Minyoung Chung

Chae Eun Lee, Hyelim Park, Yeong-Gil Shin et al.

Semi-supervised learning for medical image segmentation is an important area of research for alleviating the huge cost associated with the construction of reliable large-scale annotations in the medical domain. Recent semi-supervised approaches have demonstrated promising results by employing consistency regularization, pseudo-labeling techniques, and adversarial learning. These methods primarily attempt to learn the distribution of labeled and unlabeled data by enforcing consistency in the predictions or embedding context. However, previous approaches have focused only on local discrepancy minimization or context relations across single classes. In this paper, we introduce a novel adversarial learning-based semi-supervised segmentation method that effectively embeds both local and global features from multiple hidden layers and learns context relations between multiple classes. Our voxel-wise adversarial learning method utilizes a voxel-wise feature discriminator, which considers multilayer voxel-wise features (involving both local and global features) as an input by embedding class-specific voxel-wise feature distribution. Furthermore, we improve our previous representation learning method by overcoming information loss and learning stability problems, which enables rich representations of labeled data. Our method outperforms current best-performing state-of-the-art semi-supervised learning approaches on the image segmentation of the left atrium (single class) and multiorgan datasets (multiclass). Moreover, our visual interpretation of the feature space demonstrates that our proposed method enables a well-distributed and separated feature space from both labeled and unlabeled data, which improves the overall prediction results.

Jiwan Kim, Minchang Kim, Yeong-Gil Shin et al.

Accurate three-dimensional perception is a fundamental task in several computer vision applications. Recently, commercial RGB-depth (RGB-D) cameras have been widely adopted as single-view depth-sensing devices owing to their efficient depth-sensing abilities. However, the depth quality of most RGB-D sensors remains insufficient owing to the inherent noise from a single-view environment. Recently, several studies have focused on the single-view depth enhancement of RGB-D cameras. Recent research has proposed deep-learning-based approaches that typically train networks using high-quality supervised depth datasets, which indicates that the quality of the ground-truth (GT) depth dataset is a top-most important factor for accurate system; however, such high-quality GT datasets are difficult to obtain. In this study, we developed a novel method for high-quality GT depth generation based on an RGB-D stream dataset. First, we defined consecutive depth frames in a local spatial region as a local frame set. Then, the depth frames were aligned to a certain frame in the local frame set using an unsupervised point cloud registration scheme. The registration parameters were trained based on an overfit-training scheme, which was primarily used to construct a single GT depth image for each frame set. The final GT depth dataset was constructed using several local frame sets, and each local frame set was trained independently. The primary advantage of this study is that a high-quality GT depth dataset can be constructed under various scanning environments using only the RGB-D stream dataset. Moreover, our proposed method can be used as a new benchmark GT dataset for accurate performance evaluations. We evaluated our GT dataset on previously benchmarked GT depth datasets and demonstrated that our method is superior to state-of-the-art depth enhancement frameworks.

Achraf Ben-Hamadou, Oussama Smaoui, Ahmed Rekik et al.

Teeth localization, segmentation, and labeling from intra-oral 3D scans are essential tasks in modern dentistry to enhance dental diagnostics, treatment planning, and population-based studies on oral health. However, developing automated algorithms for teeth analysis presents significant challenges due to variations in dental anatomy, imaging protocols, and limited availability of publicly accessible data. To address these challenges, the 3DTeethSeg'22 challenge was organized in conjunction with the International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) in 2022, with a call for algorithms tackling teeth localization, segmentation, and labeling from intraoral 3D scans. A dataset comprising a total of 1800 scans from 900 patients was prepared, and each tooth was individually annotated by a human-machine hybrid algorithm. A total of 6 algorithms were evaluated on this dataset. In this study, we present the evaluation results of the 3DTeethSeg'22 challenge. The 3DTeethSeg'22 challenge code can be accessed at: https://github.com/abenhamadou/3DTeethSeg22_challenge

