RESUMO
Computer-assisted diagnosis is key for scaling up cervical cancer screening. However, current recognition algorithms perform poorly on whole slide image (WSI) analysis, fail to generalize for diverse staining and imaging, and show sub-optimal clinical-level verification. Here, we develop a progressive lesion cell recognition method combining low- and high-resolution WSIs to recommend lesion cells and a recurrent neural network-based WSI classification model to evaluate the lesion degree of WSIs. We train and validate our WSI analysis system on 3,545 patient-wise WSIs with 79,911 annotations from multiple hospitals and several imaging instruments. On multi-center independent test sets of 1,170 patient-wise WSIs, we achieve 93.5% Specificity and 95.1% Sensitivity for classifying slides, comparing favourably to the average performance of three independent cytopathologists, and obtain 88.5% true positive rate for highlighting the top 10 lesion cells on 447 positive slides. After deployment, our system recognizes a one giga-pixel WSI in about 1.5 min.
Assuntos
Citodiagnóstico/métodos , Aprendizado Profundo , Diagnóstico por Computador/métodos , Detecção Precoce de Câncer , Neoplasias do Colo do Útero/diagnóstico , Feminino , Humanos , Processamento de Imagem Assistida por Computador/métodos , Redes Neurais de Computação , Curva ROC , Reprodutibilidade dos TestesRESUMO
Digital reconstruction or tracing of 3D tree-like neuronal structures from optical microscopy images is essential for understanding the functionality of neurons and reveal the connectivity of neuronal networks. Despite the existence of numerous tracing methods, reconstructing a neuron from highly noisy images remains challenging, particularly for neurites with low and inhomogeneous intensities. Conducting deep convolutional neural network (CNN)-based segmentation prior to neuron tracing facilitates an approach to solving this problem via separation of weak neurites from a noisy background. However, large manual annotations are needed in deep learning-based methods, which is labor-intensive and limits the algorithm's generalization for different datasets. In this study, we present a weakly supervised learning method of a deep CNN for neuron reconstruction without manual annotations. Specifically, we apply a 3D residual CNN as the architecture for discriminative neuronal feature extraction. We construct the initial pseudo-labels (without manual segmentation) of the neuronal images on the basis of an existing automatic tracing method. A weakly supervised learning framework is proposed via iterative training of the CNN model for improved prediction and refining of the pseudo-labels to update training samples. The pseudo-label was iteratively modified via mining and addition of weak neurites from the CNN predicted probability map on the basis of their tubularity and continuity. The proposed method was evaluated on several challenging images from the public BigNeuron and Diadem datasets, to fMOST datasets. Owing to the adaption of 3D deep CNNs and weakly supervised learning, the presented method demonstrates effective detection of weak neurites from noisy images and achieves results similar to those of the CNN model with manual annotations. The tracing performance was significantly improved by the proposed method on both small and large datasets (>100 GB). Moreover, the proposed method proved to be superior to several novel tracing methods on original images. The results obtained on various large-scale datasets demonstrated the generalization and high precision achieved by the proposed method for neuron reconstruction.
RESUMO
Resin embedding is widely used and facilitates microscopic imaging of biological tissues. In contrast, quenching of fluorescence during embedding process hinders the application of resin embedding for imaging of fluorescence-labeled samples. For samples expressing fluorescent proteins, it has been demonstrated that the weakened fluorescence could be recovered by reactivating the fluorophore with alkaline buffer. We extended this idea to immunofluorescence-labeling technology. We showed that the fluorescence of pH-sensitive fluorescein isothiocyanate (FITC) was quenched after resin embedding but reactivated after treating by alkaline buffer. We observed 138.5% fluorescence preservation ratio of reactivated state, sixfold compared with the quenched state in embedding resin, which indicated its application for fluorescence imaging of high signal-to-background ratio. Furthermore, we analyzed the chemical reactivation mechanism of FITC fluorophore. This work would show a way for high-resolution imaging of immunofluorescence-labeled samples embedded in resin.
Assuntos
Fluoresceína-5-Isotiocianato/química , Imunofluorescência/métodos , Técnicas Histológicas/métodos , Inclusão em Plástico , Resinas Acrílicas , Animais , Encéfalo/citologia , Química Encefálica , CamundongosRESUMO
Resin embedding has been widely applied to fixing biological tissues for sectioning and imaging, but has long been regarded as incompatible with green fluorescent protein (GFP) labeled sample because it reduces fluorescence. Recently, it has been reported that resin-embedded GFP-labeled brain tissue can be imaged with high resolution. In this protocol, we describe an optimized protocol for resin embedding and chemical reactivation of fluorescent protein labeled mouse brain, we have used mice as experiment model, but the protocol should be applied to other species. This method involves whole brain embedding and chemical reactivation of the fluorescent signal in resin-embedded tissue. The whole brain embedding process takes a total of 7 days. The duration of chemical reactivation is ~2 min for penetrating 4 µm below the surface in the resin-embedded brain. This protocol provides an efficient way to prepare fluorescent protein labeled sample for high-resolution optical imaging. This kind of sample was demonstrated to be imaged by various optical micro-imaging methods. Fine structures labeled with GFP across a whole brain can be detected.
RESUMO
High-resolution three-dimensional biomolecule distribution information of large samples is essential to understanding their biological structure and function. Here, we proposed a method combining large sample resin embedding with iDISCO immunofluorescence staining to acquire the profile of biomolecules with high spatial resolution. We evaluated the compatibility of plastic embedding with an iDISCO staining technique and found that the fluorophores and the neuronal fine structures could be well preserved in the Lowicryl HM20 resin, and that numerous antibodies and fluorescent tracers worked well upon Lowicryl HM20 resin embedding. Further, using fluorescence Micro-Optical sectioning tomography (fMOST) technology combined with ultra-thin slicing and imaging, we were able to image the immunolabeled large-volume tissues with high resolution.