![](https://geox.udistrital.edu.co/public/journals/4/submission_20677_19484_coverImage_en_US.png)
DOI:
https://doi.org/10.14483/23448393.20677Published:
2024-05-22Issue:
Vol. 29 No. 2 (2024): May-AugustSection:
Electrical, Electronic and Telecommunications EngineeringAutomated Breast Tumor Detection and Segmentation Using the Threshold Density Algorithm with Logistic Regression on Microwave Images
Detección y segmentación automatizadas de tumores de mama mediante el algoritmo de densidad de umbral con regresión logística en imágenes por microondas
Keywords:
Automatic Segmentation, Breast Tumor, Logistic Regression, Microwave Images, Threshold Density (en).Keywords:
segmentación automática, tumor de mama, regresión logística, imágenes por microondas, densidad de umbral (es).Downloads
Abstract (en)
Context: Breast cancer remains a major health burden worldwide, necessitating improved screening modalities for early detection. However, existing techniques such as mammography and MRI exhibit limitations regarding sensitivity and specificity. Microwave imaging has recently emerged as a promising technology for breast cancer diagnosis, exploiting the dielectric contrast between normal and malignant tissues. Objectives: This study proposes a novel computational framework integrating thresholding, edge segmentation, and logistic regression to enhance microwave image-based breast tumor delineation. Methodology: The employed algorithm selects optimal features using logistic regression to mitigate the class imbalance between tumor and healthy tissues. Localized density thresholds are applied to identify tumor regions, followed by edge segmentation methods to precisely localize the detected lesions. Results: When evaluated on a dataset of microwave breast images, our approach demonstrated high accuracy for detecting and segmenting malignant tissues. Density thresholds ranging from 0.1 to 0.8 showcase the highest accuracy in detecting breast tumors from these images. Conclusions: The results highlight the potential of the proposed segmentation algorithm to improve the reliability of microwave imaging as an adjunct modality for breast cancer screening. This could promote earlier diagnosis and better clinical outcomes. The proposed framework represents a significant advance in developing robust image processing techniques tailored to emerging medical imaging modalities challenged by class imbalance and low intrinsic contrast.
Abstract (es)
Contexto: El cáncer de mama sigue siendo una importante carga sanitaria a nivel mundial, lo que requiere mejores modalidades de cribado para la detección temprana. Sin embargo, las técnicas existentes, como la mamografía y la resonancia magnética, presentan limitaciones en cuanto a sensibilidad y especificidad. Recientemente, la imagen por microondas ha surgido como una prometedora tecnología para el diagnóstico del cáncer de mama, aprovechando el contraste dieléctrico entre los tejidos normales y malignos. Objetivos: Este estudio propone un novedoso marco computacional que integra el umbralizado, la segmentación de bordes y la regresión logística para mejorar la delimitación de tumores mamarios basada en imágenes de microondas. Metodología: El algoritmo empleado selecciona las características óptimas utilizando la regresión logística para mitigar el desequilibrio de clases entre los tejidos tumorales y sanos. Se aplican umbrales de densidad localizados para identificar las regiones tumorales, seguidos de métodos de segmentación de bordes para localizar precisamente las lesiones detectadas. Resultados: Cuando se evaluó en un conjunto de datos de imágenes de microondas de mama, nuestro enfoque demostró una alta precisión para detectar y segmentar los tejidos malignos. Los umbrales de densidad que van desde 0,1 hasta 0,8 muestran la mayor precisión en la detección de tumores mamarios a partir de estas imágenes. Conclusiones: Los resultados resaltan el potencial del algoritmo de segmentación propuesto para mejorar la fiabilidad de la imagen por microondas como modalidad complementaria para el cribado del cáncer de mama. Esto podría promover un diagnóstico más temprano y mejores resultados clínicos. El marco propuesto representa un avance significativo en el desarrollo de técnicas robustas de procesamiento de imágenes adaptadas a las modalidades emergentes de imagen médica desafiadas por el desequilibrio de clases y el bajo contraste intrínseco.
