1
|
Mahbod A, Dorffner G, Ellinger I, Woitek R, Hatamikia S. Improving generalization capability of deep learning-based nuclei instance segmentation by non-deterministic train time and deterministic test time stain normalization. Comput Struct Biotechnol J 2024; 23:669-678. [PMID: 38292472 PMCID: PMC10825317 DOI: 10.1016/j.csbj.2023.12.042] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2023] [Revised: 12/26/2023] [Accepted: 12/26/2023] [Indexed: 02/01/2024] Open
Abstract
With the advent of digital pathology and microscopic systems that can scan and save whole slide histological images automatically, there is a growing trend to use computerized methods to analyze acquired images. Among different histopathological image analysis tasks, nuclei instance segmentation plays a fundamental role in a wide range of clinical and research applications. While many semi- and fully-automatic computerized methods have been proposed for nuclei instance segmentation, deep learning (DL)-based approaches have been shown to deliver the best performances. However, the performance of such approaches usually degrades when tested on unseen datasets. In this work, we propose a novel method to improve the generalization capability of a DL-based automatic segmentation approach. Besides utilizing one of the state-of-the-art DL-based models as a baseline, our method incorporates non-deterministic train time and deterministic test time stain normalization, and ensembling to boost the segmentation performance. We trained the model with one single training set and evaluated its segmentation performance on seven test datasets. Our results show that the proposed method provides up to 4.9%, 5.4%, and 5.9% better average performance in segmenting nuclei based on Dice score, aggregated Jaccard index, and panoptic quality score, respectively, compared to the baseline segmentation model.
Collapse
Affiliation(s)
- Amirreza Mahbod
- Research Center for Medical Image Analysis and Artificial Intelligence, Department of Medicine, Danube Private University, Krems an der Donau, Austria
| | - Georg Dorffner
- Institute of Artificial Intelligence, Medical University of Vienna, Vienna, Austria
| | - Isabella Ellinger
- Institute for Pathophysiology and Allergy Research, Medical University of Vienna, Vienna, Austria
| | - Ramona Woitek
- Research Center for Medical Image Analysis and Artificial Intelligence, Department of Medicine, Danube Private University, Krems an der Donau, Austria
| | - Sepideh Hatamikia
- Research Center for Medical Image Analysis and Artificial Intelligence, Department of Medicine, Danube Private University, Krems an der Donau, Austria
- Austrian Center for Medical Innovation and Technology, Wiener Neustadt, Austria
| |
Collapse
|
2
|
Zhang J, Lu H, Jiang Y, Ma Y, Deng L. ncRNA Coding Potential Prediction Using BiLSTM and Transformer Encoder-Based Model. J Chem Inf Model 2024; 64:6712-6722. [PMID: 39120528 DOI: 10.1021/acs.jcim.4c01097] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 08/10/2024]
Abstract
Many noncoding RNAs (ncRNAs) have been identified, and many of them play vital roles in various biological processes, including gene expression regulation, epigenetic regulation, transcription, and control. Recently, a few observations revealed that ncRNAs are translated into functional peptides. Moreover, many computational methods have been developed to predict the coding potential of these transcripts, which contributes to a deeper investigation of their functions. However, most of these are used to distinguish ncRNAs and mRNAs. It is important to develop a highly accurate computational tool for identifying the coding potential of ncRNAs, thereby contributing to the discovery of novel peptides. In this Article, we propose a novel BiLSTM And Transformer encoder-based model (nBAT) with intrinsic features encoded for ncRNA coding potential prediction. In nBAT, we introduce a learnable position encoding mechanism to better obtain the embeddings of the ncRNA sequence. Moreover, we extract 43 intrinsic features from different perspectives and encode these features into the Transformer encoder by calculating their distances. Our performance comparisons show that nBAT achieves a superior performance than the state-of-the-art methods for coding potential prediction on different datasets. We also apply the method to new ncRNAs for identifying the coding potential, and the results further indicate the competitive performance of nBAT. We expect the method can be exploited as a useful tool for high-throughput coding potential prediction for ncRNAs.
