細胞檢測在現代醫學和生物學研究中扮演著至關重要的角色，特別是在癌症檢測和治療中。準確的細胞檢測可以幫助醫生更早地發現疾病，並提供精確的治療方案。近年來，許多細胞偵測相關的資料集被釋出，提供給深度學習領域的專家們研究。其中，OCELOT資料集是少數整合了組織資料和細胞資料的資料集之一。利用組織與細胞之間的強大關聯性，期望透過組織切片來增強模型對細胞檢測的準確率。在本文中，我們基於原先應用於腳潰瘍分割任務的模型HarDNet-DFUS，將模型重新訓練並應用於細胞檢測任務，加入注意力機制和其他訓練技巧來增強模型的細胞偵測準確率。我們將模型測試在OCELOT資料集上，相較於其他團隊在此資料集上的研究，我們的方法可以達到73.24\%的mF1成績，超越了該資料集於MICCAI2023會議中舉辦的OCELOT2023 challenge第一名的成績。

Cell detection is crucial in modern medicine and biological research, especially in cancer detection and treatment. Accurate cell detection aids in early disease discovery and precise treatment plans. Recently, many cell detection datasets have become available, offering valuable resources for deep learning researchers. Among these, the OCELOT dataset stands out by integrating both tissue and cell data, aiming to enhance detection accuracy through tissue slides.

In this thesis, we retrain the HarDNet-DFUS model, originally used for foot ulcer segmentation, for cell detection. We incorporate attention mechanisms and advanced training techniques to improve accuracy. Our model was tested on the OCELOT dataset, achieving an mF1 score of 73.24\%, surpassing the first-place team in the OCELOT2023 challenge at the MICCAI2023 conference. This result highlights our method's potential to significantly advance cell detection accuracy in medical research.

Acknowledgements
摘要 i
Abstract ii
1 Introduction 1
2 Related Works 3
2.1 Datasets for Cell Detection and Tissue Segmentation . . . . . . 3
2.2 The OCELOT Dataset . . . . . . . . . . . . . . . . . . . . . . . 4
2.2.1 Cell detection as a segmentation task . . . . . . . . . . . . 4
2.2.2 Integrating information between tissue and cells . . . . . . . 4
2.3 OCELOT2023 Challenge . . . . . . . . . . . . . . . . . . . . . . 5
2.3.1 Winning teams’ approaches . . . . . . . . . . . . . . . . . . .6
2.4 HarDNet-DFUS . . . . . . . . . . . . . . . . . . . . . . . . . . 6
3 Proposed Method 9
3.1 HarDNet-DFUS Architecture . . . . . . . . . . . . . . . . . . . 9
3.1.1 HarDBlockV2 . . . . . . . . . . . . . . . . . . . . . . . . . 10
3.1.2 The decoder of Lawin Transformer . . . . . . . . . . . . . . .11
3.2 Incorporating Attention Mechanisms in the Transition Layers . . 11
3.3 Loss Function . . . . . . . . . . . . . . . . . . . . . . . . . 13
4 Experiments 15
4.1 Datasets . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
4.2 Training Setting . . . . . . . . . . . . . . . . . . . . . . . .15
4.3 Accuracy Measurement . . . . . . . . . . . . . . . . . . . . . .16
4.4 Ablation Study . . . . . . . . . . . . . . . . . . . . . . . . .17
4.4.1 Tissue image splitting during training . . . . . . . . . . . .17
4.4.2 Augmenting cell branch with tissue branch prediction . . . . .18
4.4.3 Varying attention mechanisms . . . . . . . . . . . . . . . . .19
4.4.4 Data augmentation for cell branch. . . . . . . . . . . . . . .20
4.4.5 Test time augmentation for cell branch . . . . . . . . . . . .20
4.4.6 Limitation of the proposed dual branch method. . . . . . . . .21
4.5 Comparison and Discussion. . . . . . . . . . . . . . . . . . . .22
5 Conclusions and Future Works. . . . . . . . . . . . . . . . . . . .25
References. . . . . . . . . . . . . . . . . . . .27
Appendix. . . . . . . . . . . . . . . . . . . .31

[1] S. Mohta, H. Suganuma, and Y. Tanaka, “Mrl: Learning to mix with attention and convolutions,” arXiv preprint arXiv:2208.13975, 2022.
