Three dimensional shape analysis with parametric surface modeling.

This comprehensive volume is an essential reference tool for professional and academic researchers in the filed of computer vision, image processing, and applied mathematics. Continuing rapid advances in image processing have been enhanced by the theoretical efforts of mathematicians and engineers. This marriage of mathematics and computer vision - computational vision - has resulted in a discrete approach to image processing that is more reliable when leveraging in practical tasks. This comprehensive volume provides a detailed discourse on the mathematical models used in computational vision from leading educators and active research experts in this field. Topical areas include: image reconstruction, segmentation and object extraction, shape modeling and registration, motion analysis and tracking, and 3D from images, geometry and reconstruction. The book also includes a study of applications in medical image analysis. Handbook of Mathematical Models in Computer Vision provides a graduate-level treatment of this subject as well as serving as a complete reference work for professionals.

We propose a new spherical parameterization algorithm for general genus-zero surfaces that aims to control the area and length distortions at the same time. Prior work either considers only the length distortion or applies only to volumetric surfaces. Our algorithm starts from an initial parameterization, performs local and global smoothing steps alternately to improve the mapping quality, and converges to the solution. The local method minimizes the area distortion at a local submesh by solving a linear system as well as controls the length distortion. The global method attempts to reduce the area distortion by equalizing its distribution over the whole sphere. We perform experimental studies showing the effectiveness of the technique. Our new algorithm has many applications in medical image analysis, computer vision, graphics and multimedia databases.

As a fundamental but difficult topic in computer vision, 3D object segmentation has various applications in medical image analysis, autonomous vehicles, robotics, virtual reality, lithium battery image analysis, etc. In the past, 3D segmentation was performed using hand-made features and design techniques, but these techniques could not generalize to vast amounts of data or reach acceptable accuracy. Deep learning techniques have lately emerged as the preferred method for 3D segmentation jobs as a result of their extraordinary performance in 2D computer vision. Our proposed method used a CNN-based architecture called 3D UNET, which is inspired by the famous 2D UNET that has been used to segment volumetric image data. To see the internal changes of composite materials, for instance, in a lithium battery image, it is necessary to see the flow of different materials and follow the directions analyzing the inside properties. In this paper, a combination of 3D UNET and VGG19 has been used to conduct a multiclass segmentation of publicly available sandstone datasets to analyze their microstructures using image data based on four different objects in the samples of volumetric data. In our image sample, there are a total of 448 2D images, which are then aggregated as one 3D volume to examine the 3D volumetric data. The solution involves the segmentation of each object in the volume data and further analysis of each object to find its average size, area percentage, total area, etc. The open-source image processing package IMAGEJ is used for further analysis of individual particles. In this study, it was demonstrated that convolutional neural networks can be trained to recognize sandstone microstructure traits with an accuracy of 96.78% and an IOU of 91.12%. According to our knowledge, many prior works have applied 3D UNET for segmentation, but very few papers extend it further to show the details of particles in the sample. The proposed solution offers a computational insight for real-time implementation and is discovered to be superior to the current state-of-the-art methods. The result has importance for the creation of an approximately similar model for the microstructural analysis of volumetric data.

Image registration is an important problem for image processing and computer vision with many proposed applications in medical image analysis.^{1, 2} Image registration techniques attempt to map corresponding features between two images. The problem is particularly difficult as anatomy is subject to elastic deformations. This paper considers this problem in the context of graph matching. Firstly, weighted Region Adjacency Graphs (RAGs) are constructed from each image using an approach based on watershed saliency. ³ The vertices of the RAG represent salient regions in the image and the (weighted) edges represent the relationship (bonding) between each region. Correspondences between images are then determined using a weighted graph matching method. Graph matching is considered to be one of the most complex problems in computer vision, due to its combinatorial nature. Our approach uses a multi-spectral technique to graph matching first proposed by Umeyama⁴ to find an approximate solution to the weighted graph matching problem (WGMP) based on the singular value decomposition of the adjacency matrix. Results show the technique is successful in co-registering 2-D MRI images and the method could be useful in co-registering 3-D volumetric data (e.g. CT, MRI, SPECT, PET etc.).

Medical image analysis using deep neural networks (DNN) has demonstrated state-of-the-art performance in image classification and segmentation tasks, aiding disease diagnosis. The accuracy of the DNN is largely governed by the quality and quantity of the data used to train the model. However, for the medical images, the critical security and privacy concerns regarding sharing of local medical data across medical establishments precludes exploiting the full DNN potential for clinical diagnosis. The federated learning (FL) approach enables the use of local model's parameters to train a global model, while ensuring data privacy and security. In this paper, we review the federated learning applications in medical image analysis with DNNs, highlight the security concerns, cover some efforts to improve FL model performance, and describe the challenges and future research directions.

