Graph based method for cell segmentation and detection in live-cell fluorescence microscope imaging

Machine learning for urban land use/ cover mapping: Comparison of artificial neural network, random forest and support vector machine, a case study of Dilla town

The ability to accurately classify land use/cover (LULC) is critical for environmental monitoring and land use planning. This study compares three machine learning algorithms: Artificial Neural Network (ANN), Support Vector Machine (SVM), and Random Forest (RF) for LULC classification using Google Earth images from the years 2006, 2014, and 2022. The objective of this study is to evaluate and identify the best classifier for LULC classification and change detection. Four LULC categories (Built-up, Open area, Farmland, and Agroforestry) were identified. The evaluation criteria included overall accuracy, kappa coefficient, producer's accuracy, user's accuracy, computing time, algorithm stability, and visual quality. The results showed that the RF algorithm outperformed both SVM and ANN algorithms with an average overall accuracy of 0.97, kappa coefficient of 0.98, producer's accuracy of 0.99, and user's accuracy of 0.97, surpassing the accuracies achieved by SVM (0.96, 0.97, 0.98, and 0.97) and ANN (0.89, 0.81, 0.94, and 0.88), with corresponding computing times of 6.33, 15, and 30 s. All classifiers performed stably with different training sizes. Visual quality assessment revealed that RF had the highest precision. Consequently, the built-up change detection result shows, the net change in built-up area between 2006 and 2022 was increased by 0.74 Km2 for ANN, 1.74 Km2 for SVM, and 1.66 Km2 for RF. The comparison reveals that the RF algorithm showcasing high precision in detecting change, consistent with the data (increased by 1.65 Km2 ) obtained from Dilla town land administration office. To validate the results, the study considered field surveys, reference images, local experts, and previous studies. Based on the findings, the study concludes that using RF classifier with an object-based approach is an effective way to map LULC and detect changes in the study area over time. Future researchers are recommended to utilize this effective algorithm for addressing LULC related problems in the study area.

CMTT-JTracker: a fully test-time adaptive framework serving automated cell lineage construction

Cell tracking is an essential function needed in automated cellular activity monitoring. In practice, processing methods striking a balance between computational efficiency and accuracy as well as demonstrating robust generalizability across diverse cell datasets are highly desired. This paper develops a central-metric fully test-time adaptive framework for cell tracking (CMTT-JTracker). Firstly, a CMTT mechanism is designed for the pre-segmentation of cell images, which enables extracting target information at different resolutions without additional training. Next, a multi-task learning network with the spatial attention scheme is developed to simultaneously realize detection and re-identification tasks based on features extracted by CMTT. Experimental results demonstrate that the CMTT-JTracker exhibits remarkable biological and tracking performance compared with benchmarking tracking methods. It achieves a multiple object tracking accuracy (MOTA) of $0.894$ on Fluo-N2DH-SIM+ and a MOTA of $0.850$ on PhC-C2DL-PSC. Experimental results further confirm that the CMTT applied solely as a segmentation unit outperforms the SOTA segmentation benchmarks on various datasets, particularly excelling in scenarios with dense cells. The Dice coefficients of the CMTT range from a high of $0.928$ to a low of $0.758$ across different datasets.

Significance of AI-assisted techniques for epiphyte plant monitoring and identification from drone images

Monitoring forest canopies is vital for ecological studies, particularly for assessing epiphytes in rain forest ecosystems. Traditional methods for studying epiphytes, such as climbing trees and building observation structures, are labor, cost intensive and risky. Unmanned Aerial Vehicles (UAVs) have emerged as a valuable tool in this domain, offering botanists a safer and more cost-effective means to collect data. This study leverages AI-assisted techniques to enhance the identification and mapping of epiphytes using UAV imagery. The primary objective of this research is to evaluate the effectiveness of AI-assisted methods compared to traditional approaches in segmenting/identifying epiphytes from UAV images collected in a reserve forest in Costa Rica. Specifically, the study investigates whether Deep Learning (DL) models can accurately identify epiphytes during complex backgrounds, even with a limited dataset of varying image quality. Systematically, this study compares three traditional image segmentation methods Auto Cluster, Watershed, and Level Set with two DL-based segmentation networks: the UNet and the Vision Transformer-based TransUNet. Results obtained from this study indicate that traditional methods struggle with the complexity of vegetation backgrounds and variability in target characteristics. Epiphyte identification results were quantitatively evaluated using the Jaccard score. Among traditional methods, Watershed scored 0.10, Auto Cluster 0.13, and Level Set failed to identify the target. In contrast, AI-assisted models performed better, with UNet scoring 0.60 and TransUNet 0.65. These results highlight the potential of DL approaches to improve the accuracy and efficiency of epiphyte identification and mapping, advancing ecological research and conservation.