Collapse
Affiliation(s)
- Jingpu Zhang
- School of Computer and Data Science, Henan University of Urban Construction, Pingdingshan 467000, China
| | - Hao Lu
- School of Computer and Data Science, Henan University of Urban Construction, Pingdingshan 467000, China
| | - Ying Jiang
- School of Computer Science and Engineering, Central South University, Changsha 410018, China
| | - Yuanyuan Ma
- School of Computer Engineering, Hubei University of Arts and Science, Xiangyang 441053, China
| | - Lei Deng
- School of Computer Science and Engineering, Central South University, Changsha 410018, China
| |
Collapse
|
3
|
Özcan ŞN, Uyar T, Karayeğen G. Comprehensive data analysis of white blood cells with classification and segmentation by using deep learning approaches. Cytometry A 2024; 105:501-520. [PMID: 38563259 DOI: 10.1002/cyto.a.24839] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2023] [Revised: 03/14/2024] [Accepted: 03/25/2024] [Indexed: 04/04/2024]
Abstract
Deep learning approaches have frequently been used in the classification and segmentation of human peripheral blood cells. The common feature of previous studies was that they used more than one dataset, but used them separately. No study has been found that combines more than two datasets to use together. In classification, five types of white blood cells were identified by using a mixture of four different datasets. In segmentation, four types of white blood cells were determined, and three different neural networks, including CNN (Convolutional Neural Network), UNet and SegNet, were applied. The classification results of the presented study were compared with those of related studies. The balanced accuracy was 98.03%, and the test accuracy of the train-independent dataset was determined to be 97.27%. For segmentation, accuracy rates of 98.9% for train-dependent dataset and 92.82% for train-independent dataset for the proposed CNN were obtained in both nucleus and cytoplasm detection. In the presented study, the proposed method showed that it could detect white blood cells from a train-independent dataset with high accuracy. Additionally, it is promising as a diagnostic tool that can be used in the clinical field, with successful results in classification and segmentation.
Collapse
Affiliation(s)
- Şeyma Nur Özcan
- Biomedical Engineering Department, Başkent University, Ankara, Turkey
| | - Tansel Uyar
- Biomedical Engineering Department, Başkent University, Ankara, Turkey
| | - Gökay Karayeğen
- Biomedical Equipment Technology, Vocational School of Technical Sciences, Başkent University, Ankara, Turkey
| |
Collapse
|
4
|
Erozan A, Lösel PD, Heuveline V, Weinhardt V. Automated 3D cytoplasm segmentation in soft X-ray tomography. iScience 2024; 27:109856. [PMID: 38784019 PMCID: PMC11112332 DOI: 10.1016/j.isci.2024.109856] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2023] [Revised: 03/22/2024] [Accepted: 04/27/2024] [Indexed: 05/25/2024] Open
Abstract
Cells' structure is key to understanding cellular function, diagnostics, and therapy development. Soft X-ray tomography (SXT) is a unique tool to image cellular structure without fixation or labeling at high spatial resolution and throughput. Fast acquisition times increase demand for accelerated image analysis, like segmentation. Currently, segmenting cellular structures is done manually and is a major bottleneck in the SXT data analysis. This paper introduces ACSeg, an automated 3D cytoplasm segmentation model. ACSeg is generated using semi-automated labels and 3D U-Net and is trained on 43 SXT tomograms of immune T cells, rapidly converging to high-accuracy segmentation, therefore reducing time and labor. Furthermore, adding only 6 SXT tomograms of other cell types diversifies the model, showing potential for optimal experimental design. ACSeg successfully segmented unseen tomograms and is published on Biomedisa, enabling high-throughput analysis of cell volume and structure of cytoplasm in diverse cell types.
