Re: [Freesurfer] Easyreg > cortical parcels missing after SynthSeg with --parc option ?

External Email - Use Caution

Hello Malte

Thank you for your response. I am writing to express my interest in utilizing the easy_reg tool for the purpose of normalizing patient data, specifically those diagnosed with Gliomas, to MNI space.

A particular concern of mine is the potential impact of the tumor region on the loss function during the registration process.

It is my hope that the loss function attributed to the tumor region could be excluded or minimized to ensure the accuracy of the normalization.

Furthermore, I am keen to know whether easy_reg supports the application of cost function masking, or if there exists an alternative approach within FreeSurfer that you might recommend for achieving this objective.

Thanks in advance!

Best regards, Edward

Sent from my iPad

On Apr 5, 2024, at 9:57 AM, Hoffmann, Malte,PhD MHOFFMANN@mgh.harvard.edu wrote:

What are you trying to achieve?

---

From: Iglesias Gonzalez, Juan E. JIGLESIASGONZALEZ@mgh.harvard.edu Sent: Thursday, April 4, 2024 09:02 To: Freesurfer support list Cc: Hoffmann, Malte,PhD Subject: Re: [Freesurfer] Easyreg > cortical parcels missing after SynthSeg with --parc option ?

Glad to hear, Edward! The cost masking feature is not available. To provide such a functionality, one would have to retrain with (possibly random) masks? I don’t know if Malte (CCed) plans to incorporate this into SynthMorph (or maybe he’s done already and I’m unaware of it?). Cheers, /E -- Juan Eugenio Iglesias http://secure-web.cisco.com/1ouhZwEqdGpAUrt0N7u1qdOMaij5zz0Vs6QXgRKV6i_ZM-rh...

From: freesurfer-bounces@nmr.mgh.harvard.edu freesurfer-bounces@nmr.mgh.harvard.edu on behalf of r04458005@ntu.edu.tw r04458005@ntu.edu.tw Date: Wednesday, April 3, 2024 at 7:43 PM To: 'Freesurfer support list' freesurfer@nmr.mgh.harvard.edu Subject: Re: [Freesurfer] Easyreg > cortical parcels missing after SynthSeg with --parc option ?

   External Email - Use Caution

Hello Eugenio

I just wanted you to know that the issue with the command has been resolved successfully after employing an alternative MNI template. The modification appears to have rectified the problem, and the command is now functioning as expected. However, I would like to inquire about the capabilities of Easyreg pertaining to registration processes. Specifically, does Easyreg facilitate the implementation of cost function masking during registration?

Thanks in advance for your help.

Best,

Edward From: freesurfer-bounces@nmr.mgh.harvard.edu freesurfer-bounces@nmr.mgh.harvard.edu On Behalf Of Iglesias Gonzalez, Juan E. Sent: Wednesday, April 3, 2024 4:16 AM To: Freesurfer support list freesurfer@nmr.mgh.harvard.edu Subject: Re: [Freesurfer] Easyreg > cortical parcels missing after SynthSeg with --parc option ?

Ha! I understand that sharing the images may be tricky, but do you think you could send me the segmentations /home/chang/GBM_Data/T1_template/Template_MNI_Normal122_sc_age19-40_tirq_1.0mm_T1_scalp_trip_synthseg.nii And /home/chang/GBM_Data/GBM_original/20231223_1/Pre/Kuo/Brain_only_synthseg/042/pre_042_0000_synthseg.nii.gz ? Cheers, /E -- Juan Eugenio Iglesias MailScanner has detected a possible fraud attempt from "secure-web.cisco.com" claiming to be http://secure-web.cisco.com/1ouhZwEqdGpAUrt0N7u1qdOMaij5zz0Vs6QXgRKV6i_ZM-rh...http://secure-web.cisco.com/1cT1MaLk1hUpIx5e993JvHDib3de8-4C_3q8iR19MMJyY_iyDOtcZHVEmcDwwRYd-jgjil8XL4mkI9SMIOT_GLVKDgVT39pEAOBvmVthK_Xgn3NG7fmuuH3s7TnNBrdBo5-GXN83iwCCFSP76ytMb2783KOC6SoR3RZ5stbB9h5RCT-PPQn3I3L8ExS1qdiwuv6ZYdGa3vAPxn78CHcd2BQK7nBDKEj4wPahZdiL0x_ctHCGRqG4sQL-VBmIKReZZVLMhLUCewgN1Qwj15012Ib_ucdC9X1eHuomZDBGMveOzekfh4SCRzO_6At_hfgmK/http%3A%2F%2Fwww.jeiglesias.com

From: freesurfer-bounces@nmr.mgh.harvard.edumailto:freesurfer-bounces@nmr.mgh.harvard.edu <freesurfer-bounces@nmr.mgh.harvard.edumailto:freesurfer-bounces@nmr.mgh.harvard.edu> on behalf of r04458005@ntu.edu.twmailto:r04458005@ntu.edu.tw <r04458005@ntu.edu.twmailto:r04458005@ntu.edu.tw> Date: Monday, April 1, 2024 at 10:24 AM To: 'Freesurfer support list' <freesurfer@nmr.mgh.harvard.edumailto:freesurfer@nmr.mgh.harvard.edu> Subject: Re: [Freesurfer] Easyreg > cortical parcels missing after SynthSeg with --parc option ?

   External Email - Use Caution

Hello Eugenio

Thanks for the reply!

After I follow your instruction, the command works for a while for the segmentation part and some errors come up as following.

Any hints?

Thanks in advance for your help.

