Efficient sparse shape composition with its applications in biomedical image analysis: An overview

Chapter 13 - Robust and Scalable Shape Prior Modeling via Sparse Representation and Dictionary Learning

“BAU-Insectv2” represents a novel agricultural dataset tailored for deep learning applications and biomedical image analysis focused on plant-insect interactions. This dataset encompasses a diverse collection of high-resolution images capturing intricate details of plant-insect interactions across various agricultural settings. Leveraging deep learning methodologies, this study aims to employ convolutional neural networks (CNN) and advanced image analysis techniques for precise insect detection, classification, and understanding of insect-related patterns within agricultural ecosystems. We mainly focus on addressing insect-related issues in South Asian crop cultivation. The dataset's extensive scope and high-quality imagery provide a robust foundation for developing and validating models capable of accurately identifying and analyzing diverse plant insects. The dataset's utility extends to biomedical image analysis, fostering interdisciplinary research avenues across agriculture and biomedical sciences. This dataset holds significant promise for advancing research in agricultural pest management, ecosystem dynamics, and biomedical image analysis techniques.

(Hyper)-graphical models in biomedical image analysis.

Biomedical image analysis has become critically important to the public health and welfare. However, analyzing biomedical images is time-consuming and labor-intensive, and has long been performed manually by highly trained human experts. As a result, there has been an increasing interest in applying machine learning to automate biomedical image analysis. Recent progress in deep learning research has catalyzed the development of machine learning in learning discriminative features from data with minimum human intervention. Many deep learning models have been designed and achieved superior performance in various data analysis applications. This chapter starts with the basic of deep learning models and some practical strategies for handling biomedical image applications with limited data. After that, case studies of deep feature extraction for gene expression pattern image annotations, imaging data completion for brain disease diagnosis, and segmentation of infant brain tissue images are discussed to demonstrate the effectiveness of deep learning in biomedical image analysis.

Evaluation of the benchmark datasets for testing the efficacy of deep convolutional neural networks

Exploring the complementarity of THz pulse imaging and DCE-MRIs: Toward a unified multi-channel classification and a deep learning framework

In the field of biomedical imaging analysis on single-cell level, reliable and fast segmentation of the cell nuclei from the background on three-dimensional images is highly needed for the further analysis. In this work we propose an interactive cell segmentation toolkit that first establishes a set of exemplar regions from user input through an easy and intuitive interface in both 2D and 3D in real-time, then extracts the shape and intensity features from those exemplars. Based on a local contrast-constrained region growing scheme, each connected component in the whole image would be filtered by the features from exemplars, forming an “exemplar-matching” group which passed the filtering and would be part of the final segmentation result, and a “non-exemplar-matching” group in which components would be further segmented by the gradient vector field based algorithm. The results of the filtering process are visualized back to the user in near real-time, thus enhancing the experience in exemplar selecting and parameter tuning. The toolkit is distributed as a plugin within the open source Vaa3D system (http://vaa3d.org).

Special collection on biological and biomedical image analysis

Summary form only given. The future of biomedical image analysis is no longer in anatomical imaging but in imaging of pathways and mechanisms at the cellular level and below. In this talk I present image analysis techniques for rolling leukocytes observed in vivo. Rolling leukocytes are activated white blood cells. The motion, shape, flux, number and position of these cells are important indicators of the inflammatory process. Measuring image-derived parameters are vital to validating anti-inflammatory drugs and to understanding the basic mechanism of inflammatory diseases such as atherosclerosis and arthritis. To date, these image features are typically derived manually due to the difficulty associated with intravital image clutter, noise, occlusion, instability, poor contrast, contrast changes and shape deformation. The first part of the talk details tracking methods used for rolling leukocytes. These are divided into two categories: active contour approaches and particle filter approaches. The second portion of the talk focuses on novel cell detection methods for intravital microscopy. The methods include a level set solution, the gradient inverse coefficient of variation (GICOV) technique, and the more recent Poisson inverse gradient approach. For both detection and tracking, real video data examples show the efficacy of the developed techniques. New directions in cellular image analysis are discussed including high content screening and future work in image analysis for systems biology.

Medical image segmentation is a crucial step in computer-aided diagnosis, treatment planning, and biomedical image analysis. This paper presents a segmentation approach based on Weighted Identification Level Set Evolution (WILSE), which effectively integrates local edge features to improve boundary detection and region accuracy. Traditional segmentation methods often struggle with noise, weak boundaries, and intensity inhomogeneity in medical images. The proposed method overcomes these challenges by assigning adaptive weights to local image features, enhancing the sensitivity of the level set function to significant edges while suppressing irrelevant noise. The model evolves iteratively to refine object boundaries and achieve precise delineation of anatomical structures. Experimental results on various medical imaging modalities such as MRI, CT, and ultrasound demonstrate that the WILSE approach provides superior segmentation accuracy, robustness, and computational efficiency compared to conventional edge-based or region-based methods. This technique shows promising potential for clinical applications where high-precision segmentation is essential for diagnosis and quantitative analysis.

