# Recurring bug on Shoulder tracking

**URL:** <https://discourse.slicer.org/t/recurring-bug-on-shoulder-tracking/47656>\
**Category:** SlicerAutoscoperM\
**Tags:** registration, bug\
**Created:** [July 17, 2026, 1:14pm UTC](https://discourse.slicer.org/t/recurring-bug-on-shoulder-tracking/47656 "2026-07-17T13:14:48Z")\
**Posts on this page:** 13\
**Page:** 1

<div class="post-metadata">

**Author:** ![AlonsoFigueroa](https://avatars.discourse-cdn.com/v4/letter/a/c5a1d2/32.png) [@AlonsoFigueroa](https://discourse.slicer.org/u/AlonsoFigueroa)\
**Post date:** [July 17, 2026, 1:14pm UTC](https://discourse.slicer.org/t/recurring-bug-on-shoulder-tracking/47656/1 "2026-07-17T13:14:48Z")

</div>

Hello SAM team,

We are encountering an issue while tracking a scapula in Autoscoper during an arm elevation task.

For one participant, Autoscoper consistently crashes when saving frames within specific ranges of motion. The crash occurs during tracking of the shoulder/scapula and is reproducible across multiple trials. We have attempted to process the same participant data on different computers and obtained the same result each time.

I found an older issue that appears to describe a very similar problem, although it does not seem to have been resolved:

[BrownBiomechanics/Autoscoper#305](https://github.com/BrownBiomechanics/Autoscoper/issues/305)

System information:

3D Slicer version: 5.10.1  
Operating System: Windows  
GPU: NVIDIA RTX 3080 Ti

![Adobe Express - 2026-07-09_15-41-23](https://us1.discourse-cdn.com/flex002/uploads/slicer/original/3X/2/c/2cb90a5436921c99d7fcd2f5cf8672ebc0338cfc.gif)

---

<div class="post-metadata">

**Author:** ![John\_Holtgrewe](https://avatars.discourse-cdn.com/v4/letter/j/5daacb/32.png) [@John\_Holtgrewe](https://discourse.slicer.org/u/John_Holtgrewe)\
**Post date:** [July 17, 2026, 3:03pm UTC](https://discourse.slicer.org/t/recurring-bug-on-shoulder-tracking/47656/2 "2026-07-17T15:03:02Z")

</div>

Hi Alonso,

Thanks for bringing this to our attention. My experience with SAM is limited to tracking the femur and tibia, and I have not encountered this issue. However, I know that other groups have used SAM to successfully track the scapula. @Cesar Did you have this issue with any of your data?

Does this happen when processing data from other participants, or just this one?

---

<div class="post-metadata">

**Author:** ![Cesar](https://avatars.discourse-cdn.com/v4/letter/c/e47774/32.png) [@Cesar](https://discourse.slicer.org/u/Cesar)\
**Post date:** [July 17, 2026, 5:53pm UTC](https://discourse.slicer.org/t/recurring-bug-on-shoulder-tracking/47656/3 "2026-07-17T17:53:56Z")

</div>

I remember running into a similar issue while using the optimization feature, but it was fixed fairly quickly. I haven’t seen this specific problem before. I wonder if the graphics card could be causing the crash. Alonso, are you running SAM on a remote computer?

---

<div class="post-metadata">

**Author:** ![AlonsoFigueroa](https://avatars.discourse-cdn.com/v4/letter/a/c5a1d2/32.png) [@AlonsoFigueroa](https://discourse.slicer.org/u/AlonsoFigueroa)\
**Post date:** [July 17, 2026, 8:46pm UTC](https://discourse.slicer.org/t/recurring-bug-on-shoulder-tracking/47656/4 "2026-07-17T20:46:45Z")

</div>

Hello Cesar and John,

Thank you for taking the time to investigate this issue.

We are currently running SAM on a local workstation. We’ve tested multiple computers and several different subjects, and it appears that approximately half of the subjects we upload to SAM encounter this issue.

The workstations we have been using for these trials have the following specifications:

- Dell Precision 5860
- Intel Xeon W3-2423
- NVIDIA RTX 3080 Ti

I’d be happy to share the files with your team if you’d like to investigate further. However, the image files are too large to upload through this platform. Please let me know the best way to transfer them, and I’ll send them over.

---

<div class="post-metadata">

**Author:** ![AlonsoFigueroa](https://avatars.discourse-cdn.com/v4/letter/a/c5a1d2/32.png) [@AlonsoFigueroa](https://discourse.slicer.org/u/AlonsoFigueroa)\
**Post date:** [July 29, 2026, 7:21pm UTC](https://discourse.slicer.org/t/recurring-bug-on-shoulder-tracking/47656/5 "2026-07-29T19:21:05Z")

</div>

Hi @John_Holtgrewe, I wanted to provide a brief update on the Autoscoper-CUDA crashes we previously reported. We have now reproduced the issue with multiple scapular models from different patients and CT scans. The crash is also reproducible across several computers with different hardware configurations, including RTX 3080 and 3080 Ti GPUs, different Intel processors, and at least 64 GB of RAM. This suggests that the issue is not isolated to a particular dataset or workstation.