Automatic detection of breast lesions in automated 3D breast ultrasound with cross-organ transfer learning

The limited availability of standardized datasets has hindered the implementation of artificial intelligence (AI) models in serous fluid cytology, particularly in pleural fluid analysis. In this paper, we present the construction of a dataset of pleural fluid cytology images. The objective is to generate a dataset of pleural fluid cytologic images validated by two pathologists and classified into five categories for cell diagnosis, which will be used to train AI models. As a methodology, the images represent pleural fluid cytology samples that have been prepared through medical procedures and transferred to slides, providing valuable information when evaluated under the microscope by medical specialists through cytological examination. We documented the entire process for building the pleural fluid cytological image dataset, from image capture, labeling, preprocessing, standardization, and uploading to public platforms. As a result, we obtained a pleural fluid cytology dataset based on the International System (TIS) criteria for reporting serous fluids, classifying samples into AUS, MAL, ND, NFM, and SFM. This dataset is intended to support medical research, deep learning applications in medical image analysis, and improved diagnostic methodologies.

Construction of a confounder-free clinical MRI dataset in the Mass General Brigham system for classification of Alzheimer's disease

Extensive recent work has taken place on the construction of probabilistic atlases of anatomical organs, especially the brain, and their application in medical image analysis. These techniques are leading the way into similar studies of other organs and more comprehensively of groups of organs. In this paper we report results on the analysis of anatomical variability obtained from probabilistic atlases of abdominal organs. Two factor analysis techniques, namely principal component analysis (PCA) and principal factor analysis (PFA), were used to decompose and study shape variability within the abdomen. To assess and ease the interpretability of the resulting deformation modes, a clustering technique of the deformation vectors is proposed. The analysis of deformation fields obtained using these two factor analysis techniques showed strong correlation with anatomical landmarks and known mechanical deformations in the abdomen, allowing us to conclude that PFA is a complementary decomposition technique that offers easy-to-interpret additional information to PCA in a clinical setting. The analysis of organ anatomical variability will represent a potentially important research tool for abdominal diagnosis and modeling.

The current standard for assessing neonatal pain is discontinuous and suffers from inter-observer variations, which can result in delayed intervention and inconsistent treatment of pain. Therefore, it is critical to address the shortcomings of the current standard and develop continuous and less subjective pain assessment tools. Convolutional Neural Networks have gained much popularity in the last decades due to the wide range of its successful applications in medical image analysis, object recognition, and emotion recognition. In this paper, we propose a Neonatal Convolutional Neural Network, designed and trained end-to-end to detect neonatal pain. We evaluated the proposed network in two data sets of neonates and compared its performance to the performance of ResNet architecture in the same data sets. Our proposed method outperformed ResNet in recognizing neonates’ pain and achieved around 91.00% accuracy. While further research is needed, our preliminary results suggest that the presented network can be used for automatic pain assessment, and possibly similar applications. It also suggests that the automatic recognition of neonatal pain provides a viable and more efficient alternative to the current standard of pain assessment.

Cervical cancer ranks as the second most common cancer in women worldwide. In clinical practice, colposcopy is an indispensable part of screening for cervical intraepithelial neoplasia (CIN) grades and cervical cancer but exhibits high misdiagnosis rate. Existing computer-assisted algorithms for analyzing cervigram images have neglected that colposcopy is a sequential and multistate process, which is unsuitable for clinical applications. In this work, we construct a cervigram-based recurrent convolutional neural network (C-RCNN) to classify different CIN grades and cervical cancer. Convolutional neural networks are leveraged to extract spatial features. We develop a sequence-encoding module to encode discriminative temporal features and a multistate-aware convolutional layer to integrate features from different states of cervigram images. To train and evaluate the performance of C-RCNN, we leveraged a dataset of 4,753 real cervigrams and obtained 96.13% test accuracy with a specificity and sensitivity of 98.22% and 95.09%, respectively. Areas under each receiver operating characteristic curves are above 0.94, proving that visual representations and sequential dynamics can be jointly and effectively optimized in the training phase. Comparative analysis demonstrated the effectiveness of the proposed C-RCNN against competing methods, showing significant improvement over only focusing on a single frame. This architecture can be extended to other applications in medical image analysis.

