Transfer Learning for Pancreatic Ductal Adenocarcinoma: A Comprehensive Review
DOI:
https://doi.org/10.58445/rars.2587Keywords:
Computational Biology and Bioinformatics, Computational Oncology, PDAC, Transfer Learning, Deep LearningAbstract
Transfer learning stands as a breakthrough methodology within artificial intelligence, offering unprecedented advantages in medical imaging and cancer diagnosis. Transfer learning needs less data than deep learning to build models for new problems. This paper explores how transfer learning techniques can improve both the detection and diagnostic accuracy of Pancreatic Ductal Adenocarcinoma (PDAC), a cancer known for its high mortality rate and difficulty in early diagnosis. This review analyzes transfer learning applications to three key data types: computed tomography scans, ultrasound scans, and cell biopsies. While still a young field, early findings suggest that transfer learning improves diagnostic accuracy while reducing the need for data, making it an efficient alternative to traditional deep learning. Transfer learning achieved AUC scores comparable to deep learning and demonstrated higher accuracy than human professionals. However, there is still more to be done in this field, especially the need for further studies to validate transfer learning’s efficacy in PDAC detection. This research underscores the potential use of transfer learning in advancing more effective diagnostics for PDAC, which has significant potential to improve the current poor outcomes.
References
Zhang, L., Sanagapalli, S., & Stoita, A. (2018). Challenges in diagnosis of pancreatic cancer. World Journal of Gastroenterology, 24(19), 2047–2060. https://doi.org/10.3748/wjg.v24.i19.2047
Pancreatic Cancer Diagnosis. (2024, April 5). https://www.hopkinsmedicine.org/health/conditions-and-diseases/pancreatic-cancer/pancreatic-cancer-diagnosis
CT (Computed Tomography) Scan: What It Detects. (n.d.). Cleveland Clinic. Retrieved April 25, 2025, from https://my.clevelandclinic.org/health/diagnostics/4808-ct-computed-tomography-scan
PET Scan: What It Is, Types, Purpose, Procedure & Results. (n.d.). Cleveland Clinic. Retrieved April 25, 2025, from https://my.clevelandclinic.org/health/diagnostics/10123-pet-scan
MRI (Magnetic Resonance Imaging): What It Is & Results. (n.d.). Cleveland Clinic. Retrieved April 25, 2025, from https://my.clevelandclinic.org/health/diagnostics/4876-magnetic-resonance-imaging-mri
Endoscopic Ultrasound (EUS): Procedure, Test & What it Is. (n.d.). Cleveland Clinic. Retrieved April 25, 2025, from https://my.clevelandclinic.org/health/diagnostics/12025-endoscopic-ultrasound
Ultrasound: What It Is, Purpose, Procedure & Results. (n.d.). Cleveland Clinic. Retrieved April 25, 2025, from https://my.clevelandclinic.org/health/diagnostics/4995-ultrasound
How biopsy procedures are used to diagnose cancer. (n.d.). Mayo Clinic. Retrieved April 25, 2025, from https://www.mayoclinic.org/diseases-conditions/cancer/in-depth/biopsy/art-20043922
What is a biopsy and why would I need one? (n.d.). Cleveland Clinic. Retrieved April 25, 2025, from https://my.clevelandclinic.org/health/diagnostics/15458-biopsy-overview
Health, C. for D. and R. (2025). Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices. FDA. https://www.fda.gov/medical-devices/software-medical-device-samd/artificial-intelligence-and-machine-learning-aiml-enabled-medical-devices
