Patch Extraction Research Articles

A novel deep unsupervised approach for super-resolution of remote sensing hyperspectral image using gompertz-function convergence war accelerometric-optimization generative adversarial network (GF-CWAO-GAN)

Hyperspectral remote sensing images obtained from cameras are characterized by high-dimensions and low quality, which makes them unfavorable for various analytics purposes. This is due to the presence of visible and invisible frequencies of the reflected light making it poorly reveal the spectral signatures of the image. Visual communication advancement has paved the need for Image Super-Resolution (SR) which recovers high-resolution images from low-resolution images. Several works were carried out earlier on image SR using variants of supervised and unsupervised models that still lack accuracy. In this paper, we propose an unsupervised learning model titled Gompertz Function–based Convergence War Accelerometric Optimization–GAN framework for generating of High-Resolution (HR) images. The framework comprises a pre-processing stage, where the incoming Low-Resolution (LR) image is preprocessed for noise removal by applying Shannon-Gaussian Filter (S-GF). Following is the Gradient Domain Approach based Tone-Mapping (TM). Skew correction is done to remove distortion and maintain original resolution that may change during TM stage. The next stage comprises the boundary and edge enhancement of the resulting preprocessed image generated by the method of Inverse Gradient Mapping (IGM) followed by patch extraction to extract minute low-frequency information from the resulting boundary and edge-enhanced image. The contrast of the enhanced patches is improved by removing blurriness effect. The preprocessed image patches are then fed into the Gompertz Function-based Convergence War Accelerometric Optimization – GAN for feature mapping on the trained SR Image features that are clustered using Krzanowski and Li- Kantorovich Metric-K-Means clustering Algorithm (KL-KM-KMA) for effective generation of SR image. The developed model is validated for both qualitative and quantitative measurements. Comparisons are made with several other state-of -the-art methods for accuracy of 98.05%, precision of 97.98%, inception score of 8.71, Fréchet Inception Distance of 36.4 with reduced clustering and training time proving the efficiency of the proposed model.

A patch-based deep learning MRI segmentation model for improving efficiency and clinical examination of the spinal tumor

Background and objectiveMagnetic resonance imaging (MRI) plays a vital role in diagnosing spinal diseases, including different types of spinal tumors. However, conventional segmentation techniques are often labor-intensive and susceptible to variability. This study aims to propose a full-automatic segmentation method for spine MRI images, utilizing a convolutional-deconvolution neural network and patch-based deep learning. The objective is to improve segmentation efficiency, meeting clinical needs for accurate diagnoses and treatment planning. MethodsThe methodology involved the utilization of a convolutional neural network to automatically extract deep learning features from spine data. This allowed for the effective representation of anatomical structures. The network was trained to learn discriminative features necessary for accurate segmentation of the spine MRI data. Furthermore, a patch extraction (PE) based deep neural network was developed using a convolutional neural network to restore the feature maps to their original image size. To improve training efficiency, a combination of pre-training and an enhanced stochastic gradient descent method was utilized. ResultsThe experimental results highlight the effectiveness of the proposed method for spine image segmentation using Gadolinium-enhanced T1 MRI. This approach not only delivers high accuracy but also offers real-time performance. The innovative model attained impressive metrics, achieving 90.6% precision, 91.1% recall, 93.2% accuracy, 91.3% F1-score, 83.8% Intersection over Union (IoU), and 91.1% Dice Coefficient (DC). These results indicate that the proposed method can accurately segment spine tumors CT images, addressing the limitations of traditional segmentation algorithms. ConclusionIn conclusion, this study introduces a fully automated segmentation method for spine MRI images utilizing a convolutional neural network, enhanced by the application of the PE-module. By utilizing a patch extraction based neural network (PENN) deep learning techniques, the proposed method effectively addresses the deficiencies of traditional algorithms and achieves accurate and real-time spine MRI image segmentation.

