Comparative Study on Automated Cell Nuclei Segmentation Methods for Cytology Pleural Effusion Images

  title={Comparative Study on Automated Cell Nuclei Segmentation Methods for Cytology Pleural Effusion Images},
  author={Khin Yadanar Win and Somsak Choomchuay and Kazuhiko Hamamoto and Manasanan Raveesunthornkiat},
  journal={Journal of Healthcare Engineering},
Automated cell nuclei segmentation is the most crucial step toward the implementation of a computer-aided diagnosis system for cancer cells. Studies on the automated analysis of cytology pleural effusion images are few because of the lack of reliable cell nuclei segmentation methods. Therefore, this paper presents a comparative study of twelve nuclei segmentation methods for cytology pleural effusion images. Each method involves three main steps: preprocessing, segmentation, and postprocessing… 

Computer Aided Diagnosis System for Detection of Cancer Cells on Cytological Pleural Effusion Images

A novel Computer Aided Diagnosis (CAD) system for the detection of cancer cells in cytological pleural effusion (CPE) images and a novel hybrid feature selection method based on simulated annealing combined with an artificial neural network was developed to select the most discriminant and biologically interpretable features.

Cytology Image Analysis Techniques Toward Automation

This survey focuses on image analysis techniques paving the way to automation in cytology, taking a short tour of 17 types of solid organ cytology to explore various segmentation and/or classification techniques that evolved during the past three decades to automate cytology image analysis.

A Deep Learning Model For The Automatic Detection Of Malignancy In Effusion Cytology

Architecture U-Net is used to learn the malignant and benign cells from the images and to detect the images that contain malignant cells, and the model can be used as a screening tool and has a malignant cell detection rate of 0.96 with a low false alarm rate.

A Survey for Cervical Cytopathology Image Analysis Using Deep Learning

This survey provides a comprehensive study of the state of the art approaches based on deep learning for the analysis of cervical cytology images and introduces deep learning and its simplified architectures that have been used in this field.

An Ensemble Learning and Slice Fusion Strategy for Three-Dimensional Nuclei Instance Segmentation

An ensemble learning and slice fusion strategy for 3D nuclei instance segmentation that is practical and effective, that does not need any ground truth annotations for training and can inference on any large size volumes.

Convolutional Blur Attention Network for Cell Nuclei Segmentation

The proposed convolutional blur attention (CBA) network consists of downsampling and upsampling procedures, and has the best performance, the AJI indicator on the DSB dataset and MoNuSeg is 0.8429, 0.7985, respectively.

An Efficient Deep Neural Framework for Nucleus Semantic Segmentation with Enhanced U-Net

A deep learning network is gathered which detects and parts the cell microscopy image and is implemented U-Net for the semantic segmentation of nucleus.

Ground Truth Annotator and 3D Dataset Generator for Validation of Nuclei Segmentation Programs

  • Tzu-Ching WuXu WangD. Umulis
  • Biology, Computer Science
    2019 12th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI)
  • 2019
This work provides a benchmarking dataset generator and a segmentation validation tool to improve segmentation accuracy and robustness, and to provide large databases of manually curated and segmented images.

WaveletSEG: Automatic wavelet-based 3D nuclei segmentation and analysis for multicellular embryo quantification

A size-dependent wavelet-based segmentation method is developed that provides robust segmentation without any preprocessing, filtering or fine-tuning steps, and is robust to the signal-to-noise ratio (SNR).



Automated segmentation of cell nuclei in cytology pleural fluid images using OTSU thresholding

A simple method that is capable to segment the nuclei of the variety of cells from microscopic cytology pleural fluid images is proposed and the results are very promising.

Automated segmentation and isolation of touching cell nuclei in cytopathology smear images of pleural effusion using distance transform watershed method

A watershed-based method capable to segment the nuclei of the variety of cells from cytology pleural fluid smear images is proposed that is relatively simple, and the results are very promising.

Automatic Nuclei Segmentation in H&E Stained Breast Cancer Histopathology Images

An automated nuclei segmentation method that works with hematoxylin and eosin stained breast cancer histopathology images, which represent regions of whole digital slides, is developed.

Automatic segmentation of cell nuclei in Feulgen‐stained histological sections of prostate cancer and quantitative evaluation of segmentation results

The results from the automatic method were not significantly different from the ground truth provided by manual segmentation, which opens the possibility for large‐scale nuclear analysis based on automatic segmentation of nuclei in Feulgen‐stained histological sections of prostate cancer.

Nucleus and cytoplasm segmentation in microscopic images using K-means clustering and region growing

A method based on K-means clustering and region growing is proposed in order to detect leukocytes from a blood smear microscopic image and segment its components, the nucleus and the cytoplasm.

Detecting and segmenting cell nuclei in two-dimensional microscopy images

Quantitative analysis showed that the proposed unsupervised method for cell nuclei detection and segmentation in two-dimensional microscopy images with noisy background has the potential to be used in clinic settings.

Automated Segmentation of Nuclei in Breast Cancer Histopathology Images

This paper proposes a novel segmentation algorithm for detecting individual nuclei from Hematoxylin and Eosin (H&E) stained breast histopathology images with optimal performance on the highly complex images presented in this paper.