RESUMO
Acting as a central hub in regulating brain functions, the thalamus plays a pivotal role in controlling high-order brain functions. Considering the impact of preterm birth on infant brain development, traditional studies focused on the overall development of thalamus other than its subregions. In this study, we compared the volumetric growth and shape development of the thalamic hemispheres between the infants born preterm and full-term (Left volume: P = 0.027, Left normalized volume: P < 0.0001; Right volume: P = 0.070, Right normalized volume: P < 0.0001). The ventral nucleus region, dorsomedial nucleus region, and posterior nucleus region of the thalamus exhibit higher vulnerability to alterations induced by preterm birth. The structural covariance (SC) between the thickness of thalamus and insula in preterm infants (Left: corrected P = 0.0091, Right: corrected P = 0.0119) showed significant increase as compared to full-term controls. Current findings suggest that preterm birth affects the development of the thalamus and has differential effects on its subregions. The ventral nucleus region, dorsomedial nucleus region, and posterior nucleus region of the thalamus are more susceptible to the impacts of preterm birth.
Assuntos
Recém-Nascido Prematuro , Imageamento por Ressonância Magnética , Tálamo , Humanos , Tálamo/crescimento & desenvolvimento , Tálamo/diagnóstico por imagem , Feminino , Masculino , Recém-Nascido , Recém-Nascido Prematuro/crescimento & desenvolvimento , Nascimento Prematuro/patologiaRESUMO
Electrochemical production of H2O2 is a cost-effective and environmentally friendly alternative to the anthraquinone-based processes. Metal-doped carbon-based catalysts are commonly used for 2-electron oxygen reduction reaction (2e-ORR) due to their high selectivity. However, the exact roles of metals and carbon defects on ORR catalysts for H2O2 production remain unclear. Herein, by varying the Co loading in the pyrolysis precursor, a Co-N/O-C catalyst with Faradaic efficiency greater than 90% in alkaline electrolyte was obtained. Detailed studies revealed that the active sites in the Co-N/O-C catalysts for 2e-ORR were carbon atoms in C-O-C groups at defect sites. The direct contribution of cobalt single atom sites and metallic Co for the 2e-ORR performance was negligible. However, Co plays an important role in the pyrolytic synthesis of a catalyst by catalyzing carbon graphitization, tuning the formation of defects and oxygen functional groups, and controlling O and N concentrations, thereby indirectly enhancing 2e-ORR performance.
RESUMO
Premature birth is associated with a high prevalence of neurodevelopmental impairments in surviving infants. The hippocampus is known to be critical for learning and memory, yet the putative effects of hippocampal dysfunction remain poorly understood in preterm neonates. In particular, while asymmetry of the hippocampus has been well noted both structurally and functionally, how preterm birth impairs hippocampal development and to what extent the hippocampus is asymmetrically impaired by preterm birth have not been well delineated. In this study, we compared volumetric growth and shape development in the hippocampal hemispheres and structural covariance (SC) between hippocampal vertices and cortical thickness in cerebral cortex regions between two groups. We found that premature infants had smaller volumes of the right hippocampi only. Lower thickness was observed in the hippocampal head in both hemispheres for preterm neonates compared with full-term peers, though preterm neonates exhibited an accelerated age-related change of hippocampal thickness in the left hippocampi. The SC between the left hippocampi and the limbic lobe of the premature infants was severely impaired compared with the term-born neonates. These findings suggested that the development of the hippocampus during the third trimester may be altered following early extrauterine exposure with a high degree of asymmetry.