Intense interest in applying convolutional neural networks (CNNs) in biomedical image analysis is wide spread, but its success is impeded by the lack of large annotated datasets in biomedical imaging. Annotating biomedical images is not only tedious and time consuming, but also demanding of costly, specialty-oriented knowledge and skills, which are not easily accessible. To dramatically reduce annotation cost, this paper presents a novel method called AIFT (active, incremental fine-tuning) to naturally integrate active learning and transfer learning into a single framework. AIFT starts directly with a pre-trained CNN to seek "worthy" samples from the unannotated for annotation, and the (fine-tuned) CNN is further fine-tuned continuously by incorporating newly annotated samples in each iteration to enhance the CNN's performance incrementally. We have evaluated our method in three different biomedical imaging applications, demonstrating that the cost of annotation can be cut by at least half. This performance is attributed to the several advantages derived from the advanced active and incremental capability of our AIFT method.

Cell nucleus segmentation is a fundamental task in biomedical image analysis. Generating realistic cell nucleus data with ground truth masks can help tackle difficulties such as insufficient training data for deep learning models and the need to deal with cases (e.g., tightly clumped nuclei). Known nucleus generation methods generated individual nucleus masks from parametric models or based on direct transformations of real masks. It is difficult for these methods to capture and simulate the distributions of real nuclei and interactions among hard nuclei. In this paper, we propose a new three-stage coarse-to-fine nucleus generation method for 2D and 3D nucleus segmentation. The first stage simulates the positions and sizes of nuclei; the second stage simulates the shapes of nuclei and interactions among clumped nuclei; the third stage simulates the textures of nuclei. We evaluate our method on 2D and 3D cell nucleus image datasets. Experimental results show that our new nucleus generation method considerably helps improve cell nucleus segmentation performance and outperforms known nucleus generation methods for nucleus segmentation with a small amount of training data.

In this work we detail the first algorithm that provides topological control during surface reconstruction from an input set of planar cross-sections. Our work has broad application in a number of fields including surface modeling and biomedical image analysis, where surfaces of known topology must be recovered. Given curves on arbitrarily oriented cross-sections, our method produces a manifold interpolating surface that exactly matches a user-specified genus. The key insight behind our approach is to formulate the topological search as a divide-and-conquer optimization process which scores local sets of topologies and combines them to satisfy the global topology constraint. We further extend our method to allow image data to guide the topological search, achieving even better results than relying on the curves alone. By simultaneously satisfying both geometric and topological constraints, we are able to produce accurate reconstructions with fewer input cross-sections, hence reducing the manual time needed to extract the desired shape.

In this paper we propose a novel approach for the spatial segmentation of video sequences containing multiple temporal textures. This work is based on the notion that a single temporal texture can be represented by a low-dimensional linear model. For scenes containing multiple temporal textures, e.g. trees swaying adjacent a flowing river, we extend the single linear model to a mixture of linear models and segment the scene by identifying subspaces within the data using robust generalized principal component analysis (GPCA). Computation is reduced to minutes in Matlab by first identifying models from a sampling of the sequence and using the derived models to segment the remaining data. The effectiveness of our method has been demonstrated in several examples including an application in biomedical image analysis.

The application of machine learning methods in biomedical image analysis has recently become of particular interest to researchers. One of the most common diagnostic methods with low cost and high availability is X-ray imaging. It allows the acquisition of frontal images of the chest, which can be used in the medical diagnosis of various diseases and prognosis. Due to the presence of ribs on the image, some pathologic changes may go unnoticed. The goal of this work is to develop a method, using deep learning techniques, to remove ribs from chest X-ray images. The Bone Suppression dataset, consisting of 35 pairs of standard X-ray and soft-tissue only images, was used to develop the model. COVIDx was used as an external test set. Due to the small number of images in the training cohort, a data augmentation technique was used to generate new, noisy image pairs. A deep learning model using convolutional denoising autoencoder architecture was developed to remove the ribs from the X-ray image. The effects of two image down-sampling methods and learning rate changes were evaluated. The resulting images are characterized by partial or complete suppression of the ribs. It should be noted that the problem was not posed by images of patients suffering from COVID-19, which are characterized by much more complex structures.