Search

We present a deep learning-based method that corrects motion artifacts and thus accelerates data acquisition and reconstruction of magnetic resonance images. The novel model, the Motion Artifact Correction by Swin Network (MACS-Net), uses a Swin transformer layer as the fundamental block and the Unet architecture as the neural network backbone. We employ a hierarchical transformer with shifted windows to extract multiscale contextual features during encoding. A new dual upsampling technique is employed to enhance the spatial resolutions of feature maps in the Swin transformer-based decoder layer. A raw magnetic resonance imaging dataset is used for network training and testing; the data contain various motion artifacts with ground truth images of the same subjects. The results were compared to six state-of-the-art MRI image motion correction methods using two types of motions. When motions were brief (within 5 s), the method reduced the average normalized root mean square error (NRMSE) from 45.25% to 17.51%, increased the mean structural similarity index measure (SSIM) from 79.43% to 91.72%, and increased the peak signal-to-noise ratio (PSNR) from 18.24 to 26.57 dB. Similarly, when motions were extended from 5 to 10 s, our approach decreased the average NRMSE from 60.30% to 21.04%, improved the mean SSIM from 33.86% to 90.33%, and increased the PSNR from 15.64 to 24.99 dB. The anatomical structures of the corrected images and the motion-free brain data were similar. [ABSTRACT FROM AUTHOR]

This article describes a novel approach for enhancing the three-dimensional (3D) point cloud reconstruction for light field microscopy (LFM) using U-net architecture-based fully convolutional neural network (CNN). Since the directional view of the LFM is limited, noise and artifacts make it difficult to reconstruct the exact shape of 3D point clouds. The existing methods suffer from these problems due to the self-occlusion of the model. This manuscript proposes a deep fusion learning (DL) method that combines a 3D CNN with a U-Net-based model as a feature extractor. The sub-aperture images obtained from the light field microscopy are aligned to form a light field data cube for preprocessing. A multi-stream 3D CNNs and U-net architecture are applied to obtain the depth feature fromthe directional sub-aperture LF data cube. For the enhancement of the depthmap, dual iteration-based weighted median filtering (WMF) is used to reduce surface noise and enhance the accuracy of the reconstruction. Generating a 3D point cloud involves combining two key elements: the enhanced depth map and the central view of the light field image. The proposed method is validated using synthesized Heidelberg Collaboratory for Image Processing (HCI) and real-world LFM datasets. The results are compared with different state-of-the-art methods. The structural similarity index (SSIM) gain for boxes, cotton, pillow, and pens are 0.9760, 0.9806, 0.9940, and 0.9907, respectively. Moreover, the discrete entropy (DE) value for LFM depth maps exhibited better performance than other existing methods. [ABSTRACT FROM AUTHOR]

In this paper, we present a badge awarding system for performance assessment in education using blockchain technology. Learners will be awarded badges, which are certified for a predetermined level of progress in terms of learning. All the badges are stored in a backpack, which is an environment for storing and presenting the obtained badges. Badges are immutable and verifiable as well as rigid. The use of badges in the education system makes education more interesting, skill-based, and adaptable to changes. The key contribution of our work is in terms of compatibility with Openbadge specification and integrated cooperating platform between digital badge awarding and blockchaining. Our system implementation is compatible with Open Badges of IMS Global Learning Consortium, which is used to earn, issue, and award badges across various platforms. The badges are trusted by the IMS standard, the criteria to earn a badge is verified through the network, and the overall process is transparent compared to the traditional education system. Moreover, all badge awarding events in our system are recorded in a blockchain. Once stored, the contents cannot be tampered with. Thereafter, anyone can check the validity of the badge through the blockchain. Our platform will be useful for distance learning as well as time and location independent learning. The experimental results are as follows. On a Bitcoin-based digital badge publishing platform, the execution time required to award the badge is 24.53 s, while on the Ethereum-based digital badge publishing platform, the execution time to award the badge is only 3.86 s. It can also be used for career management and personal history. The learners can obtain the current knowledge required for a job. Lifelong learning will be also possible with this platform.

Simple Summary: Skin cancer is a life-threatening condition. It is difficult to diagnose in its early stages; therefore, we proposed an easy-to-use telemedicine device to tackle skin cancer without expert intervention. The deep learning model automatically detects skin cancer patches on lesions with a credit-card-sized device named Raspberry Pi and a small camera. This paper also presents a digital hair removal algorithm to enhance the quality of medical images for better analysis by medical experts and AI methods. Our method does not need an expert operator; even ordinary people can use it with the instruction manual. It will be useful for developing countries or remote places when there is a scarcity of oncologists. Cancer remains a deadly disease. We developed a lightweight, accurate, general-purpose deep learning algorithm for skin cancer classification. Squeeze-MNet combines a Squeeze algorithm for digital hair removal during preprocessing and a MobileNet deep learning model with predefined weights. The Squeeze algorithm extracts important image features from the image, and the black-hat filter operation removes noise. The MobileNet model (with a dense neural network) was developed using the International Skin Imaging Collaboration (ISIC) dataset to fine-tune the model. The proposed model is lightweight; the prototype was tested on a Raspberry Pi 4 Internet of Things device with a Neo pixel 8-bit LED ring; a medical doctor validated the device. The average precision (AP) for benign and malignant diagnoses was 99.76% and 98.02%, respectively. Using our approach, the required dataset size decreased by 66%. The hair removal algorithm increased the accuracy of skin cancer detection to 99.36% with the ISIC dataset. The area under the receiver operating curve was 98.9%. [ABSTRACT FROM AUTHOR]