References
E. M. Proussaloglou et al., "Updates in the pathology of pregnancy associated breast cancer (PABC)," Pathol. Res. Pract., art. 154413, 2023. https://doi.org/10.1016/j.prp.2023.154413
T. H. Aldhyani et al., "Deep learning model for the detection of real time breast cancer images using improved dilation-based method," Diag., vol. 12, no. 10, art. 2505, 2022. https://doi.org/10.3390/diagnostics12102505
Z. Khandezamin, M. Naderan, and M. J. Rashti, "Detection and classification of breast cancer using logistic regression feature selection and GMDH classifier," J. Biomed. Inform., vol. 111, art. 103591, 2020. https://doi.org/10.1016/j.jbi.2020.103591
A. Najafian-Najafabady, N. Ebrahimi, and S. Vallian, "rs2682818/MiR-618 is a novel marker associated with increased risk of breast cancer in the Iranian population," Arch. Biol. Sci., vol. 73, no. 4, pp. 457–463, 2021. https://doi.org/10.2298/ABS210808039N
L. Wang, "Holographic microwave image classification using a convolutional neural network," Micromachines, vol. 13, art. 2049, 2022. https://doi.org/10.3390/mi13122049
M. A. Aldhaeebi et al., "Review of microwaves techniques for breast cancer detection," Sensors, vol. 20, no. 8, art. 2390, 2020. https://doi.org/10.3390/s20082390
S. Kwon and S. Lee, "Recent advances in microwave imaging for breast cancer detection," Int. J. Biomed. Imaging, vol. 2016, art. 5054912. https://doi.org/10.1155/2016/5054912
L. Wang, "Microwave imaging and sensing techniques for breast cancer detection," Micromachines, vol. 14, no. 7, art. 1462, 2023. https://doi.org/10.3390/mi14071462
N. AlSawaftah et al., "Microwave imaging for early breast cancer detection: Current state, challenges, and future directions," Journal of Imaging, vol. 8, no. 5, art. 123, 2022. https://doi.org/10.3390/jimaging8050123
L. Liu et al., "Automated breast tumor detection and segmentation with a novel computational framework of whole ultrasound images," Med.l Biol. Eng. Computing, vol. 56, pp. 183–199, 2018. https://doi.org/10.1007/s11517-017-1770-3
A. Melouah and S. Layachi, "A novel automatic seed placement approach for region growing segmentation in mammograms," in Proc. Int.l Conf. Intel. Info. Processing Sec. Adv. Comm., 2015, art. 51. https://doi.org/10.1145/2816839.2816892
N. Shrivastava and J. Bharti, "Breast tumor detection and classification based on density," Multimedia Tools App., vol. 79, no. 35-36, pp. 26467–26487, 2020. https://doi.org/10.1007/s11042-020-09220-x
A. A. Sandino Garzón and R. Herrera García, "Clustered microcalcifications candidates detection in mammograms," Ingeniería, vol. 24, no. 2, pp. 159–170, 2019. https://doi.org/10.14483/23448393.12512
A. Q. Al-Faris et al., "Breast MRI tumour segmentation using modified automatic seeded region growing based on particle swarm optimization image clustering," in Proc. 17th Online World Conf. Soft Computing Ind. App., 2014 pp. 49-60. https://doi.org/10.1007/978-3-319-00930-8_5
H. Shao et al., "A saliency model for automated tumor detection in breast ultrasound images," in 2015 IEEE Int. Conf. Image Proc. (ICIP), 2015, pp. 1424-1428. https://doi.org/10.1109/ICIP.2015.7351035
H. Rajaguru and S. K. Prabhakar, "Expectation maximization based logistic regression for breast cancer classification," in 2017 Int. Conf. Elec. Comm. Aerospace Tech. (ICECA), 2017, pp. 603-606. https://doi.org/10.1109/ICECA.2017.8203608
L. Khairunnahar et al., "Classification of malignant and benign tissue with logistic regression," Inform. Med. Unlocked, vol. 16, art. 100189, 2019. https://doi.org/10.1016/j.imu.2019.100189
M. Dey et al., "Automated breast lesion localisation in microwave imaging employing simplified pulse coupled neural network," PloS One, vol. 17, no. 7, art. e0271377, 2022. https://doi.org/10.1371/journal.pone.0271377
N. Saffari et al., "Fully automated breast density segmentation and classification using deep learning," Diagnostics, vol. 10, no. 11, art. 988, 2020. https://doi.org/10.3390/diagnostics10110988
T. Reimer, J. Krenkevich, and S. Pistorius, "An open-access experimental dataset for breast microwave imaging," in 2020 14th Eur. Conf. Antennas Propag. (EuCAP), 2020, p. 1-5. https://doi.org/10.23919/EuCAP48036.2020.9135659
T. Reimer, M. Solis-Nepote, and S. Pistorius, "The application of an iterative structure to the delay-and-sum and the delay-multiply-and-sum beamformers in breast microwave imaging," Diagnostics, vol. 10, no. 6, art. 411, 2020. https://doi.org/10.3390/diagnostics10060411
B. Abdollahzadeh and F. S. Gharehchopogh, "A multi-objective optimization algorithm for feature selection problems," Eng. Comp., vol. 38, no. Suppl. 3, pp. 1845–1863, 2022. https://doi.org/10.1007/s00366-021-01369-9
F. Ahmad et al., "A GA-based feature selection and parameter optimization of an ANN in diagnosing breast cancer," Patt. Analysis App., vol. 18, pp. 861–870, 2015. https://doi.org/10.1007/s10044-014-0375-9
W. Chen et al., "Density-based logistic regression," in Proc. 19th ACM SIGKDD Int. Conf. Knowledge Disc. Data Mining, 2013, pp. 140-148. https://doi.org/10.1145/2487575.2487583
R. Rodrigues et al., "A two-step segmentation method for breast ultrasound masses based on multi-resolution analysis," Ultrasound Med. Biol., vol. 41, no. 6, pp. 1737–1748, 2015. https://doi.org/10.1016/j.ultrasmedbio.2015.01.012
How to Cite
APA
ACM
ACS
ABNT
Chicago
Harvard
IEEE
MLA
Turabian
Vancouver
Download Citation
License
Copyright (c) 2024 Azhar Albaaj, Yaser Norouzi, Gholamreza Moradi
![Creative Commons License](http://i.creativecommons.org/l/by-nc-sa/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
From the edition of the V23N3 of year 2018 forward, the Creative Commons License "Attribution-Non-Commercial - No Derivative Works " is changed to the following:
Attribution - Non-Commercial - Share the same: this license allows others to distribute, remix, retouch, and create from your work in a non-commercial way, as long as they give you credit and license their new creations under the same conditions.