CycleGAN With an Improved Loss Function for Cell Detection Using Partly Labeled Images

SSW-YOLO: Enhanced Blood Cell Detection with Improved Feature Extraction and Multi-scale Attention

The integration of deep learning in medical image analysis has driven significant progress, especially in the domain of automatic blood cell detection. While the YOLO series of algorithms have become widely adopted as a real-time object detection approach, there is a need for further refinement for the detection of small targets like blood cells and in low-resolution images. In this context, we introduce SSW-YOLO, a novel algorithm designed to tackle these challenges. The primary innovations of SSW-YOLO include the use of a spatial-to-depth convolution (SPD-Conv) layer to enhance feature extraction, the adoption of a Swin Transformer for multi-scale attention mechanisms, the simplification of the c2f module to reduce model complexity, and the utilization of Wasserstein distance loss (WDLoss) function to improve localization accuracy. With these enhancements, SSW-YOLO significantly improves the accuracy and efficiency of blood cell detection, reduces human error, and consequently accelerates the diagnosis of blood disorders while enhancing the precision of clinical diagnoses. Empirical analysis on the BCCD blood cell dataset indicates that SSW-YOLO achieves a mean average precision (mAP) of 94.0%, demonstrating superior performance compared to existing methods.

Toward Digital Periodontal Health: Recent Advances and Future Perspectives

Periodontal diseases, ranging from gingivitis to periodontitis, are prevalent oral diseases affecting over 50% of the global population. These diseases arise from infections and inflammation of the gums and supporting bones, significantly impacting oral health. The established link between periodontal diseases and systemic diseases, such as cardiovascular diseases, underscores their importance as a public health concern. Consequently, the early detection and prevention of periodontal diseases have become critical objectives in healthcare, particularly through the integration of advanced artificial intelligence (AI) technologies. This paper aims to bridge the gap between clinical practices and cutting-edge technologies by providing a comprehensive review of current research. We examine the identification of causative factors, disease progression, and the role of AI in enhancing early detection and treatment. Our goal is to underscore the importance of early intervention in improving patient outcomes and to stimulate further interest among researchers, bioengineers, and AI specialists in the ongoing exploration of AI applications in periodontal disease diagnosis.

Deep UV-excited fluorescence microscopy installed with CycleGAN-assisted image translation enhances precise detection of lymph node metastasis towards rapid intraoperative diagnosis

Rapid and precise intraoperative diagnosing systems are required for improving surgical outcomes and patient prognosis. Because of the poor quality and time-intensive process of the prevalent frozen section procedure, various intraoperative diagnostic imaging systems have been explored. Microscopy with ultraviolet surface excitation (MUSE) is an inexpensive, maintenance-free, and rapid imaging technique that yields images like thin-sectioned samples without sectioning. However, pathologists find it nearly impossible to assign diagnostic labels to MUSE images of unfixed specimens; thus, AI for intraoperative diagnosis cannot be trained in a supervised learning manner. In this study, we propose a deep-learning pipeline model for lymph node metastasis detection, in which CycleGAN translate MUSE images of unfixed lymph nodes to formalin-fixed paraffin-embedded (FFPE) sample, and diagnostic prediction is performed using deep convolutional neural network trained on FFPE sample images. Our pipeline yielded an average accuracy of 84.6% when using each of the three deep convolutional neural networks, which is a 18.3% increase over the classification-only model without CycleGAN. The modality translation to FFPE sample images using CycleGAN can be applied to various intraoperative diagnostic imaging systems and eliminate the difficulty for pathologists in labeling new modality images in clinical sites. We anticipate our pipeline to be a starting point for accurate rapid intraoperative diagnostic systems for new imaging modalities, leading to healthcare quality improvement.

PA-Tran: Learning to Estimate 3D Hand Pose with Partial Annotation

This paper tackles a novel and challenging problem-3D hand pose estimation (HPE) from a single RGB image using partial annotation. Most HPE methods ignore the fact that the keypoints could be partially visible (e.g., under occlusions). In contrast, we propose a deep-learning framework, PA-Tran, that jointly estimates the keypoints status and 3D hand pose from a single RGB image with two dependent branches. The regression branch consists of a Transformer encoder which is trained to predict a set of target keypoints, given an input set of status, position, and visual features embedding from a convolutional neural network (CNN); the classification branch adopts a CNN for estimating the keypoints status. One key idea of PA-Tran is a selective mask training (SMT) objective that uses a binary encoding scheme to represent the status of the keypoints as observed or unobserved during training. In addition, by explicitly encoding the label status (observed/unobserved), the proposed PA-Tran can efficiently handle the condition when only partial annotation is available. Investigating the annotation percentage ranging from 50-100%, we show that training with partial annotation is more efficient (e.g., achieving the best 6.0 PA-MPJPE when using about 85% annotations). Moreover, we provide two new datasets. APDM-Hand, is for synthetic hands with APDM sensor accessories, which is designed for a specific hand task. PD-APDM-Hand, is a real hand dataset collected from Parkinson's Disease (PD) patients with partial annotation. The proposed PA-Tran can achieve higher estimation accuracy when evaluated on both proposed datasets and a more general hand dataset.

