From Black Box to Glass Box: A Survey of Explainable AI in Mammographic Screening

Saja Murtadha Hashim; Hakan Kutucu

doi:10.35377/saucis...1766498

journal article Mar 30, 2026

From Black Box to Glass Box: A Survey of Explainable AI in Mammographic Screening

Saja Murtadha Hashim

Hakan Kutucu

Sakarya University Journal of Computer and Information Sciences Vol. 9 No. 1 pp. 292-305 · Sakarya University Journal of Computer and Information Sciences

View at Publisher Save 10.35377/saucis...1766498

Abstract

Breast cancer remains a leading global health concern, with early, accurate diagnosis through mammography being critical for effective treatment. The emergence of artificial intelligence (AI) has revolutionized breast cancer screening, yet the opacity of “black box” models in clinical applications has sparked pressing calls for greater transparency. Explainable AI (XAI) offers essential solutions by making model decisions interpretable, enabling clinicians to trust and adopt advanced algorithms more confidently. This review synthesizes the current landscape of XAI methods applied to mammographic imaging, examining cutting-edge techniques such as Grad-CAM, LIME, SHAP, attention mechanisms, and prototype-based models. We analyze how these approaches provide meaningful visual and textual explanations that bridge the gap between technical innovation and clinical utility. Unique to this survey is its focus on practical case studies, integration pathways, and challenges in real-world implementation, from balancing interpretability and diagnostic accuracy to the urgent need for robust, diverse datasets. As demand grows for ethical, transparent AI in medicine, our review highlights actionable strategies, future directions, and the collaborative role of radiologists, AI specialists, and patients. By connecting technical advances to clinical trust and patient-centered care, this work sets the foundation for safe, transparent breast cancer diagnosis and aims to inspire further progress throughout the field.

Topics

No keywords indexed for this article. Browse by subject →

References

45

[1]

Breast cancer development and progression: Risk factors, cancer stem cells, signaling pathways, genomics, and molecular pathogenesis

Yixiao Feng, Mia Spezia, Shifeng Huang et al.

Genes & Diseases 10.1016/j.gendis.2018.05.001

[2]

Y. Shen et al., “Artificial intelligence system reduces false-positive findings in the interpretation of breast ultrasound exams,” Nat. Commun., vol. 12, no. 1, p. 5645, Dec. 2021. doi: 10.1038/s41467-021-26023-2 10.1038/s41467-021-26023-2

[3]

Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries

Hyuna Sung, Jacques Ferlay, Rebecca L. Siegel et al.

CA: A Cancer Journal for Clinicians 10.3322/caac.21660

[4]

A. Gerbasi et al., “DeepMiCa: Automatic segmentation and classification of breast MIcroCAlcifications from mammograms,” Comput. Methods Programs Biomed., vol. 235, Jun. 2023. doi: 10.1016/j.cmpb.2023.107483 10.1016/j.cmpb.2023.107483

[5]

S. Bai, S. Nasir, R. A. Khan, S. Arif, A. Meyer, and H. Konik, “Breast cancer diagnosis: A comprehensive exploration of explainable artificial intelligence (XAI) techniques,” arXiv preprint, arXiv:2406.00532, Jun. 2024. 10.1109/access.2025.3639184

[6]

Impact of Mammography Screening Frequency on Breast Cancer Mortality Rates

Enas Abu Abeelh, Zain AbuAbeileh

Cureus 10.7759/cureus.49066

[7]

N. Shifa, M. Saleh, Y. Akbari, and S. Al Maadeed, “A review of explainable AI techniques and their evaluation in mammography for breast cancer screening,” Clin. Imaging, p. 110492, Jul. 2025. doi: 10.1016/j.clinimag.2025.110492 10.1016/j.clinimag.2025.110492

[8]

B. Abhisheka, S. K. Biswas, and B. Purkayastha, “A Comprehensive review on breast cancer detection, classification and segmentation using deep learning,” Arch. Comput. Methods Eng., Nov. 2023. doi:10.1007/s11831-023-09968-z 10.1007/s11831-023-09968-z

[9]

M. Ahmed, T. Bibi, R. A. Khan, and S. Nasir, “Enhancing breast cancer diagnosis in mammography: Evaluation and integration of convolutional neural networks and explainable AI,” Institute of Electrical and Electronics Engineers (IEEE), May 2025, pp. 1–6. doi: 10.1109/inmic64792.2024.11004362 10.1109/inmic64792.2024.11004362

[10]

Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI

Alejandro Barredo Arrieta, Natalia Díaz-Rodríguez, Javier Del Ser et al.

