Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022;34(1):333-348.
doi: 10.1007/s00521-021-06372-1. Epub 2021 Aug 7.

Thermal-based early breast cancer detection using inception V3, inception V4 and modified inception MV4

Mohammed Abdulla Salim Al Husaini  1 , Mohamed Hadi Habaebi  1 , Teddy Surya Gunawan  1 , Md Rafiqul Islam  1 , Elfatih A A Elsheikh  2 , F M Suliman  2
Affiliations

Thermal-based early breast cancer detection using inception V3, inception V4 and modified inception MV4

Mohammed Abdulla Salim Al Husaini et al. Neural Comput Appl. 2022.

Abstract

Breast cancer is one of the most significant causes of death for women around the world. Breast thermography supported by deep convolutional neural networks is expected to contribute significantly to early detection and facilitate treatment at an early stage. The goal of this study is to investigate the behavior of different recent deep learning methods for identifying breast disorders. To evaluate our proposal, we built classifiers based on deep convolutional neural networks modelling inception V3, inception V4, and a modified version of the latter called inception MV4. MV4 was introduced to maintain the computational cost across all layers by making the resultant number of features and the number of pixel positions equal. DMR database was used for these deep learning models in classifying thermal images of healthy and sick patients. A set of epochs 3-30 were used in conjunction with learning rates 1 × 10-3, 1 × 10-4 and 1 × 10-5, Minibatch 10 and different optimization methods. The training results showed that inception V4 and MV4 with color images, a learning rate of 1 × 10-4, and SGDM optimization method, reached very high accuracy, verified through several experimental repetitions. With grayscale images, inception V3 outperforms V4 and MV4 by a considerable accuracy margin, for any optimization methods. In fact, the inception V3 (grayscale) performance is almost comparable to inception V4 and MV4 (color) performance but only after 20-30 epochs. inception MV4 achieved 7% faster classification response time compared to V4. The use of MV4 model is found to contribute to saving energy consumed and fluidity in arithmetic operations for the graphic processor. The results also indicate that increasing the number of layers may not necessarily be useful in improving the performance.

Keywords: Breast cancer; Deep convolutional neural network; Inception MV4; Inception V3; Inception V4; Thermography.

PubMed Disclaimer

Conflict of interest statement

Conflict of interestThe authors declare no conflict of interest.

Figures

Fig. 1
Fig. 1
Flowchart of breast cancer detection process
Fig. 2
Fig. 2
Inception V3 Model
Fig. 3
Fig. 3
a Inception V4 Model, b Details of inception A, B and C layers, c Stem composition [16]
Fig. 4
Fig. 4
Modified inception B
Fig. 5
Fig. 5
Detection accuracy of inception V3, V4 & MV4 by using Color and Grayscale image in: (a) SGDM optimization, (b) ADAM optimization, (c) RMSPROP optimization
Fig. 6
Fig. 6
Giga floating-point operations per second (G-FLOPS) of inception V3, V4 & MV4
Fig. 7
Fig. 7
Average accuracy of different database training and testing for inception V4 and MV4
Fig. 8
Fig. 8
Average accuracy of different epoch for inception V4 and MV4
Fig. 9
Fig. 9
Average accuracy of different learning rate for inception V4 and MV4
See this image and copyright information in PMC

References

    1. Baffa, Matheus F. O, Lattari L. G. (2018). Convolutional neural networks for static and dynamic breast infrared imaging classification. In: Proceedings - 31st conference on graphics, patterns and images, SIBGRAPI, pp. 174–181. 10.1109/SIBGRAPI.2018.00029
    1. Zuluaga GJ, Al Masry Z, Benaggoune K, Meraghni S, Zerhouni N. A CNN-based methodology for breast cancer diagnosis using thermal images. Comput Methods Biomech Biomed Eng Imaging Vis. 2019 doi: 10.1080/21681163.2020.1824685. - DOI
    1. Torres G. J. C, Guevara E, González F. J. (2019) Comparison of deep learning architectures for pre-screening of breast cancer thermograms. In: 2019 photonics north, PN 2019, pp. 2–3. 10.1109/PN.2019.8819587
    1. Kakileti S. T, Manjunath G, Madhu H. J. (2019). Cascaded CNN for view independent breast segmentation in thermal images. In: 2019 41st annual international conference of the IEEE engineering in medicine and biology society (EMBC), pp. 6294–6297. 10.1109/embc.2019.8856628 - PubMed
    1. Roslidar R., Saddami K, Arnia F, Syukri M, Munadi K. (2019) A study of fine-tuning CNN models based on thermal imaging for breast cancer classification. In: 2019 IEEE international conference on cybernetics and computational intelligence (CyberneticsCom), November, pp. 77–81. 10.1109/CYBERNETICSCOM.2019.8875661

LinkOut - more resources