Improved Prediction of Geckler Classification in Gram Stained Smears Images for Sputum
DOI:
https://doi.org/10.52731/liir.v006.407Keywords:
Gram stained smears images, Geckler classification, image classification, object detectionAbstract
In this paper, we predict Geckler classification as Geckler classes and quality classes in Gram stained smears images for sputum, by using image classification and object detection. Here, we adopt VGG, MobileNet, DenseNet, RegNet, ConvNeXt, ViT and EfficientNet as image classifiers and YOLO11, HIC-YOLO11 and SOD-YOLO11 as object detectors. Note that, whereas the image classifiers classify the classes of images directly, the object detectors first detect buccal squamous epithelial (BSE) cells and leukocytes in the image and then predict the class of the image by the number of them.
References
J. W. Bartholomew, T. Mittwer: The Gram stain, Bacteriol. Rev. 16, 1–29 (1952). https://doi.org/10.1128/br.16.1.1-29.1952.
J.G. Bartlett, N. S. Brewer, K. J. Ryan: Cumitech 7: Laboratory diagnosis of lower respiratory tract infections, American Society for Microbiology (1978).
E. M. Chen, S. S. Kasturi: Microbiology and immunology (2nd edition), McGraw Hill (2010).
M. Crossman, A. Wiliem, J. Jennings, B. C. Lovell: A multiple covariance approach for cell detection of Gram-stained smears images, Proc. ICASSP’15, 932–936 (2015). https://doi.org/10.1109/ICASSP.2015.7178106.
A. Dosoviskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, N. Houlsby: An image is worth 16×16 words: Transformers for image recognition at scale, Proc. ICLR’21 (2021). https://openreview.net/forum?id=YicbFdNTTy.
M. Everingham, L. V. Gool, C. K. I. Williams, J. Winn, A. Zisserman: The PASCAL visual object classes (VOC) challenge, Internat. J. Comput. Vision 88, 303–338 (2010). https://doi.org/10.1007/s11263-009-0275-4.
R. W. Geckler, D. H. Gremillon, C. K. McAllister, C. Ellenbogen: Microscopic and bacteriological comparison of paired sputa and transtracheal aspirates, J. Clin. Microbio. 6, 396–399 (1977). https://doi.org/10.1128/jcm.6.4.396-399.1977.
S. Gillespie, K. Bamford: Medical microbiology and infection at a glance (3rd edition), Blackwell Publishing (2007).
K. Hashimoto, R. Iida, K. Hirata, K. Matsuoka, S. Yokoyama: Detecting Geckler classification from Gram stained smears images for sputum, Proc. ICPRAM’20, 469–476 (2020). https://doi.org/10.5220/0008962304690476.
A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, H. Adams: MobileNets: Efficient convolution neural networks for mobile vision applications, arXiv 1704.04861 (2017). https://doi.org/10.48500/arXiv.1704.04861.
A. Howard, M. Sandler, G. Chu, L. Chen, B. Chen, M. Tan,W.Wang, Y. Zhu, R. Pang, V. Vasudevan, Q. V. Le, H. Adam: Searching forMobileNetV3, Proc. ICCV’19, 1314–1324 (2019). https://doi.org/10.1109/ICCV.2019.00140
G. Huang, Z. Liu, L. van der Maaten, K. Q. Weinberger: Densely connected convolution networks, Proc. CVPR’17, 2261–2269 (2017). https://doi.org/10.1109/CVPR.2017.243.
G. Jocher: YOLOv5, https://github.com/ultralytics/yolov5 (2020).
G. Jocher, J. Qui: YOLO11 by Ultralytics, https://github.com/ultralytics/ultralytics (2024).
B. Khalili, A. W. Smyth: SOD-YOLO: Enhancing YOLOv8 for small object detection in aerial imagery and traffic scenes, Sensor 24, 6209 (2024). https://doi.org/10.3309/s24196209
H. Kobata, H. Kashino, K. Hirata: Detecting bacteria in Gram stained smears images by YOLO and SOD-YOLO, Proc. ESKM’25 (2025) (to appear).
M. Laposate, P. Mocaffrey: Clinical laboratory methods: Atlas of commonly performed tests, McGraw-Hill (2022).
Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell, S. Xie: A ConvNet for the 2020s, Proc. CVPR’22, 11966–11976 (2022). https://doi.org/10.1109/CVPR52688.2022.01167.
L. M. Marler, J. A. Siders, S. D. Allen: Direct smear atlas: A monograph of Gramstained preparations of clinical specimens, Lippincott Williams & Wilkins (2001).
I. Radosavoic, R. P. Kosaraju, R. Girshick, K. He, P. Doll´ar: Designing network design spaces, Proc. CVPR’20, 10425–10433 (2020). https://doi.org/10.1019/CVPR42600.2020.01044.
A. Robinson: Assessing microbiology test orders and specimen quality, Clinical Microbiology Newsletter 27, 78–82 (2005). https://doi.org/10.1016/S0196-4399(05)80030-3.
K. Simonyan, A. Zisserman: Very deep convolution networks for large-scale image recognition, Proc. ICLR’15 (2015).
H. Sugimoto, K. Hirata: Predicting Geckler classification from Gram stained smears images for sputum: Image classification versus object detection, Proc. ESKM’23, 122–127 (2023). https://doi.org/10.1109/IIAI-AAI59060.2023.00033
H. Tabakotani, H. Kashino, K. Hirata: Detecting bacteria in Gram stained smears images by HIC-YOLO and Its Variants, Proc. ESKM’25 (2025) (to appear).
M. Tan, Q. V. Le: EfficientNet: Rethinking model scaling for convolutional neural networks, Proc. ICML’19, 6105–6114 (2019).
S. Tang, S. Zhang, Y. Fang: HIC-YOLOv5: Improved YOLOv5 for small object detection, arXiv.2309.16393 (2023). https://doi.org/10.48500/arXiv.2309.16393.
The Japanese Respiratory Society: Diagnosis of hospital-acquired pneumonia and methods of testing for pathogens, Respirology 14, 510–522 (2009). https://doi.org/10.1111/j.1440-1843.2009.01572.x.
C. Y. Wang, A. Bochkovskiy, H. Y. M. Liao: YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors, arXiv.2207.02696 (2022). https://doi.org/10.48500/arXiv.2207.02696.
D. F. Welch, M. T. Kelly: Sputum screening by Nomarski interference contrast microscopy, J. Clin. Microbio. 9, 520–524 (1979). https://doi.org/10.1128/jcm.9.4.520-524.1979.
J. Xu, Y. Pan, X. Pan, S. Hoi, Z. Yi, Z. Xu: RegNet: Self-regulated network for image classification, IEEE Trans. Neural Netw. Learn. Sys. 34, 9562–9567 (2023). https://doi.org/10.1109/TNNLS.2022.3158966.
F. Zhuang, Z. Qi, K. Duan, D. Xi, Y. Zhu, H. Zhu, H. Xiong, Q. He: A comprehensive survey on transfer learning, Proc. IEEE 109, 43–76 (2021). https://doi.org/10.1109/JPROC.2020.3004555