Deep‐Learning‐Based Facial Retargeting Using Local Patches

AbstractIn the era of digital animation, the quest to produce lifelike facial animations for virtual characters has led to the development of various retargeting methods. While the retargeting facial motion between models of similar shapes has been very successful, challenges arise when the retargeting is performed on stylized or exaggerated 3D characters that deviate significantly from human facial structures. In this scenario, it is important to consider the target character's facial structure and possible range of motion to preserve the semantics assumed by the original facial motions after the retargeting. To achieve this, we propose a local patch‐based retargeting method that transfers facial animations captured in a source performance video to a target stylized 3D character. Our method consists of three modules. The Automatic Patch Extraction Module extracts local patches from the source video frame. These patches are processed through the Reenactment Module to generate correspondingly re‐enacted target local patches. The Weight Estimation Module calculates the animation parameters for the target character at every frame for the creation of a complete facial animation sequence. Extensive experiments demonstrate that our method can successfully transfer the semantic meaning of source facial expressions to stylized characters with considerable variations in facial feature proportion.

Multi-variants vision transformer-based malware image classification model using multi-criteria decision-making

Visualization-based malware detection gets more and more attention for detecting sophisticated malware that traditional antivirus software may miss. The approach involves creating a visual representation of the memory or portable executable files (PEs). However, most current visualization-based malware classification models focus on convolution neural networks instead of Vision transformers (ViT) even though ViT has a higher performance and captures the spatial representation of malware. Therefore, more research should be performed on malware classification using vision transformers. This paper proposes a multi-variants vision transformer-based malware image classification model using multi-criteria decision-making. The proposed method employs Multi-variants transformer encoders to show different visual representation embeddings sets of one malware image. The proposed architecture contains five steps: (1) patch extraction and embeddings, (2) positional encoding, (3) multi-variants transformer encoders, (4) classification, and (5) decision-making. The variants of transformer encoders are transfer learning-based models i.e., it was originally trained on ImageNet dataset. Moreover, the proposed malware classifier employs MEREC-VIKOR, a hybrid standard evaluation approach, which combines multi-inconsistent performance metrics. The performance of the transformer encoder variants is assessed both on individual malware families and across the entire set of malware families within two datasets i.e., MalImg and Microsoft BIG datasets achieving overall accuracy 97.64 and 98.92 respectively. Although the proposed method achieves high performance, the metrics exhibit inconsistency across some malware families. The results of standard evaluation metrics i.e., Q, R, and U show that TE3 outperform the TE1, TE2, and TE4 variants achieving minimal values equal to 0. Finally, the proposed architecture demonstrates a comparable performance to the state-of-the-art that use CNNs.

CroMAM: A Cross-Magnification Attention Feature Fusion Model for Predicting Genetic Status and Survival of Gliomas using Histological Images.

Predicting the gene mutation status in whole slide images (WSI) is crucial for the clinical treatment, cancer management, and research of gliomas. With advancements in CNN and Transformer algorithms, several promising models have been proposed. However, existing studies have paid little attention on fusing multi-magnification information, and the model requires processing all patches from a whole slide image. In this paper, we propose a cross-magnification attention model called CroMAM for predicting the genetic status and survival of gliomas. The CroMAM first utilizes a systematic patch extraction module to sample a subset of representative patches for downstream analysis. Next, the CroMAM applies Swin Transformer to extract local and global features from patches at different magnifications, followed by acquiring high-level features and dependencies among single-magnification patches through the application of a Vision Transformer. Subsequently, the CroMAM exchanges the integrated feature representations of different magnifications and encourage the integrated feature representations to learn the discriminative information from other magnification. Additionally, we design a cross-magnification attention analysis method to examine the effect of cross-magnification attention quantitatively and qualitatively which increases the model's explainability. To validate the performance of the model, we compare the proposed model with other multi-magnification feature fusion models on three tasks in two datasets. Extensive experiments demonstrate that the proposed model achieves state-of-the-art performance in predicting the genetic status and survival of gliomas. The implementation of the CroMAM will be publicly available upon the acceptance of this manuscript at https://github.com/GuoJisen/CroMAM.

