Explainable Artificial Intelligence (XAI) en el diagnóstico por imágenes para la detección temprana del cáncer: una revisión sistemática de la literatura
Palabras clave:
Apoyo a la toma de decisiones médicas; detección temprana del cáncer; diagnostico oncológico; diagnóstico por imágenes; inteligencia artificial explicable; XAIResumen
Introducción: El cáncer constituye una de las principales causas de mortalidad mundial y la detección temprana mediante imágenes médicas representa un factor crítico para mejorar la supervivencia. En este contexto, la Inteligencia Artificial Explicativa ha emergido como una estrategia para superar la opacidad de los modelos de inteligencia artificial diagnósticos.
Objetivo: Analizar la evidencia científica disponible sobre la efectividad de las técnicas de Inteligencia Artificial Explicativa aplicadas al diagnóstico por imágenes para la detección temprana de diversos tipos de cáncer.
Material y Métodos: Se realizó una revisión sistemática siguiendo la guía PRISMA 2020 y los criterios PICO en las bases de datos Scopus y Web of Science, seleccionándose 25 estudios publicados entre 2020 y 2025 tras la evaluación de calidad medianteQUADAS-2 y ROBINS-I.
Resultados: Técnicas como Grad-CAM, SHAP y LIME son las más utilizadas y se aplican principalmente en resonancia magnética, tomografía computarizada, mamografía y dermatoscopía para cáncer de pulmón, mama, cerebro y piel. En múltiples estudios, los modelos explicables igualaron o superaron a los sistemas de “caja negra”, se alcanzaron altas métricas de precisión diagnóstica, reduciendo falsos positivos y mejorando la confianza clínica al permitir validar visualmente las decisiones algorítmicas.
Conclusiones: La Inteligencia Artificial Explicativa no solo incrementa la interpretabilidad, sino que fortalece el rendimiento y la aceptabilidad clínica de la inteligencia artificial médica, posicionándose como un componente esencial para la implementación segura y efectiva de sistemas de diagnóstico oncológico asistido por IA en la práctica clínica contemporánea y en futuros entornos sanitarios digitalizados.
Descargas
Citas
1. World Health Organization. Global cancer burden growing, amidst mounting need for services [Internet]. Ginebra: WHO; 2024. [Citado 26/06/2025]. Disponible en: https://www.who.int/news/item/01-02-2024-global-cancer-burden-growing--amidst-mounting-need-for-services
2. Crosby D, Bhatia S, Brindle KM, Coussens LM, Dive C, Emberton M, et al. Early detection of cancer. Science [Internet]. 2022;375(6586):eaay9040. Disponible en:http://doi.org/10.1126/science.aay9040
3. World Health Organization. Cancer [Internet]. Ginebra: WHO; 2025. [Citado 26/06/2025]. Disponible en: https://www.who.int/news-room/fact-sheets/detail/cancer
4. Cheng CH, Shi S sheng. Artificial intelligence in cancer: applications, challenges, and future perspectives. Mol Cancer [Internet]. 2025;24(1):274. Disponible en: http://doi.org/10.1186/s12943-025-02450-3
5. Swanson K, Wu E, Zhang A, Alizadeh AA, Zou J. From patterns to patients: Advances in clinical machine learning for cancer diagnosis, prognosis, and treatment. Cell [Internet]. 2023;186(8):1772–91. Disponible en: http://doi.org/10.1016/j.cell.2023.01.035
6. Miao KH, Miao JH, Finkelstein M, Chatterjee A, Oto A. Next-Generation Advances in Prostate Cancer Imaging and Artificial Intelligence Applications. J Imaging [Internet]. 2025;11(11):390. Disponible en: http://doi.org/10.3390/jimaging11110390
7. Koh DM, Papanikolaou N, Bick U, Illing R, Kahn CE, Kalpathi-Cramer J, et al. Artificial intelligence and machine learning in cancer imaging. Commun Med [Internet]. 2022;2(1):133. Disponible en: http://doi.org/10.1038/s43856-022-00199-0
8. Cellina M, Cè M, Irmici G, Ascenti V, Khenkina N, Toto-Brocchi M, et al. Artificial Intelligence in Lung Cancer Imaging: Unfolding the Future. Diagnostics [Internet]. 2022;12(11):2644. Disponible en: http://doi.org/10.3390/diagnostics12112644
