ECR 2024 / C-21327
Facilitating radiologist involvement in artificial intelligence with MONAI Label and 3D-slicer
Congress:
ECR 2024
Poster Number:
C-21327
Type:
Educational Exhibit
Keywords:
Artificial Intelligence, CT, MR, Computer Applications-3D, Computer Applications-Detection, diagnosis, Segmentation, Education and training
Authors:
F. Buemi, C. Giardina, A. Perri, S. Caloggero, A. Celona, N. Sicilia, O. Ventura Spagnolo, F. Galletta, G. Mastroeni
DOI:
10.26044/ecr2024/C-21327
Personal information and conflict of interest
Fig 1:
MONAI Label is structured around three primary high-level modules: the client,...
Table 1:
Some radiology models available on the MONAI model Zoo website.
Fig 2:
Deepgrow relies on positive and negative interactions. Positive clicks from...
Fig 3:
Example of Deepgrow. Positive and negative clicks are provided to refine the...
Fig 4:
Deepedit enhances Deepgrow's segmentation by incorporating a two-stage process....
Fig 5:
Example of Deepedit combined with Deepgrow. After the first click, both kidneys...
Fig 6:
Scribbles-based segmentation model enables interactive segmentation through...
Fig 7:
Scribbles applied in the segmentation of the liver. The foreground and...
![](https://epos.myesr.org/posterimage/esr/ecr2024/164872/media/979913?maxheight=150&maxwidth=150 "Fig 8: Example of auto-segmentation using the Prostate MRI anatomy model of MONAI zoo, trained with the U-Net architecture. Just click "Run" to obtain the segmentation of the peripheral and transitional zone of the prostate.")
Fig 8:
Example of auto-segmentation using the Prostate MRI anatomy model of MONAI zoo,...
![](https://epos.myesr.org/posterimage/esr/ecr2024/164872/media/979891?maxheight=150&maxwidth=150 "Fig 9: The name "U-Net" derives from its U-shaped architecture, which consists of a contracting path, a bottleneck, and an expanding path.
1) Contracting Path:
Utilizes downsampling to extract contextual information from a broad range of image pixels.
2) Bottleneck:
Marks the transition from the contracting to expanding paths, enhancing model generalization.
3) Expanding Path:
Implements upsampling to combine feature maps and generate final class information.
This architecture efficiently captures both contextual and positional details, making it well-suited for tasks like image segmentation (Modified figure from the article by Ronneberger et al (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. arXiv:1505.04597 [cs.CV]).")
Fig 9:
The name "U-Net" derives from its U-shaped architecture, which consists of a...
Table 2:
Installation requirements. It is strongly recommended to have a GPU (graphics...
Table 3:
Installation methods. MONAI label can be installed through three methods: from...
Table 4:
The key metrics during the training, in particular the epoch, train loss, dice,...
![](https://epos.myesr.org/posterimage/esr/ecr2024/164872/media/979893?maxheight=150&maxwidth=150 "Fig 10: The radiology and bundle apps are saved in the "apps" folder, located in the path: Local Disk (C:)/Users/(User name)/apps.")
Fig 10:
The radiology and bundle apps are saved in the "apps" folder, located in the...
![](https://epos.myesr.org/posterimage/esr/ecr2024/164872/media/979892?maxheight=150&maxwidth=150 "Fig 11: Typing the command "monailabel datasets" all datasets available as part of the medical segmentation decathlon are enlisted.")
Fig 11:
Typing the command "monailabel datasets" all datasets available as part of the...
![](https://epos.myesr.org/posterimage/esr/ecr2024/164872/media/979895?maxheight=150&maxwidth=150 "Fig 12: Example of how a dataset is organized (in this case the "Task09_Spleen folder is shown). Typically, a dataset consists of both training and testing data. The "images Tr" folder contains training images, while the "images Ts" folder contains testing images. The labels are stored in the "labels Tr" folder. Additionally, the "dataset.json" file contains information about the dataset.")
Fig 12:
Example of how a dataset is organized (in this case the "Task09_Spleen folder...
Fig 13:
The extension manager of 3D-Slicer with MONAI label.
Fig 14:
The top panel of MONAI label in 3D-Slicer (MONAI label server, app name, source...
Fig 15:
The top panel of MONAI label in 3D-Slicer (Active learning).
Fig 16:
The bottom panel of MONAI label in 3D-Slicer (Segment editor, autosegmentation,...
![](https://epos.myesr.org/posterimage/esr/ecr2024/164872/media/979904?maxheight=150&maxwidth=150 "Fig 17: Examples of how to perform segmentation with Deepedit and Deepgrow. In Deepedit mode, simply place the landmark on the organ of interest to obtain segmentation. With Deepgrow, on the other hand, segmentation is achieved by placing the cursor on "foreground" for positive clicks and "background" for negative clicks.")
Fig 17:
Examples of how to perform segmentation with Deepedit and Deepgrow. In Deepedit...
Fig 18:
Example of how to perform segmentation with scribbles. In the first phase, one...
![](https://epos.myesr.org/posterimage/esr/ecr2024/164872/media/979910?maxheight=150&maxwidth=150 "Fig 19: Wholebrainseg large UNest segmentation model. The model, based on UNest, is trained to segment 133 structures, each of which is individually listed in the Segment Editor. The final result is partially degraded by background noise, which has been removed using the "Erase" tool in the Segment Editor.")
Fig 19:
Wholebrainseg large UNest segmentation model. The model, based on UNest, is...
Fig 20:
Pancreas ct dints segmentation model. This model, through the U-Net...
Fig 21:
Lung nodule ct detection model. The model performed well in this case, although...
Fig 22:
Renal structures UNest segmentation. The model is trained to recognize the...
Fig 23:
WholeBody ct segmentation. This model is based on U-Net and can label up to 104...
Fig 24:
The three subsequent stages after completing the segmentation are: 1) Submit...
Fig 25:
The active learning module during training. As the training progresses, the...
Fig 26:
The active learning cycle (from the article by Diaz-Pinto A. et al (2023) MONAI...
