Comprehensive identification and prioritization of developed artificial intelligence methods for the detection and diagnosis of breast cancer can help to select proper techniques. This study aimed to introduce the best artificial intelligence techniques developed for the detection and diagnosis of breast cancer using microscopic images by fuzzy AHP-TOPSIS techniques.
Methods:
To identify the artificial intelligence techniques developed, a systematic search was performed in five reliable databases. After that, the Delphi method was applied to determine the proper criteria for selecting the best artificial intelligence techniques. To estimate the relative weights of the criteria, the fuzzy analytical hierarchy process (FAHP) method was used. In the next step, to prioritize the identified artificial intelligence techniques, the technique for order of preference by similarity to the ideal solution (TOPSIS) method was applied.
Results:
Forty-four artificial intelligence techniques were identified. Seven selection criteria, validity, accuracy, comprehensiveness, processing time, cost, simplicity, and executive capability, were introduced. Ensemble deep learning architectures integrated with web of things (weight = 0.8041), the computer-aided diagnosis method (weight = 0.7774), the ensemble strategy (VGG16 - ResNet34 - ResNet50) (weight = 0.7475), automated tumor-stroma interface zone detection (weight = 0.7475), and MultiNet/Computer-Aided Diagnosis (CAD)-based deep learning model (weight = 0.7262) were selected as the best methods, respectively.
Conclusion:
These findings represent a total approach to the developed techniques which can be used for designing methods with better performance in the future.
KhoshakhlaghAHGhobakhlooSPeijnenburgWJ, et al. To breathe or not to breathe: Inhalational exposure to heavy metals and related health risk. Sci Total Environ2024; 932: 172556.
2.
KhoshakhlaghAHAskari MajdabadiMYazdaniradS, et al. Health risk assessment of exposure to benzene, toluene, ethylbenzene, and xylene (BTEX) in a composite manufacturing plant: Monte-Carlo simulations. Human Ecol Risk Assess Int J2023; 29: 728-742.
3.
BrayFFerlayJSoerjomataramI, et al. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. Cancer J Clin2018; 68: 394-424.
4.
NardinSMoraEVarugheseFM, et al. Breast cancer survivorship, quality of life, and late toxicities. Front Oncol2020; 10: 864.
5.
BrayFLaversanneMSungHFerlayJSiegelRLSoerjomataramIJemalA. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin2024;74(3):229-263.
6.
BellangerMZeinomarNTehranifarP, et al. Are global breast cancer incidence and mortality patterns related to country-specific economic development and prevention strategies?J Global Oncol2018;4:1-16.
7.
KhanSIShahriorAKarimR, et al. MultiNet: A deep neural network approach for detecting breast cancer through multi-scale feature fusion. J King Saud Uni Computer Info Sci2022; 34: 6217-228.
8.
KorkmazSAPoyrazM.Least square support vector machine and minumum redundacy maximum relavance for diagnosis of breast cancer from breast microscopic images. Procedia-Social Behav Sci2015; 174: 4026-4031.
9.
ChetlenAMackJChanT.Breast cancer screening controversies: who, when, why, and how?Clin Imag2016; 40: 279-282.
10.
BhargavaRMadabhushiA.Emerging themes in image informatics and molecular analysis for digital pathology. Ann Rev Biomed Engineer2016; 18: 387-412.
11.
ChenXWilliamsBMVallabhaneniSR, et al. Learning active contour models for medical image segmentation. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Long Beach, CA, USA; 2019: 11624-11632.
12.
TariqMIqbalSAyeshaH, et al. Medical image based breast cancer diagnosis: State of the art and future directions. Exp Syst App2021; 167: 114095.
13.
SheebaAKumarPSRamamoorthyM, et al. Microscopic image analysis in breast cancer detection using ensemble deep learning architectures integrated with web of things. Biomed Sig Process Cont2023; 79: 104048.
14.
HanXLiuYZhangS, et al. Improving the diagnosis of ductal carcinoma in situ with microinvasion without immunohistochemistry: An innovative method with H&E-stained and multiphoton microscopy images. Int J Cancer2024; 154: 1802-1813.
15.
AliyuBSIsuwaJAbdulrahimA, et al. Enhanced feature selection for imbalanced microarray cancer gene classification using chaotic salp swarm algorithm. Int J Theor App Comput Intell2025;258-283.
16.
PatilRSBiradarN.Automated mammogram breast cancer detection using the optimized combination of convolutional and recurrent neural network. Evolut Intell2021; 14: 1459-1474.
17.
ZhangNLouWJiF, et al. Low molecular weight heparin and cancer survival: clinical trials and experimental mechanisms. J Cancer Res Clin Oncol2016; 142: 1807-1816.