9. Hammad M, ElAffendi M, El-Latif AAA, Ateya AA, Ali G, Plawiak P. Explainable AI for lung cancer detection via a custom CNN on CT images. Sci Rep [Internet]. 2025;15(1):12707. Disponible en: http://doi.org/10.1038/s41598-025-97645-5
10. Marias K. The Constantly Evolving Role of Medical Image Processing in Oncology: From Traditional Medical Image Processing to Imaging Biomarkers and Radiomics. J Imaging [Internet]. 2021;7(8):8. Disponible en: http://doi.org/10.3390/jimaging7080124
11. Agarwal D. Explainable AI in Cancer Diagnosis: Enhancing Interpretability with SHAP on Benign and Malignant Tumor Detection. Int J Res Appl Sci Eng Technol [Internet]. 2025;13(1):1394–402. Disponible en: http://doi.org/10.22214/ijraset.2025.66580
12. Alom MR, Farid FA, Rahaman MA, Rahman A, Debnath T, Miah ASM, et al. An explainable AI-driven deep neural network for accurate breast cancer detection from histopathological and ultrasound images. Sci Rep [Internet]. 2025;15(1):17531. Disponible en: http://doi.org/10.1038/s41598-025-97718-5
13. Hrinivich WT, Wang T, Wang C. Editorial: Interpretable and explainable machine learning models in oncology. Front Oncol [Internet]. 2023;13. Disponible en: http://doi.org/10.3389/fonc.2023.1184428
14. Tanveer H, Faheem M, Khan AH. Explainable AI in Medical Decision-Making: Challenges and Opportunities [Internet]. 2022;5(12) [Citado 26/06/2025]. Disponible en: https://www.irejournals.com/formatedpaper/1703509.pdf
15. Olumuyiwa BI, Han TA, Shamszaman ZU. Enhancing Cancer Diagnosis with Explainable & Trustworthy Deep Learning Models [Internet]. EE UU: arXiv; 2024 [Citado 26/06/2025]. Disponible en: http://doi.org/10.48550/arXiv.2412.17527
16. Singhal A, Agrawal KK, Quezada A, Aguiñaga AR, Jiménez S, Yadav SP. Explainable Artificial Intelligence (XAI) Model for Cancer Image Classification. Comput Model Eng Sci [Internet]. 2024;141(1):401–41. Disponible en: http://doi.org/10.32604/cmes.2024.051363
17. Wyatt LS, van Karnenbeek LM, Wijkhuizen M, Geldof F, Dashtbozorg B. Explainable Artificial Intelligence (XAI) for Oncological Ultrasound Image Analysis: A Systematic Review. Appl Sci [Internet]. 2024;14(18):18. Disponible en: http://doi.org/10.3390/app14188108
18. Ghasemi A, Hashtarkhani S, Schwartz DL, Shaban-Nejad A. Explainable artificial intelligence in breast cancer detection and risk prediction: A systematic scoping review. Cancer Innov [Internet]. 2024;3(5):e136. Disponible en: http://doi.org/10.1002/cai2.136
19. Muhammad D, Bendechache M. Unveiling the black box: A systematic review of Explainable Artificial Intelligence in medical image analysis. Comput Struct Biotechnol J [Internet]. 2024;24:542–60. Disponible en: http://doi.org/10.1016/j.csbj.2024.08.005
20. Koutoulakis E, Trivizakis E, Markodimitrakis E, Agelaki S, Tsiknakis M, Marias K. A critical review of explainable deep learning in lung cancer diagnosis. Artif Intell Rev [Internet]. 2025;59(1):28. Disponible en: http://doi.org/10.1007/s10462-025-11445-x
21. Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ [Internet]. 2021;372(71). Disponible en: http://doi.org/10.1136/bmj.n71
22. Abdel-Salam M, Askr H, Hassanien AE. Revolutionizing cervical cancer detection: a new optimized explainable artificial intelligence model. Neural Comput Appl [Internet]. 2025;37(29):23979–4023. Disponible en: http://doi.org/10.1007/s00521-025-11548-0
23. Ali SA, Arain KR, Mushtaq NA, Rehman O. Interpretable Deep Learning for Brain Tumor Diagnosis: Occlusion Sensitivity-Driven Explainability in MRI Classification. VFAST Trans Softw Eng [Internet]. 2025;13(2):135–46. Disponible en: http://doi.org/10.21015/vtse.v13i2.2082
24. Arshad M, Khan MA, Almujally NA, Alasiry A, Marzougui M, Nam Y. Multiclass skin lesion classification and localziation from dermoscopic images using a novel network-level fused deep architecture and explainable artificial intelligence. BMC Med Inform Decis Mak [Internet]. 2025;25(1):215. Disponible en: http://doi.org/10.1186/s12911-025-03051-2
