nnUNet VS medicaldetectiontoolkit

Now just run your images and masks in nnUNet to see if it works. https://github.com/MIC-DKFZ/nnUNet

I would also try the nnU-Net which should give state-of-the-art performance, and so will give you a good idea of what's possible with the dataset that you have: https://github.com/MIC-DKFZ/nnUNet

I used the nnUnet repo and their guide on using it on your own data

Hi all, Does anyone have experience with converting a nnUNet pytorch models into Tf using Onnx?

If you want my honest opinion, you should probably always use nnUnet as a baseline for any 3d segmentation tasks - https://github.com/MIC-DKFZ/nnUNet.

Not a "detection" but a "segmenting" CNN: https://github.com/MIC-DKFZ/nnunet

I ran some model fitting performance benchmarks on a 3D (medical) image segmentation UNET on various cloud providers and I am flabbergasted by the very low performance of V100 and A100 machines on vast.ai.

Checkout https://github.com/MIC-DKFZ/medicaldetectiontoolkit, they have a recent 3d rcnn implementation. Their paper is a good start on the topic. Also have a look at nnDetection from the same group, it might provide some more leads. Hth

I'm doing research in the area of biomedical image processing using deep learning. At the moment, I'm focused in the detection of biological structures in 3D microscopy images. For this task I trained a Faster R-CNN architecture, however I noticed that while the training loss is decreasing the validation loss is high, doesn't decrease and sometimes oscillates. When I looked at the results, the bounding boxes in the training and validation sets were too small but located at random spots. At first I thought that I should adjust the size of the anchors, however, even after trying different anchor sizes the results didn't improve. I would like to know if anyone has experience in working with 3D Faster R-CNN that could help me with suggestions for this project. (btw, I'm using the code available in this repo). Thanks in advance.