Structure tensor-based Gaussian kernel edge-adaptive depth map refinement with triangular point view in images

<span lang="EN-US">Image reconstruction is the process of restoring the image resolution. In 3D image reconstruction, the objects in different viewpoints are processed with the triangular point view (TPV) method to estimate object geometry structure for 3D model. This work proposes a depth refinement methodology in preserving the geometric structure of objects using the structure tensor method with a Gaussian filter by transforming a series of 2D input images into a 3D model. The computation of depth map errors can be found by comparing the masked area/patch with the distribution of the original image's greyscale levels using the error pixel-based patch extraction algorithm. The presence of errors in the depth estimation could seriously deteriorate the quality of the 3D effect. The depth maps were iteratively refined based on histogram bins number to improve the accuracy of initial depth maps reconstructed from rigid objects. The existing datasets such as the dataset tanks and unit (DTU) and Middlebury datasets, were used to build the model out of the object scene structure. The results of this work have demonstrated that the proposed patch analysis outperformed the existing state of the art models depth refinement methods in terms of accuracy.</span>

Prognostic stratification of glioblastoma patients by unsupervised clustering of morphology patterns on whole slide images furthering our disease understanding.

Glioblastoma (GBM) is a highly aggressive malignant tumor of the central nervous system that displays varying molecular and morphological profiles, leading to challenging prognostic assessments. Stratifying GBM patients according to overall survival (OS) from H&E-stained whole slide images (WSI) using advanced computational methods is challenging, but with direct clinical implications. This work is focusing on GBM (IDH-wildtype, CNS WHO Gr.4) cases, identified from the TCGA-GBM and TCGA-LGG collections after considering the 2021 WHO classification criteria. The proposed approach starts with patch extraction in each WSI, followed by comprehensive patch-level curation to discard artifactual content, i.e., glass reflections, pen markings, dust on the slide, and tissue tearing. Each patch is then computationally described as a feature vector defined by a pre-trained VGG16 convolutional neural network. Principal component analysis provides a feature representation of reduced dimensionality, further facilitating identification of distinct groups of morphology patterns, via unsupervised k-means clustering. The optimal number of clusters, according to cluster reproducibility and separability, is automatically determined based on the rand index and silhouette coefficient, respectively. Our proposed approach achieved prognostic stratification accuracy of 83.33% on a multi-institutional independent unseen hold-out test set with sensitivity and specificity of 83.33%. We hypothesize that the quantification of these clusters of morphology patterns, reflect the tumor's spatial heterogeneity and yield prognostic relevant information to distinguish between short and long survivors using a decision tree classifier. The interpretability analysis of the obtained results can contribute to furthering and quantifying our understanding of GBM and potentially improving our diagnostic and prognostic predictions.

Spatial-attention ConvMixer architecture for classification and detection of gastrointestinal diseases using the Kvasir dataset

Gastrointestinal (GI) disorders, encompassing conditions like cancer and Crohn’s disease, pose a significant threat to public health. Endoscopic examinations have become crucial for diagnosing and treating these disorders efficiently. However, the subjective nature of manual evaluations by gastroenterologists can lead to potential errors in disease classification. In addition, the difficulty of diagnosing diseased tissues in GI and the high similarity between classes made the subject a difficult area. Automated classification systems that use artificial intelligence to solve these problems have gained traction. Automatic detection of diseases in medical images greatly benefits in the diagnosis of diseases and reduces the time of disease detection. In this study, we suggested a new architecture to enable research on computer-assisted diagnosis and automated disease detection in GI diseases. This architecture, called Spatial-Attention ConvMixer (SAC), further developed the patch extraction technique used as the basis of the ConvMixer architecture with a spatial attention mechanism (SAM). The SAM enables the network to concentrate selectively on the most informative areas, assigning importance to each spatial location within the feature maps. We employ the Kvasir dataset to assess the accuracy of classifying GI illnesses using the SAC architecture. We compare our architecture’s results with Vanilla ViT, Swin Transformer, ConvMixer, MLPMixer, ResNet50, and SqueezeNet models. Our SAC method gets 93.37% accuracy, while the other architectures get respectively 79.52%, 74.52%, 92.48%, 63.04%, 87.44%, and 85.59%. The proposed spatial attention block improves the accuracy of the ConvMixer architecture on the Kvasir, outperforming the state-of-the-art methods with an accuracy rate of 93.37%.