Information Fusion 10.1016/j.inffus.2019.12.012

[11]

M. R. Alom et al., “An explainable AI-driven deep neural network for accurate breast cancer detection from histopathological and ultrasound images,” Sci. Rep., vol. 15, no. 1, Dec. 2025. doi: 10.1038/s41598-025-97718-5 10.1038/s41598-025-97718-5

[12]

K. Lekadir et al., “FUTURE-AI: Guiding principles and consensus recommendations for trustworthy artificial intelligence in medical imaging,” arXiv preprint, arXiv:2109.09658, Jul. 2024.

[13]

T. Dhar, N. Dey, S. Borra, and R. S. Sherratt, “Challenges of deep learning in medical image analysis—improving explainability and trust,” IEEE Trans. Technol. Soc., vol. 4, no. 1, pp. 68–75, Jan. 2023. doi: 10.1109/tts.2023.3234203 10.1109/tts.2023.3234203

[14]

A. Chaddad, Y. Hu, Y. Wu, B. Wen, and R. Kateb, “Generalizable and explainable deep learning for medical image computing: An overview,” Curr. Opin. Biomed. Eng., vol. 33, p. 100567, Mar. 2025. doi: 10.1016/j.cobme.2024.100567 10.1016/j.cobme.2024.100567

[15]

W. Samek, T. Wiegand, and K.-R. Müller, “Explainable Artificial Intelligence: Understanding, visualizing and interpreting deep learning models,” arXiv preprint, arXiv:1708.08296, Aug. 2017.

[16]

A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI

Erico Tjoa, Cuntai Guan

IEEE Transactions on Neural Networks and Learning... 10.1109/tnnls.2020.3027314

[17]

C. Patrício, J. C. Neves, and L. F. Teixeira, “Explainable deep learning methods in medical image classification: A survey,” ACM Comput. Surv., vol. 56, no. 4, Apr. 2024. doi: 10.1145/3625287 10.1145/3625287

[18]

J. R. Kaczmarzyk, J. H. Saltz, and P. K. Koo, “Explainable AI for computational pathology identifies model limitations and tissue biomarkers,” arXiv preprint, arXiv:2409.03080, Nov. 2024.

[19]

T. Chanda et al., “Dermatologist-like explainable AI enhances melanoma diagnosis accuracy: eye-tracking study,” Nat. Commun., vol. 16, no. 1, Dec. 2025. doi: 10.1038/s41467-025-59532-5 10.1038/s41467-025-59532-5

[20]

S. Alsaedi, M. Ogasawara, M. Alarawi, X. Gao, and T. Gojobori, “AI-powered precision medicine: utilizing genetic risk factor optimization to revolutionize healthcare,” NAR Genom Bioinform, vol. 7, no. 2, Jun. 2025. doi: 10.1093/nargab/lqaf038 10.1093/nargab/lqaf038

[21]

J. Hou et al., “Self-explainable AI for medical image analysis: A survey and new outlooks,” arXiv preprint, arXiv:2410.02331, Nov. 2024.

