Enhancing AI-Driven Diagnosis of Invasive Ductal Carcinoma with Morphologically Guided and Interpretable Deep Learning
Source abstract
Abstract
Artificial intelligence is increasingly shaping the landscape of computer-aided diagnosis of breast cancer. Despite incrementally improved accuracy, pathologist supervision remains essential for verified interpretation. While prior research focused on devising deep model architecture, this study examines the pivotal role of multi-band visual-enhanced features in invasive ductal carcinoma classification using whole slide imaging. Our results showed that orientation invariant filters achieved an accuracy of 0.8125, F1-score of 0.8134, and AUC of 0.8761, while preserving cellular arrangement and tissue morphology. By utilizing spatial relationships across varying extents, the proposed fusion strategy aligns with pathological interpretation principles. While integrating Gabor wavelet responses into ResNet-50 enhanced feature association, the comparative analysis emphasized the benefits of weighted morphological fusion, further strengthening diagnostic performance. These insights underscore the crucial role of informative filters in advancing DL schemes for breast cancer screening. Future research incorporating diverse, multi-center datasets could further validate the approach and broaden its diagnostic applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: AI in cancer detection · Radiomics and Machine Learning in Medical Imaging · Colorectal Cancer Screening and Detection
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Engineering, Institute of Engineering, Suranaree University of Technology, Nakhon Ratchasima 30000, Thailand
Funding
Suranaree University of Technology (SUT)
References (50)
Show source-provided references
1. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries10.3322/caac.21834 ↗
2. Comparative study of cancer profiles between 2020 and 2022 using global cancer statistics (GLOBOCAN)10.1016/j.jncc.2024.05.001 ↗
3. American Cancer Society (2025, April 17). Invasive Breast Cancer (IDC/ILC). American Cancer Society. Available online: https://www.cancer.org/cancer/types/breast-cancer/about/types-of-breast-cancer/invasive-breast-cancer.html.
4. Murcia-Gómez, D., Rojas-Valenzuela, I., and Valenzuela, O. (2022). Impact of image preprocessing methods and deep learning models for classifying histopathological breast cancer images. Appl. Sci., 12.10.3390/app122211375 ↗
5. Evolutionary measures show that recurrence of DCIS is distinct from progression to breast cancer10.1186/s13058-025-01966-2 ↗
6. Golestan, A., Tahmasebi, A., Maghsoodi, N., Faraji, S.N., Irajie, C., and Ramezani, A. (2024). Unveiling promising breast cancer biomarkers: An integrative approach combining bioinformatics analysis and experimental verification. BMC Cancer, 24.10.1186/s12885-024-11913-7 ↗
7. Exploring the immunomodulatory potential of Brahmi (Bacopa monnieri) in the treatment of invasive ductal carcinoma10.1007/s12032-024-02365-x ↗
8. Artificial intelligence in disease diagnostics: A critical review and classification on the current state of research guiding future direction10.1007/s12553-021-00555-5 ↗
9. Artificial intelligence in disease diagnosis: A systematic literature review, synthesizing framework and future research agenda10.1007/s12652-021-03612-z ↗
10. Edge deep learning in computer vision and medical diagnostics: A comprehensive survey10.1007/s10462-024-11033-5 ↗
11. NVIDIA (2023, July 02). CUDA Toolkit (release 11.8). Available online: https://developer.nvidia.com/cuda-toolkit.
12. Chen, H., Belash, E., Liu, Y., and Recheis, M. (2025, February 05). TensorFlow.NET: Google’s TensorFlow full binding in .NET Standard. Available online: https://github.com/SciSharp/TensorFlow.NET.