Assuntos
Nascimento Prematuro , Córtex Cerebral , Feminino , Hipocampo/diagnóstico por imagem , Humanos , Lactente , Recém-Nascido , Recém-Nascido Prematuro , Imageamento por Ressonância MagnéticaRESUMO
Accurate segmentation of brain tumors from medical images is important for diagnosis and treatment planning, and it often requires multi-modal or contrast-enhanced images. However, in practice some modalities of a patient may be absent. Synthesizing the missing modality has a potential for filling this gap and achieving high segmentation performance. Existing methods often treat the synthesis and segmentation tasks separately or consider them jointly but without effective regularization of the complex joint model, leading to limited performance. We propose a novel brain Tumor Image Synthesis and Segmentation network (TISS-Net) that obtains the synthesized target modality and segmentation of brain tumors end-to-end with high performance. First, we propose a dual-task-regularized generator that simultaneously obtains a synthesized target modality and a coarse segmentation, which leverages a tumor-aware synthesis loss with perceptibility regularization to minimize the high-level semantic domain gap between synthesized and real target modalities. Based on the synthesized image and the coarse segmentation, we further propose a dual-task segmentor that predicts a refined segmentation and error in the coarse segmentation simultaneously, where a consistency between these two predictions is introduced for regularization. Our TISS-Net was validated with two applications: synthesizing FLAIR images for whole glioma segmentation, and synthesizing contrast-enhanced T1 images for Vestibular Schwannoma segmentation. Experimental results showed that our TISS-Net largely improved the segmentation accuracy compared with direct segmentation from the available modalities, and it outperformed state-of-the-art image synthesis-based segmentation methods.
RESUMO
Logo detection is one of the crucial branches in computer vision due to various real-world applications, such as automatic logo detection and recognition, intelligent transportation, and trademark infringement detection. Compared with traditional handcrafted-feature-based methods, deep learning-based convolutional neural networks (CNNs) can learn both low-level and high-level image features. Recent decades have witnessed the great feature representation capabilities of deep CNNs and their variants, which have been very good at discovering intricate structures in high-dimensional data and are thereby applicable to many domains including logo detection. However, logo detection remains challenging, as existing detection methods cannot solve well the problems of a multiscale and large aspect ratios. In this paper, we tackle these challenges by developing a novel long-range dependence involutional network (LDI-Net). Specifically, we designed a strategy that combines a new operator and a self-attention mechanism via rethinking the intrinsic principle of convolution called long-range dependence involution (LD involution) to alleviate the detection difficulties caused by large aspect ratios. We also introduce a multilevel representation neural architecture search (MRNAS) to detect multiscale logo objects by constructing a novel multipath topology. In addition, we implemented an adaptive RoI pooling module (ARM) to improve detection efficiency by addressing the problem of logo deformation. Comprehensive experiments on four benchmark logo datasets demonstrate the effectiveness and efficiency of the proposed approach.
RESUMO
Growing evidence indicates that amyloid-beta (Aß) accumulation is one of the most common neurobiological biomarkers in Alzheimer's disease (AD). The primary aim of this study was to explore whether the radiomic features of Aß positron emission tomography (PET) images are used as predictors and provide a neurobiological foundation for AD. The radiomics features of Aß PET imaging of each brain region of the Brainnetome Atlas were computed for classification and prediction using a support vector machine model. The results showed that the area under the receiver operating characteristic curve (AUC) was 0.93 for distinguishing AD (N = 291) from normal control (NC; N = 334). Additionally, the AUC was 0.83 for the prediction of mild cognitive impairment (MCI) converting (N = 88) (vs. no conversion, N = 100) to AD. In the MCI and AD groups, the systemic analysis demonstrated that the classification outputs were significantly associated with clinical measures (apolipoprotein E genotype, polygenic risk scores, polygenic hazard scores, cerebrospinal fluid Aß, and Tau, cognitive ability score, the conversion time for progressive MCI subjects and cognitive changes). These findings provide evidence that the radiomic features of Aß PET images can serve as new biomarkers for clinical applications in AD/MCI, further providing evidence for predicting whether MCI subjects will convert to AD.
