Official RCS-YOLO

Description

This is the source code for the paper titled "RCS-YOLO: A Fast and High-Accuracy Object Detector for Brain Tumor Detection" published in the Proceedings of the 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI 2023), of which I am the first author. The paper is available to download from Springer or arXiv.

Model

The RepVGG/RepConv ShuffleNet You Only Look Once (RCS-YOLO) model configuration (i.e., network construction) file is rcs-yolo.yaml (2 heads) or rcs3-yolo.yaml (3 heads) in the directory ./cfg/training/. The RepVGG/RepConv ShuffleNet based One-Shot Aggregation (RCS-OSA) module file is rcsosa.py in the directory ./models/, which is the unique module we proposed.

Installation

Install requirements.txt with recommended dependencies Python >= 3.8 environment including Torch <= 1.7.1 and CUDA <= 11.1:

pip install -r requirements.txt

Training

The hyperparameter setting file is hyp_training.yaml in the directory ./data/.

Single GPU training

python train.py --workers 8 --device 0 --batch-size 32 --data data/br35h.yaml --img 640 640 --cfg cfg/training/rcs-yolo.yaml --weights '' --name rcs-yolo --hyp data/hyp_training.yaml

Multiple GPU training

python -m torch.distributed.launch --nproc_per_node 4 --master_port 9527 train.py --workers 8 --device 0,1,2,3 --sync-bn --batch-size 128 --data data/br35h.yaml --img 640 640 --cfg cfg/training/rcs-yolo.yaml --weights '' --name rcs-yolo --hyp data/hyp_training.yaml

Testing

The model weights we pretrained on the brain tumor detection was saved as best.pt in the directory ./runs/train/exp/weights/.

python test.py --data data/br35h.yaml --img 640 --batch 32 --conf 0.001 --iou 0.65 --device 0 --weights runs/train/exp/weights/best.pt --name val

Evaluation

We trained and evaluated RCS-YOLO on the dataset Br35H :: Brain Tumor Detection 2020. The .txt format annotations in the folder dataset-Br35H are coverted from original json format. We used 500 images of which in the ’traindata’ folder were selected as the training set, while the other 201 images in the ’valdata’ folder as the testing set.

The screenshots of evaluation results were saved in the directory ./runs/val/.

Ablation Study

The files train_repvgg-csp.py and https://test_repvgg-csp.py are used for an ablation study of the comparison network repvgg-csp.yaml in the directory ./cfg/ablation/.

Referencing Guide

Please cite the paper if using this repository. Here is a guide to referencing this work in various styles for formatting your references:

Plain Text

• Springer Reference Style
  Kang, M., Ting, C.-M., Ting, F.F., Phan, R.C.-W.: RCS-YOLO: a fast and high-accuracy object detector for brain tumor detection. In: Greenspan, H., et al. (eds.) MICCAI 2023. LNCS, vol. 14223, pp. 600–610. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-43901-8_57
  ^{NOTE: MICCAI and ECCV conference proceedings are part of the book series LNCS in which Springer's format for bibliographical references is strictly enforced. This is important, for instance, when citing previous MICCAI and ECCV proceedings. LNCS stands for Lecture Notes in Computer Science.}

• Nature Referencing Style
  Kang, M., Ting, C.-M., Ting, F. F. & Phan, R. C.-W. RCS-YOLO: a fast and high-accuracy object detector for brain tumor detection. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2023: 26th International Conference, Vancouver, Canada, October 8–12, 2023, Proceedings, Part IV (eds. Greenspan, H. et al.) 600–610 (Springer, 2023).
  

• Elsevier Numbered Style
  M. Kang, C.-M. Ting, F.F. Ting, R.C.-W. Phan, RCS-YOLO: a fast and high-accuracy object detector for brain tumor detection, in: H. Greenspan, A. Madabhushi, P. Mousavi, S. Salcudean, J. Duncan, T. Syeda-Mahmood, et al. (Eds.), Medical Image Computing and Computer Assisted Intervention – MICCAI 2023: 26th International Conference, Vancouver, Canada, October 8–12, 2023, Proceedings, Part IV, Lecture Notes in Computer Science (LNCS), vol. 14223, 2023, pp. 600–610.
  ^{NOTE: Day(s) Month Year, City, Abbrev. State, Country of Conference, Publiser, and Place of Publication are optional and omitted. Alterative version of the booktitle, series and volume is 'Proceedings of the 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Vol. 14223 of Lecture Notes in Computer Science (LNCS)'.}