18.
SelvathiDPoornilaAA.Breast cancer detection in mammogram images using deep learning technique. Middle-East J Sci Res2017; 25: 417-426.
19.
NasirSBilalMKhalidiH.Detection and classification of skin cancer by using CNN-enabled cloud storage data access control algorithm based on blockchain technology. Int J Theor App Comput Intell2025; 145-169.
20.
MughalBSharifMMuhammadN, et al. A novel classification scheme to decline the mortality rate among women due to breast tumor. Micro Res Tech2018; 81: 171-180.
21.
MahmoodTSabaTRehmanA, et al. Harnessing the power of radiomics and deep learning for improved breast cancer diagnosis with multiparametric breast mammography. Exp Syst App2024; 249: 123747.
22.
SabaTKhanSUIslamN, et al. Cloud-based decision support system for the detection and classification of malignant cells in breast cancer using breast cytology images. Micro Res Tech2019; 82: 775-785.
23.
MughalBMuhammadNSharifM, et al. Removal of pectoral muscle based on topographic map and shape-shifting silhouette. BMC Cancer2018; 18: 778.
24.
KarimiMKarimiZKhosraviM, et al. Feature selection methods in big medical databases: A comprehensive survey. Int J Theor App Comp Intell2025;181-209.
25.
NassifABTalibMANasirQ, et al. Breast cancer detection using artificial intelligence techniques: A systematic literature review. Art Intell Med2022; 127: 102276.
26.
AlongiPRoveraGStracuzziF, et al. Artificial intelligence in breast cancer: A systematic review on PET imaging clinical applications. Curr Med Imag Rev2023; 19: 832-843.
27.
SadoughiFKazemyZHamedanF, et al. Artificial intelligence methods for the diagnosis of breast cancer by image processing: a review. Breast Cancer Target Ther2018; 1: 219-230.
28.
Uzun OzsahinDIkechukwu EmeganoDUzunB, et al. The systematic review of artificial intelligence applications in breast cancer diagnosis. Diagnostics2022; 13: 45.
29.
MarttunenMLienertJBeltonV.Structuring problems for Multi-Criteria Decision Analysis in practice: A literature review of method combinations. Eur J Op Res2017; 263: 1-17.
30.
MousaviSMYazdaniradSAlthubitiS, et al. Determination and prioritization of factors affecting the occurrence of needle stick injuries among healthcare workers using techniques of Delphi and fuzzy analytical hierarchy process (FAHP). BMC Pub Health2023; 23: 2009.
31.
MamunMAliMSChowdhuryMSA, et al. A Differential Privacy and TOPSIS Enhanced Explainable Machine Learning Framework for Diabetes Risk Diagnosis. 2025 International Conference on Electrical, Computer and Communication Engineering (ECCE), Chittagong, Bangladesh; 2025: IEEE.
32.
JanaPKunduPJanaP.Decision-making in selecting diagnostic methods for early-stage cancer using hybrid MCDM-fuzzy approach. Int J2025; 8: 304.
33.
GuptaAKumarRKumarR, et al. A post-benchmarking framework towards evaluating and ranking deep learning models for breast cancer detection using hybrid MCDM. 2024 International Conference on Network Security and Blockchain Technology, Singapore; 2024: Springer.
34.
KellyCJKarthikesalingamASuleymanM, et al. Key challenges for delivering clinical impact with artificial intelligence. BMC Med2019; 17: 195.
35.
KeeneySMcKennaHPHassonF.The Delphi Technique in Nursing and Health Research. John Wiley & Sons; 2010.
36.
YangXYanLZengL.How to handle uncertainties in AHP: The Cloud Delphi hierarchical analysis. Info Sci2013; 222: 384-404.
37.
BehzadianMOtaghsaraSKYazdaniM, et al. A state-of the-art survey of TOPSIS applications. Exp Syst App2012; 39: 13051-13069.
38.
MoherDLiberatiATetzlaffJ, et al. Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. Rev Esp Nutr Humana Diet2014; 18: 172-181.
39.
YazdaniradSKhoshakhlaghAHAl SulaieS, et al. The effects of occupational noise on sleep: a systematic review. Sleep Med Rev2023; 72: 101846.
40.
DlikililiXvan RooyenJ. An application of a two-step Delphi model in identification of factors affecting the competitive performance of the South African citrus industry. Agriculture Economics Association of South Africa, Annual Conference, Cape Town, South Africa; 2018: 284731.
41.
MousaviSMAbbasiMYazdaniradS, et al. Fuzzy AHP-TOPSIS method as a technique for prioritizing noise control solutions. Noise Control Eng J2019; 67: 415-421.
