UTILIZING AUTOENCODERS FOR ANALYSIS AND CLASSIFICATION OF MICROSCOPIC IN SITU HYBRIDIZATION IMAGES

被引：0

作者：

Yanev, Aleksandar A. ^{[1
]}

Momcheva, Galina D. ^{[2
]}

Pavlov, Stoyan P. ^{[3
,4
]}

机构：

[1] High Sch Math Dr Petar Beron, Aleksander Stamboliyski Blvd, Varna 9000, Bulgaria

[2] Bulgarian Acad Sci, Inst Math & Informat, Akad Georgi Bonchev St,Bl 8, Sofia 1113, Bulgaria

[3] Med Univ Varna, Dept Anat & Cell Biol, 55 Prof Marin Drinov St, Varna 9002, Bulgaria

[4] Med Univ Prof Dr Paraskev Stoyanov, Adv Computat Bioimaging Res Inst, Varna, Bulgaria

来源：

COMPTES RENDUS DE L ACADEMIE BULGARE DES SCIENCES | 2023年 / 76卷 / 11期

关键词：

artificial neural networks; deep learning autoencoders; image analysis; unsupervised learning; fuzzy clustering;

D O I：

10.7546/CRABS.2023.11.11

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

Currently, analysis of microscopic In Situ Hybridization (ISH) images is done manually by experts. Precise evaluation and classification of such micro-scopic images can ease experts' work and reveal further insights about the data. In this work, we propose a deep-learning workflow to detect and classify areas of microscopic images with similar levels of gene expression. Analysis of the data is done by employing a type of ANN - Deep Learning Autoencoders - suitable for unsupervised learning. The model's performance is optimised by balancing the latent layers' length and complexity and fine-tuning hyperparameters. The results are validated by adapting the mean-squared error (MSE) metric and comparison to expert's evaluation. Reconstruction of the whole-scale micro-scopic images is used to summarise and visualise the results.

引用

页码：1733 / 1742

页数：10

共 50 条

[21] Feature representation and signal classification in fluorescence in-situ hybridization image analysis
Lerner, B
Clocksin, WF
Dhanjal, S
Hultén, MA
Bishop, CM
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-SYSTEMS AND HUMANS, 2001, 31 (06): : 655 - 665
[22] Hybridization of CNN with LBP for Classification of Melanoma Images
Iqbal, Saeed
Qureshi, Adnan N.
Mustafa, Ghulam
CMC-COMPUTERS MATERIALS & CONTINUA, 2022, 71 (03): : 4915 - 4939
[23] Scaling of Texture in Training Autoencoders for Classification of Histological Images of Colorectal Cancer
Pham, Tuan D.
ADVANCES IN NEURAL NETWORKS, PT II, 2017, 10262 : 524 - 532
[24] Classification of multi-spectral florescence in situ hybridization images with fuzzy clustering and multiscale feature selection
Wang, Yu-Ping
Dandpat, Kumar
2006 IEEE INTERNATIONAL WORKSHOP ON GENOMIC SIGNAL PROCESSING AND STATISTICS, 2006, : 95 - +
[25] Gender Classification In Face Images Based On Stacked-Autoencoders Method
Zhang, Hao
Zhu, Qing
2014 7TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING (CISP 2014), 2014, : 486 - 491
[26] Utilizing in situ hybridization to shed light on the genetics of cave adaptation
Luc, H.
Raczka, A.
Cao, C.
Warden, M.
Gross, J. B.
INTEGRATIVE AND COMPARATIVE BIOLOGY, 2018, 58 : E368 - E368
[27] Mueller polarimetric microscopic images analysis based classification of breast cancer cells
Xia, Longyu
Yao, Yue
Dong, Yang
Wang, Mingzhe
Ma, Hui
Ma, Lan
OPTICS COMMUNICATIONS, 2020, 475
[28] Hardwood Species Classification with Hyperspectral Microscopic Images
Zhao, Peng
Wang, Cheng-Kun
JOURNAL OF SPECTROSCOPY, 2019, 2019
[29] Cell classification in microscopic images for anemia detection
Ravisankar, Priyadharsini
Arul, Beulah
Elango, Srivarsha
ROMANIAN JOURNAL OF INFORMATION TECHNOLOGY AND AUTOMATIC CONTROL-REVISTA ROMANA DE INFORMATICA SI AUTOMATICA, 2024, 34 (01): : 7 - 12
[30] Fluorescence in situ hybridization (FISH) signal analysis using automated generated projection images
Wang, Xingwei
Chen, Xiaodong
Li, Yuhua
Liu, Hong
Li, Shibo
Zhang, Roy R.
Zheng, Bin
ANALYTICAL CELLULAR PATHOLOGY, 2012, 35 (5-6) : 395 - 405

← 1 2 3 4 5 →