Assuntos
Doença de Alzheimer/diagnóstico por imagem , Peptídeos beta-Amiloides/metabolismo , Processamento de Imagem Assistida por Computador/métodos , Tomografia por Emissão de Pósitrons/métodos , Idoso , Idoso de 80 Anos ou mais , Doença de Alzheimer/psicologia , Peptídeos beta-Amiloides/líquido cefalorraquidiano , Atlas como Assunto , Biomarcadores , Encéfalo/diagnóstico por imagem , Disfunção Cognitiva/diagnóstico por imagem , Progressão da Doença , Feminino , Humanos , Aprendizado de Máquina , Masculino , Testes Neuropsicológicos , Valor Preditivo dos Testes , Curva ROC , Sensibilidade e Especificidade , Proteínas tau/líquido cefalorraquidianoRESUMO
The specific identification and elimination of cancer cells has been a great challenge in the past few decades. In this study, the circular dichroism (CD) of cells was measured by a self-designed special system through the folate-conjugated chiral nano-sensor. A novel method was established to recognize cancer cells from normal cells according to the chirality of cells based on their CD signals. After a period of interaction between the nano-sensor and cells, the sharp weakening of CD signals was induced in cancer cells but normal cells remained unchanged. The biocompatibility of the nano-sensor was evaluated and the result showed that it exhibited significant cytotoxic activity against cancer cells while no obvious damage on normal cells. Notably, the research indicated that the nano-sensor may selectively cause apoptosis in cancer cells, and thus, have the potential to act as an antitumor agent.
Assuntos
Compostos de Cádmio , Neoplasias/terapia , Pontos Quânticos/química , Sulfetos , Telúrio , Apoptose , Neoplasias da Mama/terapia , Linhagem Celular Tumoral , Dicroísmo Circular , Feminino , Ácido Fólico , HumanosRESUMO
Multicolor (MC) imaging is an imaging modality that records confocal scanning laser ophthalmoscope (cSLO) fundus images, which can be used for the diabetic retinopathy (DR) detection. By utilizing this imaging technique, multiple modal images can be obtained in a single case. Additional symptomatic features can be obtained if these images are considered during the diagnosis of DR. However, few studies have been carried out to classify MC Images using deep learning methods, let alone using multi modal features for analysis. In this work, we propose a novel model which uses the multimodal information bottleneck network (MMIB-Net) to classify the MC Images for the detection of DR. Our model can extract the features of multiple modalities simultaneously while finding concise feature representations of each modality using the information bottleneck theory. MC Images classification can be achieved by picking up the combined representations and features of all modalities. In our experiments, it is shown that the proposed method can achieve an accurate classification of MC Images. Comparative experiments also demonstrate that the use of multimodality and information bottleneck improves the performance of MC Images classification. To the best of our knowledge, this is the first report of DR identification utilizing the multimodal information bottleneck convolutional neural network in MC Images.
Assuntos
Aprendizado Profundo , Retinopatia Diabética/diagnóstico , Diagnóstico por Imagem/classificação , Retina/diagnóstico por imagem , Fundo de Olho , Humanos , Estudos RetrospectivosRESUMO
OBJECTIVES: The aim of this study was to determine the invasiveness of ground-glass nodules (GGNs) using a 3D multi-task deep learning network. METHODS: We propose a novel architecture based on 3D multi-task learning to determine the invasiveness of GGNs. In total, 770 patients with 909 GGNs who underwent lung CT scans were enrolled. The patients were divided into the training (n = 626) and test sets (n = 144). In the test set, invasiveness was classified using deep learning into three categories: atypical adenomatous hyperplasia (AAH) and adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive pulmonary adenocarcinoma (IA). Furthermore, binary classifications (AAH/AIS/MIA vs. IA) were made by two thoracic radiologists and compared with the deep learning results. RESULTS: In the three-category classification task, the sensitivity, specificity, and accuracy were 65.41%, 82.21%, and 64.9%, respectively. In the binary classification task, the sensitivity, specificity, accuracy, and area under the ROC curve (AUC) values were 69.57%, 95.24%, 87.42%, and 0.89, respectively. In the visual assessment of GGN invasiveness of binary classification by the two thoracic radiologists, the sensitivity, specificity, and accuracy of the senior and junior radiologists were 58.93%, 90.51%, and 81.35% and 76.79%, 55.47%, and 61.66%, respectively. CONCLUSIONS: The proposed multi-task deep learning model achieved good classification results in determining the invasiveness of GGNs. This model may help to select patients with invasive lesions who need surgery and the proper surgical methods. KEY POINTS: ⢠The proposed multi-task model has achieved good classification results for the invasiveness of GGNs. ⢠The proposed network includes a classification and segmentation branch to learn global and regional features, respectively. ⢠The multi-task model could assist doctors in selecting patients with invasive lesions who need surgery and choosing appropriate surgical methods.
