Home / Current Issue / Paper 1723671
Automatic Lymphocyte Detection On Gastric Cancer Using Deep Learning
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence and Deep Learning
Abstract
Gastric cancer still has rather high rates of incidences around the globe and the amount of tumor infiltrating lymphocytes in the tumor tissues has proved to be a reliable predictor of prognosis in patients suffering from this type of disease. At this point, the manual count of TILs had been performed by pathologists on tissue samples stained and analyzed under microscope. The paper suggests a fully automated pipeline for detecting lymphocytes in the histological pictures of patients with gastric cancer using YOLOv5 detector with ResNet-50 backbone. Namely, the pipeline presupposes slicing the picture into overlapped tiles, colour stain distribution normalization based on the Macenko algorithm, data set augmentation, and providing the slices to detection head that was upgraded by means of feature pyramid network, anchor optimization by k-means and convolutional block attention module, allowing for highlighting the features specific for lymphocytes. Duplications in the tile borders are handled through non-maximum suppression and weighted box fusion. As the data set used for testing is quite small, the precision of detections exceeded 92% and exact values of precision, recall and F1-score should be determined once the training is over. Tumor-infiltrating lymphocytes (TILs) are important indicators in cancer research because their abundance and distribution can be associated with prognosis and other clinical characteristics. For pathologists, identifying these immune cells in gastric cancer tissue images.
Keywords
lymphocyte detection; deep learning; gastric cancer; cell detection; convolutional neural network
References
[1] Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians. 2018;68(6):394–424.
[2] Veta M, Pluim JP, van Diest PJ, Viergever MA. Breast cancer histopathology image analysis: A review. IEEE Transactions on Biomedical Engineering. 2014;61(5):1400–1411.
[3] Ciresan DC, Giusti A, Gambardella LM, Schmidhuber J. Mitosis detection in breast cancer histology images with deep neural networks. In: Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). Berlin: Springer; 2013.
[4] Sirinukunwattana K, Raza SEA, Tsang YW. IEEE Transactions on Medical Imaging. 2016;35(5):1196–1206.
[5] Saltz J, Gupta R, Hou L, Kurc T, Singh P, Nguyen V, et al. Spatial organization and molecular correlation of tumor-infiltrating lymphocytes using deep learning on pathology images. Cell Reports. 2018;23(1):181–193.
[6] Amgad M, Elfandy H, Hussein H, Atteya LA, Elsebaie MAT, Abo Elnasr LS, et al. Structured crowdsourcing enables convolutional segmentation of histology images. Bioinformatics. 2019;35(18):3461–3467.
[7] Salgado R, Denkert C, Demaria S, Sirtaine N, Klauschen F, Pruneri G, et al. The evaluation of tumor-infiltrating lymphocytes (TILs) in breast cancer: recommendations by an International TILs Working Group 2014. Annals of Oncology. 2015;26(2):259–271.
[8] Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: Unified, real-time object detection. In: Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR). 2016.
[9] Ren S, He K, Girshick R, Sun J. Faster R-CNN: Towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems (NeurIPS). 2015.
[10] Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko A. End-to-end object detection with transformers. In: Proceedings of the European Conference on Computer Vision (ECCV). Cham: Springer; 2020.
How to cite this paper
@article{1723671,
author = {Avinash Chikkayya Kamble, G G Yashwanth, Bhanu Kiran, Bhagyashri Wakde, Soniya Komal V},
title = {Automatic Lymphocyte Detection On Gastric Cancer Using Deep Learning},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {10},
number = {4},
pages = {1237-1245},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1723671.pdf},
abstract = {Gastric cancer still has rather high rates of incidences around the globe and the amount of tumor infiltrating lymphocytes in the tumor tissues has proved to be a reliable predictor of prognosis in patients suffering from this type of disease. At this point, the manual count of TILs had been performed by pathologists on tissue samples stained and analyzed under microscope. The paper suggests a fully automated pipeline for detecting lymphocytes in the histological pictures of patients with gastric cancer using YOLOv5 detector with ResNet-50 backbone. Namely, the pipeline presupposes slicing the picture into overlapped tiles, colour stain distribution normalization based on the Macenko algorithm, data set augmentation, and providing the slices to detection head that was upgraded by means of feature pyramid network, anchor optimization by k-means and convolutional block attention module, allowing for highlighting the features specific for lymphocytes. Duplications in the tile borders are handled through non-maximum suppression and weighted box fusion. As the data set used for testing is quite small, the precision of detections exceeded 92% and exact values of precision, recall and F1-score should be determined once the training is over. Tumor-infiltrating lymphocytes (TILs) are important indicators in cancer research because their abundance and distribution can be associated with prognosis and other clinical characteristics. For pathologists, identifying these immune cells in gastric cancer tissue images.},
keywords = {lymphocyte detection; deep learning; gastric cancer; cell detection; convolutional neural network},
month = {October},
}