[22]

Y. W. Chang et al., “Artificial Intelligence for breast cancer screening in Mammography (AI-STREAM): A prospective multicenter study design in Korea using AI-Based CADe/x,” J. Breast Cancer, vol. 25, no. 1, pp. 57–68, Feb. 2022. doi: 10.4048/jbc.2022.25.e4 10.4048/jbc.2022.25.e4

[23]

P. E. S. C. Branco et al., “Artificial intelligence in mammography: a systematic review of the external validation,” Rev. Bras. Ginecol. Obstet., vol. 46, 2024. doi: 10.61622/RBGO/2024RBGO71 10.61622/rbgo/2024rbgo71

[24]

S. M. Friedewald et al., “Triaging mammography with artificial intelligence: an implementation study,” Breast Cancer Res Treat, vol. 211, no. 1, pp. 1–10, May 2025. doi: 10.1007/s10549-025-07616-7 10.1007/s10549-025-07616-7

[25]

Standalone AI for Breast Cancer Detection at Screening Digital Mammography and Digital Breast Tomosynthesis: A Systematic Review and Meta-Analysis

Jung Hyun Yoon, Fredrik Strand, Pascal A. T. Baltzer et al.

Radiology 10.1148/radiol.222639

[26]

D. K. Gurmessa, and W. Jimma, “Explainable machine learning for breast cancer diagnosis from mammography and ultrasound images: a systematic review,” BMJ Health Care Inform., Feb. 2024. doi: 10.1136/bmjhci-2023-100954 10.1136/bmjhci-2023-100954

[27]

A. Alhussen, M. Anul Haq, A. Ahmad Khan, R. K. Mahendran, and S. Kadry, “XAI-RACapsNet: Relevance aware capsule network-based breast cancer detection using mammography images via explainability O-net ROI segmentation,” Expert Syst Appl, vol. 261, Feb. 2025. doi: 10.1016/j.eswa.2024.125461 10.1016/j.eswa.2024.125461

[28]

E. Cerekci et al., “Quantitative evaluation of Saliency-Based Explainable artificial intelligence (XAI) methods in Deep Learning-Based mammogram analysis,” Eur J Radiol, vol. 173, Apr. 2024. doi: 10.1016/j.ejrad.2024.111356 10.1016/j.ejrad.2024.111356

[29]

O. O. Oladimeji, H. Ayaz, I. McLoughlin, and S. Unnikrishnan, “Mutual information-based radiomic feature selection with SHAP explainability for breast cancer diagnosis,” Results in Engineering, vol. 24, Dec. 2024. doi: 10.1016/j.rineng.2024.103071 10.1016/j.rineng.2024.103071

[30]

K. K. Sreekala, and J. Sahoo, “Enhancing mammogram classification using explainable conditional self-attention generative adversarial network,” Expert Syst. Appl., vol. 293, Dec. 2025. doi: 10.1016/j.eswa.2025.128640 10.1016/j.eswa.2025.128640

[31]

Grad-CAM Enabled Breast Cancer Classification with a 3D Inception-ResNet V2: Empowering Radiologists with Explainable Insights

Fatma M. Talaat, Samah A. Gamel, Rana Mohamed El-Balka et al.

Cancers 10.3390/cancers16213668

[32]

Y. Abas Mohamed, B. Ee Khoo, M. Shahrimie Mohd Asaari, M. Ezane Aziz, and F. Rahiman Ghazali, “Decoding the black box: Explainable AI (XAI) for cancer diagnosis, prognosis, and treatment planning-A state-of-the art systematic review,” Int. J. Med. Inform., p. 105689, Jan. 2025. doi: 10.1016/j.ijmedinf.2024.105689 10.1016/j.ijmedinf.2024.105689

[33]

Transformer-Based Explainable Deep Learning for Breast Cancer Detection in Mammography: The MammoFormer Framework

Ojonugwa Peter, Daniel Emakporuena, Bamidele Tunde et al.