Anisotropic Green Tide Patch Information Extraction Based on Deformable Convolution

Green tides are marine disasters caused by the explosive proliferation or high concentration of certain large algae in seawater, which causes discoloration of the water body. Accurate monitoring of its distribution area is highly important for early warning and the protection of marine ecology. However, existing deep learning methods have difficulty in effectively identifying green tides with anisotropic characteristics due to the complex and variable shapes of the patches and the wide range of scales. To address this issue, this paper presents an anisotropic green tide patch extraction network (AGE-Net) based on deformable convolution. The main structure of AGE-Net consists of stacked anisotropic feature extraction (AFEB) modules. Each AFEB module contains two branches for extracting green tide patches. The first branch consists of multiple connected dense blocks. The second branch introduces a deformable convolution module and a depth residual module based on a multiresolution feature extraction network for extracting anisotropic features of green tide patches. Finally, an irregular green tide patch feature enhancement module is used to fuse the high-level semantic features extracted from the two branches. To verify the effectiveness of the AGE-Net model, experiments were conducted on the MODIS Green Tide dataset. The results show that AGE-Net has better recognition performance, with F1-scores and IoUs reaching 0.8317 and 71.19% on multi-view test images, outperforming other comparison methods.

Detection and Removal of Assymmetrical Skin Lesions Using DU-Net for Patch Extraction

The incidence of melanoma, a highly fatal kind of malignant tumor, is exhibiting an upward trend in its progression. Timely intervention and management of skin cancer significantly enhance the likelihood of survival. Analyzing dermoscopic images poses challenges for dermatologists due to various distracting factors, including fluctuations in lighting and reflections on the skin's surface. Accurately delineating the area of skin pathology is crucial for diagnosing the specific skin condition. This study introduces DU-net, a method for identifying and removing pigmented skin lesions. The DU-net framework incorporates deep convolutional neural networks, notably YOLOv5, to perform patch detection. It also employs asymmetrical patch contouring methods to preserve edge information. Additionally, clustering algorithms are utilized to identify pixel groups and extract patches from the image. The De Trop Noise Exclusion technique, in conjunction with the process of in-painting, is employed to successfully eliminate hair from the images within the ISIC-2018 and 2019 datasets. Rigorous annotation of skin images with lesions of various sizes and shapes using rectangle bounding is carried out, and YOLOv5 hyper-parameters are fine-tuned to achieve high-confidence multiple lesion detection in dermoscopic images. Despite complex textures and unclear boundaries, our approach consistently detects and labels patches, accurately segmenting the areas of skin pathology. The model's performance is assessed on these datasets using various parameter metrics, the results of the study indicate that the segmentation strategies described in this research exhibit an average accuracy ranging from about 92% to 94%.

An Automatic and Robust Visual SLAM Method for Intra-Abdominal Environment Reconstruction

Three-dimensional (3D) surface reconstruction is used to solve the problem of the narrow field of view in laparoscopy. It can provide surgeons or computer-assisted surgery systems with real-time complete internal abdominal anatomy. However, rapid changes in image depth, less texture, and specular reflection pose a challenge for the reconstruction. It is difficult to stably complete the reconstruction process using feature-based simultaneous localization and mapping (SLAM) method. This paper proposes a robust laparoscopic 3D surface reconstruction method using SLAM, which can automatically select appropriate parameters for stereo matching and robustly find matching point pairs for laparoscope motion estimation. The changing trend of disparity maps is used to predict stereo matching parameters to improve the quality of the disparity map. Feature patch extraction and tracking are selected to replace feature point extraction and matching in motion estimation, which reduces its failure and interruption in feature-based SLAM. The proposed feature patch matching method is suitable for parallel computing, which can improve its computing speed. Evaluation results on public in vivo and ex vivo porcine abdominal video data show the efficiency and robustness of our 3D surface reconstruction approach.

