New references

[mxochicale]

Open this one to add new references either via issue or creating branch and doing PRs. Cheers, --Miguel

Detection Transformer: Object Detection with DETR - a minimal implementation;

• https://colab.research.google.com/github/facebookresearch/detr/blob/colab/notebooks/detr_demo.ipynb#scrollTo=kqe_0nc5dyAq
• [ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection" https://github.com/IDEA-Research/DINO?tab=readme-ov-file https://arxiv.org/pdf/2203.03605.pdf https://arxiv.org/pdf/2203.03605.pdf https://arxiv.org/abs/2203.03605
• Google search images of "Detection Transformer" https://www.google.co.uk/search?q=Detection+Transformer+&tbm=isch&
• End-to-End Object Detection with Transformers https://arxiv.org/pdf/2005.12872v3.pdf https://github.com/facebookresearch/detr
• https://github.com/mobarakol/tutorial_notebooks/blob/main/Grounded_SAM_Tool_Instance_Segmentation.ipynb

LSTM-related topics

• https://towardsdatascience.com/how-to-use-transformer-networks-to-build-a-forecasting-model-297f9270e630
• Conv- LSTM https://www.google.co.uk/search?sca_esv=de7a49ba27450786&q=Conv-+LSTM&tbm=isch&source=lnms&sa=X&ved=2ahUKEwjpmMGV_IeEAxWhgv0HHT_pDUkQ0pQJegQIDBAB&biw=1920&bih=1100
• Weakly supervised convolutional LSTM approach for tool tracking in laparoscopic videos https://link.springer.com/article/10.1007/s11548-019-01958-6
• multi-object tracking surgical: https://www.google.co.uk/search?sca_esv=6e8c819a630d1523&q=multi-object+tracking+surgical&tbm=isch&source=lnms&sa=X&ved=2ahUKEwiy6_-3odOEAxV8QkEAHc-KC4EQ0pQJegQIDRAB&biw=1920&bih=1100
• Holoscan Sample App Data for AI-based Endoscopy Tool Tracking https://catalog.ngc.nvidia.com/orgs/nvidia/teams/clara-holoscan/resources/holoscan_endoscopy_sample_data

Venues for publication

• For data https://www.nature.com/sdata/
• Cell protocols is a good references for experiment protocols: https://www.cell.com/star-protocols/home https://twitter.com/STARProtocols

[mxochicale]

We would like to browse the table of content of this book

Sensors for Healthcare and Medical Applications
Formica, Domenico Formica, Domenico Schena, Emiliano
Basel, Switzerland MDPI - Multidisciplinary Digital Publishing Institute, 2021

Other relevant papers:

• A Transformer-based Framework for Multivariate Time Series Representation Learning
  • https://arxiv.org/abs/2010.02803
  • https://www.youtube.com/watch?v=K5U9v2SW7_Q
  • https://github.com/gzerveas/mvts_transformer

[mxochicale]

Thanks Steve for sharing, we will review and discuss it.

Heiliger, Christian, Dorian Andrade, Christian Geister, Alexander Winkler, Khaled Ahmed, Alessandra Deodati, Viktor H. Ehrlich V. Treuenstätt et al. "Tracking and evaluating motion skills in laparoscopy with inertial sensors." Surgical Endoscopy (2023): 1-11. https://link.springer.com/article/10.1007/s00464-023-09983-y

[mxochicale]

Lam, Kyle, Junhong Chen, Zeyu Wang, Fahad M. Iqbal, Ara Darzi, Benny Lo, Sanjay Purkayastha, and James M. Kinross. "Machine learning for technical skill assessment in surgery: a systematic review." NPJ digital medicine 5, no. 1 (2022): 24. https://scholar.google.com/scholar?cites=18255856507017471578&as_sdt=2005&sciodt=0,5&hl=en

Lavanchy, Joël L., Joel Zindel, Kadir Kirtac, Isabell Twick, Enes Hosgor, Daniel Candinas, and Guido Beldi. "Automation of surgical skill assessment using a three-stage machine learning algorithm." Scientific reports 11, no. 1 (2021): 5197. https://scholar.google.com/scholar?cites=14668467219995507872&as_sdt=2005&sciodt=0,5&hl=en

Liu, Daochang, Qiyue Li, Tingting Jiang, Yizhou Wang, Rulin Miao, Fei Shan, and Ziyu Li. "Towards unified surgical skill assessment." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9522-9531. 2021. https://scholar.google.com/scholar?cites=12208140246219122622&as_sdt=2005&sciodt=0,5&hl=en

