide therapy based on the imaging structure of tumors.
Asunto(s)
Neoplasias Encefálicas , Carcinoma de Pulmón de Células no Pequeñas , Aprendizaje Profundo , Neoplasias Pulmonares , Humanos , Carcinoma de Pulmón de Células no Pequeñas/diagnóstico por imagen , Carcinoma de Pulmón de Células no Pequeñas/patología , Carcinoma de Pulmón de Células no Pequeñas/secundario , Neoplasias Pulmonares/diagnóstico por imagen , Neoplasias Pulmonares/patología , Estudios Retrospectivos , Imagen por Resonancia Magnética , Neoplasias Encefálicas/diagnóstico por imagenRESUMEN
In this paper, one spin-selected vortex metalens composed of silicon nanobricks is designed and numerically investigated at the mid-infrared band, which can produce vortex beams with different topological charges and achieve different spin lights simultaneously. Another type of spin-independent vortex metalens is also designed, which can focus the vortex beams with the same topological charge at the same position for different spin lights, respectively. Both of the two vortex metalenses can achieve high-efficiency focusing for different spin lights. In addition, the spin-to-orbital angular momentum conversion through the vortex metalens is also discussed in detail. Our work facilitates the establishment of high-efficiency spin-related integrated devices, which is significant for the development of vortex optics and spin optics.
RESUMEN
Colorectal cancer (CRC) is one of the main alimentary tract system malignancies affecting people worldwide. Adenomatous polyps are precursors of CRC, and therefore, preventing the development of these lesions may also prevent subsequent malignancy. However, the adenoma detection rate (ADR), a measure of the ability of a colonoscopist to identify and remove precancerous colorectal polyps, varies significantly among endoscopists. Here, we attempt to use a convolutional neural network (CNN) to generate a unique computer-aided diagnosis (CAD) system by exploring in detail the multiple-scale performance of deep neural networks. We applied this system to 3,375 hand-labeled images from the screening colonoscopies of 1,197 patients; of whom, 3,045 were assigned to the training dataset and 330 to the testing dataset. The images were diagnosed simply as either an adenomatous or non-adenomatous polyp. When applied to the testing dataset, our CNN-CAD system achieved a mean average precision of 89.5%. We conclude that the proposed framework could increase the ADR and decrease the incidence of interval CRCs, although further validation through large multicenter trials is required.
RESUMEN
Metastasis is the primary cause of mortality in patients with nonsmall cell lung cancer (NSCLC). Actin cytoskeletal reorganization is usually accompanied by the epithelialmesenchymal transition (EMT)induced invasion and metastasis of cancer cells. In the present study, expression levels of the actinassociated protein cofilin1 and of the pivotal EMT molecule Twist1 were determined in NSCLC tissues. Using lung cancer tissue arrays, the identification of 67.4% of tissue spots that exhibited reciprocal levels of cofilin1 and Twist1 was achieved by immunohistochemical (IHC) staining. This reciprocal expression pattern was also detected in 21 out of 25 clinicopathological NSCLC tissue sections, and in 10 out of 15 NSCLC cell lines. In addition, high levels of cofilin1 and low levels of Twist1 accounted for 80 and 71.5% of the reciprocal expression pattern in tissue arrays and clinicopathological tissue samples, respectively. This pattern was also detected in normal lung tissues, stage I and II lung cancer tissues, and adenocarcinoma subtypes of NSCLC tissues. Although cofilin1 and Twist1 were expressed inversely, a positive correlation of these two proteins was present in normal lung tissues and lung tumor tissues. Furthermore, enforced expression of cofilin1 suppressed the expression level of Twist1 in NSCLC H1299 cells. An online KaplanMeier survival analytic tool allowed access to a public microarray dataset with a maximum of 1,926 NSCLC samples. The analysis revealed that high expression levels of both cofilin1 (CFL1) and Twist1 (TWIST1) genes were associated with decreased survival of NSCLC patients, notably with regard to the adenocarcinoma subtype. The analysis was conducted using the multivariate Cox regression model. Although the reciprocal association of the expression levels of cofilin1 and Twist1 with the survival rate of NSCLC patients requires additional information, it may be a significant indicator of the progression of NSCLC.