Accurate pre-harvest yield estimation is fundamental to pineapple production, as it facilitates optimized harvest scheduling, informs market-responsive pricing strategies, and supports data-driven decision-making in smart agriculture. The rapid advancement of object detection algorithms, coupled with the deployment of miniaturized cameras on Unmanned Aerial Vehicle (UAV) platforms, has made high-throughput pineapple counting for precise yield estimation increasingly feasible. Nonetheless, accurate detection of pineapples in UAV imagery remains challenging due to factors such as the small size of individual fruits, significant scale variations, and complex background textures, all of which impede precise localization and identification. To address these challenges, the present study introduces a novel object detection framework, termed YOLO-Pineapple, designed for accurate pineapple detection in high-resolution color images captured by UAVs. YOLO-Pineapple enhances the baseline YOLOv8 model through several key innovations: (1) the Dynamic Interactive Task Alignment Head (DITAH) is proposed to resolve feature inconsistency and task misalignment between localization and classification branches by integrating interactive and independent features, thereby improving detection accuracy; (2) the incorporation of the Grouped Multi-Scale Convolution (GMSC) module reduces redundant feature computations while capturing richer multi-scale features, enhancing performance in cluttered and heavily occluded field environments; (3) the introduction of the Spatial and Channel Synergistic Attention (SCSA) mechanism facilitates enhanced semantic feature interaction via the combined application of multi-semantic spatial attention and channel self-attention; and (4) the integration of a sample-adaptive weighting mechanism derived from Focaler-IoU with the angle-aware distance component of SIoU culminates in a novel loss function, designated Focaler_SIoU, which achieves more precise bounding box regression, particularly for small objects. Experimental evaluations demonstrate the effectiveness of the proposed YOLO-Pineapple model, which attains a mean average precision (mAP) of 94.4%, a Recall rate of 88.9%, and a precision of 94.6%. The optimized YOLO-Pineapple algorithm constitutes a significant advancement in overcoming the challenges associated with pineapple detection from UAV imagery, while exhibiting promising potential for yield estimation and pineapple field management.

Magnetic resonance imaging (MRI) is an indispensable tool for clinical knee examination, which often scans 2D stacked slices from multiple views. Radiologists typically locate lesion regions in one view, and then refer to other views to formulate a comprehensive diagnosis. However, existing computer-aided diagnosis methods fall short of identifying and fusing local regions in multi-view scans, leading to a decline in diagnostic performance and a heavy reliance on extensively annotated data. This paper introduces a novel framework that represents multi-view MRI scans as a knee graph, and conducts diagnosis using the proposed Knee Graph Network (KGNet). Moreover, KGNet is greatly enhanced by multi-task pre-training, which requires KGNet to reconstruct masked knee local patches and segment unmasked ones working alongside corresponding decoders. Experimental evaluations on public and in-house clinical datasets confirm that our framework outperforms existing approaches in diagnosing cartilage defects, anterior cruciate ligament tears, and knee abnormalities. In conclusion, our framework demonstrates the potential of enhancing knee disease diagnosis by representing multi-view MRI scans as a graph and employing multi-task pre-training in the graph network. The code is publicly available at https://github.com/zixuzhuang/KGNet.

Aneurysm segmentation in computed tomography angiography (CTA) images is essential for medical intervention aimed at preventing subarachnoid hemorrhages. However, most existing studies tend to overlook the topological characteristics of arteries related to aneurysms, often resulting in suboptimal performance in aneurysm segmentation. To address this challenge, we propose an artery-aware global-to-local framework for aneurysm segmentation (AASeg) using CTA images of head and neck. This framework consists of two key components: 1) a centerline graph network (CG-Net) for aneurysm global localization, and 2) a point cloud network (PC-Net) for local aneurysm segmentation. The centerline graph is generated by extracting artery centerline structures from vessel masks obtained through a pre-trained model for head and neck vessel segmentation. This representation serves as a high-level representation of the artery structure, allowing for analysis of aneurysms along the entire arteries. It facilitates aneurysm localization via aneurysm-segment graph classification along the arteries. Then, local region of aneurysm segment can be sampled from the vessel mask according to the aneurysm-segment graph. Subsequently, aneurysm segmentation is performed on the point cloud constructed from the aneurysm segment through the PC-Net. Extensive experiments show that the proposed framework achieves state-of-the-art performance in aneurysm localization on a main dataset and an external testing dataset, with Recall of 84.1% and 80.7%, false positives per case of 1.72 and 1.69, and segmentation DSC of 66.1% and 60.2%, respectively.