Collapse
Affiliation(s)
- Ayse Erozan
- Centre for Organismal Studies, Heidelberg University, Heidelberg, Germany
- Engineering Mathematics and Computing Lab, Interdisciplinary Center for Scientific Computing, Heidelberg University, Heidelberg, Germany
- Data Mining and Uncertainty Quantification, Heidelberg Institute for Theoretical Studies, Heidelberg, Germany
| | - Philipp D. Lösel
- Engineering Mathematics and Computing Lab, Interdisciplinary Center for Scientific Computing, Heidelberg University, Heidelberg, Germany
- Data Mining and Uncertainty Quantification, Heidelberg Institute for Theoretical Studies, Heidelberg, Germany
- Department of Materials Physics Research School of Physics, The Australian National University, Acton ACT, Australia
| | - Vincent Heuveline
- Engineering Mathematics and Computing Lab, Interdisciplinary Center for Scientific Computing, Heidelberg University, Heidelberg, Germany
- Data Mining and Uncertainty Quantification, Heidelberg Institute for Theoretical Studies, Heidelberg, Germany
| | - Venera Weinhardt
- Centre for Organismal Studies, Heidelberg University, Heidelberg, Germany
- Molecular Biophysics and Integrated Bioimaging Division, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
| |
Collapse
|
5
|
Ascencio-Piña C, García-De-Lira S, Cuevas E, Pérez M. Image segmentation with Cellular Automata. Heliyon 2024; 10:e31152. [PMID: 38784542 PMCID: PMC11112328 DOI: 10.1016/j.heliyon.2024.e31152] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2024] [Revised: 05/07/2024] [Accepted: 05/10/2024] [Indexed: 05/25/2024] Open
Abstract
Image segmentation is a computer vision technique that involves dividing an image into distinct and meaningful regions or segments. The objective was to partition the image into areas that share similar visual characteristics. Noise and undesirable artifacts introduce inconsistencies and irregularities in image data. These inconsistencies severely affect the ability of most segmentation algorithms to distinguish between true image features, leading to less reliable and lower-quality results. Cellular Automata (CA) is a computational concept that consists of a grid of cells, each of which can be in a finite number of states. These cells evolve over discrete time steps based on a set of predefined rules that dictate how a cell's state changes according to its own state and the states of its neighboring cells. In this paper, a new segmentation approach based on the CA model was introduced. The proposed approach consisted of three phases. In the initial two phases of the process, the primary objective was to eliminate noise and undesirable artifacts that can interfere with the identification of regions exhibiting similar visual characteristics. To achieve this, a set of rules is designed to modify the state value of each cell or pixel based on the states of its neighboring elements. In the third phase, each element is assigned a state that is chosen from a set of predefined states. These states directly represent the final segmentation values for the corresponding elements. The proposed method was evaluated using different images, considering important quality indices. The experimental results indicated that the proposed approach produces better-segmented images in terms of quality and robustness.
Collapse
Affiliation(s)
- Cesar Ascencio-Piña
- Departamento de Computación, Universidad de Guadalajara, CUCEI, Av. Revolución 1500, Guadalajara, Jal, Mexico
| | - Sonia García-De-Lira
- Departamento de Computación, Universidad de Guadalajara, CUCEI, Av. Revolución 1500, Guadalajara, Jal, Mexico
| | - Erik Cuevas
- Departamento de Computación, Universidad de Guadalajara, CUCEI, Av. Revolución 1500, Guadalajara, Jal, Mexico
| | - Marco Pérez
- Departamento de Computación, Universidad de Guadalajara, CUCEI, Av. Revolución 1500, Guadalajara, Jal, Mexico
| |
Collapse
|
6
|
Wu L, Chen A, Salama P, Winfree S, Dunn KW, Delp EJ. NISNet3D: three-dimensional nuclear synthesis and instance segmentation for fluorescence microscopy images. Sci Rep 2023; 13:9533. [PMID: 37308499 PMCID: PMC10261124 DOI: 10.1038/s41598-023-36243-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2023] [Accepted: 05/31/2023] [Indexed: 06/14/2023] Open
Abstract
The primary step in tissue cytometry is the automated distinction of individual cells (segmentation). Since cell borders are seldom labeled, cells are generally segmented by their nuclei. While tools have been developed for segmenting nuclei in two dimensions, segmentation of nuclei in three-dimensional volumes remains a challenging task. The lack of effective methods for three-dimensional segmentation represents a bottleneck in the realization of the potential of tissue cytometry, particularly as methods of tissue clearing present the opportunity to characterize entire organs. Methods based on deep learning have shown enormous promise, but their implementation is hampered by the need for large amounts of manually annotated training data. In this paper, we describe 3D Nuclei Instance Segmentation Network (NISNet3D) that directly segments 3D volumes through the use of a modified 3D U-Net, 3D marker-controlled watershed transform, and a nuclei instance segmentation system for separating touching nuclei. NISNet3D is unique in that it provides accurate segmentation of even challenging image volumes using a network trained on large amounts of synthetic nuclei derived from relatively few annotated volumes, or on synthetic data obtained without annotated volumes. We present a quantitative comparison of results obtained from NISNet3D with results obtained from a variety of existing nuclei segmentation techniques. We also examine the performance of the methods when no ground truth is available and only synthetic volumes were used for training.