Early detection and treatment are crucial for improving the prognosis of breast cancer. While ultrasound imaging is widely utilized for screening, its interpretation is subjective and heavily dependent on clinician expertise. Although supervised models have shown great promise in medical image segmentation, they encounter challenges such as the need for large labeled datasets, extended training times, and limited generalization to external datasets. We propose TFSeg, a Training-Free automatic image segmentation framework based on Segment Anything Model 2 (SAM2). TFSeg eliminates the need for re-training new models and tuning hyper-parameters by generating image sequences through the retrieval of the top-k most similar images from the training set, using their mask prompts to guide SAM2 in achieving accurate and efficient segmentation. Our approach, validated on a breast ultrasound image dataset, achieved a Dice score of 82.66%, surpassing the performance of most supervised and training-free segmentation models. Notably, it achieved the highest precision (87.93%) among all the compared methods. By combining image retrieval with sequence generation, TFSeg leverages SAM2 to provide an efficient and effective solution for breast cancer ultrasound image segmentation and demonstrates potential for broader applications in medical image analysis. The Training-Free automatic image Segmentation framework addresses challenges associated with supervised models, making it a promising method for improving breast cancer diagnosis.

BackgroundWe utilized 3‐dimensional, surface‐based, morphometric analysis to investigate hippocampus shape between 2 groups: (1) idiopathic normal‐pressure hydrocephalus (INPH) patients who had a positive response to the cerebrospinal fluid tap test and (2) healthy controls. The aims were (1) to evaluate INPH‐related structural abnormalities of the hippocampi and (2) to investigate relationships between hippocampal shape changes and gait disturbance in INPH patients.MethodForty‐eight INPH patients and 25 healthy controls were imaged with MRI, including 3‐dimensional volumetric images, for vertex‐based 3‐dimensional hippocampal shape analysis.ResultVertex‐wise shape analysis revealed significant bilateral deformation in patients with INPH compared with healthy controls after FDR correction. Both the left and right hippocampi were more elongated and narrowed in INPH patients than in the healthy controls. In both hemispheres, INPH patients demonstrated an upward bending of the middle and posterior hippocampus reflecting a bilateral vertical displacement from body to tail. Significant correlations were found between local shape deformity and the timed up and go and 10 meter walking tests (to a greater degree on the right than on the left). Bilateral inward deformations at the superomedial hippocampal tail and inferior hippocampal body were consistently associated with inferior performance across tests. Inward deformations at the right medial and lateral hippocampal head and right superior hippocampal body were also consistently associated with worse performance across tests.ConclusionThese results suggest that patients with INPH have unique patterns of hippocampal shape changes. Our findings encourage future studies to elucidate the underlying mechanism of hippocampal morphometric abnormalities in INPH patients. Changes in overall shape may contribute to the distinctive gait abnormalities associated with INPH.

We present a new framework for 3D surface object classification that combines a powerful shape description method with suitable pattern classification techniques. Spherical harmonic parameterization and normalization techniques are used to describe a surface shape and derive a dual high dimensional landmark representation. A point distribution model is applied to reduce the dimensionality. Fisher's linear discriminants and support vector machines are used for classification. Several feature selection schemes are proposed for learning better classifiers. After showing the effectiveness of this framework using simulated shape data, we apply it to real hippocampal data in schizophrenia and perform extensive experimental studies by examining different combinations of techniques. We achieve best leave-one-out cross-validation accuracies of 93% (whole set, N = 56) and 90% (right-handed males, N = 39), respectively, which are competitive with the best results in previous studies using different techniques on similar types of data. Furthermore, to help medical diagnosis in practice, we employ a threshold-free receiver operating characteristic (ROC) approach as an alternative evaluation of classification results as well as propose a new method for visualizing discriminative patterns.

Surface-based representation and classification techniques are studied for hippocampal shape analysis. The goal is twofold: (1) develop a new framework of salient feature extraction and accurate classification for 3D shape data; (2) detect hippocampal abnormalities in schizophrenia using this technique. A fine-scale spherical harmonic expansion is employed to describe a closed 3D surface object. The expansion can then easily be transformed to extract only shape information (i.e., excluding translation, rotation, and scaling) and create a shape descriptor comparable across different individuals. This representation captures shape features and is flexible enough to do shape modeling, identify statistical group differences, and generate similar synthetic shapes. Principal component analysis is used to extract a small number of independent features from high dimensional shape descriptors, and Fisher's linear discriminant is applied for pattern classification. This framework is shown to be able to perform well in distinguishing clear group differences as well as small and noisy group differences using simulated shape data. In addition, the application of this technique to real data indicates that group shape differences exist in hippocampi between healthy controls and schizophrenic patients.