American Journal of Computer Science and Technolog... 10.11648/j.ajcst.20250802.16

[34]

S. Goh et al., “Challenges in implementing artificial intelligence in breast cancer screening programs: systematic review and framework for safe adoption,” JMIR Med. Inform., 2025. doi: 10.2196/62941 10.2196/62941

[35]

E. B. Mendelson, “Artificial intelligence in breast imaging: Potentials and limitations,” AJR Am. J. Roentgenol., vol. 212, no. 2, pp. 293–298, Feb. 2019. doi: 10.2214/AJR.18.20532 10.2214/ajr.18.20532

[36]

B. Lokaj, M. T. Pugliese, K. Kinkel, C. Lovis, and J. Schmid, “Barriers and facilitators of artificial intelligence conception and implementation for breast imaging diagnosis in clinical practice: a scoping review,” Eur. Radiol., vol. 34, pp. 1–13, Mar. 2024. doi: 10.1007/s00330-023-10181-6 10.1007/s00330-023-10181-6

[37]

A. Ghasemi, S. Hashtarkhani, D. L. Schwartz, and A. Shaban-Nejad, “Explainable artificial intelligence in breast cancer detection and risk prediction: A systematic scoping review,” John Wiley and Sons Inc. 2024. doi: 10.1002/cai2.136 10.1002/cai2.136

[38]

E. Yahata, P. D. Dos Santos, M. M. De Souza Pires, R. Suyama, and P. W. Simoes, “Neural networks and explainable artificial intelligence for breast cancer prediction and classification,” in Proc. Comput. Sci., vol. 235, pp. 1159–1166, 2025. doi: 10.1016/j.procs.2025.02.224 10.1016/j.procs.2025.02.224

[39]

N. Hariprasad, M. Annal Priyanga, S. Duraimurugan, M. Sushmitha, and S. Vedha Shri, “A comparative study of machine learning classifiers and ensemble method for breast cancer detection using XAI technique,” in Proc. IEEE Delhi Sect. Flagship Conf. (DELCON), 2024. doi: 10.1109/DELCON64804.2024.10866753 10.1109/delcon64804.2024.10866753

[40]

M. R. Alom et al., “An explainable AI-driven deep neural network for accurate breast cancer detection from histopathological and ultrasound images,” Sci. Rep., vol. 15, no. 1, Dec. 2025. doi: 10.1038/s41598-025-97718-5 10.1038/s41598-025-97718-5

[41]

M. Di Giammarco et al., “Explainable deep learning for breast cancer classification and localization,” ACM Trans. Comput. Healthc., vol. 6, no. 1, Jan. 2025. doi: 10.1145/3702237 10.1145/3702237

[42]

A.-K. Balve, and P. Hendrix, “Interpretable breast cancer classification using CNNs on mammographic images,” Aug. 2024, arXiv preprint, arXiv:2408.13154, 2024.

[43]

N. Berberian et al., “Evaluation of an ai-powered portable thermal imaging solution as a pre-screening tool for breast cancer,” Cancer Screening Prev., vol. 3, no. 1, pp. 8–15, Mar. 2024. doi: 10.14218/csp.2023.00034s 10.14218/csp.2023.00034s

[44]

T. Alelyani, M. M. Alshammari, A. Almuhanna, and O. Asan, “Explainable artificial intelligence in quantifying breast cancer factors: Saudi Arabia context,” Healthcare, vol. 12, no. 10, May 2024. doi: 10.3390/healthcare12101025 10.3390/healthcare12101025

[45]

V. Gupta, and R. Sharma, “Enhancing breast cancer prediction with xai-enabled boosting algorithms,” in Proc. Int. Conf. Comput. Commun. Netw. Technol. (ICCCNT), 2024, pp. 1–. doi: 10.1109/ICCCNT61001.2024.10723843 10.1109/icccnt61001.2024.10723843

Metrics

0

Citations

45

References

Details

Published: Mar 30, 2026
Vol/Issue: 9(1)
Pages: 292-305

Authors

KARABÜK ÜNİVERSİTESİ

KARABÜK ÜNİVERSİTESİ

Cite This Article

Saja Murtadha Hashim, Hakan Kutucu (2026). From Black Box to Glass Box: A Survey of Explainable AI in Mammographic Screening. Sakarya University Journal of Computer and Information Sciences, 9(1), 292-305. https://doi.org/10.35377/saucis...1766498

From Black Box to Glass Box: A Survey of Explainable AI in Mammographic Screening

You May Also Like