Assuntos
Adenocarcinoma in Situ , Adenocarcinoma de Pulmão , Adenocarcinoma , Neoplasias Pulmonares , Adenocarcinoma/diagnóstico por imagem , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Invasividade Neoplásica , Estudos RetrospectivosRESUMO
Microarray technique is a prevalent method for the classification and prediction of colorectal cancer (CRC). Nevertheless, microarray data suffers from the curse of dimensionality when selecting feature genes of the disease based on imbalance samples, thus causing low prediction accuracy. Hence, it is of vital significance to build proper models that can avoid the above problems and predict the CRC more accurately. In this paper, we use an ensemble model to classify samples into healthy and CRC groups and improve prediction performance. The proposed model is composed of three functional modules. The first module mainly performs the function of removing redundant genes. The main feature genes are selected using minimum redundancy maximum relevance (mRMR) method to reduce the dimensionality of features thereby increasing the prediction results. The second module aims to solve the problem caused by imbalanced data using hybrid sampling algorithm RUSBoost. The third module focuses on the classification algorithm optimization. We use mixed kernel function (MKF) based support vector machine (SVM) model to classify an unknown sample into healthy individuals and CRC patients, and then, the Whale Optimization Algorithm (WOA) is applied to find most optimal parameters of the proposed MKF-SVM. The final results show that the proposed model achieves higher G-means than other comparable models. The conclusion comes to show that RUSBoost wrapping WOAâ¯+â¯MKF-SVM model can be applied to improve the predictive performance of colorectal cancer based on the imbalanced data.
Assuntos
Algoritmos , Neoplasias Colorretais/diagnóstico , Perfilação da Expressão Gênica/métodos , Máquina de Vetores de Suporte , Neoplasias Colorretais/genética , Neoplasias Colorretais/metabolismo , Humanos , Software , Transcriptoma/genéticaRESUMO
Longitudinal brain morphometry probes time-related brain morphometric patterns. We propose a method called dynamic network modeling with continuous valued nodes to generate a dynamic brain network from continuous valued longitudinal morphometric data. The mathematical framework of this method is based on state-space modeling. We use a bootstrap-enhanced least absolute shrinkage operator to solve the network-structure generation problem. In contrast to discrete dynamic Bayesian network modeling, the proposed method enables network generation directly from continuous valued high-dimensional short sequence data, being free from any discretization process. We applied the proposed method to a study of normal brain development.
Assuntos
Substância Cinzenta/crescimento & desenvolvimento , Imageamento por Ressonância Magnética/métodos , Modelos Teóricos , Rede Nervosa/crescimento & desenvolvimento , Adolescente , Teorema de Bayes , Criança , Pré-Escolar , Simulação por Computador , Substância Cinzenta/diagnóstico por imagem , Humanos , Estudos Longitudinais , Rede Nervosa/diagnóstico por imagem , Redes Neurais de ComputaçãoRESUMO
Multispectral Imaging (MSI) produces a sequence of discrete spectral slices that penetrate different light-absorbing species or chromophores and is a noninvasive technology useful for the early detection of various retinal, optic nerve and choroidal diseases. However, eye movement during the image acquisition process may introduce spatial misalignment between MSI images. This potentially causes trouble in the manual/automatic interpretation of MSI, but still remains an unresolved problem to this date. To deal with this MSI misalignment problem, we present a method on the groupwise registration of sequential images from MSI of the retina and choroid. The advantage of our algorithm is at least threefold: 1) simultaneous estimation of landmark correspondences and a parametric motion model via quadratic programming, 2) enforcement of temporal smoothness on the estimated motion, and 3) inclusion of a robust matching cost function. As validated in our experiments with a database of 22 MSI sequences, our algorithm outperforms two state-of-the-art registration techniques proposed originally in other domains. Our algorithm is potentially invaluable in ophthalmologists' clinical practice regarding various eye diseases.
