Artificial intelligence modelling in differentiating core biopsies of fibroadenoma from phyllodes tumor

Chee Leong Cheng, Nur Diyana Md Nasir, Gary Jian Zhe Ng, Kenny Wei Jie Chua, Yier Li, Joshua Rodrigues, Aye Aye Thike, Seow Ye Heng, Valerie Cui Yun Koh, Johnathan Xiande Lim, Venice Jing Ning Hiew, Ruoyu Shi, Benjamin Yongcheng Tan, Timothy Kwang Yong Tay, Sudha Ravi, Kim Hock Ng, Kevin Seng Loong Oh, Puay Hoon Tan, Chee Leong Cheng, Nur Diyana Md Nasir, Gary Jian Zhe Ng, Kenny Wei Jie Chua, Yier Li, Joshua Rodrigues, Aye Aye Thike, Seow Ye Heng, Valerie Cui Yun Koh, Johnathan Xiande Lim, Venice Jing Ning Hiew, Ruoyu Shi, Benjamin Yongcheng Tan, Timothy Kwang Yong Tay, Sudha Ravi, Kim Hock Ng, Kevin Seng Loong Oh, Puay Hoon Tan

Abstract

Breast fibroepithelial lesions (FEL) are biphasic tumors which consist of benign fibroadenomas (FAs) and the rarer phyllodes tumors (PTs). FAs and PTs have overlapping features, but have different clinical management, which makes correct core biopsy diagnosis important. This study used whole-slide images (WSIs) of 187 FA and 100 PT core biopsies, to investigate the potential role of artificial intelligence (AI) in FEL diagnosis. A total of 9228 FA patches and 6443 PT patches was generated from WSIs of the training subset, with each patch being 224 × 224 pixel in size. Our model employed a two-stage architecture comprising a convolutional neural network (CNN) component for feature extraction from the patches, and a recurrent neural network (RNN) component for whole-slide classification using activation values from the global average pooling layer in the CNN model. It achieved an overall slide-level accuracy of 87.5%, with accuracies of 80% and 95% for FA and PT slides respectively. This affirms the potential role of AI in diagnostic discrimination between FA and PT on core biopsies which may be further refined for use in routine practice.

© 2021. The Author(s), under exclusive licence to United States and Canadian Academy of Pathology.