Field Patch Extraction Based on High-Resolution Imaging and U2-Net++ Convolutional Neural Networks

Accurate extraction of farmland boundaries is crucial for improving the efficiency of farmland surveys, achieving precise agricultural management, enhancing farmers’ production conditions, protecting the ecological environment, and promoting local economic development. Remote sensing and deep learning are feasible methods for creating large-scale farmland boundary maps. However, existing neural network models have limitations that restrict the accuracy and reliability of agricultural parcel extraction using remote sensing technology. In this study, we used high-resolution satellite images (2 m, 1 m, and 0.8 m) and the U2-Net++ model based on the RSU module, deep separable convolution, and the channel-spatial attention mechanism module to extract different types of fields. Our model exhibited significant improvements in farmland parcel extraction compared with the other models. It achieved an F1-score of 97.13%, which is a 7.36% to 17.63% improvement over older models such as U-Net and FCN and a more than 2% improvement over advanced models such as DeepLabv3+ and U2-Net. These results indicate that U2-Net++ holds the potential for widespread application in the production of large-scale farmland boundary maps.

Unsupervised machine learning and multi-seismic attributes for fault and fracture network interpretation in the Kerry Field, Taranaki Basin, New Zealand

Unsupervised machine learning using an unsupervised vector quantization neural network (UVQ-NN) integrated with meta-geometrical attributes as a novel computation process as opposed to traditional methodologies is currently used effectively in the 3D seismic structural interpretation for high-resolution detection of fault patterns, fracture network zones, and small-scale faults (SSFs). This technology has a crucial role in locating prospective well sites and building a 3D structural model while saving time and cost. The innovation of the current workflow involves combining geostatistical and structural filtering, optimal geometrical seismic attributes, UVQ-NN for automatic major faults, fracture network zones, and SSFs volumes extraction due to the unavailability of well logs and cores. To sharpen the fault edges and discontinuities, a steered volume was first extracted. Structural filters were then applied to the 3D volume, first with a dip-steered median filter (DSMF), followed by a dip-steered diffusion filter (DSDF), and finally, both DSMF and DSDF were combined to generate the fault enhancement filter (FEF). After that, optimal geometrical attributes were computed and extracted, such as similarity, FEF on similarity, maximum curvature, polar dip, fracture density, and thinned fault likelihood (TFL) attributes. Finally, selected attributes were inserted as the input layer to the UVQ-NN to generate segmentation and matching volumes. On the other hand, the TFL was used with the voxel connectivity filter (VCF) for 3D automatic fault patches extraction. The results from the UVQ-NN and VCF identified the locations, orientations, and extensions of the main faults, SSFs, and fracture networks. The implemented approach is innovative and can be employed in the future for the identification, extraction, and classification of geological faults and fracture networks in any region of the world.

Self-Supervised Learning for Industrial Image Anomaly Detection by Simulating Anomalous Samples

Industrial image anomaly detection (AD) is a critical issue that has been investigated in different research areas. Many works have attempted to detect anomalies by simulating anomalous samples. However, how to simulate abnormal samples remains a significant challenge. In this study, a method for simulating anomalous samples is designed. First, for the object category, patch extraction and patch paste are designed to ensure that the extracted image patches come from the objects and are pasted to the objects in the image. Second, based on the statistical analysis of various anomalies’ presence, a combination of data augmentation is proposed to cover various anomalies as much as possible. The method is evaluated on MVTec AD and BTAD datasets; the experimental results demonstrate that our method achieves an overall detection AUC of 97.6% in MVTec AD datasets, outperforming the baseline by 1.5%, and the improvement over VT-ADL method is 4.3% on the BTAD datasets, demonstrating our method’s effectiveness and generalization.