13. Very deep convolutional networks for large-scale image recognition
14. Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
15. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
16. A review on deep learning in medical image analysis10.1007/s13735-021-00218-1 ↗
17. A comprehensive review of deep neural networks for medical image processing: Recent developments and future opportunities10.1016/j.health.2023.100216 ↗
18. Mahmud, T., Barua, K., Habiba, S.U., Sharmen, N., Hossain, M.S., and Andersson, K. (2024). An explainable AI paradigm for Alzheimer’s diagnosis using deep transfer learning. Diagnostics, 14.10.3390/diagnostics14030345 ↗
19. A Practical Guide to Whole Slide Imaging: A White Paper from the Digital Pathology Association10.5858/arpa.2018-0343-RA ↗
20. Artificial intelligence as a tool for diagnosis in digital pathology whole slide images: A systematic review10.1016/j.jpi.2022.100138 ↗
21. Transforming diagnostics: A comprehensive review of advances in digital pathology
22. Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., and Li, S. (2022). ReMix: A General and Efficient Framework for Multiple Instance Learning Based Whole Slide Image Classification. Medical Image Computing and Computer Assisted Intervention—MICCAI 2022. MICCAI 2022, Springer. Lecture Notes in Computer Science.10.1007/978-3-031-16434-7_4 ↗
23. Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Bag-Level Classifier is a Good Instance-Level Teacher10.1109/TMI.2024.3404549 ↗
24. Validating whole slide imaging systems for diagnostic purposes in pathology: Guideline update from the College of American Pathologists10.5858/arpa.2020-0723-CP ↗
25. A tree based multiclassification of breast tumor histopathology images through deep learning10.1016/j.compmedimag.2021.101870 ↗
26. Quantitative assessment of H&E staining for pathology: Development and clinical evaluation of a novel system10.1186/s13000-024-01461-w ↗
27. Color transfer between images10.1109/38.946629 ↗
28. ImageNet classification with deep convolutional neural networks
29. Multi-focus image fusion with a deep convolutional neural network10.1016/j.inffus.2016.12.001 ↗
30. A comprehensive review of explainable AI for disease diagnosis10.1016/j.array.2024.100345 ↗
31. Unveiling the black box: A systematic review of Explainable Artificial Intelligence in medical image analysis10.1016/j.csbj.2024.08.005 ↗
32. Automatic grading of barley grain for brewery industries using convolutional neural network based on texture features
33. Serte, S., and Demirel, H. (2019). Gabor wavelet-based deep learning for skin lesion classification. Comput. Biol. Med., 113.10.1016/j.compbiomed.2019.103423 ↗
34. Deep Gabor convolution network for person re-identification10.1016/j.neucom.2019.10.083 ↗
35. Deep Gabor Neural Network for Automatic Detection of Mine-Like Objects in Sonar Imagery10.1109/ACCESS.2020.2995390 ↗
36. Jaber, A.G., Muniyandi, R.C., Usman, O.L., and Singh, H.K.R. (2022). A Hybrid Method of Enhancing Accuracy of Facial Recognition System Using Gabor Filter and Stacked Sparse Autoencoders Deep Neural Network. Appl. Sci., 12.10.3390/app122111052 ↗
37. Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases10.4103/2153-3539.186902 ↗
38. Mooney, P. (2024, December 02). (n.d.). Breast Histopathology Images [Data Set]. Kaggle. Available online: https://www.kaggle.com/datasets/paultimothymooney/breast-histopathology-images.
39. Theory of communication
40. Learning 2D Gabor filters by infinite kernel learning regression10.1016/j.jcmds.2021.100016 ↗
41. Alekseev, A., and Bobe, A. (2019, January 20–21). GaborNet: Gabor filters with learnable parameters in deep convolutional neural network. Proceedings of the 2019 International Conference on Engineering and Telecommunication (EnT), Dolgoprudny, Russia.10.1109/EnT47717.2019.9030571 ↗
42. Families of models for gabor paths demonstrate the importance of spatial adjacency10.1167/8.7.23 ↗
43. Saleh, A.Y., and Chern, L.H. (2021). Autism spectrum disorder classification using deep learning. Int. J. Online Biomed. Eng., 17.10.3991/ijoe.v17i08.24603 ↗
44. Pereira, C., Guede-Fernández, F., Vigário, R., Coelho, P., Fragata, J., and Londral, A. (2023). Image analysis system for early detection of cardiothoracic surgery wound alterations based on artificial intelligence models. Appl. Sci., 13.10.3390/app13042120 ↗
45. GLMKD: Joint global and local mutual knowledge distillation for weakly supervised lesion segmentation in histopathology images, Expert10.1016/j.eswa.2025.127425 ↗
46. Adaptive Gabor convolutional networks10.1016/j.patcog.2021.108495 ↗
47. Finger vein recognition: Utilization of adaptive gabor filters in the enhancement stage combined with SIFT/SURF-based feature extraction10.1007/s11760-022-02270-8 ↗
48. Ensemble deep learning: A review10.1016/j.engappai.2022.105151 ↗
49. A Survey on ensemble learning under the era of deep learning10.1007/s10462-022-10283-5 ↗
50. Clinicopathologic characteristics of pleomorphic carcinoma of the breast10.1007/s00428-009-0862-3 ↗