A Coarse-to-Fine Data Generation Method for 2D and 3D Cell Nucleus Segmentation

With the use of computer-aided diagnostic systems, the automatic detection and segmentation of the cell nuclei have become essential in pathology due to cellular nuclei counting and nuclear pleomorphism analysis are critical for the classification and grading of breast cancer histopathology. This work describes a methodology for automatic detection and segmentation of cellular nuclei in breast cancer histopathology images obtained from the BreakHis database, the Standford tissue microarray database, and the Breast Cancer Cell Segmentation database. The proposed scheme is based on the characterization of Hematoxylin and Eosin (H&E) staining, size, and shape features. In addition, we use the information obtained from morphological transformations and adaptive intensity adjustments to detect and separate each cell nucleus detected in the image. The segmentation was carried out by testing the proposed methodology in a histological breast cancer database that provides the associated groundtruth segmentation. Subsequently, the Sørensen-Dice similarity coefficient was calculated to analyze the suitability of the results.Clinical relevance- In this work, the detection and segmentation of cell nuclei in breast cancer histological images are carried out automatically. The method can identify cell nuclei regardless of variations in the level of staining and image magnification. Moreover, a granulometric analysis of the components allows identifying cell clumps and segment them into individual cell nuclei. Improved identification of cell nuclei under different image conditions was demonstrated to reach a sensitivity average of 0.76 ± 0.12. The results provide a base for further and complex processes such as cell counting, feature analysis, and nuclear pleomorphism, which are relevant tasks in the evaluation and diagnostic performed by the expert pathologist.

Globally optimal segmentation of cell nuclei in fluorescence microscopy images using shape and intensity information.

Pap smear is a microscopic screening process of cervical smear used to detect pre-cancerous and cancerous cells in the cervix region. Cell nuclei segmentation is one of the most significant task in cervical cell image analysis which aids in identifyi

Segmentation accuracy determines the success or failure of computerized analysis procedure in biomedical applications. This paper aims to develop a unique segmentation technique to identify mitotic nuclei from microscopy images of breast histopathology slides. The process involves detection and classification of cell nuclei based on computed features. The proposed method uses Active Contour Model for segmentation of cell nuclei and two versatile classifiers such as Support Vector Machine (SVM) and Random Forest (RF) for classification stage. Segmentation stage provides an accuracy of 95% for cell nuclei. This technique uses a single color channel and a reduced feature set for the whole process. Classification performance is evaluated in terms of sensitivity, specificity, accuracy and F-score measures. Analysis results showed good detection accuracy for RF classifier compared to SVM.

Detecting and segmenting cell nuclei in two-dimensional microscopy images

Quantification of phenotypes in high-content screening experiments depends on the accuracy of single cell analysis. In such analysis workflows, cell nuclei segmentation is typically the first step and is followed by cell body segmentation, feature extraction, and subsequent data analysis workflows. Therefore, it is of utmost importance that the first steps of high-content analysis are done accurately in order to guarantee correctness of the final analysis results. In this paper, we present a novel cell nuclei image segmentation framework which exploits robustness of graph cut to obtain initial segmentation for image intensity-based clump splitting method to deliver the accurate overall segmentation. By using quantitative benchmarks and qualitative comparison with real images from high-content screening experiments with complicated multinucleate cells, we show that our method outperforms other state-of-the-art nuclei segmentation methods. Moreover, we provide a modular and easy-to-use implementation of the method for a widely used platform.

The deep learning models play an essential role in many areas, including medical image analysis. These models extract important features without human intervention. In this paper, we propose a deep convolution neural network, named as deep U-Net model, for the segmentation of the cell nucleus, a critical functional unit that determines the function and structure of the body. The nucleus contains all kinds of DNA, RNA, chromosomes, and genes governing all life activities, and its disorder may lead to different types of diseases such as cancer, heart disease, diabetes, Alzheimer’s, etc. If the nucleus structure is known correctly, diseases due to nucleus disorder may be detected early. It may also reduce the drug discovery time if the shape and size of the nucleus are known. We evaluate the performance of the proposed models on the nucleus segmentation data set used by the Data Science Bowl 2018 competition hosted by Kaggle. We compare its performance with that of the U-Net, Attention U-Net, R2U-Net, Attention R2U-Net, and both versions of the U-Net++ with and without supervision, in terms of loss, dice coefficient, dice loss, intersection over union, and accuracy. Our model performs better than the existing models.