Hunter, B., Hindocha, S., & Lee, R. W. (2022). The Role of Artificial Intelligence in Early Cancer Diagnosis. Cancers, 14(6), Article 6. https://doi.org/10.3390/cancers14061524
Luchini, C., Pea, A., & Scarpa, A. (2022). Artificial intelligence in oncology: Current applications and future perspectives. British Journal of Cancer, 126(1), 4–9. https://doi.org/10.1038/s41416-021-01633-1
Usama, M. (2024, July 27). Deep Learning in Healthcare: Algorithms and Applications. Medium. https://medium.com/@usama.6832/introduction-to-deep-learning-in-healthcare-519336d651b1
Bhinder, B., Gilvary, C., Madhukar, N. S., & Elemento, O. (2021). Artificial Intelligence in Cancer Research and Precision Medicine. Cancer Discovery, 11(4), 900–915. https://doi.org/10.1158/2159-8290.CD-21-0090
What is transfer learning? | IBM. (2024, February 12). https://www.ibm.com/think/topics/transfer-learning
Huynh, B., Drukker, K., & Giger, M. (2016). MO-DE-207B-06: Computer-Aided Diagnosis of Breast Ultrasound Images Using Transfer Learning From Deep Convolutional Neural Networks. Medical Physics, 43(6Part30), 3705–3705. https://doi.org/10.1118/1.4957255
Agarwal, D., Marques, G., de la Torre-Díez, I., Franco Martin, M. A., García Zapiraín, B., & Martín Rodríguez, F. (2021). Transfer Learning for Alzheimer’s Disease through Neuroimaging Biomarkers: A Systematic Review. Sensors, 21(21), Article 21. https://doi.org/10.3390/s21217259
Al-Shouka, T. T., & Alheeti, K. M. A. (2023). A Transfer Learning for Intelligent Prediction of Lung Cancer Detection. 2023 Al-Sadiq International Conference on Communication and Information Technology (AICCIT), 54–59. https://doi.org/10.1109/AICCIT57614.2023.10217967
Valverde, J. M., Imani, V., Abdollahzadeh, A., De Feo, R., Prakash, M., Ciszek, R., & Tohka, J. (2021). Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review. Journal of Imaging, 7(4), 66. https://doi.org/10.3390/jimaging7040066
What is Survival Analysis in Machine Learning. (n.d.). JADBio - Automated Machine Learning - AutoML. Retrieved April 25, 2025, from https://jadbio.com/what-is-survival-analysis/
Segmentation vs Detection vs Classification in Computer Vision: A Comparative Analysis — Picsellia. (n.d.). Retrieved April 25, 2025, from https://www.picsellia.com/post/segmentation-vs-detection-vs-classification-in-computer-vision-a-comparative-analysis
Feature Extraction. (2019, May 17). DeepAI. https://deepai.org/machine-learning-glossary-and-terms/feature-extraction
Tanisha.Digital. (2024, December 30). Key Evaluation Metrics For AI Model Performance. Gen AI Adventures. https://medium.com/gen-ai-adventures/key-evaluation-metrics-for-ai-model-performance-8e372f17a0a2
Allende, A. S. (2024, March 12). Concordance index. Analytics Vidhya. https://medium.com/analytics-vidhya/concordance-index-72298c11eac7
Kattan, M. W., & Gerds, T. A. (2018). The index of prediction accuracy: An intuitive measure useful for evaluating risk prediction models. Diagnostic and Prognostic Research, 2(1), 7. https://doi.org/10.1186/s41512-018-0029-2
Shreffler, J., & Huecker, M. R. (2025). Diagnostic Testing Accuracy: Sensitivity, Specificity, Predictive Values and Likelihood Ratios. In StatPearls. StatPearls Publishing. http://www.ncbi.nlm.nih.gov/books/NBK557491/
Zhang, Y., Lobo-Mueller, E. M., Karanicolas, P., Gallinger, S., Haider, M. A., & Khalvati, F. (2020). CNN-based survival model for pancreatic ductal adenocarcinoma in medical imaging. BMC Medical Imaging, 20(1), 11. https://doi.org/10.1186/s12880-020-0418-1