25. Choi JY, Park S, Shim JS, Park HJ, Kuh SU, Jeong Y, et al. Explainable artificial intelligence-driven prostate cancer screening using exosomal multi-marker based dual-gate FET biosensor. Biosens Bioelectron [Internet]. 2025 ;267:116773. Disponible en: http://doi.org/10.1016/j.bios.2024.116773
26. Cimino MGCA, Campisi G, Galatolo FA, Neri P, Tozzo P, Parola M, et al. Explainable screening of oral cancer via deep learning and case-based reasoning. Smart Health [Internet]. 2025;35:100538. Disponible en: http://doi.org/10.1016/j.smhl.2024.100538
27. Dahan F, Shah JH, Saleem R, Hasnain M, Afzal M, Alfakih TM. A hybrid XAI-driven deep learning framework for robust GI tract disease diagnosis. Sci
Rep [Internet]. 2025;15(1):21139. Disponible en: http://doi.org/10.1038/s41598-025-07690-3
28. Gamage L, Isuranga U, Meedeniya D, De Silva S, Yogarajah P. Melanoma Skin Cancer Identification with Explainability Utilizing Mask Guided Technique. Electronics [Internet]. 2024;13(4):680. Disponible en: http://doi.org/10.3390/electronics13040680
29. Gerbasi A, Clementi G, Corsi F, Albasini S, Malovini A, Quaglini S, et al. DeepMiCa: Automatic segmentation and classification of breast MIcroCAlcifications from mammograms. Comput Methods Programs Biomed [Internet]. 2023;235:107483. Disponible en: http://doi.org/10.1016/j.cmpb.2023.107483
30. Guha S, Kodipalli A, Fernandes SL, Dasar S. Explainable AI for Interpretation of Ovarian Tumor Classification Using Enhanced ResNet50. Diagnostics [Internet]. 2024;14(14):1567. Disponible en: http://doi.org/10.3390/diagnostics14141567
31. Haque R, Khan MA, Rahman H, Khan S, Siddiqui MIH, Limon ZH, et al. Explainable deep stacking ensemble model for accurate and transparent brain tumor diagnosis. Comput Biol Med [Internet]. 2025;191:110166. Disponible en: http://doi.org/10.1016/j.compbiomed.2025.110166
32. Hermoza R, Nascimento JC, Carneiro G. Weakly-supervised preclinical tumor localization associated with survival prediction from lung cancer screening Chest X-ray images. Comput Med Imaging Graph [Internet]. 2024 ;115:102395. Disponible en: http://doi.org/10.1016/j.compmedimag.2024.102395
33. Kakon SC, Sazid ZA, Begum IA, Samad MA, Hosen ASMS. Explainable Deep Ensemble Meta-Learning Framework for Brain Tumor Classification Using MRI Images. Cancers [Internet]. 2025;17(17):2853. Disponible en: http://doi.org/10.3390/cancers17172853
34. Kalita M, Mahanta LB, Das AK, Laskar D. An Interpretable Hybrid AI Model for Breast Fine Needle Aspiration Cytology Image Classification. J Med Syst [Internet]. 2025;49(1):182. Disponible en: http://doi.org/10.1007/s10916-025-02267-z
35. Khare SK, Booth BB, Blanes-Vidal V, Petersen LK, Nadimi ES. An explainable attention model for cervical precancer risk classification using colposcopic images. Comput Methods Programs Biomed [Internet]. 2025;271:108976. Disponible en: http://doi.org/10.1016/j.cmpb.2025.108976
36. Latha M, Kumar PS, Chandrika RR, Mahesh TR, Kumar VV, Guluwadi S. Revolutionizing breast ultrasound diagnostics with EfficientNet-B7 and Explainable AI. BMC Med Imaging [Internet]. 2024;24(1):230. Disponible en: http://doi.org/10.1186/s12880-024-01404-3
37. Lee YH, Jeon S, Jung J, Auh QS, Lee JS, Chaurasia A, et al. DCNN models with post-hoc interpretability for the automated detection of glossitis and OSCC on the tongue. Sci Rep [Internet]. 2025;15(1):31940. Disponible en: http://doi.org/10.1038/s41598-025-16760-5
38. Liu H, She Q, Lin J, Chen Q, Fang F, Zhang Y. Attribute and Malignancy Analysis of Lung Nodule on Chest CT with Cause-and-Effect Logic. J Med Biol Eng [Internet]. 2024;44(5):763–76. Disponible en: http://doi.org/10.1007/s40846-024-00895-3
39. Oumlaz M, Oumlaz Y, Oukaira A, Benelhaouare AZ, Lakhssassi A. Advancing Pulmonary Nodule Detection with ARSGNet: EfficientNet and Transformer Synergy. Electronics [Internet]. 2024;13(22):4369. Disponible en: http://doi.org/10.3390/electronics13224369