Further testing suggests that the crash may be related to the size or extent of the scapular model. If we crop the model to approximately half of the scapula, excluding the inferior portion, the crash no longer occurs. However, this is not a practical solution for our application because excluding the inferior scapula removes landmarks that we use for tracking and reduces the reliability and capability of the autotracking function.

We have also been investigating the source of the crash on our side and have found the following:

Windows Reliability Monitor initially reported exception code `0xc0000409` in `ucrtbase.dll`. We therefore configured Windows Error Reporting to capture a full crash dump and analyzed it with WinDbg. The dump indicates that, following the relevant button click in Autoscoper, the application throws an unhandled native C++ exception (`0xe06d7363`). The C++ runtime then calls `terminate()` and `abort()`, producing the final `FAST_FAIL_FATAL_APP_EXIT` (`0xc0000409`). The first identifiable Autoscoper frame is `autoscoper-CUDA+0x660c7`, but without the corresponding debug symbols we cannot resolve it to a specific function.

I can provide the complete WinDbg output, crash dump, and additional reproduction details if helpful.

---

<div class="post-metadata">

**Author:** ![mikebind](https://avatars.discourse-cdn.com/v4/letter/m/71e660/32.png) [@mikebind](https://discourse.slicer.org/u/mikebind)\
**Post date:** [July 30, 2026, 5:38pm UTC](https://discourse.slicer.org/t/recurring-bug-on-shoulder-tracking/47656/6 "2026-07-30T17:38:12Z")

</div>

I’m not familiar with AutoScoper, but it sounds from your troubleshooting like the scapula model may just have too many points for the processing occurring and the memory problems are leading to the crash (running out of memory is probably the most common reason for Slicer crashes). For models, the typical best solution is decimation. For models with a high density of points, you can often reduce the number of points very dramatically (\>90%) without much loss of detail. So, rather than cropping, perhaps you can decimate the model to stay within memory limits. Interactively, you can do this using the SurfaceToolbox module, and it is also possible via python/VTK if it needs to be integrated into the workflow more deeply.

---

<div class="post-metadata">

**Author:** ![John\_Holtgrewe](https://avatars.discourse-cdn.com/v4/letter/j/5daacb/32.png) [@John\_Holtgrewe](https://discourse.slicer.org/u/John_Holtgrewe)\
**Post date:** [August 7, 2026, 6:01pm UTC](https://discourse.slicer.org/t/recurring-bug-on-shoulder-tracking/47656/7 "2026-08-07T18:01:57Z")

</div>

Hi Alonso,

I apologize for just now getting back to you. The size of the volumes possibly causing the crash is interesting. We have only worked with relatively smaller volumes (distal end of the femur and proximal end of tibia). Could you share the following details about the volumes that you are trying to load in: dimensions of the tiff stack (including number of slices), voxel size, and file size?

Yes, any additional reproduction details you can provide will be helpful with documenting this issue.

Thanks!

John

---

<div class="post-metadata">

**Author:** ![AlonsoFigueroa](https://avatars.discourse-cdn.com/v4/letter/a/c5a1d2/32.png) [@AlonsoFigueroa](https://discourse.slicer.org/u/AlonsoFigueroa)\
**Post date:** [August 10, 2026, 3:32pm UTC](https://discourse.slicer.org/t/recurring-bug-on-shoulder-tracking/47656/8 "2026-08-10T15:32:06Z")

</div>

Hello John,

Thank you so much for getting back to us.

We followed @mikebind advice and decimated both the STL models and the TIFF stacks, but unfortunately, the issue persists. Thank you as well, Mike, we’ll report back as soon as we resolve it. I am adding the details of the data that we are using, but I am happy to share the volumes and images if you’d like.

Please find the details of our data below:

**Original CT scan**

- Dimensions: 512 × 512 × 411
- Voxel spacing: 0.48828125 × 0.48828125 × 0.6 mm

**X-ray images**

- File size: 2 MB per frame
- Bit depth: 16-bit
- Dimensions: 1024 × 1024

**Scapula**

- TIFF: 20.5 MB; 229 × 239 × 241; VoxelSize 0.488 0.488 0.6; 16-bit
- STL: 16.2 MB; 231,301 vertices

**Clavicle**

- TIFF: 715 KB; 328 × 166 × 80; VoxelSize 0.488 0.488 0.6; 16-bit
- STL: 5.3 MB; 94,912 vertices

**Humerus**

- TIFF: 2 MB; 110 × 140 × 285; VoxelSize 0.488 0.488 0.6; 16-bit
- STL: 9.3 MB; 94,912 vertices

---

<div class="post-metadata">

**Author:** ![John\_Holtgrewe](https://avatars.discourse-cdn.com/v4/letter/j/5daacb/32.png) [@John\_Holtgrewe](https://discourse.slicer.org/u/John_Holtgrewe)\
**Post date:** [August 13, 2026, 1:58pm UTC](https://discourse.slicer.org/t/recurring-bug-on-shoulder-tracking/47656/9 "2026-08-13T13:58:10Z")

</div>

If you could share the volumes and images, just so I could replicate the issue on my end, that would be helpful. Your scapula volume is quite a bit bigger than our femur and tibia volumes, so we don’t have anything comparable to test.