An Approach for Monitoring Shallow Surface Outcrop Mining Activities Based on Multisource Satellite Remote Sensing Data

Monitoring mine activities can help management track the status of mineral resource exploration and mine rehabilitation. It is crucial to the sustainable development of the mining industry and the protection of the geological environment in mining areas. To monitor the mining activities of shallow surface outcrops in the arid and semi-arid regions of northwest China, this paper proposes a remote sensing monitoring approach of mining activities based on deep learning and integrated interferometric synthetic aperture radar technique. This approach uses the DeepLabV3-ResNet model to identify and extract the spatial location of the mine patches and then uses object-oriented analysis and spatial analysis methods to optimize the mine patch boundaries. SBAS-InSAR technique is used to obtain the time-series deformation information of the mine patches and is combined with the multi-temporal optical imagery to analyze the mining activities in the study area. The proposed approach has a recognition accuracy of 95.80% for the identification and extraction of mine patches, with an F1-score of 0.727 at the pixel level, and the average area similarity for all patches is 0.78 at the object-oriented level. The proposed approach possesses the capability to analyze mining activities, indicating promising prospects for engineering applications. It provides a reference for monitoring mining activities using multisource satellite remote sensing.

LSGP-USFNet: Automated Attention Deficit Hyperactivity Disorder Detection Using Locations of Sophie Germain's Primes on Ulam's Spiral-Based Features with Electroencephalogram Signals.

Anxiety, learning disabilities, and depression are the symptoms of attention deficit hyperactivity disorder (ADHD), an isogenous pattern of hyperactivity, impulsivity, and inattention. For the early diagnosis of ADHD, electroencephalogram (EEG) signals are widely used. However, the direct analysis of an EEG is highly challenging as it is time-consuming, nonlinear, and nonstationary in nature. Thus, in this paper, a novel approach (LSGP-USFNet) is developed based on the patterns obtained from Ulam's spiral and Sophia Germain's prime numbers. The EEG signals are initially filtered to remove the noise and segmented with a non-overlapping sliding window of a length of 512 samples. Then, a time-frequency analysis approach, namely continuous wavelet transform, is applied to each channel of the segmented EEG signal to interpret it in the time and frequency domain. The obtained time-frequency representation is saved as a time-frequency image, and a non-overlapping n × n sliding window is applied to this image for patch extraction. An n × n Ulam's spiral is localized on each patch, and the gray levels are acquired from this patch as features where Sophie Germain's primes are located in Ulam's spiral. All gray tones from all patches are concatenated to construct the features for ADHD and normal classes. A gray tone selection algorithm, namely ReliefF, is employed on the representative features to acquire the final most important gray tones. The support vector machine classifier is used with a 10-fold cross-validation criteria. Our proposed approach, LSGP-USFNet, was developed using a publicly available dataset and obtained an accuracy of 97.46% in detecting ADHD automatically. Our generated model is ready to be validated using a bigger database and it can also be used to detect other children's neurological disorders.

Automated carcinoma classification using efficient nuclei-based patch selection and deep learning techniques

Breast cancer can be successfully treated if diagnosed at its earliest, though it is considered as a fatal disease among women. The histopathology slide turned images are the gold standard for tumor diagnosis. However, the manual diagnosis is still tedious due to its structural complexity. With the advent of computer-aided diagnosis, time and computation intensive manual procedure can be managed with the development of an automated classification system. The feature extraction and classification are quite challenging as these images involve complex structures and overlapping nuclei. A novel nuclei-based patch extraction method is proposed for the extraction of non-overlapping nuclei patches obtained from the breast tumor dataset. An ensemble of pre-trained models is used to extract the discriminating features from the identified and augmented non-overlapping nuclei patches. The discriminative features are further fused using p-norm pooling technique and are classified using a LightGBM classifier with 10-fold cross-validation. The obtained results showed an increase in the overall performance in terms of accuracy, sensitivity, specificity, and precision. The proposed framework yielded an accuracy of 98.3% for binary class classification and 95.1% for multi-class classification on ICIAR 2018 dataset.

