Page 185 - AI for Good Innovate for Impact

AI for Good Innovate for Impact

continuous scanning, reconstruction method - chest CT (mediastinal window) or abdominal
CT. Resolution 512*512.

REQ-03: For hybrid cloud deployment, it is required to have Front-end Machine (CPU): 16
cores, 32GB RAM or higher. Operating System: CentOS 7.9 or a compatible version of Ubuntu 4.1-Healthcare
20.04. Public Network Bandwidth: 100 Mbps or higher.

REQ-04: For on-premises deployment, it is required to have Inference Machine (GPU): 16 cores,
32GB RAM or higher, Nvidia 3090 or better. Operating System: CentOS 7.9 or a compatible
version of Ubuntu 20.04. Public Network Bandwidth: 100 Mbps or higher.

4 Sequence Diagram

5 References

[1] K. Cao et al., “Large-scale pancreatic cancer detection via non-contrast CT and deep
learning,” Nature Medicine, vol. 29, Nov. 2023, doi: https:// doi .org/ 10 .1038/ s41591 -023
-02640 -w
[2] J. Yao et al., “Effective Opportunistic Esophageal Cancer Screening Using Noncontrast
CT Imaging,” Lecture notes in computer science, pp. 344–354, Jan. 2022, doi: https:// doi
.org/ 10 .1007/ 978 -3 -031 -16437 -8 _33 .
[3] L. Yao et al., “DeepCRC: Colorectum and Colorectal Cancer Segmentation in CT Scans via
Deep Colorectal Coordinate Transform,” Lecture notes in computer science, pp. 564–573,
Jan. 2022, doi: https:// doi .org/ 10 .1007/ 978 -3 -031 -16437 -8 _54 .
[4] D. Guo et al., “Thoracic Lymph Node Segmentation in CT Imaging via Lymph Node
Station Stratification and Size Encoding,” Lecture notes in computer science, pp. 55–65,
Jan. 2022, doi: https:// doi .org/ 10 .1007/ 978 -3 -031 -16443 -9 _6 .
[5] J. Chen et al., “CancerUniT: Towards a Single Unified Model for Effective Detection,
Segmentation, and Diagnosis of Eight Major Cancers Using a Large Collection of CT
Scans Cancer Detection in 8 Organs.” Accessed: Jun. 09, 2025. [Online]. Available:
https:// openaccess .thecvf .com/ content/ ICCV2023/ papers/ Chen _CancerUniT _Towards
_a _Single _Unified _Model _for _Effective _Detection _Segmentation _ICCV _2023 _paper .pdf

149