Medical image analysis poses significant challenges due to limited availability of clinical data, which is crucial for training accurate models. This limitation is further compounded by the specialized and labor-intensive nature of the data annotation process. For example, despite the popularity of computed tomography angiography (CTA) in diagnosing atherosclerosis with an abundance of annotated datasets, magnetic resonance (MR) images stand out with better visualization for soft plaque and vessel wall characterization. However, the higher cost and limited accessibility of MR, as well as time-consuming nature of manual labeling, contribute to fewer annotated datasets. To address these issues, we formulate a multi-modal transfer learning network, named MT-Net, designed to learn from unpaired CTA and sparsely-annotated MR data. Additionally, we harness the Segment Anything Model (SAM) to synthesize additional MR annotations, enriching the training process. Specifically, our method first segments vessel lumen regions followed by precise characterization of carotid artery vessel walls, thereby ensuring both segmentation accuracy and clinical relevance. Validation of our method involved rigorous experimentation on publicly available datasets from COSMOS and CARE-II challenge, demonstrating its superior performance compared to existing state-of-the-art techniques.

Anatomical labeling of head and neck vessels is a vital step for cerebrovascular disease diagnosis. However, it remains challenging to automatically and accurately label vessels in computed tomography angiography (CTA) since head and neck vessels are tortuous, branched, and often spatially close to nearby vasculature. To address these challenges, we propose a novel topology-aware graph network (TaG-Net) for vessel labeling. It combines the advantages of volumetric image segmentation in the voxel space and centerline labeling in the line space, wherein the voxel space provides detailed local appearance information, and line space offers high-level anatomical and topological information of vessels through the vascular graph constructed from centerlines. First, we extract centerlines from the initial vessel segmentation and construct a vascular graph from them. Then, we conduct vascular graph labeling using TaG-Net, in which techniques of topology-preserving sampling, topology-aware feature grouping, and multi-scale vascular graph are designed. After that, the labeled vascular graph is utilized to improve volumetric segmentation via vessel completion. Finally, the head and neck vessels of 18 segments are labeled by assigning centerline labels to the refined segmentation. We have conducted experiments on CTA images of 401 subjects, and experimental results show superior vessel segmentation and labeling of our method compared to other state-of-the-art methods.

Knee osteoarthritis (OA) is the most common osteoarthritis and a leading cause of disability. Cartilage defects are regarded as major manifestations of knee OA, which are visible by magnetic resonance imaging (MRI). Thus early detection and assessment for knee cartilage defects are important for protecting patients from knee OA. In this way, many attempts have been made on knee cartilage defect assessment by applying convolutional neural networks (CNNs) to knee MRI. However, the physiologic characteristics of the cartilage may hinder such efforts: the cartilage is a thin curved layer, implying that only a small portion of voxels in knee MRI can contribute to the cartilage defect assessment; heterogeneous scanning protocols further challenge the feasibility of the CNNs in clinical practice; the CNN-based knee cartilage evaluation results lack interpretability. To address these challenges, we model the cartilages structure and appearance from knee MRI into a graph representation, which is capable of handling highly diverse clinical data. Then, guided by the cartilage graph representation, we design a non-Euclidean deep learning network with the self-attention mechanism, to extract cartilage features in the local and global, and to derive the final assessment with a visualized result. Our comprehensive experiments show that the proposed method yields superior performance in knee cartilage defect assessment, plus its convenient 3D visualization for interpretability.

It has been reported that chronic heroin intake induces changes in central nervous system of human brain; however, few studies investigate the carry-over adverse effects on brain after heroin withdrawal. In this work we examined the alpha rhythms of resting-state Electroencephalogram (EEG) signals to measure the neuroelectrical differences between the heroin addicts after heroin withdrawal and normal control. Eyes-closed resting EEG signals from 20 heroin addicts with the abstinence length ranging from 4-16 months and 20 normal controls were recorded using 64 electrodes. Comparing the nonlinear characteristics of EEG signals, such as the correlation dimension, Kolmogorov entropy and Lempel-Ziv complexity, we found that the EEG signals from heroin addicts were significantly more irregular than those from normal controls. Furthermore, the topography of the each nonlinear feature was examined, and the abnormal changes were widely spread over the brain. These findings suggest that nonlinear methods may contribute to gain new insights into brain dysfunction in heroin addicts even after heroin abstinence.