42.
KhoshakhlaghAHGhasemiMPourtaghiG.Association between fatigue and occupational physical trauma among male Iranian workers in the copper extraction industry. Trauma Month2017; 22:1-10.
43.
RasmussonAZilenaiteDNestarenkaiteA, et al. Immunogradient indicators for antitumor response assessment by automated tumor-stroma interface zone detection. Am J Pathol2020; 190: 1309-1322.
44.
VNSKVijayM.Diagnosing Cancer Cells Using Histopathological Images with Deep Learning. 2021 Sixth International Conference on Wireless Communications, Signal Processing and Networking (WiSPNET), Chennai, India; 2021: IEEE.
45.
KowalMFilipczukP.Nuclei segmentation for computer-aided diagnosis of breast cancer. InternationalJ App Math Comp Sci2014; 24: 19-31.
46.
KalitaMMahantaLBDasAK, et al. A new deep learning model with interface for fine needle aspiration cytology image-based breast cancer detection. Indo J Elec Eng Comp Sci2024; 34: 1739-1752.
47.
MoallemGPoreAAGangadharA, et al. Detection of live breast cancer cells in bright-field microscopy images containing white blood cells by image analysis and deep learning. J Biomed Opt2022; 27: 076003.
48.
Al-HaijaQAAdebanjoA.Breast cancer diagnosis in histopathological images using ResNet-50 convolutional neural network. 2020 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS), Vancouver, Canada; 2020: IEEE.
49.
BakerQBBanatSEaydatE, et al. Automated detection of benign and malignant in breast histopathology images. 2018 IEEE/ACS 15th International Conference on Computer Systems and Applications (AICCSA), Aqaba, Jordan; 2018: IEEE.
50.
DequitANafaF.Advancing early detection of breast cancer: a user-friendly convolutional neural network automation system. BioMedInform2024; 4: 992-1005.
51.
FilipczukPKowalMObuchowiczA.Breast fibroadenoma automatic detection using k-means based hybrid segmentation method. 2012 9th IEEE International Symposium on Biomedical Imaging (ISBI), Barcelona, Spain; 2012: IEEE.
52.
BalasubramanianAAAl-HeejawiSMASinghA, et al. Ensemble deep learning-based image classification for breast cancer subtype and invasiveness diagnosis from whole slide image histopathology. Cancers2024; 16: 2222.
53.
ChakrabortySChatterjeeSChatterjeeA, et al. Automated breast cancer identification by analyzing histology slides using metaheuristic supported supervised classification coupled with bag-of-features. 2018 Fourth International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN), Kalyani, West Bengal, India; 2018: IEEE.
54.
KowalMFilipczukPObuchowiczA, et al. Computer-aided diagnosis of breast cancer based on fine needle biopsy microscopic images. Comp Bio Med2013; 43: 1563-1572.
55.
LaxmisagarHHanumantharajuM.Detection of breast cancer with lightweight deep neural networks for histology image classification. Crit Rev Biomed Eng2022; 50: 1-15.
56.
WeynBVan De WouwerGVan DaeleA, et al. Automated breast tumor diagnosis and grading based on wavelet chromatin texture description. Cytometry1998; 33: 32-40.
57.
EldinSNHamdyJKAdnanGT, et al. Deep learning approach for breast cancer diagnosis from microscopy biopsy images. 2021 International Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), Cairo, Egypt; 2021: IEEE.
58.
UppadaRKodatiSPKoteswara RaoS.Automated computer aided diagnosis using altered multi-phase level sets in application to categorize the breast cancer biopsy images. IETE J Res2023; 69: 4930-4944.
59.
KolarevicDVujasinovićTKanjerK, et al. Effects of different preprocessing algorithms on the prognostic value of breast tumour microscopic images. J Microscopy2018; 270: 17-26.
60.
GeorgeLEMohammedEZ.Cancer tissues recognition system using box counting method and artificial neural network. 2011 International Conference of Soft Computing and Pattern Recognition (SoCPaR), Dalian, China; 2011: IEEE.
61.
BalleriniLFranzénL. Genetic optimization of morphological filters with applications in breast cancer detection. In: Workshops on Applications of Evolutionary Computation; 2004: Springer.
62.
ZengRQuBLiuW, et al. FastLeakyResNet-CIR: A novel deep learning framework for breast cancer detection and classification. IEEE Access. 2024;12:70825-70832.
63.
FatichahCIliyasuAMSalamaAS.A trichotomie technique to separate overlapped nuclei in microscopic cancer images. 2016 SAI Computing Conference (SAI), London, UK; 2016: IEEE.