Collapse
Affiliation(s)
- Liming Wu
- Video and Image Processing Laboratory, School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, 47907, USA
| | - Alain Chen
- Video and Image Processing Laboratory, School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, 47907, USA
| | - Paul Salama
- Department of Electrical and Computer Engineering, Indiana University-Purdue University Indianapolis, Indianapolis, IN, 46202, USA
| | - Seth Winfree
- Department of Pathology and Microbiology, University of Nebraska Medical Center, Omaha, NE, 68198, USA
| | - Kenneth W Dunn
- School of Medicine, Indiana University, Indianapolis, IN, 46202, USA
| | - Edward J Delp
- Video and Image Processing Laboratory, School of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, 47907, USA.
| |
Collapse
|
7
|
Buyukcelik ON, Lapierre-Landry M, Kolluru C, Upadhye AR, Marshall DP, Pelot NA, Ludwig KA, Gustafson KJ, Wilson DL, Jenkins MW, Shoffstall AJ. Deep-learning segmentation of fascicles from microCT of the human vagus nerve. Front Neurosci 2023; 17:1169187. [PMID: 37332862 PMCID: PMC10275336 DOI: 10.3389/fnins.2023.1169187] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2023] [Accepted: 04/12/2023] [Indexed: 06/20/2023] Open
Abstract
Introduction MicroCT of the three-dimensional fascicular organization of the human vagus nerve provides essential data to inform basic anatomy as well as the development and optimization of neuromodulation therapies. To process the images into usable formats for subsequent analysis and computational modeling, the fascicles must be segmented. Prior segmentations were completed manually due to the complex nature of the images, including variable contrast between tissue types and staining artifacts. Methods Here, we developed a U-Net convolutional neural network (CNN) to automate segmentation of fascicles in microCT of human vagus nerve. Results The U-Net segmentation of ~500 images spanning one cervical vagus nerve was completed in 24 s, versus ~40 h for manual segmentation, i.e., nearly four orders of magnitude faster. The automated segmentations had a Dice coefficient of 0.87, a measure of pixel-wise accuracy, thus suggesting a rapid and accurate segmentation. While Dice coefficients are a commonly used metric to assess segmentation performance, we also adapted a metric to assess fascicle-wise detection accuracy, which showed that our network accurately detects the majority of fascicles, but may under-detect smaller fascicles. Discussion This network and the associated performance metrics set a benchmark, using a standard U-Net CNN, for the application of deep-learning algorithms to segment fascicles from microCT images. The process may be further optimized by refining tissue staining methods, modifying network architecture, and expanding the ground-truth training data. The resulting three-dimensional segmentations of the human vagus nerve will provide unprecedented accuracy to define nerve morphology in computational models for the analysis and design of neuromodulation therapies.
Collapse
Affiliation(s)
- Ozge N. Buyukcelik
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States
- Advanced Platform Technologies Center, Louis Stokes Cleveland VA Medical Center, Cleveland, OH, United States
| | - Maryse Lapierre-Landry
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States
| | - Chaitanya Kolluru
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States
| | - Aniruddha R. Upadhye
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States
- Advanced Platform Technologies Center, Louis Stokes Cleveland VA Medical Center, Cleveland, OH, United States
| | - Daniel P. Marshall
- Department of Biomedical Engineering, Duke University, Durham, NC, United States
| | - Nicole A. Pelot
- Department of Biomedical Engineering, Duke University, Durham, NC, United States
| | - Kip A. Ludwig
- Department of Biomedical Engineering, University of Wisconsin Madison, Madison, WI, United States
- Department of Neurological Surgery, University of Wisconsin Madison, Madison, WI, United States
- Wisconsin Institute for Translational Neuroengineering, Madison, WI, United States
| | - Kenneth J. Gustafson
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States
- Functional Electrical Stimulation Center, Louis Stokes Cleveland VA Medical Center, Cleveland, OH, United States
| | - David L. Wilson
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States
| | - Michael W. Jenkins
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States
- Department of Pediatrics, School of Medicine, Case Western Reserve University, Cleveland, OH, United States
| | - Andrew J. Shoffstall
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, United States
- Advanced Platform Technologies Center, Louis Stokes Cleveland VA Medical Center, Cleveland, OH, United States
| |
Collapse
|