Computer-assisted image analysis cytology play an important function in modern cancer diagnostics. A crucial task of such systems is segmentation of cell nuclei. Automatic procedure have to locate their exact position in cytological preparation and determine precise edges in order to extract morphometric features. Unfortunately, segmentation of individual nuclei is a huge challenge because they often creates complex clusters without clear edges. To deal with this problem we are proposing to combine Bayesian object recognition approach to approximate nuclei by circles with marker-controlled watershed employed to determine their exact shape. Watershed segmentation can reconstruct a precise shape of nuclei but only if their approximate location is known. On the other hand, Bayesian object recognition approach allows to isolate single nuclei even in complex nuclei structures but without determining their exact shape. Thus, we used Bayesian object recognition to generate markers required to form a topographic map for a watershed method. The effectiveness of the proposed approach was examined using artificially generated images and real cytological images of breast cancer. Tests carried out have shown that the proposed version of the marked-controlled watershed can be used with success to segment elliptic-shaped objects.

In this paper, we propose a method based on an adaptive active contour modelling to segment the cell nuclei from cervical smear images. The basic idea of our method is to make a contour to adaptively deform so as to get a minimized given region energy function. In order to make the evolution of the contour rely less on the intensity homogeneity and achieve the purpose of adaptive segmentation of the cell nuclei, the proposed method utilizes the morphology method to initialize the active contour modelling. Then a Gaussian kernel function is used to extract the local region and defines its local region fitting energy function which approximates the image intensities on the two sides of the contour in the local region. Finally, the Split Bregman method is used to obtain a robust numerical solution and to generate the segmentation results. In our experiments, the proposed approach can obtain accurate segmentation results compared with some state-of-the-art approaches.

Automated detection and segmentation of cell nuclei is an essential step in breast cancer histopathology, so that there is improved accuracy, speed, level of automation and adaptability to new application. The goal of this paper is to develop efficient and accurate algorithms for detecting and segmenting cell nuclei in 2-D histological images. In this paper we will implement the utility of our nuclear segmentation algorithm in accurate extraction of nuclear features for automated grading of (a) breast cancer, and (b) distinguishing between cancerous and benign breast histology specimens. In order to address the issue the scheme integrates image information across three different scales: (1) low level information based on pixel values, (2) high-level information based on relationships between pixels for object detection, and(3)domain-specific information based on relationships between histological structures. Low-level information is utilized by a Bayesian Classifier to generate likelihood that each pixel belongs to an object of interest. High-level information is extracted in two ways: (i) by a level-set algorithm, where a contour is evolved in the likelihood scenes generated by the Bayesian classifier to identify object boundaries, and (ii) by a template matching algorithm, where shape models are used to identify glands and nuclei from the low-level likelihood scenes. Structural constraints are imposed via domain specific knowledge in order to verify whether the detected objects do indeed belong to structures of interest. The efficiency of our segmentation algorithm is evaluated by comparing breast cancer grading and benign vs. cancer discrimination accuracies with corresponding accuracies obtained via manual detection and segmentation of glands and nuclei.

GeDa: Improving training data with large language models for Aspect Sentiment Triplet Extraction

Philadelphia chromosome-positive (Ph+) acute lymphoblastic leukemia (ALL) may include the lymphoid blast crisis of chronic myeloid leukemia (CML-BC). We applied fluorescence in situ hybridization (FISH) of the BCR-ABL fusion gene to peripheral blood and/or bone marrow smears to determine whether the fusion was restricted to mononuclear cell nuclei or if segmented cell nuclei representing mature neutrophils also carried the fusion (Seg-FISH). Among 20 patients with Ph+ ALL without a prior diagnosis of CML, 9 were Seg-FISH+ and 11 were Seg-FISH-. Seg-FISH+ cases were characterized by a higher rate of p210-type BCR-ABL transcripts, higher white cell and blast counts, and a higher rate of myeloid and T-lymphoid antigen expression than Seg-FISH- cases, in addition to ‘major route' cytogenetic abnormalities associated with CML-BC. Eighteen patients were treated with tyrosine kinase inhibitors (TKIs) either alone or in combination with multiagent chemotherapy, and 7 underwent allogeneic hematopoietic stem cell transplantation. Progression-free and overall survivals were greater in the Seg-FISH+ group than in the Seg-FISH- group. These results suggest that the Seg-FISH+ group represents lymphoid CML-BC that occurs de novo, while the Seg-FISH- represents Ph+ ALL in the strict sense, and the two groups are associated with survival when treated with TKIs or TKI-combined therapy.