Application of generative adversarial networks (GAN) for ophthalmology image domains: a survey

BACKGROUND

Recent advances in deep learning techniques have led to improved diagnostic abilities in ophthalmology. A generative adversarial network (GAN), which consists of two competing types of deep neural networks, including a generator and a discriminator, has demonstrated remarkable performance in image synthesis and image-to-image translation. The adoption of GAN for medical imaging is increasing for image generation and translation, but it is not familiar to researchers in the field of ophthalmology. In this work, we present a literature review on the application of GAN in ophthalmology image domains to discuss important contributions and to identify potential future research directions.

METHODS

We performed a survey on studies using GAN published before June 2021 only, and we introduced various applications of GAN in ophthalmology image domains. The search identified 48 peer-reviewed papers in the final review. The type of GAN used in the analysis, task, imaging domain, and the outcome were collected to verify the usefulness of the GAN.

RESULTS

In ophthalmology image domains, GAN can perform segmentation, data augmentation, denoising, domain transfer, super-resolution, post-intervention prediction, and feature extraction. GAN techniques have established an extension of datasets and modalities in ophthalmology. GAN has several limitations, such as mode collapse, spatial deformities, unintended changes, and the generation of high-frequency noises and artifacts of checkerboard patterns.

CONCLUSIONS

The use of GAN has benefited the various tasks in ophthalmology image domains. Based on our observations, the adoption of GAN in ophthalmology is still in a very early stage of clinical validation compared with deep learning classification techniques because several problems need to be overcome for practical use. However, the proper selection of the GAN technique and statistical modeling of ocular imaging will greatly improve the performance of each image analysis. Finally, this survey would enable researchers to access the appropriate GAN technique to maximize the potential of ophthalmology datasets for deep learning research.

SDoF-Net: Super Depth of Field Network for Cell Detection in Leucorrhea Micrograph

Accompanied with the rapid increase of the demand for routine examination of leucorrhea, efficiency and accuracy become the primary task. However, in super depth of field (SDoF) system, the problem of automatic detection and localization of cells in leucorrhea micro-images is still a big challenge. The changing of the relative position between the cell center and focus plane of microscope lead to variable cell morphological structure in the two-dimensional image, which is an important reason for the low accuracy of current deep learning target detection algorithms. In this paper, an object detection method based on Retinanet in state of super depth of field is proposed, which can achieve high precision detecting of leucorrhea components by the SDoF feature aggregation module. Compared with the current mainstream algorithms, the mean average accuracy (mAP) index has been improved significantly, the mAP index is 82.7% for SDoF module and 83.0% for SDoF+ module, with an average increase of more than 10%. These improved features can significantly improve the efficiency and accuracy of the algorithm. The algorithm proposed in this paper can be integrated into the leucorrhea automatic detection system.

CMMCSegNet: Cross-Modality Multicascade Indirect LGE Segmentation on Multimodal Cardiac MR

Since Late-Gadolinium Enhancement (LGE) of cardiac magnetic resonance (CMR) visualizes myocardial infarction, and the balanced-Steady State Free Precession (bSSFP) cine sequence can capture cardiac motions and present clear boundaries; multimodal CMR segmentation has played an important role in the assessment of myocardial viability and clinical diagnosis, while automatic and accurate CMR segmentation still remains challenging due to a very small amount of labeled LGE data and the relatively low contrasts of LGE. The main purpose of our work is to learn the real/fake bSSFP modality with ground truths to indirectly segment the LGE modality of cardiac MR by using a proposed cross-modality multicascade framework: cross-modality translation network and automatic segmentation network, respectively. In the segmentation stage, a novel multicascade pix2pix network is designed to segment the fake bSSFP sequence obtained from a cross-modality translation network. Moreover, we propose perceptual loss measuring features between ground truth and prediction, which are extracted from the pretrained vgg network in the segmentation stage. We evaluate the performance of the proposed method on the multimodal CMR dataset and verify its superiority over other state-of-the-art approaches under different network structures and different types of adversarial losses in terms of dice accuracy in testing. Therefore, the proposed network is promising for Indirect Cardiac LGE Segmentation in clinical applications.