Fathollahi, Mona, Mohammad Hasan Sarhan, Ramon Pena, Lela DiMonte, Anshu Gupta, Aishani Ataliwala, and Jocelyn Barker. "Video-based surgical skills assessment using long term tool tracking." In International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 541-550. Cham: Springer Nature Switzerland, 2022. https://scholar.google.com/scholar?cites=14295532720293422183&as_sdt=2005&sciodt=0,5&hl=en

Kasa, Kevin, David Burns, Mitchell G. Goldenberg, Omar Selim, Cari Whyne, and Michael Hardisty. "Multi-Modal Deep Learning for Assessing Surgeon Technical Skill." Sensors 22, no. 19 (2022): 7328. https://scholar.google.com/scholar?cites=5754549589610006787&as_sdt=2005&sciodt=0,5&hl=en

[mxochicale]

A8. VIDEO ANALYTICS, AI, MACHINE LEARNING AND DEEP LEARNING Such granular, trainee level data are currently not widely available but platforms such as Medtronic’s Touch Surgery and Johnson & Johnson’s C-SATS offering personalised video libraries and surgical analytics already exist. If we can utilise these datasets and harness the capability of big data104 to predict error, this could accelerate training and improve patient safety (Figure 9). Their widespread adoption has not occurred yet but undoubtedly will occur in the future given that as more research is conducted in this area, a shift will occur towards personalised, automated performance analysis. Collaboration between surgeons, computer scientists and engineers is crucial to facilitate adoption, drive AI literacy among clinicians and promote their active involvement in this field. Only then can the benefits of AI and ML be translated into better surgical training and ultimately, improved patient safety https://futureofsurgery.rcseng.ac.uk/wp-content/uploads/2022/08/FOS_Test_Report_2022.pdf (page 69.)

[mxochicale]

Few related references that apply Grey level co-occurrence matrix method

• https://haralick-org.torahcode.us/journals/TexturalFeaturesHaralickShanmugamDinstein.pdf
• https://scikit-image.org/docs/dev/auto_examples/features_detection/plot_glcm.html#sphx-glr-auto-examples-features-detection-plot-glcm-py
• http://www.geo-5.com/pdf/papers/2015_FirstBreak_Eichkitz.pdf
• Figure 3: https://www.researchgate.net/publication/277085093_Haralick_Texture_Analysis_of_prostate_MRI_Utility_for_differentiating_non-cancerous_prostate_from_prostate_cancer_and_differentiating_prostate_cancers_with_different_Gleason_Scores
• Figure 1: https://www.researchgate.net/publication/337940559_Steel_Surface_Defect_Diagnostics_Using_Deep_Convolutional_Neural_Network_and_Class_Activation_Map
• Figure 6: https://www.researchgate.net/publication/350466003_Understanding_Sources_of_Variation_to_Improve_the_Reproducibility_of_Radiomics

[mxochicale]

Fathabadi, Fatemeh Rashidi, Janos L. Grantner, Saad A. Shebrain, and Ikhlas Abdel-Qader. "Autonomous sequential surgical skills assessment for the peg transfer task in a laparoscopic box-trainer system with three cameras." Robotica 41, no. 6 (2023): 1837-1855. https://www.cambridge.org/core/journals/robotica/article/autonomous-sequential-surgical-skills-assessment-for-the-peg-transfer-task-in-a-laparoscopic-boxtrainer-system-with-three-cameras/DCB01829946A6E22AD3FE68BE5057746 dataset: https://drive.google.com/drive/folders/1F97CvN3GnLj-rqg1tk2rHu8x0J740DpC github: https://github.com/Atena-Rashidi

[mxochicale]

Lavanchy, J. L., J. Zindel, K. Kirtac, I. Twick, E. Hosgor, D. Candinas, and G. Beldi. "Automation of surgical skill assessment using a three-stage machine learning algorithm. Sci Rep 11: 5197." (2021). https://scholar.google.com/scholar?cites=6644914990870187003

[mxochicale]

Vasu, Pavan Kumar Anasosalu, James Gabriel, Jeff Zhu, Oncel Tuzel, and Anurag Ranjan. "MobileOne: An Improved One Millisecond Mobile Backbone." In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7907-7917. 2023. https://arxiv.org/abs/2206.04040 https://scholar.google.com/scholar?cites=17349182165322877132

[mxochicale]

Chadebecq, François, Laurence B. Lovat, and Danail Stoyanov. "Artificial intelligence and automation in endoscopy and surgery." Nature Reviews Gastroenterology & Hepatology 20, no. 3 (2023): 171-182. https://scholar.google.com/scholar?cites=1544539509892715943&as_sdt=2005&sciodt=0,5&hl=en