@Cesar Can you comment on how the size of their volumes compares to the scapula volumes that you have tracked previously?

We currently have limited ability to address bugs in the software; however, we do have a student who will be joining us to specifically work on SlicerAutoscoper, and bug fixes (with this one as a priority) are at the top of the list for things to work on.

---

<div class="post-metadata">

**Author:** ![AlonsoFigueroa](https://avatars.discourse-cdn.com/v4/letter/a/c5a1d2/32.png) [@AlonsoFigueroa](https://discourse.slicer.org/u/AlonsoFigueroa)\
**Post date:** [August 17, 2026, 3:49pm UTC](https://discourse.slicer.org/t/recurring-bug-on-shoulder-tracking/47656/11 "2026-08-17T15:49:14Z")

</div>

Happy to share the volumes and images with your team. However, I think the folders are larger than what can be uploaded to Discourse, What would be your best alternative to share the data with you?

---

<div class="post-metadata">

**Author:** ![John\_Holtgrewe](https://avatars.discourse-cdn.com/v4/letter/j/5daacb/32.png) [@John\_Holtgrewe](https://discourse.slicer.org/u/John_Holtgrewe)\
**Post date:** [August 21, 2026, 2:08pm UTC](https://discourse.slicer.org/t/recurring-bug-on-shoulder-tracking/47656/13 "2026-08-21T14:08:34Z")

</div>

@AlonsoFigueroa I totally missed that you had shared the files on GitHub, so I was able to download them from there.

---

<div class="post-metadata">

**Author:** ![John\_Holtgrewe](https://avatars.discourse-cdn.com/v4/letter/j/5daacb/32.png) [@John\_Holtgrewe](https://discourse.slicer.org/u/John_Holtgrewe)\
**Post date:** [August 27, 2026, 2:09pm UTC](https://discourse.slicer.org/t/recurring-bug-on-shoulder-tracking/47656/14 "2026-08-27T14:09:13Z")

</div>

Hi @AlonsoFigueroa ,

Could you share a subset of the radiograph images for trial you are trying to track the scapula in (just 5-10 frames)? You can add them to the issue in Github, or if the files are too large we can figure something else out.

Thanks!

John

---

<div class="post-metadata">

**Author:** ![AlonsoFigueroa](https://avatars.discourse-cdn.com/v4/letter/a/c5a1d2/32.png) [@AlonsoFigueroa](https://discourse.slicer.org/u/AlonsoFigueroa)\
**Post date:** [August 27, 2026, 4:13pm UTC](https://discourse.slicer.org/t/recurring-bug-on-shoulder-tracking/47656/15 "2026-08-27T16:13:35Z")

</div>

Hi @John_Holtgrewe

Thank you for continuing to investigate this issue. I’m glad you were able to download the files from GitHub.

We have assembled a dataset from a trial that consistently crashes. The dataset contains 10 continuous frames. On our systems, the first five frames track successfully, while the second half of the video causes the software to crash.

Unfortunately, I was unable to upload the files directly to this thread. However, the cropped trials have now been uploaded to the GitHub issue:

> <https://github.com/BrownBiomechanics/SlicerAutoscoperM/issues/195>
>
> Hello SAM team,
> 
> We are encountering an issue while tracking a scapula in Autosc…oper during an arm elevation task.
> 
> For one participant, Autoscoper consistently crashes when saving frames within specific ranges of motion. The crash occurs during tracking of the shoulder/scapula and is reproducible across multiple trials. We have attempted to process the same participant data on different computers and obtained the same result each time.
> 
> I found an older issue that appears to describe a very similar problem, although it does not seem to have been resolved:
> 
> https://github.com/BrownBiomechanics/Autoscoper/issues/305
> 
> System information:
> 
> 3D Slicer version: 5.10.1
> Operating System: Windows
> GPU: NVIDIA RTX 3080 Ti
> 
> \[Config Files.zip\](https://github.com/user-attachments/files/29865648/Config.Files.zip)
> \[Video-evidence.zip\](https://github.com/user-attachments/files/29865651/Video-evidence.zip)
> \[Maya Cams.zip\](https://github.com/user-attachments/files/29865650/Maya.Cams.zip)
> \[Tracking Files.zip\](https://github.com/user-attachments/files/29865649/Tracking.Files.zip)
> \[Volumes.zip\](https://github.com/user-attachments/files/29865731/Volumes.zip)
> 
> (Image data is to large to upload in this post, I am happy to share these images)

I’m also bringing @sydney.wheaton into the conversation. Sydney is our research engineer who focuses on shoulder-related projects and has the most experience with this issue. If you have any specific questions about the crashes, she will be able to provide additional details and insight.