CellT-Net: A Composite Transformer Method for 2-D Cell Instance Segmentation

Cell instance segmentation (CIS) via light microscopy and artificial intelligence (AI) is essential to cell and gene therapy-based health care management, which offers the hope of revolutionary health care. An effective CIS method can help clinicians to diagnose neurological disorders and quantify how well these deadly disorders respond to treatment. To address the CIS task challenged by dataset characteristics such as irregular morphology, variation in sizes, cell adhesion, and obscure contours, we propose a novel deep learning model named CellT-Net to actualize effective cell instance segmentation. In particular, the Swin transformer (Swin-T) is used as the basic model to construct the CellT-Net backbone, as the self-attention mechanism can adaptively focus on useful image regions while suppressing irrelevant background information. Moreover, CellT-Net incorporating Swin-T constructs a hierarchical representation and generates multi-scale feature maps that are suitable for detecting and segmenting cells at different scales. A novel composite style named cross-level composition (CLC) is proposed to build composite connections between identical Swin-T models in the CellT-Net backbone and generate more representational features. The earth mover's distance (EMD) loss and binary cross entropy loss are used to train CellT-Net and actualize the precise segmentation of overlapped cells. The LiveCELL and Sartorius datasets are utilized to validate the model effectiveness, and the results demonstrate that CellT-Net can achieve better model performance for dealing with the challenges arising from the characteristics of cell datasets than state-of-the-art models.

A Weakly Supervised Learning Method for Cell Detection and Tracking Using Incomplete Initial Annotations

The automatic detection of cells in microscopy image sequences is a significant task in biomedical research. However, routine microscopy images with cells, which are taken during the process whereby constant division and differentiation occur, are notoriously difficult to detect due to changes in their appearance and number. Recently, convolutional neural network (CNN)-based methods have made significant progress in cell detection and tracking. However, these approaches require many manually annotated data for fully supervised training, which is time-consuming and often requires professional researchers. To alleviate such tiresome and labor-intensive costs, we propose a novel weakly supervised learning cell detection and tracking framework that trains the deep neural network using incomplete initial labels. Our approach uses incomplete cell markers obtained from fluorescent images for initial training on the Induced Pluripotent Stem (iPS) cell dataset, which is rarely studied for cell detection and tracking. During training, the incomplete initial labels were updated iteratively by combining detection and tracking results to obtain a model with better robustness. Our method was evaluated using two fields of the iPS cell dataset, along with the cell detection accuracy (DET) evaluation metric from the Cell Tracking Challenge (CTC) initiative, and it achieved 0.862 and 0.924 DET, respectively. The transferability of the developed model was tested using the public dataset FluoN2DH-GOWT1, which was taken from CTC; this contains two datasets with reference annotations. We randomly removed parts of the annotations in each labeled data to simulate the initial annotations on the public dataset. After training the model on the two datasets, with labels that comprise 10% cell markers, the DET improved from 0.130 to 0.903 and 0.116 to 0.877. When trained with labels that comprise 60% cell markers, the performance was better than the model trained using the supervised learning method. This outcome indicates that the model's performance improved as the quality of the labels used for training increased.

A lightweight network based on dual-stream feature fusion and dual-domain attention for white blood cells segmentation

Introduction

Accurate white blood cells segmentation from cytopathological images is crucial for evaluating leukemia. However, segmentation is difficult in clinical practice. Given the very large numbers of cytopathological images to be processed, diagnosis becomes cumbersome and time consuming, and diagnostic accuracy is also closely related to experts' experience, fatigue and mood and so on. Besides, fully automatic white blood cells segmentation is challenging for several reasons. There exists cell deformation, blurred cell boundaries, and cell color differences, cells overlapping or adhesion.

Methods

The proposed method improves the feature representation capability of the network while reducing parameters and computational redundancy by utilizing the feature reuse of Ghost module to reconstruct a lightweight backbone network. Additionally, a dual-stream feature fusion network (DFFN) based on the feature pyramid network is designed to enhance detailed information acquisition. Furthermore, a dual-domain attention module (DDAM) is developed to extract global features from both frequency and spatial domains simultaneously, resulting in better cell segmentation performance.

Results

Experimental results on ALL-IDB and BCCD datasets demonstrate that our method outperforms existing instance segmentation networks such as Mask R-CNN, PointRend, MS R-CNN, SOLOv2, and YOLACT with an average precision (AP) of 87.41%, while significantly reducing parameters and computational cost.

Discussion

Our method is significantly better than the current state-of-the-art single-stage methods in terms of both the number of parameters and FLOPs, and our method has the best performance among all compared methods. However, the performance of our method is still lower than the two-stage instance segmentation algorithms. in future work, how to design a more lightweight network model while ensuring a good accuracy will become an important problem.

Cell segmentation in fluorescence microscopy images based on multi-scale histogram thresholding

Cell segmentation from fluorescent microscopy images plays an important role in various applications, such as disease mechanism assessment and drug discovery research. Exiting segmentation methods often adopt image binarization as the first step, through which the foreground cell is separated from the background so that the subsequent processing steps can be greatly facilitated. To pursue this goal, a histogram thresholding can be performed on the input image, which first applies a Gaussian smoothing to suppress the jaggedness of the histogram curve and then exploits Rosin's method to determine a threshold for conducting image binarization. However, an inappropriate amount of smoothing could lead to the inaccurate segmentation of cells. To address this crucial problem, a multi-scale histogram thresholding (MHT) technique is proposed in the present paper, where the scale refers to the standard deviation of the Gaussian that determines the amount of smoothing. To be specific, the image histogram is smoothed at three chosen scales first, and then the smoothed histogram curves are fused to conduct image binarization via thresholding. To further improve the segmentation accuracy and overcome the difficulty of extracting overlapping cells, our proposed MHT technique is incorporated into a multi-scale cell segmentation framework, in which a region-based ellipse fitting technique is adopted to identify overlapping cells. Extensive experimental results obtained on benchmark datasets show that the new method can deliver superior performance compared to the current state-of-the-arts.