• Elsevier Name–Date (Harvard) Style
  Kang, M., Ting, C.-M., Ting, F.F., Phan, R.C.-W., 2023. RCS-YOLO: a fast and high-accuracy object detector for brain tumor detection. In: H. Greenspan, A. Madabhushi, P. Mousavi, S. Salcudean, J. Duncan, T. Syeda-Mahmood, et al. (Eds.), Medical Image Computing and Computer Assisted Intervention – MICCAI 2023: 26th International Conference, Vancouver, Canada, October 8–12, 2023, Proceedings, Part IV. Vol. 14223 of Lecture Notes in Computer Science (LNCS), Springer, Cham, Germany, pp. 600–610.
  ^{NOTE: Day(s) Month Year, City, Abbrev. State, Country of Conference, Publiser, and Place of Publication are optional. Alterative version of the booktitle, Day(s) Month Year, City, and Country of Conference is 'Proceedings of the 26th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 8–12 October 2023, Vancouver, BC, Canada.'.}

• Elsevier Vancouver Style
  Kang M, Ting C-M, Ting FF, Phan RC-W. RCS-YOLO: a fast and high-accuracy object detector for brain tumor detection. In: Greenspan H, Madabhushi A, Mousavi P, Salcudean S, Duncan J, Syeda-Mahmood T, et al., editors. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023: 26th International Conference, Vancouver, Canada, October 8–12, 2023, Proceedings, Part IV. Lecture Notes in Computer Science (LNCS), vol. 14223. Cham: Springer; 2023. p. 600–10.
  

• Elsevier Embellished Vancouver Style
  Kang M, Ting C-M, Ting FF, Phan RC-W. RCS-YOLO: a fast and high-accuracy object detector for brain tumor detection. In: Greenspan H, Madabhushi A, Mousavi P, Salcudean S, Duncan J, Syeda-Mahmood T, et al., editors. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023: 26th International Conference, Vancouver, Canada, October 8–12, 2023, Proceedings, Part IV. Lecture Notes in Computer Science (LNCS), vol. 14223. Cham: Springer; 2023. p. 600–10.
  

• IEEE Reference Style
  M. Kang, C.-M. Ting, F. F. Ting, and R. C.-W. Phan, "Rcs-yolo: A fast and high-accuracy object detector for brain tumor detection," in Proc. Int. Conf. Med. Image Comput. Comput. Assist. Interv. (MICCAI), Vancouver, BC, Canada, Oct. 8–12, 2023, vol. 14223, pp. 600–610.
  ^{NOTE: City of Conf., Abbrev. State, Country, Month & Day(s) are optional.}

• IEEE Full Name Reference Style
  Ming Kang, Chee-Ming Ting, Fung Fung Ting, and Raphaël C.-W. Phan. Rcs-yolo: A fast and high-accuracy object detector for brain tumor detection. In MICCAI, vol. 14223, pages 600–610, 2023.
  ^{NOTE: This is a modification to the standard IEEE Reference Style and used by most IEEE/CVF conferences, including CVPR, ICCV, and WACV, to render first names in the bibliography as "Firstname Lastname" rather than "F. Lastname" or "Lastname, F.".}
   - IJCAI Full Name-Year Variation
  [Kang et al., 2023] Ming Kang, Chee-Ming Ting, Fung Fung Ting, and Raphaël C.-W. Phan. Rcs-yolo: A fast and high-accuracy object detector for brain tumor detection. In Proceedings of the 26th International Conference on Medical Image Computing and Computer Assisted Intervention, vol. 14223, pages 600–610, Cham, Germany, October 2023. Springer.
   - ACL Full Name-Year Variation
  Ming Kang, Chee-Ming Ting, Fung Fung Ting, and Raphaël C.-W. Phan. 2023. Rcs-yolo: A fast and high-accuracy object detector for brain tumor detection. In Proceedings of the 26th International Conference on Medical Image Computing and Computer Assisted Intervention, vol. 14223, pages 600–610, Cham, Germany. Springer.
  