Assuntos
Algoritmos , Movimentos Oculares , Aumento da Imagem , Reconhecimento Automatizado de Padrão , Retina/diagnóstico por imagem , Corioide , HumanosRESUMO
In this article, the controllability of Boolean networks via input controls under Harvey's update scheme is investigated. First, the model of Boolean control networks under Harvey's stochastic update is proposed, by means of semi-tensor product approach, which is converted into discrete-time linear representation. And, a general formula of control-depending network transition matrix is provided. Second, based on discrete-time dynamics, controllability of the proposed model is analytically discussed by revealing the necessary and sufficient conditions of the reachable sets, respectively, for three kinds of controls, i.e., free Boolean control sequence, input control networks, and close-loop control. Examples are showed to demonstrate the effectiveness and feasibility of the proposed scheme.
Assuntos
Algoritmos , Modelos TeóricosRESUMO
OBJECTIVE: Visualizing implanted subdural electrodes in three-dimensional (3D) space can greatly aid in planning, executing, and validating resection in epilepsy surgery. Coregistration software is available, but cost, complexity, insufficient accuracy, or validation limit adoption. We present a fully automated open-source application, based on a novel method using postimplant computerized tomography (CT) and postimplant magnetic resonance (MR) images, for accurately visualizing intracranial electrodes in 3D space. METHODS: CT-MR rigid brain coregistration, MR nonrigid registration, and prior-based segmentation were carried out on seven patients. Postimplant CT, postimplant MR, and an external labeled atlas were then aligned in the same space. The coregistration algorithm was validated by manually marking identical anatomic landmarks on the postimplant CT and postimplant MR images. Following coregistration, distances between the center of the landmark masks on the postimplant MR and the coregistered CT images were calculated for all subjects. Algorithms were implemented in open-source software and translated into a "drag and drop" desktop application for Apple Mac OS X. RESULTS: Despite postoperative brain deformation, the method was able to automatically align intrasubject multimodal images and segment cortical subregions, so that all electrodes could be visualized on the parcellated brain. Manual marking of anatomic landmarks validated the coregistration algorithm with a mean misalignment distance of 2.87 mm (standard deviation 0.58 mm)between the landmarks. Software was easily used by operators without prior image processing experience. SIGNIFICANCE: We demonstrate an easy to use, novel platform for accurately visualizing subdural electrodes in 3D space on a parcellated brain. We rigorously validated this method using quantitative measures. The method is unique because it involves no preprocessing, is fully automated, and freely available worldwide. A desktop application, as well as the source code, are both available for download on the International Epilepsy Electrophysiology Portal (https://www.ieeg.org) for use and interactive refinement.
Assuntos
Encéfalo/patologia , Processamento Eletrônico de Dados , Imageamento Tridimensional , Imageamento por Ressonância Magnética , Espaço Subdural/patologia , Tomografia Computadorizada por Raios X , Adulto , Eletrodos , Epilepsia/diagnóstico , Feminino , Humanos , Masculino , Adulto JovemRESUMO
Accurate segmentation of brain tumors in MRI images is imperative for precise clinical diagnosis and treatment. However, existing medical image segmentation methods exhibit errors, which can be categorized into two types: random errors and systematic errors. Random errors, arising from various unpredictable effects, pose challenges in terms of detection and correction. Conversely, systematic errors, attributable to systematic effects, can be effectively addressed through machine learning techniques. In this paper, we propose a corrective diffusion model for accurate MRI brain tumor segmentation by correcting systematic errors. This marks the first application of the diffusion model for correcting systematic segmentation errors. Additionally, we introduce the Vector Quantized Variational Autoencoder (VQ-VAE) to compress the original data into a discrete coding codebook. This not only reduces the dimensionality of the training data but also enhances the stability of the correction diffusion model. Furthermore, we propose the Multi-Fusion Attention Mechanism, which can effectively enhances the segmentation performance of brain tumor images, and enhance the flexibility and reliability of the corrective diffusion model. Our model is evaluated on the BRATS2019, BRATS2020, and Jun Cheng datasets. Experimental results demonstrate the effectiveness of our model over state-of-the-art methods in brain tumor segmentation.