64.
CiurteASeliceanCSoritauO, et al. Automatic detection of circulating tumor cells in darkfield microscopic images of unstained blood using boosting techniques. PloS One2018; 13: e0208385.
65.
FilipczukPWojtakWObuchowiczA.Automatic nuclei detection on cytological images using the firefly optimization algorithm. Information Technologies in Biomedicine: Third International Conference, ITIB 2012, Gliwice, Poland, June 11-13, 2012 Proceedings; 2012: Springer.
66.
FilipczukPFevensTKrzyżakA, et al. Computer-aided breast cancer diagnosis based on the analysis of cytological images of fine needle biopsies. IEEE Transact Med Imag2013; 32: 2169-2178.
67.
JeongYJBongJGKimHT, et al. Evaluation of phase-contrast microscopic imaging with synchrotron radiation in the diagnosis of breast cancer and differentiation of various breast diseases: Preliminary results. J Breast Cancer2010; 13: 349-356.
68.
KulikovaMVeillardARouxL, et al. Nuclei extraction from histopathological images using a marked point process approach. 2012 Proceedings of SPIE - The International Society for Optical Engineering, San Diego, California, United States; 2012: SPIE.
69.
LesTMarkiewiczTPateraJ.Automatic Detection of Cells in FISH Images Using Map of Colors and Three-Track Segmentation. Recent Developments and Achievements in Biocybernetics and Biomedical Engineering: Proceedings of the 20th Polish Conference on Biocybernetics and Biomedical Engineering, Kraków, Poland, September20-22, 201720; 2018: Springer.
70.
YamaguchiMSasakiTUemuraK, et al. Automatic breast carcinoma detection in histopathological micrographs based on Single Shot Multibox Detector. J Pathol Informat2022; 13: 100147.
71.
KowalMKorbiczJ.Marked point process for nuclei detection in breast cancer microscopic images. Recent Developments and Achievements in Biocybernetics and Biomedical Engineering: Proceedings of the 20th Polish Conference on Biocybernetics and Biomedical Engineering, Kraków, Poland, September 20-22, 2017. 2018: Springer.
72.
FilipczukPKowalMObuchowiczA.Multi-label fast marching and seeded watershed segmentation methods for diagnosis of breast cancer cytology. 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Osaka, Japan; 2013: IEEE.
73.
PribicJVasiljevicJKanjerK, et al. Fractal dimension and lacunarity of tumor microscopic images as prognostic indicators of clinical outcome in early breast cancer. Biomark Med2015; 9: 1279-1277.
74.
VasiljevicJPribicJKanjerK, et al. Multifractal analysis of tumour microscopic images in the prediction of breast cancer chemotherapy response. Biomed Microdevice2015; 17: 1-5.
75.
KolarevicDTomasevicZDzodicR, et al. Early prognosis of metastasis risk in inflammatory breast cancer by texture analysis of tumour microscopic images. Biomed Microdevice2015; 17: 1-8.
76.
RajkovićNKolarevićDKanjerK, et al. Comparison of Monofractal, Multifractal and gray level Co-occurrence matrix algorithms in analysis of Breast tumor microscopic images for prognosis of distant metastasis risk. Biomed Microdevice2016; 18: 83.
77.
KorkmazSAPoyrazM.A new method based for diagnosis of breast cancer cells from microscopic images: DWEE—JHT. J Med Syst2014; 38: 1-9.
78.
KorkmazSAKorkmazMFPoyrazM.Diagnosis of breast cancer in light microscopic and mammographic images textures using relative entropy via kernel estimation. Med Biol Eng Comput2016; 54: 561-573.
79.
BeckAHSangoiARLeungS, et al. Systematic analysis of breast cancer morphology uncovers stromal features associated with survival. Sci Translat Med2011; 3: 108ra13-ra13.
80.
WienertSHeimDSaegerK, et al. Detection and segmentation of cell nuclei in virtual microscopy images: a minimum-model approach. Sci Rep2012; 2: 503.
81.
ZahirSAmirAZahriNAH. Applying the deep learning model on an IoT board for breast cancer detection based on histopathological images. J Phys Conf Ser2021: 1755 012026.
82.
ConversanoAAbbaciMvan DiestP, et al. Breast carcinoma detection in ex vivo fresh human breast surgical specimens using a fast slide-free confocal microscopy scanner: HIBISCUSS project. BJS Open2023; 7: zrad046.
83.
MughalBMuhammadNSharifM, et al. Extraction of breast border and removal of pectoral muscle in wavelet domain. Biomed Res2017; 28: 5041-5043.
84.
JiangFJiangYZhiH, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol2017; 2: 4.