References

    1. WHO Classification of Tumours Editorial Board. WHO classification of tumours of the breast, 5th edn. Lyon: IARC Press; 2019.
    1. Tan, P. H. Fibroepithelial lesions revisited: implications for diagnosis and management. Mod. Pathol. 34, 15–37 (2021).
    1. Tan, B. Y. et al. Phyllodes tumours of the breast: a consensus review. Histopathology 68, 5–21 (2016).
    1. Jacklin, R. K. et al. Optimising preoperative diagnosis in phyllodes tumour of the breast. J. Clin. Pathol. 59, 454–459 (2006).
    1. McCarthy, E. et al. Phyllodes tumours of the breast: radiological presentation, management and follow-up. Br. J. Radiol. 87, 20140239 (2014).
    1. Yasir, S. et al. Cellular fibroepithelial lesions of the breast: a long term follow up study. Ann. Diagn. Pathol. 35, 85–91 (2018).
    1. Komenaka, I. K., El-Tamer, M., Pile-Spellman, E. & Hibshoosh, H. Core needle biopsy as a diagnostic tool to differentiate phyllodes tumor from fibroadenoma. Arch. Surg. 138, 987–990 (2003).
    1. Jacobs, T. W. et al. Fibroepithelial lesions with cellular stroma on breast core needle biopsy: are there predictors of outcome on surgical excision? Am. J. Clin. Pathol. 124, 342–354 (2005).
    1. Dillon, M. F. et al. Needle core biopsy in the diagnosis of phyllodes neoplasm. Surgery 140, 779–784 (2006).
    1. Lee, A. H., Hodi, Z., Ellis, I. O. & Elston, C. W. Histological features useful in the distinction of phyllodes tumor and fibroadenoma on needle core biopsy of the breast. Histopathology 51, 336–344 (2007).
    1. Morgan, J. M., Douglas-Jones, A. G. & Gupta, S. K. Analysis of histological features in needle core biopsy of breast useful in preoperative distinction between fibroadenoma and phyllodes tumour. Histopathology 56, 489–500 (2010).
    1. Jara-Lazaro, A. R. et al. Predictors of phyllodes tumours on core biopsy specimens of fibroepithelial neoplasms. Histopathology 57, 220–232 (2010).
    1. Resetkova, E., Khazai, L., Albarracin, C. T. & Arribas, E. Clinical and radiologic data and core needle biopsy findings should dictate management of cellular fibroepithelial tumors of the breast. Breast J. 16, 573–580 (2010).
    1. Ward, S. T. et al. The sensitivity of needle core biopsy in combination with other investigations for the diagnosis of phyllodes tumours of the breast. Int. J. Surg. 10, 527–531 (2012).
    1. Gould, D. J. et al. Factors associated with phyllodes tumor of the breast after core needle biopsy identifies fibroepithelial neoplasm. J. Surg. Res. 178, 299–303 (2012).
    1. Van Osdol, A. D. et al. Determining whether excision of all fibroepithelial lesions of the breast is needed to exclude phyllodes tumor: upgrade rate of fibroepithelial lesions of the breast to phyllodes tumor. JAMA Surg. 149, 1081–1085 (2014).
    1. Tan, B. Y. et al. Morphologic and genetic heterogeneity in breast fibroepithelial lesions-a comprehensive mapping study. Mod. Pathol. 33, 1732–1745 (2020).
    1. Pareja, F. et al. Phyllodes tumors with and without fibroadenoma-like areas display distinct genomic features and may evolve through distinct pathways. NPJ Breast Cancer 3, 40 (2017).
    1. Lawton, T. J. et al. Interobserver variability by pathologists in the distinction between cellular fibroadenomas and phyllodes tumors. Int. J. Surg. Pathol. 22, 695–698 (2014).
    1. Dessauvagie, B. F. et al. Interobserver variation in the diagnosis of fibroepithelial lesions of the breast: a multicentre audit by digital pathology. J. Clin. Pathol. 71, 672–679 (2018).
    1. Tan, W. J. et al. A five-gene reverse transcription-PCR assay for pre-operative classification of breast fibroepithelial lesions. Breast Cancer Res. 18, 31 (2016).
    1. Sim, Y. et al. A novel genomic panel as an adjunctive diagnostic tool for the characterization and profiling of breast Fibroepithelial lesions. BMC Med. Genom. 12, 142 (2019).
    1. Ng, C. C. Y. et al. Genetic differences between benign phyllodes tumors and fibroadenomas revealed through targeted next generation sequencing. Mod. Pathol. 34, 1320–1332 (2021).
    1. Iizuka, O. et al. Deep learning models for histopathological classification of gastric and colonic epithelial tumours. Sci. Rep. 10, 1–11 (2020).
    1. Dimitriou, N., Arandjelović, O. & Caie, P. D. Deep learning for whole slide image analysis: an overview. Front. Med. 6, 264 (2019). Erratum in: Front Med (Lausanne) 7, 419 (2020).
