TUM-CAMP-tutorials-contribution: DAF3D and Quicknat

[vgonzalezd]

Fixes # .

Description

@Al3xand1a and @ge96lip create these 2 tutorials for 2 networks that were recently accepted in MONAI core:
DAF3D[1] and Quicknat[2]
We would like to have your feedback to improve the contribution. Thank you in advance!
For any questions send us an email to [email protected]

[1]DAF3D:
Wang, Y., Dou, H., Hu, X., Zhu, L., Yang, X., Xu, M., ... & Ni, D. (2019). Deep attentive features for prostate segmentation in 3D transrectal ultrasound. IEEE transactions on medical imaging, 38(12), 2768-2778.
https://github.com/wulalago/DAF3D/blob/master/README.md

[2]QuickNAT:
Roy, A. G., Conjeti, S., Navab, N., Wachinger, C., & Alzheimer's Disease Neuroimaging Initiative. (2019). QuickNAT: A fully convolutional network for quick and accurate segmentation of neuroanatomy. NeuroImage, 186, 713-727.
https://www.sciencedirect.com/science/article/abs/pii/S1053811918321232

Checks

• Avoid including large-size files in the PR.
• Clean up long text outputs from code cells in the notebook
• For security purposes, please check the contents and remove any sensitive info such as user names and private key.
• Ensure (1) hyperlinks and markdown anchors are working (2) use relative paths for tutorial repo files (3) put figure and graphs in the ./figure folder
• Notebook runs automatically ./runner.sh -t <path to .ipynb file>

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

mingxin-zheng commented on 2023-06-28T07:15:46Z
----------------------------------------------------------------

Thank you for the PR. According to our contributing guideline we would need a "Setup imports" instead of "Preprocess the data in folders" here.

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

mingxin-zheng commented on 2023-06-28T07:15:48Z
----------------------------------------------------------------

Line #13.        image_path_expression = "PROCESSED/MPRAGE/T88_111/OAS1_*_MR*_mpr_n*_anon_111_t88_masked_gfc.img"

Is the path correct? It seems the runner is complaining about not finding the files:

IndexError                                Traceback (most recent call last)
681

Input In [4], in <cell line: 2>()
682

14 segmentation_path_expression = "FSL_SEG/OAS1__MR_mpr_n*_anon_111_t88_masked_gfc_fseg.img"
683

15 image_paths = glob(os.path.join(data_dir, "*", image_path_expression))
684

---> 16 print(image_paths[0])
685

17 image_paths += glob(os.path.join(data_dir, "/", image_path_expression))
686

18 segmentation_paths = glob(os.path.join(data_dir, "*", segmentation_path_expression))
687
688

IndexError: list index out of range

For more details, this can be found in:

TUM-CAMP-tutorials-contribution: DAF3D and Quicknat · Project-MONAI/tutorials@fd221ce (github.com)

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

mingxin-zheng commented on 2023-06-28T07:15:49Z
----------------------------------------------------------------

Line #5.    lossFunction = DiceCELoss(include_background=True, to_onehot_y=True, softmax=True)

Please check the PEP 8 error regarding the variable naming:

TUM-CAMP-tutorials-contribution: DAF3D and Quicknat · Project-MONAI/tutorials@fd221ce (github.com)

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

mingxin-zheng commented on 2023-06-28T07:15:51Z
----------------------------------------------------------------

Line #1.    num_epochs = 20

We typically use max_epochs to control the notebook running pipeline (build). For more details, please refer to our contributing guide: https://github.com/Project-MONAI/tutorials/blob/main/CONTRIBUTING.md#notebook-execution

[Nic-Ma]

Hi @vgonzalezd ,

As the module had been merged into MONAI core, could you please help update and complete this PR?

Thanks in advance.

[smith-kyle]

Just a heads up, you can review notebook changes like this using GitNotebooks.

e.g. this pull request https://gitnotebooks.com/Project-MONAI/tutorials/pull/1440

It allows inline comments on code and markdown, and it's free for public repos so I thought I'd share..