Assuntos
Neoplasias Encefálicas , Processamento de Imagem Assistida por Computador , Humanos , Reprodutibilidade dos Testes , Processamento de Imagem Assistida por Computador/métodos , Algoritmos , Imageamento por Ressonância Magnética/métodos , Neoplasias Encefálicas/diagnóstico por imagem , Encéfalo/diagnóstico por imagemRESUMO
The executors of organismal functions are proteins, and the transition from RNA to protein is subject to post-transcriptional regulation; therefore, considering both RNA and surface protein expression simultaneously can provide additional evidence of biological processes. Cellular indexing of transcriptomes and epitopes by sequencing (CITE-Seq) technology can measure both RNA and protein expression in single cells, but these experiments are expensive and time-consuming. Due to the lack of computational tools for predicting surface proteins, we used datasets obtained with CITE-seq technology to design a deep generative prediction method based on diffusion models and to find biological discoveries through the prediction results. In our method, the scDM, which predicts protein expression values from RNA expression values of individual cells, uses a novel way of encoding the data into a model and generates predicted samples by introducing Gaussian noise to gradually remove the noise to learn the data distribution during the modelling process. Comprehensive evaluation across different datasets demonstrated that our predictions yielded satisfactory results and further demonstrated the effectiveness of incorporating information from single-cell multiomics data into diffusion models for biological studies. We also found that new directions for discovering therapeutic drug targets could be provided by jointly analysing the predictive value of surface protein expression and cancer cell drug scores.
Assuntos
Biologia Computacional , Proteínas de Membrana , Análise de Célula Única , Humanos , Algoritmos , Biologia Computacional/métodos , Perfilação da Expressão Gênica/métodos , Proteínas de Membrana/metabolismo , Proteínas de Membrana/genética , Análise de Célula Única/métodos , TranscriptomaRESUMO
Medical image segmentation is a crucial field of computer vision. Obtaining correct pathological areas can help clinicians analyze patient conditions more precisely. We have observed that both CNN-based and attention-based neural networks often produce rough segmentation results around the edges of the regions of interest. This significantly impacts the accuracy of obtaining the pathological areas. Without altering the original data and model architecture, further refining the initial segmentation outcomes can effectively address this issue and lead to more satisfactory results. Recently, diffusion models have demonstrated outstanding results in image generation, showcasing their powerful ability to model distributions. We believe that this ability can greatly enhance the accuracy of the reshaping results. This research proposes ERSegDiff, a neural network based on the diffusion model for reshaping segmentation borders. The diffusion model is trained to fit the distribution of the target edge area and is then used to modify the segmentation edge to produce more accurate segmentation results. By incorporating prior knowledge into the diffusion model, we can help it more accurately simulate the edge probability distribution of the samples. Moreover, we introduce the edge concern module, which leverages attention mechanisms to produce feature weights and further refine the segmentation outcomes. To validate our approach, we employed the COVID-19 and ISIC-2018 datasets for lung segmentation and skin cancer segmentation tasks, respectively. Compared with the baseline model, ERSegDiff improved the dice score by 3%-4% and 2%-4%, respectively, and achieved state-of-the-art scores compared to several mainstream neural networks, such as swinUNETR.
