Adaptive classification model based on artificial immune system for breast cancer detection

Jayaraman, S. Velappa; Casti, Paola; Mencattini, Arianna; Natale, Corrado Di; Martinelli, Eugenio

doi:10.1109/aisem.2015.7066842

Cited by 11 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…SAR automatic target detection methods are mainly divided into two types, i.e., template-based [27]- [29] and model-based methods [30]- [32]. The core of template-based method performs feature extraction and selection, which requires wide professional knowledge as the basis.…”

mentioning

confidence: 99%

CNN-Based Target Detection and Classification When Sparse SAR Image Dataset is Available

Deng

Yang

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Synthetic aperture radar (SAR) is an earth observation technology that can obtain high-resolution image in allweather and all-time conditions, and hence has been widely used in civil and military applications. SAR target detection and classification are the key processes for the detailed feature information extraction of the interested target. Compared with traditional matched filtering (MF) recovered result, sparse SAR image has lower sidelobes, noise and clutter. Thus it will theoretically has better performance in target detection and classification. In this paper, we propose a novel sparse SAR image based target detection and classification framework. This novel framework first obtains the sparse SAR image dataset by complex approximate message passing (CAMP), which is an L1norm regularization sparse imaging method. Different from other regularization recovery algorithms, CAMP can output not only a sparse solution, but also a non-sparse estimation of considered scene that well preserves the statistical characteristic of the image when protruding the target. Then we detect and classify the targets by using the convolutional neural network (CNN) based technologies from the sparse SAR image datasets constructed by the sparse and non-sparse solutions of CAMP, respectively. For clarify, these two kinds of sparse SAR image datasets are named as DSp and DNsp. Experimental results show that under standard operating conditions (SOC), the proposed framework can obtain 92.60% and 99.29% mAP on Faster RCNN and YOLOv3 by using the DNsp sparse SAR image dataset. Under extended operating conditions (EOC), the mAP value of Faster RCNN and YOLOv3 are 95.69% and 89.91% mAP, respectively. These values based on the DNsp dataset are much higher than the classified result based on the corresponding MF dataset. Index Terms-Sparse synthetic aperture radar (SAR) image, convolutional neural network (CNN), complex approximate message passing (CAMP), target detection and classification. I. INTRODUCTIONA S a kind of high-resolution earth observation technique, synthetic aperture radar (SAR) has all-time and allweather surveillance ability, and has been widely used in many military and civilian fields [1], [2]. Target detection and classification are the key fields of SAR applications,

show abstract

mentioning

confidence: 99%

CNN-Based Target Detection and Classification When Sparse SAR Image Dataset is Available

Deng

Yang

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The results showed that the A 2 INET system achieves better results compared to more conventional classifications. The classification accuracy rate in this system is 85% [9]. In the research presented by Pawar and Talbar (2016), the method of co-occurrence wavelet feature selection using the fuzzy system of co-occurrence wavelet feature selection using the fuzzy genetic system is proposed in the problem of classifying mammography images [10].…”

Section: Magenda Et Al (2015) Have Investigated the Classification Pe...mentioning

confidence: 99%

Application of a New Hybrid Machine Learning (Fuzzy-PSO) for Detection of Breast's Tumor

Rituraj¹

2023

Preprint

View full text Add to dashboard Cite

Breast cancer is the second leading cause of death after lung cancer. The only possible way to save patients' lives is early diagnosis of the disease; Because if this disease is diagnosed in the early stages and with a high level of accuracy, the chance of survival increases. Different fuzzy-based soft computing techniques have been proposed. In this research, the proposed fuzzy hybrid algorithm - particle swarm has been used to detect the type of breast tumors based on the analysis of features in mammography images. The proposed method in this study, the fuzzy hybrid algorithm - the proposed particle swarm algorithm, has a remarkable performance of 94.58% in breast cancer diagnosis. The results obtained from this study can be used for timely diagnosis and providing effective treatments for breast cancer

show abstract

“…Como resultado se obtiene un modelo con un acierto en la clasificación del 90% usando la base de datos de imágenes DDSM mini-MIAS, lo cual muestra mejores resultados en comparación con trabajos que usan los mismos datos como el propuesto en (Magna et al, 2015) con 85% y en (Casti et al, 2015) con 82%.…”

Section: Sistema Inmune Artificial (Ais)unclassified

Técnicas de inteligencia artificial utilizadas en el procesamiento de imágenes y su aplicación en el análisis de pavimentos

Reyes-Ortiz

Mejía

Useche-Castelblanco

2019

reveia

View full text Add to dashboard Cite

Debido al incremento en los costos de mantenimiento, rehabilitación y construcción de vías, estudiar las estructuras de pavimento para determinar su comportamiento y sus características mecánicas propias analizando la distribución y posición de sus partículas, se ha vuelto un campo de gran importancia en la ingeniería. Las nuevas herramientas de análisis buscan hacer este estudio más eficiente reduciendo su costo y tiempo de ejecución mediante el procesamiento digital de imágenes. El procesamiento digital tradicional está limitado en su sensibilidad ante perturbaciones externas que puedan modificar la imagen, por eso se han implementado diferentes técnicas de inteligencia artificial (IA) para optimizar los algoritmos. Este trabajo presenta una revisión de las diferentes aplicaciones de técnicas de IA recientes en el procesamiento de imágenes. Después se revisan los trabajos realizados específicamente con imágenes de pavimentos y se proponen posibles aplicaciones para implementar en este campo con inteligencia artificial

show abstract

Adaptive classification model based on artificial immune system for breast cancer detection

Cited by 11 publications

References 7 publications

CNN-Based Target Detection and Classification When Sparse SAR Image Dataset is Available

CNN-Based Target Detection and Classification When Sparse SAR Image Dataset is Available

Application of a New Hybrid Machine Learning (Fuzzy-PSO) for Detection of Breast's Tumor

Técnicas de inteligencia artificial utilizadas en el procesamiento de imágenes y su aplicación en el análisis de pavimentos

Contact Info

Product

Resources

About