Interpretable pap-smear image retrieval for cervical cancer detection with rotation invariance mask generation deep hashing

Özbay, Erdal; Özbay, Feyza Altunbey

doi:10.1016/j.compbiomed.2023.106574

Cited by 19 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ozbay, E., and zbay, F.A et al. ( 22 ) developed a method for tumor image retrieval in the cervical cavity using hash coding and a Convolutional Neural Network (CNN). They proposed a deep hashing technique incorporating mask synthesis and rotation invariance to detect cervical cancer.…”

Section: Related Workmentioning

confidence: 99%

HO-SsNF: heap optimizer-based self-systematized neural fuzzy approach for cervical cancer classification using pap smear images

Shanmugam,

KVN,

Radhabai

et al. 2024

Front. Oncol.

View full text Add to dashboard Cite

Cervical cancer is a significant concern for women, necessitating early detection and precise treatment. Conventional cytological methods often fall short in early diagnosis. The proposed innovative Heap Optimizer-based Self-Systematized Neural Fuzzy (HO-SsNF) method offers a viable solution. It utilizes HO-based segmentation, extracting features via Gray-Level Co-Occurrence Matrix (GLCM) and Local Binary Pattern (LBP). The proposed SsNF-based classifier achieves an impressive 99.6% accuracy in classifying cervical cancer cells, using the Herlev Pap Smear database. Comparative analyses underscore its superiority, establishing it as a valuable tool for precise cervical cancer detection. This algorithm has been seamlessly integrated into cervical cancer diagnosis centers, accessible through smartphone applications, with minimal resource demands. The resulting insights provide a foundation for advancing cancer prevention methods.

show abstract

Section: Related Workmentioning

confidence: 99%

HO-SsNF: heap optimizer-based self-systematized neural fuzzy approach for cervical cancer classification using pap smear images

Shanmugam,

KVN,

Radhabai

et al. 2024

Front. Oncol.

View full text Add to dashboard Cite

show abstract

“…Further, the use of CAE decreases the data dimensionality for processing with the involvement of softmax layer for training. In [13], an approach for the retrieval of CC images using hash coding with CNN was implemented. A sensitive deep hashing technique that combines rotation invariance and interpretable mask generation is developed for CC recognition.…”

Section: Related Workmentioning

confidence: 99%

Multi-Class Segmentation with Deep Learning based Pap Smear Image Analysis for Cervical Cancer Detection and Classification Model

C. Suguna, Dr. S. P. Balamurugan

2023

tjjpt

View full text Add to dashboard Cite

Cervical cancer (CC) is a significant global health issue, but earlier diagnosis and accurate detection could considerably enhance treatment outcomes and reduce mortality rates. Pap smear test is a popular screening technique for CC. But the manual interpretation of Pap smear images can be subjective and error-prone. Deep learning (DL) technique assists to automate and enhance the performance of CC detection on Pap smear images. DL model continuously enhances with more diverse and larger datasets, potentially resulting in even more reliable and more accurate diagnoses. In this aspect, this study introduces an Automated Deep Learning based Pap Smear Image Analysis for Cervical Cancer Detection and Classification (ADLPSIA-CCD) method. The objective of the ADLPSIA-CCD technique is to utilize DL models for the segmentation and classification of Pap smear images for CC diagnosis. In the presented ADLPSIA-CCD method, the initial stage of image preprocessing takes place in two levels such as image sharpening using Gaussian blur and contrast enhancement. In addition, the ADLPSIA-CCD technique exploits U-Net based image segmentation process with EfficientNetB3 as a backbone network. Next, radiomics feature extraction process takes place where the features in every segmented class are extracted separately. Finally,Conv-Recurrent Hopfield Neural Network (CRHNN) model is exploited for the classification of CC. Notably, the CRHNN model trains the segmented class features separately. The simulation outcome of the ADLPSIA-CCD algorithm is tested against a benchmark dataset. The comprehensive result analysis showed the superior performance of the ADLPSIA-CCD technique on CC detection.

show abstract

“…Over the last three decades, several natural phenomena have been used to formulate new mathematical generalizations for solving optimization problems including medical imaging 1 – 3 , robotics, business management, mathematical science 4 , 5 , segmentation 6 – 10 , clustering 11 , feature selection 12 – 16 , among others 17 – 19 . These algorithms are used because of their simple implementation and low computational complexity.…”

Section: Introductionmentioning

confidence: 99%

A hybrid swarm intelligence algorithm for region-based image fusion

Salgotra,

Lamba,

Talwar

et al. 2024

Sci Rep

View full text Add to dashboard Cite

This paper proposes a novel multi-hybrid algorithm named DHPN, using the best-known properties of dwarf mongoose algorithm (DMA), honey badger algorithm (HBA), prairie dog optimizer (PDO), cuckoo search (CS), grey wolf optimizer (GWO) and naked mole rat algorithm (NMRA). It follows an iterative division for extensive exploration and incorporates major parametric enhancements for improved exploitation operation. To counter the local optima problems, a stagnation phase using CS and GWO is added. Six new inertia weight operators have been analyzed to adapt algorithmic parameters, and the best combination of these parameters has been found. An analysis of the suitability of DHPN towards population variations and higher dimensions has been performed. For performance evaluation, the CEC 2005 and CEC 2019 benchmark data sets have been used. A comparison has been performed with differential evolution with active archive (JADE), self-adaptive DE (SaDE), success history based DE (SHADE), LSHADE-SPACMA, extended GWO (GWO-E), jDE100, and others. The DHPN algorithm is also used to solve the image fusion problem for four fusion quality metrics, namely, edge-based similarity index ($$Q^{AB/F}$$ Q A B / F ), sum of correlation difference (SCD), structural similarity index measure (SSIM), and artifact measure ($$N^{AB/F}$$ N A B / F ). The average $$Q^{AB/F} = 0.765508$$ Q A B / F = 0.765508 , $$SCD = 1.63185$$ S C D = 1.63185 , $$SSIM = 0.726317$$ S S I M = 0.726317 , and $$N^{AB/F} = 0.006617$$ N A B / F = 0.006617 shows the best combination of results obtained by DHPN with respect to the existing algorithms such as DCH, CBF, GTF, JSR and others. Experimental and statistical Wilcoxon’s and Friedman’s tests show that the proposed DHPN algorithm performs significantly better in comparison to the other algorithms under test.

show abstract

Interpretable pap-smear image retrieval for cervical cancer detection with rotation invariance mask generation deep hashing

Cited by 19 publications

References 37 publications

HO-SsNF: heap optimizer-based self-systematized neural fuzzy approach for cervical cancer classification using pap smear images

HO-SsNF: heap optimizer-based self-systematized neural fuzzy approach for cervical cancer classification using pap smear images

Multi-Class Segmentation with Deep Learning based Pap Smear Image Analysis for Cervical Cancer Detection and Classification Model

A hybrid swarm intelligence algorithm for region-based image fusion

Contact Info

Product

Resources

About