Zhang, Y., Lobo-Mueller, E. M., Karanicolas, P., Gallinger, S., Haider, M. A., & Khalvati, F. (2021). Improving prognostic performance in resectable pancreatic ductal adenocarcinoma using radiomics and deep learning features fusion in CT images. Scientific Reports, 11(1), 1378. https://doi.org/10.1038/s41598-021-80998-y
Kothawade, S., & Sherje, N. (2023). Prediction Analysis of Pancreatic Tumour using Transfer Learning. Research Journal of Computer Systems and Engineering, 4(1), Article 1. https://doi.org/10.52710/rjcse.58
Zhu, X., Xiang, D., Shi, F., Zhu, W., & Chen, X. (2023). Pancreatic CT image segmentation based on transfer learning. Medical Imaging 2023: Image Processing, 12464, 848–853. https://doi.org/10.1117/12.2651437
Kim, S., Kim, S., Kim, E., Cecchini, M., Park, M.-S., Choi, J. A., Kim, S. H., Hwang, H. K., Kang, C. M., Choi, H. J., Shin, S. J., Kang, J., & Lee, C. (2024). Deep-Transfer-Learning–Based Natural Language Processing of Serial Free-Text Computed Tomography Reports for Predicting Survival of Patients With Pancreatic Cancer. JCO Clinical Cancer Informatics, 8, e2400021. https://doi.org/10.1200/CCI.24.00021
Chhikara, J., Goel, N., & Rathee, N. (2025). Integrating expert guidance with gradual moment approximation (GMAp)-enhanced transfer learning for improved pancreatic cancer classification. Neural Computing and Applications, 37(3), 1357–1373. https://doi.org/10.1007/s00521-024-10521-7
Chen, P.-T., Wu, T., Wang, P., Chang, D., Liu, K.-L., Wu, M.-S., Roth, H. R., Lee, P.-C., Liao, W.-C., & Wang, W. (2023). Pancreatic Cancer Detection on CT Scans with Deep Learning: A Nationwide Population-based Study. Radiology, 306(1), 172–182. https://doi.org/10.1148/radiol.220152
Cao, K., Xia, Y., Yao, J., Han, X., Lambert, L., Zhang, T., Tang, W., Jin, G., Jiang, H., Fang, X., Nogues, I., Li, X., Guo, W., Wang, Y., Fang, W., Qiu, M., Hou, Y., Kovarnik, T., Vocka, M., … Lu, J. (2023). Large-scale pancreatic cancer detection via non-contrast CT and deep learning. Nature Medicine, 29(12), 3033–3043. https://doi.org/10.1038/s41591-023-02640-w
Gandikota, H. P., S, A., & M, S. K. (2023). CT scan pancreatic cancer segmentation and classification using deep learning and the tunicate swarm algorithm. PLOS ONE, 18(11), e0292785. https://doi.org/10.1371/journal.pone.0292785
Ramaekers, M., Viviers, C. G. A., Hellström, T. A. E., Ewals, L. J. S., Tasios, N., Jacobs, I., Nederend, J., Sommen, F. van der, Luyer, M. D. P., & E/MTIC Oncology Collaborative Group. (2024). Improved Pancreatic Cancer Detection and Localization on CT Scans: A Computer-Aided Detection Model Utilizing Secondary Features. Cancers, 16(13), 2403. https://doi.org/10.3390/cancers16132403
Alves, N., Schuurmans, M., Litjens, G., Bosma, J. S., Hermans, J., & Huisman, H. (2022). Fully Automatic Deep Learning Framework for Pancreatic Ductal Adenocarcinoma Detection on Computed Tomography. Cancers, 14(2), Article 2. https://doi.org/10.3390/cancers14020376
Cheng, P. M., & Malhi, H. S. (2017). Transfer Learning with Convolutional Neural Networks for Classification of Abdominal Ultrasound Images. Journal of Digital Imaging, 30(2), 234–243. https://doi.org/10.1007/s10278-016-9929-2