[2] S. Graham, D. Epstein, and N. Rajpoot, “Dense steerable filter cnns for exploiting rotational symmetry in histology images,” IEEE Transactions on Medical Imaging, vol. 39,no. 12, pp. 4124–4136, 2020.
[3] S. Graham, Q. D. Vu, S. E. A. Raza, A. Azam, Y. W. Tsang, J. T. Kwak, and N. Rajpoot, “Hover-net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images,” Medical image analysis, vol. 58, p. 101563, 2019.
[4] N. Kumar, R. Verma, D. Anand, Y. Zhou, O. F. Onder, E. Tsougenis, H. Chen, P.-A. Heng, J. Li, Z. Hu, et al., “A multi-organ nucleus segmentation challenge,” IEEE transactions on medical imaging, vol. 39, no. 5, pp. 1380–1391, 2019.
[5] Z. Li, Y. Li, Q. Li, P. Wang, D. Guo, L. Lu, D. Jin, Y. Zhang, and Q. Hong, “Lvit: language meets vision transformer in medical image segmentation,” IEEE transactions on medical imaging, 2023.
[6] Z. Pan, J. Chen, and Y. Shi, “Masked diffusion as self-supervised representation learner,”arXiv preprint arXiv:2308.05695, 2023.
[7] J. M. J. Valanarasu, P. Oza, I. Hacihaliloglu, and V. M. Patel, “Medical transformer: Gated axial-attention for medical image segmentation,” in Medical Image Computing and Com- puter Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part I 24, pp. 36–46, Springer, 2021.
[8] J. Ryu, A. V. Puche, J. Shin, S. Park, B. Brattoli, J. Lee, W. Jung, S. I. Cho, K. Paeng, C.-Y. Ock, et al., “Ocelot: Overlapped cell on tissue dataset for histopathology,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 23902 23912, 2023.
[9] Z. Swiderska-Chadaj, H. Pinckaers, M. Van Rijthoven, M. Balkenhol, M. Melnikova, O. Geessink, Q. Manson, M. Sherman, A. Polonia, J. Parry, et al., “Learning to detect lymphocytes in immunohistochemistry with deep learning,” Medical image analysis, vol. 58, p. 101547, 2019.
[10] L.-C. Chen, Y. Zhu, G. Papandreou, F. Schroff, and H. Adam, “Encoder-decoder with atrous separable convolution for semantic image segmentation,” in Proceedings of the European conference on computer vision (ECCV), pp. 801–818, 2018.
[11] Z. Li, W. Li, H. Mai, T. Zhang, and Z. Xiong, “Enhancing cell detection in histopathology images: A vit-based u-net approach,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 150–160, Springer, 2023.
[12] A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A. C. Berg, W.-Y. Lo, et al., “Segment anything,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 4015–4026, 2023.
[13] E. J. Hu, Y. Shen, P. Wallis, Z. Allen-Zhu, Y. Li, S. Wang, L. Wang, and W. Chen, “Lora: Low-rank adaptation of large language models,” arXiv preprint arXiv:2106.09685, 2021.
[14] J. Millward, Z. He, and A. Nibali, “Dense prediction of cell centroids using tissue context and cell refinement,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 138–149, Springer, 2023.
[15] E. Xie, W. Wang, Z. Yu, A. Anandkumar, J. M. Alvarez, and P. Luo, “Segformer: Simple and efficient design for semantic segmentation with transformers,” Advances in neural information processing systems, vol. 34, pp. 12077–12090, 2021.
[16] L. A. Schoenpflug and V. H. Koelzer, “Softctm: Cell detection by soft instance segmentation and consideration of cell-tissue interaction,” in International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 109–122, Springer, 2023.