Assuntos
Processamento de Imagem Assistida por Computador , Redes Neurais de Computação , Humanos , Processamento de Imagem Assistida por Computador/métodos , Difusão , COVID-19/diagnóstico por imagemRESUMO
Feature matching, which refers to establishing the correspondence of regions between two images (usually voxel features), is a crucial prerequisite of feature-based registration. For deformable image registration tasks, traditional feature-based registration methods typically use an iterative matching strategy for interest region matching, where feature selection and matching are explicit, but specific feature selection schemes are often useful in solving application-specific problems and require several minutes for each registration. In the past few years, the feasibility of learning-based methods, such as VoxelMorph and TransMorph, has been proven, and their performance has been shown to be competitive compared to traditional methods. However, these methods are usually single-stream, where the two images to be registered are concatenated into a 2-channel whole, and then the deformation field is output directly. The transformation of image features into interimage matching relationships is implicit. In this paper, we propose a novel end-to-end dual-stream unsupervised framework, named TransMatch, where each image is fed into a separate stream branch, and each branch performs feature extraction independently. Then, we implement explicit multilevel feature matching between image pairs via the query-key matching idea of the self-attention mechanism in the Transformer model. Comprehensive experiments are conducted on three 3D brain MR datasets, LPBA40, IXI, and OASIS, and the results show that the proposed method achieves state-of-the-art performance in several evaluation metrics compared to the commonly utilized registration methods, including SyN, NiftyReg, VoxelMorph, CycleMorph, ViT-V-Net, and TransMorph, demonstrating the effectiveness of our model in deformable medical image registration.
Assuntos
Algoritmos , Encéfalo , Encéfalo/diagnóstico por imagem , Processamento de Imagem Assistida por Computador/métodosRESUMO
In recent years, predicting gene mutations on whole slide imaging (WSI) has gained prominence. The primary challenge is extracting global information and achieving unbiased semantic aggregation. To address this challenge, we propose a novel Transformer-based aggregation model, employing a self-learning weight aggregation mechanism to mitigate semantic bias caused by the abundance of features in WSI. Additionally, we adopt a random patch training method, which enhances model learning richness by randomly extracting feature vectors from WSI, thus addressing the issue of limited data. To demonstrate the model's effectiveness in predicting gene mutations, we leverage the lung adenocarcinoma dataset from Shandong Provincial Hospital for prior knowledge learning. Subsequently, we assess TP53, CSMD3, LRP1B, and TTN gene mutations using lung adenocarcinoma tissue pathology images and clinical data from The Cancer Genome Atlas (TCGA). The results indicate a notable increase in the AUC (Area Under the ROC Curve) value, averaging 4%, attesting to the model's performance improvement. Our research offers an efficient model to explore the correlation between pathological image features and molecular characteristics in lung adenocarcinoma patients. This model introduces a novel approach to clinical genetic testing, expected to enhance the efficiency of identifying molecular features and genetic testing in lung adenocarcinoma patients, ultimately providing more accurate and reliable results for related studies.
Assuntos
Adenocarcinoma de Pulmão , Adenocarcinoma , Neoplasias Pulmonares , Humanos , Adenocarcinoma de Pulmão/genética , Mutação/genética , Adenocarcinoma/genética , Fontes de Energia Elétrica , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/genéticaRESUMO
Breast cancer pathological image segmentation (BCPIS) holds significant value in assisting physicians with quantifying tumor regions and providing treatment guidance. However, achieving fine-grained semantic segmentation remains a major challenge for this technology. The complex and diverse morphologies of breast cancer tissue structures result in high costs for manual annotation, thereby limiting the sample size and annotation quality of the dataset. These practical issues have a significant impact on the segmentation performance. To overcome these challenges, this study proposes a semi-supervised learning model based on classification-guided segmentation. The model first utilizes a multi-scale convolutional network to extract rich semantic information and then employs a multi-expert cross-layer joint learning strategy, integrating a small number of labeled samples to iteratively provide the model with class-generated multi-cue pseudo-labels and real labels. Given the complexity of the breast cancer samples and the limited sample quantity, an innovative approach of augmenting additional unlabeled data was adopted to overcome this limitation. Experimental results demonstrate that, although the proposed model falls slightly behind supervised segmentation models, it still exhibits significant progress and innovation. The semi-supervised model in this study achieves outstanding performance, with an IoU (Intersection over Union) value of 71.53%. Compared to other semi-supervised methods, the model developed in this study demonstrates a performance advantage of approximately 3%. Furthermore, the research findings indicate a significant correlation between the classification and segmentation tasks in breast cancer pathological images, and the guidance of a multi-expert system can significantly enhance the fine-grained effects of semi-supervised semantic segmentation.