Subspace clustering refers to the task of clustering a collection of points drawn from a high-dimensional space into a union of multiple subspaces that best fits them. State-of-the-art approaches have been proposed for tackling this clustering problem by using the low-rank or sparse optimization techniques. However, most of the traditional subspace clustering methods are developed for single-view data and are not directly applicable to the multi-view scenario. In this paper, we present a Manifold Regularized Multi-view Subspace Clustering (MRMSC) method to better incorporate the correlated and complementary information from different views. MRMSC yields a unified affinity representation by joint optimization across different views. To respect the data manifold locally, the graph Laplacian is constructed to maintain the intrinsic geometrical structure of each view. In the multi-view integration, a sparsity constraint is imposed to the unified affinity representation in order to better reflect the data relationship from multiple views or features. In experiments, we compared the performance of clustering using MRMSC with the single-view and concatenate-multi-view methods on different datasets. The results showed that better clustering performance can be achieved by fusing the multiple features with a unified affinity representation by MRMSC.

According to the level of information provided in images, segmentation techniques can be categorized into two groups. One is region-labeling, which obeys the intensity-based classification methods. Although modeling the tissue intensity is straightforward by applying local statistical methods and spatial dependencies, the results might suffer from noise and incomplete data. The second group of techniques applies active contour models, in which the objective is to find the optimal partition of the image domain using a closed or open curve by using prior constraints on the shape variation. However, estimating optimal curve is intractable due to the incomplete observation data. This paper extends a previously reported joint active contour model for medical image segmentation in a new Expectation-Maximization (EM) framework, wherein the evolution curve is constrained not only by a shape-based statistical model but also by applying a hidden variable model from the image observation. In this approach, the hidden variable model is defined by the local voxel labeling computed from its likelihood function, depended on the image functions and the prior anatomical knowledge. Comparative results on segmenting putamen and caudate shapes in MR brain images confirmed both robustness and accuracy of the proposed curve evolution algorithm.

In this paper, a new coupled implicit shape-based segmentation algorithm is proposed for medical image segmentation. In the method, both region-based and statistical model-based curve evolution algorithms are jointly used to match the object in a new input image. Compared to the previous method that solely uses statistical shape models, our new algorithm is able to match the boundaries of the object shapes more accurately and at the same time, it maintains similar robustness since the same shape prior information is used to regularize the object shapes. Experiments on segmenting the ventricle frontal horn and putamen shapes in MR brain images confirm that the proposed algorithm yields more accurate segmentation results.

This paper presents a new deformable model using both population-based and patient-specific shape statistics to segment lung fields from serial chest radiographs. There are two novelties in the proposed deformable model. First, a modified scale invariant feature transform (SIFT) local descriptor, which is more distinctive than the general intensity and gradient features, is used to characterize the image features in the vicinity of each pixel. Second, the deformable contour is constrained by both population-based and patient-specific shape statistics, and it yields more robust and accurate segmentation of lung fields for serial chest radiographs. In particular, for segmenting the initial time-point images, the population-based shape statistics is used to constrain the deformable contour; as more subsequent images of the same patient are acquired, the patient-specific shape statistics online collected from the previous segmentation results gradually takes more roles. Thus, this patient-specific shape statistics is updated each time when a new segmentation result is obtained, and it is further used to refine the segmentation results of all the available time-point images. Experimental results show that the proposed method is more robust and accurate than other active shape models in segmenting the lung fields from serial chest radiographs.