[17] T.-Y. Liao, C.-H. Yang, Y.-W. Lo, K.-Y. Lai, P.-H. Shen, and Y.-L. Lin, “Hardnet-dfus: Enhancing backbone and decoder of hardnet-mseg for diabetic foot ulcer image segmentation,” in Diabetic Foot Ulcers Grand Challenge, pp. 21–30, Springer, 2022.
[18] T.-Y. Liao, C.-H. Yang, Y.-W. Lo, K.-Y. Lai, P.-H. Shen, and Y.-L. Lin, “Hardnet-dfus: An enhanced harmonically-connected network for diabetic foot ulcer image segmentation and colonoscopy polyp segmentation,” arXiv preprint arXiv:2209.07313, 2022.
[19] C.-H. Huang, H.-Y. Wu, and Y.-L. Lin, “Hardnet-mseg: A simple encoder-decoder polyp segmentation neural network that achieves over 0.9 mean dice and 86 fps,” arXiv preprint arXiv:2101.07172, 2021.
[20] P. Chao, C.-Y. Kao, Y.-S. Ruan, C.-H. Huang, and Y.-L. Lin, “Hardnet: A low memory traffic network,” in Proceedings of the IEEE/CVF international conference on computer vision, pp. 3552–3561, 2019.
[21] F. Iandola, M. Moskewicz, S. Karayev, R. Girshick, T. Darrell, and K. Keutzer, “Densenet: Implementing efficient convnet descriptor pyramids,” arXiv preprint arXiv:1404.1869, 2014.
[22] H.-Y. Wu and Y.-L. Lin, “Hardnet-bts: A harmonic shortcut network for brain tumor segmentation,” in International MICCAI Brainlesion Workshop, pp. 261–271, Springer, 2021.
[23] H. Yan, C. Zhang, and M. Wu, “Lawin transformer: Improving semantic segmentation transformer with multi-scale representations via large window attention,” arXiv preprint arXiv:2201.01615, 2022.
[24] “Efficient real-time semantic segmentation: Enhancing fc-hardnetv2 with training-time techniques and structural re-parameterization,” 2023. https://etd.lib.nycu.edu.tw/cgi-bin/gs32/hugsweb.cgi?o=dnthucdr&s=id=%22G021100626550%22.&searchmode=basic.
[25] K. Han, Y. Wang, Q. Tian, J. Guo, C. Xu, and C. Xu, “Ghostnet: More features from cheap operations,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 1580–1589, 2020.
[26] Z. Wu, L. Su, and Q. Huang, “Cascaded partial decoder for fast and accurate salient object detection,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 3907–3916, 2019.
[27] I. O. Tolstikhin, N. Houlsby, A. Kolesnikov, L. Beyer, X. Zhai, T. Unterthiner, J. Yung, A. Steiner, D. Keysers, J. Uszkoreit, et al., “Mlp-mixer: An all-mlp architecture for vision,” Advances in neural information processing systems, vol. 34, pp. 24261–24272, 2021.
[28] K. He, X. Zhang, S. Ren, and J. Sun, “Spatial pyramid pooling in deep convolutional networks for visual recognition,” IEEE transactions on pattern analysis and machine intelligence, vol. 37, no. 9, pp. 1904–1916, 2015.
[29] M. Cordts, M. Omran, S. Ramos, T. Rehfeld, M. Enzweiler, R. Benenson, U. Franke, S. Roth, and B. Schiele, “The cityscapes dataset for semantic urban scene understanding,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3213–3223, 2016.
[30] B. Zhou, H. Zhao, X. Puig, S. Fidler, A. Barriuso, and A. Torralba, “Scene parsing through ade20k dataset,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 633–641, 2017.
[31] J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7132–7141, 2018.
[32] M.-H. Guo, C.-Z. Lu, Z.-N. Liu, M.-M. Cheng, and S.-M. Hu, “Visual attention network,” Computational Visual Media, vol. 9, no. 4, pp. 733–752, 2023.
[33] C.-Y. Lee, S. Xie, P. Gallagher, Z. Zhang, and Z. Tu, “Deeply-supervised nets,” in Artificial intelligence and statistics, pp. 562–570, Pmlr, 2015.