• APA7 (Author–Date) Style
  Kang, M., Ting, C.-M., Ting, F. F., & Phan, R. C.-W. (2023). RCS-YOLO: A fast and high-accuracy object detector for brain tumor detection. In H. Greenspan, A. Madabhushi, P. Mousavi, S. Salcudean, J. Duncan, T. Syeda-Mahmood, R. Taylor (Eds.), Medical Image Computing and Computer Assisted Intervention – MICCAI 2023: 26th International Conference, Vancouver, Canada, October 8–12, 2023, Proceedings, Part IV (pp. 600–610). Springer. https://doi.org/10.1007/978-3-031-43901-8_57
   - AAAI (Author–Year) Variation
  Kang, M.; Ting, C.-M.; Ting, F. F.; and Phan, R. C.-W. 2023. RCS-YOLO: A Fast and High-Accuracy Object Detector for Brain Tumor Detection. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2023: 26th International Conference, Vancouver, Canada, October 8–12, 2023, Proceedings, Part IV, 600–610. Cham, Germany: Springer.
   - ICML (Author–Year) Variation
  Kang, M., Ting, C.-M., Ting, F. F., and Phan, R. C.-W. RCS-YOLO: A fast and high-accuracy object detector for brain tumor detection. In M.G. Linguraru, Q. Dou, A. Feragen, S. Giannarou, B. Glocker, K. Lekadir, J. A. Schnabel (Eds.), Medical Image Computing and Computer Assisted Intervention – MICCAI 2023: 26th International Conference, Vancouver, Canada, October 8–12, 2023, Proceedings, Part IV, pp. 600–610, Cham, Germany, 2023. Springer.
  ^{NOTE: For NeurIPS and ICLR, any reference/citation style is acceptable as long as it is used consistently. The sample of references in Formatting Instructions For NeurIPS almost follows APA7 (author–date) style and that in Formatting Instructions For ICLR Conference Submissions is similar to IJCAI full name-year variation.}

BibTeX Format

\begin{thebibliography}{1}
\bibitem{Kang23Rcsyolo} Kang, M., Ting, C.-M., Ting, F.F., Phan, R.C.-W.: RCS-YOLO: a fast and high-accuracy object detector for brain tumor detection. In: Greenspan, H., et al. (eds.) MICCAI 2023. LNCS, vol. 14223, pp. 600--610. Springer, Cham (2023). {\UrlFont https://doi.org/10.1007/978-3-031-43901-8\_57}
\end{thebibliography}

@inproceedings{Kang23Rcsyolo,
  author = "Kang, Ming and Ting, Chee-Ming and Ting, Fung Fung and Phan, Rapha{\"e}l C.-W.",
  title = "{RCS-YOLO}: a fast and high-accuracy object detector for brain tumor detection",
  editor = "Greenspan, Hayit and others",
  % editor = "Greenspan, Hayit and Madabhushi, Anant and Mousavi, Parvin and Salcudean, Septimiu and Duncan, James and Syeda-Mahmood, Tanveer and et al." %% Elsevier Style
  booktitle = "Medical Image Computing and Computer Assisted Intervention – MICCAI 2023: 26th International Conference, Vancouver, Canada, October 8--12, 2023, Proceedings, Part IV",
  series = "Lecture Notes in Computer Science (LNCS)",
  volume = "14223",
  pages = "600--610",
  publisher = "Springer",
  address = "Cham",
  year = "2023",
  doi= "10.1007/978-3-031-43901-8_57",
  url = "https://doi.org/10.1007/978-3-031-43901-8_57"
}

@inproceedings{Kang23Rcsyolo,
  author = "Ming Kang and Chee-Ming Ting and Fung Fung Ting and Rapha{\"e}l C.-W. Phan",
  title = "Rcs-yolo: A fast and high-accuracy object detector for brain tumor detection",
  booktitle = "Proc. Int. Conf. Med. Image Comput. Comput. Assist. Interv. (MICCAI)",
  % booktitle = MICCAI, %% IEEE Full Name Reference Style
  address = "Vancouver, BC, Canada, Oct. 8--12",\
  volume = "14223",
  pages = "600--610",
  year = "2023"
}

^{NOTE: Please remove some optional BibTeX fields/tags such as series, volume, address, url, and so on if the LaTeX compiler produces an error. Author names may be manually modified if not automatically abbreviated by the compiler under the control of the bibliography/reference style (i.e., .bst) file. The BibTex citation key may be bib1, b1, or ref1 when references appear in numbered style in which they are cited. others in the author and editor may be et al. under some bibliography style files, such as IEEEtran.bst. The quotation mark pair "" in the field could be replaced by the brace {}, whereas the brace {} in the BibTeX field/tag title plays a role of keeping letters/characters/text original lower/uppercases or sentence/capitalized cases unchanged while using Springer Nature bibliography style files, for example, sn-nature.bst.}

License

RCS-YOLO is released under the GNU General Public License v3.0. Please view the LICENSE file for more information.

Copyright Notice

Many utility codes of our project base on the codes of YOLOv7, RepVGG, ShuffleNet, and VoVNetV2 repositories.