Automated cell nuclei determination of stained images is of uttermost importance for diagnosis. In this work, we have proposed a novel efficient and accurate image segmentation technique for densely clustered overlapping cell nuclei. Firstly, we have extracted the cell body (foreground) from the background using global thresholding followed by local thresholding. Then, we have employed the fusion of seeded region growing technique and level-set algorithm. The initial seed points need to be selected accurately and precisely in order to generate appropriate outcomes from region growing framework. Initial contours for level-set evolution relies heavily on an output of this adaptive region growing approach and some morphological operations. Finally, Global Gaussian distribution with several means and variances is employed in an enhanced edge-based level-set approach for precise nuclei segmentation. We have performed our analysis on Nissl stained EMF exposed, and SHAM exposed cell images. The proposed framework is very much capable of extracting the cell nuclei from stained cell images. Experimental outcomes reveal that our approach has out-performed existing state of art techniques for cell nuclei extraction and segmentation.

Simple SummaryLeukemia is a type of cancer that affects white blood cells and can lead to serious health problems and death. Diagnosing leukemia is currently performed through a combination of morphological and molecular criteria, which can be time-consuming and, in some cases, unreliable. Computer-aided diagnosis (CAD) systems based on deep-learning methods have shown promise in improving diagnosis efficiency and accuracy. However, these systems suffer from the “black box problem,” which can lead to incorrect classifications. This research proposes a novel deep-learning approach with visual explainability for ALL diagnoses based on robust white blood cell nuclei segmentation to provide a highly reliable and interpretable classification. The aim is to develop a CAD system that can assist physicians in diagnosing leukemia more efficiently, potentially improving patient outcomes. The findings of this research may impact the research community by providing a more reliable and explainable deep-learning-based approach to blood disorder diagnosis.Leukemia is a significant health challenge, with high incidence and mortality rates. Computer-aided diagnosis (CAD) has emerged as a promising approach. However, deep-learning methods suffer from the “black box problem”, leading to unreliable diagnoses. This research proposes an Explainable AI (XAI) Leukemia classification method that addresses this issue by incorporating a robust White Blood Cell (WBC) nuclei segmentation as a hard attention mechanism. The segmentation of WBC is achieved by combining image processing and U-Net techniques, resulting in improved overall performance. The segmented images are fed into modified ResNet-50 models, where the MLP classifier, activation functions, and training scheme have been tested for leukemia subtype classification. Additionally, we add visual explainability and feature space analysis techniques to offer an interpretable classification. Our segmentation algorithm achieves an Intersection over Union (IoU) of 0.91, in six databases. Furthermore, the deep-learning classifier achieves an accuracy of 99.9% on testing. The Grad CAM methods and clustering space analysis confirm improved network focus when classifying segmented images compared to non-segmented images. Overall, the proposed visual explainable CAD system has the potential to assist physicians in diagnosing leukemia and improving patient outcomes.

To improve the accuracy of classification with a small amount of training data, this paper presents a self-learning approach that defines class labels from sequential patterns using a series of past land-cover maps. By stacking past land-cover maps, unique sequence rule information from sequential change patterns of land-covers is first generated, and a rule-based class label image is then prepared for a given time. After the most informative pixels with high uncertainty are selected from the initial classification, rule-based class labels are assigned to the selected pixels. These newly labeled pixels are added to training data, which then undergo an iterative classification process until a stopping criterion is reached. Time-series MODIS NDVI data sets and cropland data layers (CDLs) from the past five years are used for the classification of various crop types in Kansas. From the experiment results, it is found that once the rule-based labels are derived from past CDLs, the labeled informative pixels could be properly defined without analyst intervention. Regardless of different combinations of past CDLs, adding these labeled informative pixels to training data increased classification accuracy and the maximum improvement of 8.34 percentage points in overall accuracy was achieved when using three CDLs, compared to the initial classification result using a small amount of training data. Using more than three consecutive CDLs showed slightly better classification accuracy than when using two CDLs (minimum and maximum increases were 1.56 and 2.82 percentage points, respectively). From a practical viewpoint, using three or four CDLs was the best choice for this study area. Based on these experiment results, the presented approach could be applied effectively to areas with insufficient training data but access to past land-cover maps. However, further consideration should be given to select the optimal number of past land-cover maps and reduce the impact of errors of rule-based labels.