Segmenting medical images into different tissues is an important task in medical image analysis, e.g., classifying every voxel of input image into different tissue types: CSF, gray matter and white matter. This paper investigates the fully-tuned radial basis function (RBF) and compares it with the traditional fuzzy c-mean (FCM) clustering algorithm in MR image segmentation. It turns out that FCM is not only biased by the number of voxels in different groups, but also by the intensity differences between different tissue groups, while the fully-tuned RBF captures the multi-Gaussian distribution of the image intensities very well and thus it can be used to segment image intensities accurately. Moreover, in order to generate spatially smooth segmentation results, a Markov random field model is applied to the segmentation results of the fully-tuned RBF algorithm. Experimental results show that fully-tuned RBF method can capture the tissue intensity distribution more accurately than the FCM algorithm

Finding point correspondence in anatomical images is a key step in shape analysis and deformable registration. This paper proposes an automatic correspondence detection algorithm for intramodality MR brain images of different subjects using wavelet-based attribute vectors (WAVs) defined on every image voxel. The attribute vector (AV) is extracted from the wavelet subimages and reflects the image structure in a large neighborhood around the respective voxel in a multiscale fashion. It plays the role of a morphological signature for each voxel, and our goal is, therefore, to make it distinctive of the respective voxel. Correspondence is then determined from similarities of AVs. By incorporating the prior knowledge of the spatial relationship among voxels, the ability of the proposed algorithm to find anatomical correspondence is further improved. Experiments with MR images of human brains show that the algorithm performs similarly to experts, even for complex cortical structures.

This paper presents a novel application of the Bayesian shape model (BSM) for facial feature extraction. First, a full-face model is designed to describe the shape of a face, and the PCA is used to estimate the shape variance of the face model. Then, the BSM is applied to match and extract the face patch from input face images. Finally, using the face model, the extracted face patches are easily warped or normalized to a standard view. Applications of this facial feature extraction algorithm include face recognition, face video coding and retrieval, face animation and multimedia.

A new algorithm is proposed to extract the facial features and estimate the control points for facial image warping using the principle component analysis (PCA) based statistic face model. In this algorithm, first a full-face model consisting the contour points and the control points is built. Based on a number of manually marked training samples, the prior distribution of the full-face model can be obtained by using the PCA. Given an input face image, first the contour points are obtained by using the Bayesian shape model (BSM), and then the control points are estimated from the contour points. Finally, the extracted face path is normalized using the piece-wise affine triangle warping algorithm. Experimental results illustrate the effectiveness of the proposed algorithm.

This paper proposed a novel semi-local feature set, which is proved to be affine invariant. The proposed feature set can be local or global based on the mask parameter selected. Small mask indicates local features, which are more precise and not sensitive to occlusion problems. Large mask indicates global features, which are more robust and less sensitive to noise. Using this feature set a correspondence based velocity estimation algorithm is developed. This motion estimation method can be used in motion detection, motion segmentation, and motion based recognition.

A deformable template model for object extraction is proposed based on the fuzzy alignment algorithm (FAA). This object matching algorithm is partitioned into two iterative processes, the first is to estimate the pose relationship (point correspondence and transform parameters) between the current template and the prototype using FAA, the second is to adjust the current template under the exertion of internal energy and external energy functions. An affine-invariant internal energy function of the deformable template is utilized to deal with the transformation of the templates between different domains. Comparative studies with G-Snake model demonstrate the effectiveness of the proposed algorithm and show that it outperforms G-Snake in matching objects with large shearing of shapes.

An affine-invariant deformable contour model for object matching, called affine-invariant eigensnake (AI-ES), is presented in the Bayesian framework. In AI-ES, the prior distribution of object shapes is estimated and utilized to constrain the prototype contour, which is dynamically adjustable in the matching process. Also, an affine-invariant internal energy is presented to define the global and local shape deformation of the contours between the shape domain and the image domain. Experiments on real object matching show that the proposed method is more robust and insensitive to the positions, viewpoints, and large deformations of object shapes, than the active shape model (ASM) and the AI-snake model.

The paper proposes a novel eigenvector approach for pose and correspondence estimation between the feature points of two images or two point patterns under affine transformation. In the method, the proximity matrices, which record the normalized area features extracted from the two point sets are utilized to calculate the modes of each point set and the corresponding feature vectors. Then the point correspondence can be obtained by calculating the correlation of the feature vectors. To reduce the computation time, the idea of the principal component analysis (PCA) is adopted, which considers only the principal eigenvectors corresponding to the larger eigenvalues of each proximity matrix. As compared with the traditional eigenvector algorithm proposed by L.S. Shapiro and J.M. Brady (1992), the proposed algorithm is demonstrated to be more effective in estimating the point correspondence and the relevant parameters of affine transformation.