Sanguk Park, Minyoung Chung

Cardiac segmentation of atriums, ventricles, and myocardium in computed tomography (CT) images is an important first-line task for presymptomatic cardiovascular disease diagnosis. In several recent studies, deep learning models have shown significant breakthroughs in medical image segmentation tasks. Unlike other organs such as the lungs and liver, the cardiac organ consists of multiple substructures, i.e., ventricles, atriums, aortas, arteries, veins, and myocardium. These cardiac substructures are proximate to each other and have indiscernible boundaries (i.e., homogeneous intensity values), making it difficult for the segmentation network focus on the boundaries between the substructures. In this paper, to improve the segmentation accuracy between proximate organs, we introduce a novel model to exploit shape and boundary-aware features. We primarily propose a shape-aware attention module, that exploits distance regression, which can guide the model to focus on the edges between substructures so that it can outperform the conventional contour-based attention method. In the experiments, we used the Multi-Modality Whole Heart Segmentation dataset that has 20 CT cardiac images for training and validation, and 40 CT cardiac images for testing. The experimental results show that the proposed network produces more accurate results than state-of-the-art networks by improving the Dice similarity coefficient score by 4.97%. Our proposed shape-aware contour attention mechanism demonstrates that distance transformation and boundary features improve the actual attention map to strengthen the responses in the boundary area. Moreover, our proposed method significantly reduces the false-positive responses of the final output, resulting in accurate segmentation.

Jusang Lee, Minyoung Chung, Minkyung Lee et al.

Individual tooth segmentation and identification from cone-beam computed tomography images are preoperative prerequisites for orthodontic treatments. Instance segmentation methods using convolutional neural networks have demonstrated ground-breaking results on individual tooth segmentation tasks, and are used in various medical imaging applications. While point-based detection networks achieve superior results on dental images, it is still a challenging task to distinguish adjacent teeth because of their similar topologies and proximate nature. In this study, we propose a point-based tooth localization network that effectively disentangles each individual tooth based on a Gaussian disentanglement objective function. The proposed network first performs heatmap regression accompanied by box regression for all the anatomical teeth. A novel Gaussian disentanglement penalty is employed by minimizing the sum of the pixel-wise multiplication of the heatmaps for all adjacent teeth pairs. Subsequently, individual tooth segmentation is performed by converting a pixel-wise labeling task to a distance map regression task to minimize false positives in adjacent regions of the teeth. Experimental results demonstrate that the proposed algorithm outperforms state-of-the-art approaches by increasing the average precision of detection by 9.1%, which results in a high performance in terms of individual tooth segmentation. The primary significance of the proposed method is two-fold: 1) the introduction of a point-based tooth detection framework that does not require additional classification and 2) the design of a novel loss function that effectively separates Gaussian distributions based on heatmap responses in the point-based detection framework.

Seunghwan Jung, Yeong-Gil Shin, Minyoung Chung

Feature descriptors of point clouds are used in several applications, such as registration and part segmentation of 3D point clouds. Learning discriminative representations of local geometric features is unquestionably the most important task for accurate point cloud analyses. However, it is challenging to develop rotation or scale-invariant descriptors. Most previous studies have either ignored rotations or empirically studied optimal scale parameters, which hinders the applicability of the methods for real-world datasets. In this paper, we present a new local feature description method that is robust to rotation, density, and scale variations. Moreover, to improve representations of the local descriptors, we propose a global aggregation method. First, we place kernels aligned around each point in the normal direction. To avoid the sign problem of the normal vector, we use a symmetric kernel point distribution in the tangential plane. From each kernel point, we first projected the points from the spatial space to the feature space, which is robust to multiple scales and rotation, based on angles and distances. Subsequently, we perform graph convolutions by considering local kernel point structures and long-range global context, obtained by a global aggregation method. We experimented with our proposed descriptors on benchmark datasets (i.e., ModelNet40 and ShapeNetPart) to evaluate the performance of registration, classification, and part segmentation on 3D point clouds. Our method showed superior performances when compared to the state-of-the-art methods by reducing 70$\%$ of the rotation and translation errors in the registration task. Our method also showed comparable performance in the classification and part-segmentation tasks with simple and low-dimensional architectures.