In-silico and in-vitro morphometric analysis of intestinal organoids

Organoids offer a powerful model to study cellular self-organisation, the growth of specific tissue morphologies in-vitro, and to assess potential medical therapies. However, the intrinsic mechanisms of these systems are not entirely understood yet, which can result in variability of organoids due to differences in culture conditions and basement membrane extracts used. Improving the standardisation of organoid cultures is essential for their implementation in clinical protocols. Developing tools to assess and predict the behaviour of these systems may produce a more robust and standardised biological model to perform accurate clinical studies. Here, we developed an algorithm to automate crypt-like structure counting on intestinal organoids in both in-vitro and in-silico images. In addition, we modified an existing two-dimensional agent-based mathematical model of intestinal organoids to better describe the system physiology, and evaluated its ability to replicate budding structures compared to new experimental data we generated. The crypt-counting algorithm proved useful in approximating the average number of budding structures found in our in-vitro intestinal organoid culture images on days 3 and 7 after seeding. Our changes to the in-silico model maintain the potential to produce simulations that replicate the number of budding structures found on days 5 and 7 of in-vitro data. The present study aims to aid in quantifying key morphological structures and provide a method to compare both in-vitro and in-silico experiments. Our results could be extended later to 3D in-silico models.

Graphical Image Region Extraction with K-Means Clustering and Watershed

With a wide range of applications, image segmentation is a complex and difficult preprocessing step that plays an important role in automatic visual systems, which accuracy impacts, not only on segmentation results, but directly affects the effectiveness of the follow-up tasks. Despite the many advances achieved in the last decades, image segmentation remains a challenging problem, particularly, the segmenting of color images due to the diverse inhomogeneities of color, textures and shapes present in the descriptive features of the images. In trademark graphic images segmentation, beyond these difficulties, we must also take into account the high noise and low resolution, which are often present. Trademark graphic images can also be very heterogeneous with regard to the elements that make them up, which can be overlapping and with varying lighting conditions. Due to the immense variation encountered in corporate logos and trademark graphic images, it is often difficult to select a single method for extracting relevant image regions in a way that produces satisfactory results. Many of the hybrid approaches that integrate the Watershed and K-Means algorithms involve processing very high quality and visually similar images, such as medical images, meaning that either approach can be tweaked to work on images that follow a certain pattern. Trademark images are totally different from each other and are usually fully colored. Our system solves this difficulty given it is a generalized implementation designed to work in most scenarios, through the use of customizable parameters and completely unbiased for an image type. In this paper, we propose a hybrid approach to Image Region Extraction that focuses on automated region proposal and segmentation techniques. In particular, we analyze popular techniques such as K-Means Clustering and Watershedding and their effectiveness when deployed in a hybrid environment to be applied to a highly variable dataset. The proposed system consists of a multi-stage algorithm that takes as input an RGB image and produces multiple outputs, corresponding to the extracted regions. After preprocessing steps, a K-Means function with random initial centroids and a user-defined value for k is executed over the RGB image, generating a gray-scale segmented image, to which a threshold method is applied to generate a binary mask, containing the necessary information to generate a distance map. Then, the Watershed function is performed over the distance map, using the markers defined by the Connected Component Analysis function that labels regions on 8-way pixel connectivity, ensuring that all regions are correctly found. Finally, individual objects are labelled for extraction through a contour method, based on border following. The achieved results show adequate region extraction capabilities when processing graphical images from different datasets, where the system correctly distinguishes the most relevant visual elements of images with minimal tweaking.

A Review of Watershed Implementations for Segmentation of Volumetric Images

Watershed is a widely used image segmentation algorithm. Most researchers understand just an idea of this method: a grayscale image is considered as topographic relief, which is flooded from initial basins. However, frequently they are not aware of the options of the algorithm and the peculiarities of its realizations. There are many watershed implementations in software packages and products. Even if these packages are based on the identical algorithm-watershed, by flooding their outcomes, processing speed, and consumed memory, vary greatly. In particular, the difference among various implementations is noticeable for huge volumetric images; for instance, tomographic 3D images, for which low performance and high memory requirements of watershed might be bottlenecks. In our review, we discuss the peculiarities of algorithms with and without waterline generation, the impact of connectivity type and relief quantization level on the result, approaches for parallelization, as well as other method options. We present detailed benchmarking of seven open-source and three commercial software implementations of marker-controlled watershed for semantic or instance segmentation. We compare those software packages for one synthetic and two natural volumetric images. The aim of the review is to provide information and advice for practitioners to select the appropriate version of watershed for their problem solving. In addition, we forecast future directions of software development for 3D image segmentation by watershed.