Automated fatty liver disease detection in point-of-care ultrasound B-mode images.

Non-alcoholic fatty liver disease (NAFLD) is an increasing global health concern, with a prevalence of 25% worldwide. The rising incidence of NAFLD, an asymptomatic condition, reinforces the need for systematic screening strategies in primary care. We present the use of non-expert acquired point-of-care ultrasound (POCUS) B-mode images for the development of an automated steatosis classification algorithm. We obtained a Health Insurance Portability and Accountability Act compliant dataset consisting of 478 patients [body mass index , age ], imaged with POCUS by non-expert health care personnel. A U-Net deep learning (DL) model was used for liver segmentation in the POCUS B-mode images, followed by patch extraction of liver parenchyma. Several DL models including VGG-16, ResNet-50, Inception V3, and DenseNet-121 were trained for binary classification of steatosis. All layers of each tested model were unfrozen, and the final layer was replaced with a custom classifier. Majority voting was applied for patient-level results. On a hold-out test set of 81 patients, the final DenseNet-121 model yielded an area under the receiver operator characteristic curve of 90.1%, sensitivity of 95.0%, and specificity of 85.2% for the detection of liver steatosis. Average cross-validation performance in models using patches of liver parenchyma as input outperformed methods using complete B-mode frames. Despite minimal POCUS acquisition training, and low-quality B-mode images, it is possible to detect steatosis using DL algorithms. Implementation of this algorithm in POCUS software may offer an accessible, low-cost steatosis screening technology, for use by non-expert health care personnel.

High-fidelity point cloud completion with low-resolution recovery and noise-aware upsampling

Completing an unordered partial point cloud is a challenging task. Existing approaches that rely on decoding a latent feature to recover the complete shape, often lead to the completed point cloud being over-smoothing, losing details, and noisy. Instead of decoding a whole shape, we propose to decode and refine a low-resolution (low-res) point cloud first, and then perform a patch-wise noise-aware upsampling rather than interpolating the whole sparse point cloud at once, which tends to lose details. Regarding the possibility of lacking details of the initially decoded low-res point cloud, we propose an iterative refinement to recover the geometric details and a symmetrization process to preserve the trustworthy information from the input partial point cloud. After obtaining a sparse and complete point cloud, we propose a patch-wise upsampling strategy. Patch-based upsampling allows to recover fine details better rather than decoding a whole shape. The patch extraction approach is to generate training patch pairs between the sparse and ground-truth point clouds with an outlier removal step to suppress the noisy points from the sparse point cloud. Together with the low-res recovery, our whole pipeline can achieve high-fidelity point cloud completion. Comprehensive evaluations are provided to demonstrate the effectiveness of the proposed method and its components.

GFNet: A Deep Learning Framework for Breast Mass Detection

Background: Breast mass is one of the main symptoms of breast cancer. Effective and accurate detection of breast masses at an early stage would be of great value for clinical breast cancer analysis. Methods: We developed a novel mass detection framework named GFNet. The GFNet is comprised of three modules, including patch extraction, feature extraction, and mass detection. The developed breast mass detection framework is of high robustness and generality that can be self-adapted to images collected by different imaging devices. The patch-based detection is deployed to improve performance. A novel feature extraction technique based on gradient field convergence features (GFCF) is proposed to enhance the information of breast mass and, therefore, provide useful information for the following patch extraction module. A novel false positives reduction method is designed by combining the texture and morphological features in breast mass patch. This is the first attempt at fusing morphological and texture features for breast mass false positive reduction. Results: Compared to other state-of-the-art methods, the proposed GFNet showed the best performance on CBIS-DDSM and INbreast with an accuracy of 0.90 at 2.91 false positive per image (FPI) and 0.99 at only 0.97 FPI, respectively. Conclusions: The GFNet is an effective tool for detecting breast mass.