Baldota, S., Sharma, S., & Malathy, C. (2021). Deep Transfer Learning for Pancreatic Cancer Detection. 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), 1–7. https://doi.org/10.1109/ICCCNT51525.2021.9580000
Tian, G., Xu, D., He, Y., Chai, W., Deng, Z., Cheng, C., Jin, X., Wei, G., Zhao, Q., & Jiang, T. (2022). Deep learning for real-time auxiliary diagnosis of pancreatic cancer in endoscopic ultrasonography. Frontiers in Oncology, 12, 973652. https://doi.org/10.3389/fonc.2022.973652
Saraiva, M. M., González-Haba, M., Widmer, J., Mendes, F., Gonda, T., Agudo, B., Ribeiro, T., Costa, A., Fazel, Y., Lera, M. E., Horneaux de Moura, E., Ferreira de Carvalho, M., Bestetti, A., Afonso, J., Martins, M., Almeida, M. J., Vilas-Boas, F., Moutinho-Ribeiro, P., Lopes, S., … Macedo, G. (2024). Deep Learning and Automatic Differentiation of Pancreatic Lesions in Endoscopic Ultrasound: A Transatlantic Study. Clinical and Translational Gastroenterology, 15(11), e00771. https://doi.org/10.14309/ctg.0000000000000771
Kronberg, R. M., Haeberle, L., Pfaus, M., Xu, H. C., Krings, K. S., Schlensog, M., Rau, T., Pandyra, A. A., Lang, K. S., Esposito, I., & Lang, P. A. (2022). Communicator-Driven Data Preprocessing Improves Deep Transfer Learning of Histopathological Prediction of Pancreatic Ductal Adenocarcinoma. Cancers, 14(8), 1964. https://doi.org/10.3390/cancers14081964
Saillard, C., Delecourt, F., Schmauch, B., Moindrot, O., Svrcek, M., Bardier-Dupas, A., Emile, J. F., Ayadi, M., Rebours, V., de Mestier, L., Hammel, P., Neuzillet, C., Bachet, J. B., Iovanna, J., Dusetti, N., Blum, Y., Richard, M., Kermezli, Y., Paradis, V., … Cros, J. (2023). Pacpaint: A histology-based deep learning model uncovers the extensive intratumor molecular heterogeneity of pancreatic adenocarcinoma. Nature Communications, 14(1), 3459. https://doi.org/10.1038/s41467-023-39026-y
DeMarco, C. (n.d.). What is a biopsy? 7 questions, answered. MD Anderson Cancer Center. Retrieved April 26, 2025, from https://www.mdanderson.org/cancerwise/what-is-a-biopsy--7-questions-answered.h00-159621801.html
Ohno, E., Kawashima, H., Ishikawa, T., Mizutani, Y., Iida, T., Nishio, R., Uetsuki, K., Yashika, J., Yamada, K., Yoshikawa, M., Gibo, N., Aoki, T., Kataoka, K., Mori, H., Takada, Y., Aoi, H., Takahashi, H., Yamamura, T., Furukawa, K., … Fujishiro, M. (2022). The role of EUS elastography-guided fine needle biopsy in the histological diagnosis of solid pancreatic lesions: A prospective exploratory study. Scientific Reports, 12(1), 16603. https://doi.org/10.1038/s41598-022-21178-4
Naito, Y., Tsuneki, M., Fukushima, N., Koga, Y., Higashi, M., Notohara, K., Aishima, S., Ohike, N., Tajiri, T., Yamaguchi, H., Fukumura, Y., Kojima, M., Hirabayashi, K., Hamada, Y., Norose, T., Kai, K., Omori, Y., Sukeda, A., Noguchi, H., … Yano, H. (2021). A deep learning model to detect pancreatic ductal adenocarcinoma on endoscopic ultrasound-guided fine-needle biopsy. Scientific Reports, 11(1), 8454. https://doi.org/10.1038/s41598-021-87748-0
Mahmoudi, T., Kouzahkanan, Z. M., Radmard, A. R., Kafieh, R., Salehnia, A., Davarpanah, A. H., Arabalibeik, H., & Ahmadian, A. (2022). Segmentation of pancreatic ductal adenocarcinoma (PDAC) and surrounding vessels in CT images using deep convolutional neural networks and texture descriptors. Scientific Reports, 12(1), 3092. https://doi.org/10.1038/s41598-022-07111-9
Downloads
Posted
Categories
License
Copyright (c) 2025 Jonathan Song
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.