RETRACTED ARTICLE: Three factor nonnegative matrix factorization based HE stain unmixing in histopathological images

Sikkandar, Mohamed Yacin; Jayasankar, T.; Kavitha, K. R.; Prakash, N. B.; Sudharsan, N. M.; Hemalakshmi, G. R.

doi:10.1007/s12652-020-02265-8

Cited by 11 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the state of the art, there are examples of SU in medical image processing for classification and detection tasks. In [ 14 ], two approaches for the classification of craniotomy HS images were presented for the detection of type IV GB, while [ 15 ] uses SU to study H&E for histopathological analysis of cellular tissues. Finally, [ 16 ] describes a method for the analysis of Raman microspectroscopy data by SU.…”

Section: Introductionmentioning

confidence: 99%

Hybrid brain tumor classification of histopathology hyperspectral images by linear unmixing and an ensemble of deep neural networks

Cruz‐Guerrero,

Campos‐Delgado,

Mejía‐Rodríguez

et al. 2024

Healthcare Tech Letters

View full text Add to dashboard Cite

Hyperspectral imaging has demonstrated its potential to provide correlated spatial and spectral information of a sample by a non‐contact and non‐invasive technology. In the medical field, especially in histopathology, HSI has been applied for the classification and identification of diseased tissue and for the characterization of its morphological properties. In this work, we propose a hybrid scheme to classify non‐tumor and tumor histological brain samples by hyperspectral imaging. The proposed approach is based on the identification of characteristic components in a hyperspectral image by linear unmixing, as a features engineering step, and the subsequent classification by a deep learning approach. For this last step, an ensemble of deep neural networks is evaluated by a cross‐validation scheme on an augmented dataset and a transfer learning scheme. The proposed method can classify histological brain samples with an average accuracy of 88%, and reduced variability, computational cost, and inference times, which presents an advantage over methods in the state‐of‐the‐art. Hence, the work demonstrates the potential of hybrid classification methodologies to achieve robust and reliable results by combining linear unmixing for features extraction and deep learning for classification.

show abstract

Section: Introductionmentioning

confidence: 99%

Hybrid brain tumor classification of histopathology hyperspectral images by linear unmixing and an ensemble of deep neural networks

Cruz‐Guerrero,

Campos‐Delgado,

Mejía‐Rodríguez

et al. 2024

Healthcare Tech Letters

View full text Add to dashboard Cite

show abstract

“…Encryption-Then-Compression algorithm was developed [14]. The block based image compression and encryption was developed for secured image communication [15][16][17]. After having the detailed study about the encryption algorithm, we have analyzed the performance of block based perceptual encryption and the AES algorithm with arithmetic compression techniques for the bioimage.…”

Section: Introductionmentioning

confidence: 99%

An Analysis on Image Encryption for Secured Transmission of Biomedical Applications

al¹

2021

ITII

View full text Add to dashboard Cite

Digital images are very popularly used for communications over the internet. Embedded information in the digital image has to be securely transmitted without any modification in the image. The biomedical telemedicine gains significant importance in information transmission and with increasing popularity with Tele-ophthalmology, requirement of medical data confidentiality and privacy also increases for data storage and secure transformation. The objective is to analyse the bioimage encryption algorithms which provides security and privacy to the bioimages. In this paper retinal fundus image online available dataset have used. The proposed work is analysed by considering, three performance parameters such as PSNR, MSE and CR. The two different encryption algorithms namely block-based perceptual encryption (BBPE) and advanced encryption standard (AES) algorithm along with arithmetic compression have tested . The proposed work results tested on standard test images and retinal fundus images shows that the BBPE method attains PSNR of 27.58db , MSE of 3.20e+03 and CR of 4.27 for standard test images and 13.35db, 1.4046e+04 and 7.28 respectively for medical HRF images. The BBPE algorithm can be used in tele-ophthalmology and telemedicine applications.

show abstract

Liver Tumor Detection Using CNN

Vijayalakshmi¹,

Kavitha²,

Tamilarasi³

et al. 2022

Inventive Systems and Control

View full text Add to dashboard Cite

RETRACTED ARTICLE: Three factor nonnegative matrix factorization based HE stain unmixing in histopathological images

Cited by 11 publications

References 27 publications

Hybrid brain tumor classification of histopathology hyperspectral images by linear unmixing and an ensemble of deep neural networks

Hybrid brain tumor classification of histopathology hyperspectral images by linear unmixing and an ensemble of deep neural networks

An Analysis on Image Encryption for Secured Transmission of Biomedical Applications

Liver Tumor Detection Using CNN

Contact Info

Product

Resources

About