40. Oviedo F, Kazerouni AS, Liznerski P, Xu Y, Hirano M, Vandermeulen RA, et al. Cancer Detection in Breast MRI Screening via Explainable AI Anomaly Detection. Radiology [Internet]. 2025;316(1):e241629. Disponible en: http://doi.org/10.1148/radiol.241629
41. Rajpoot R, Jain S, Semwal VB. BioTransX: A novel bi-former based hybrid model with bi-level routing attention for brain tumor classification with explainable insights. Comput Biol Med [Internet]. 2025;195:110515. Disponible en: http://doi.org/10.1016/j.compbiomed.2025.110515
42. Rezaeijo SM, Eftekhar A, Rouhi S, Keshavarzi B, Mohammadi Z, Firouzabad LA, et al. Neighboring tissues as diagnostic windows: Neighborhood effects in radiomic detection of pancreatic ductal adenocarcinoma. Comput Methods Programs Biomed [Internet]. 2025;272:109056. Disponible en: http://doi.org/10.1016/j.cmpb.2025.109056
43. Shariaty F, Pavlov V, Baranov M. AI-Driven Precision Oncology: Integrating Deep Learning, Radiomics, and Genomic Analysis for Enhanced Lung Cancer Diagnosis and Treatment. Signal Image Video Process [Internet]. 2025;19(9):693. Disponible en: http://doi.org/10.1007/s11760-025-04244-y
44. Singh A, Nooka AK, Modanwal G, Jain N, Dhodapkar MV, Arepalli S, et al. AI-informed retinal biomarkers predict 10-year risk of onset of multiple hematological malignancies. Eur J Cancer [Internet]. 2025;229. Disponible en: http://doi.org/10.1016/j.ejca.2025.115752
45. Wang H, Wei L, Liu B, Li J, Li J, Fang J, et al. Transformer-Based Explainable Model for Breast Cancer Lesion Segmentation. Appl Sci [Internet]. 2025;15(3):1295. Disponible en: http://doi.org/10.3390/app15031295
46. Wickstrøm K, Kampffmeyer M, Jenssen R. Uncertainty and interpretability in convolutional neural networks for semantic segmentation of colorectal polyps. Med Image Anal [Internet]. 2020;60:101619. Disponible en: http://doi.org/10.1016/j.media.2019.101619
47. Ahmed F, Naz NS, Khan S, Rehman AU, Ismael WM, Khan MA. Explainable artificial intelligence (XAI) in medical imaging: a systematic review of techniques, applications, and challenges. BMC Med Imaging [Internet]. 2026 ;26(1):37. Disponible en: http://doi.org/10.1186/s12880-025-02118-w
48. Abas Mohamed Y, Ee Khoo B, Shahrimie Mohd Asaari M, Ezane Aziz M, Rahiman Ghazali F. Decoding the black box: Explainable AI (XAI) for cancer diagnosis, prognosis, and treatment planning-A state-of-the art systematic review. Int J Med Inf [Internet]. 2025;193:105689. Disponible en: http://doi.org/10.1016/j.ijmedinf.2024.105689
49. Gurmessa Dk, Jimma W. Explainable machine learning for breast cancer diagnosis from mammography and ultrasound images: a systematic review. BMJ Health Care Inform [Internet]. 2024;31(1):e100954. Disponible en: http://doi.org/10.1136/bmjhci-2023-100954
50. Ghasemi A, Hashtarkhani S, Schwartz DL, Shaban‐Nejad A. Explainable artificial intelligence in breast cancer detection and risk prediction: A systematic scoping review. Cancer Innov [Internet]. 2024 Jul 3;3(5):e136. Disponible en: http://doi.org/10.1002/cai2.136
51. Purwono P, Wulandari ANE, Nisa K. Explainable Artificial Intelligence (XAI) in Medical Imaging: Techniques, Applications, Challenges, and Future Directions. Adv Mech Mechatron Syst [Internet]. 2025;1(1):1. Disponible en: http://doi.org/10.53623/amms.v1i1.692
52. Shifa N, Saleh M, Akbari Y, Maadeed SA. A review of explainable AI techniques and their evaluation in mammography for breast cancer screening. Clin Imaging [Internet]. 2025;123. Disponible en: http://doi.org/10.1016/j.clinimag.2025.110492
Descargas
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2026 Walter Fabián Taday Guashpa, Jaime David Camacho Castillo
Esta obra está bajo una licencia internacional Creative Commons Atribución-NoComercial 4.0.
Todo el contenido de esta revista se encuentra en Acceso Abierto, distribuido según los términos de la Licencia Creative Commons Atribución–NoComercial 4.0 que permite el uso, distribución y reproducción no comerciales y sin restricciones en cualquier medio, siempre que sea debidamente citada la fuente primaria de publicación.
Descargar PDF