    1. Ianni, J. D. et al. Tailored for real-world: a whole slide image classification system validated on uncurated multi-site data emulating the prospective pathology workload. Sci. Rep. 10, 3217 (2020).
    1. Chan, A. & Tuszynski, J. A. Automatic prediction of tumour malignancy in breast cancer with fractal dimension. R Soc. Open Sci. 3, 160558 (2016).
    1. Xie, J., Liu, R., Luttrell, J. IV & Zhang, C. Deep learning based analysis of histopathological images of breast cancer. Front. Genet. 10, 80 (2019).
    1. Zheng, Y. et al. Feature extraction from histopathological images based on nucleus-guided convolutional neural network for breast lesion classification. Pattern Recognit. 71, 14–25 (2017).
    1. Han, Z. et al. Breast cancer multi-classification from histopathological images with structured deep learning model. Sci. Rep. 7, 4172 (2017).
    1. Bautista, P. A. & Yagi, Y. Improving the visualization and detection of tissue folds in whole slide images through colour enhancement. J. Pathol. Inform. 1, 25 (2010).
    1. Macenko, M., et al. A method for normalizing histology slides for quantitative analysis. Proceedings of the IEEE International Symposium on Biomedical Imaging, 1107-1110 (IEEE, 2009).
    1. Mahbod, A., Ellinger, I., Ecker, R., Örjan, S. Breast cancer histological image classification using fine-tuned deep network fusion. In: Campilho, A., Karray, F.& Romney, B. T. H., eds. Image analysis and recognition. p. 754–762 (Springer, Switzerland, 2018).
    1. Rakhlin, A., Shvets, A., Iglovikov, V., Kalinin, A. A. Deep convolutional neural networks for breast cancer histology image analysis. In: Campilho, A., Karray, F. & Romney, B. T. H., eds. Image Analysis and Recognition. p. 737-744 (Springer, Switzerland, 2018).
    1. Wang, Y., Dong, N., Dai, W., Rosario, S. D., Xing, E. P. Classification of breast cancer histopathological images using convolutional neural networks with hierarchical loss and global pooling. In: Campilho, A., Karray, F., Romney, B. T. H., eds. Image Analysis and Recognition. p. 845–852 (Springer, Switzerland, 2018).
    1. He, K., Zhang, X., Ren, S., Sun, J. Deep residual learning for image recognition. In: Proceedings of the IEEE Computing Society Conference on Computer Vision and Pattern Recognition, 770–778 (CVPR, 2016).
    1. Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735–1780 (1997).
    1. Kingma D. P., Ba, J. Adam: A method for stochastic optimization. Preprint at (2014).
    1. Biewald L. Experiment tracking with weights and biases. Weights and Biases, 2020. .
    1. Chow, Z. L. et al. Counting mitoses with digital pathology in breast phyllodes tumors. Arch. Pathol. Lab. Med. 144, 1397–1400 (2020).
    1. Stoffel, E. et al. Distinction between phyllodes tumor and fibroadenoma in breast ultrasound using deep learning image analysis. Eur. J. Radiol. Open 5, 165–170 (2018).
    1. Reddy, S. B., Juliet, D. S. Transfer learning with ResNet-50 for malaria cell-image classification. In: IEEE International Conference on Communication and Signal Processing. 949 (IEEE, 2019).
    1. Ferreira, C. A. et al. Classification of breast cancer histology images through transfer learning using a pre-trained inception Resnet V2. In: Campilho, A., Karray, F., & ter Haar Romeny, B., eds. Image Analysis and Recognition. ICIAR 2018. Lecture Notes in Computer Science, vol. 10882. p. 763–770. (Springer, Switzerland, 2018).
    1. Hong, J., Cheng, H., Zhang, Y. D. & Liu, J. Detecting cerebral microbleeds with transfer learning. Mach. Vis. Appl. 30, 1123–1133 (2019).
    1. Huang, W. C. et al. Automatic HCC detection using convolutional network with multi-magnification input images. In: 2019 IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), 194-198 (IEEE, 2019).
    1. Pratiher, S., Chattoraj, S., Agarwal, S., Bhattacharya, S. Grading tumor malignancy via deep bidirectional LSTM on graph manifold encoded histopathological image. In: IEEE International Conference on Data Mining Workshops, 674–681 (IEEE, 2018).
    1. Kong, B., Wang, X., Li, Z., Song, Q., Zhang, S. Cancer metastasis detection via spatially structured deep network. In: Niethammer, M., Styner, M., Aylward, S., Zhu, H., Oguz, I., Yap, P. T. & Shen, D., eds. Information Processing in Medical Imaging. p. 236–248 (Springer, Switzerland, 2017).

Source: PubMed

Patrocinadores e Colaboradores

Condições médicas

Intervenções de drogas

3
Se inscrever