Best,

Edward

mri_easyreg --ref /home/chang/GBM_Data/T1_template/Template_MNI_Normal122_sc_age19-40_tirq_1.0mm_T1_scalp_trip.nii --flo /home/chang/GBM_Data/GBM_original/20231223_1/Pre/Kuo/Brain_only/pre_042_0000.nii.gz --ref_seg /home/chang/GBM_Data/T1_template/Template_MNI_Normal122_sc_age19-40_tirq_1.0mm_T1_scalp_trip_synthseg.nii --flo_seg /home/chang/GBM_Data/GBM_original/20231223_1/Pre/Kuo/Brain_only_synthseg/042/pre_042_0000_synthseg.nii.gz --ref_reg /home/chang/GBM_Data/GBM_original/20231223_1/Pre/Kuo/Brain_only_synthseg/042/pre_042_ref_reg.nii.gz --flo_reg /home/chang/GBM_Data/GBM_original/20231223_1/Pre/Kuo/Brain_only_synthseg/042/pre_042_flo_reg.nii.gz --fwd_field /home/chang/GBM_Data/GBM_original/20231223_1/Pre/Kuo/Brain_only_synthseg/042/pre_042_FWF.nii.gz --bak_field /home/chang/GBM_Data/GBM_original/20231223_1/Pre/Kuo/Brain_only_synthseg/042/pre_042_BWF.nii.gz 2024-04-01 22:08:39.479784: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used. 2024-04-01 22:08:39.500470: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used. 2024-04-01 22:08:39.500724: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2024-04-01 22:08:39.793976: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT using 1 thread Segmenting reference image Reading reference image Setting up segmentation net 2024-04-01 22:08:41.454567: E tensorflow/compiler/xla/stream_executor/cuda/cuda_driver.cc:266] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected 2024-04-01 22:08:41.454592: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:168] retrieving CUDA diagnostic information for host: chang-System-Product-Name 2024-04-01 22:08:41.454595: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:175] hostname: chang-System-Product-Name 2024-04-01 22:08:41.454678: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:199] libcuda reported version is: 545.23.8 2024-04-01 22:08:41.454689: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:203] kernel reported version is: 545.23.8 2024-04-01 22:08:41.454691: I tensorflow/compiler/xla/stream_executor/cuda/cuda_diagnostics.cc:309] kernel version seems to match DSO: 545.23.8 Inference / segmentation 2024-04-01 22:08:42.569555: W tensorflow/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 471859200 exceeds 10% of free system memory. 2024-04-01 22:08:43.290274: W tensorflow/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 471859200 exceeds 10% of free system memory. 2024-04-01 22:08:45.227286: W tensorflow/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 471859200 exceeds 10% of free system memory. 2024-04-01 22:08:49.154534: W tensorflow/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 353894400 exceeds 10% of free system memory. 2024-04-01 22:08:51.720818: W tensorflow/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 471859200 exceeds 10% of free system memory. 1/1 [==============================] - 85s 85s/step Postprocessing Saving result Segmenting floating image Reading floating image Inference / segmentation 1/1 [==============================] - 190s 190s/step Postprocessing Saving result Linear registration Computing centroids and estimating affine transform Traceback (most recent call last): File "/usr/local/freesurfer/python/scripts/mri_easyreg", line 1809, in <module> main() File "/usr/local/freesurfer/python/scripts/mri_easyreg", line 180, in main Mref = getM(atlasCOG[:, ok > 0], refCOG[:, ok > 0]) File "/usr/local/freesurfer/python/scripts/mri_easyreg", line 1198, in getM x = np.matmul(np.linalg.inv(np.matmul(np.transpose(A), A)), np.matmul(np.transpose(A), b)) File "<__array_function__ internals>", line 180, in inv File "/usr/local/freesurfer/python/lib/python3.8/site-packages/numpy/linalg/linalg.py", line 552, in inv ainv = _umath_linalg.inv(a, signature=signature, extobj=extobj) File "/usr/local/freesurfer/python/lib/python3.8/site-packages/numpy/linalg/linalg.py", line 89, in _raise_linalgerror_singular raise LinAlgError("Singular matrix") numpy.linalg.LinAlgError: Singular matrix

From: freesurfer-bounces@nmr.mgh.harvard.edumailto:freesurfer-bounces@nmr.mgh.harvard.edu <freesurfer-bounces@nmr.mgh.harvard.edumailto:freesurfer-bounces@nmr.mgh.harvard.edu> On Behalf Of Iglesias Gonzalez, Juan E. Sent: Monday, April 1, 2024 8:41 PM To: Freesurfer support list <freesurfer@nmr.mgh.harvard.edumailto:freesurfer@nmr.mgh.harvard.edu> Subject: Re: [Freesurfer] Easyreg > cortical parcels missing after SynthSeg with --parc option ?

Dear Edward, Try deleting: /home/chang/GBM_Data/T1_template/Template_MNI_Normal122_sc_age19-40_tirq_1.0mm_T1_scalp_trip_synthseg.nii and /home/chang/GBM_Data/GBM_original/20231223_1/Pre/Kuo/Brain_only_synthseg/042/pre_042_0000_synthseg.nii.gz And then run the same command. Easy_reg will create the right segmentations for you. Cheers, /Eugenio

-- Juan Eugenio Iglesias MailScanner has detected a possible fraud attempt from "secure-web.cisco.com" claiming to be http://secure-web.cisco.com/1ouhZwEqdGpAUrt0N7u1qdOMaij5zz0Vs6QXgRKV6i_ZM-rh...http://secure-web.cisco.com/1-q3mT9vTdAapiqbsXI3OPjVT3m8xjQKkHHLvyVZZFFM9DJ_5k0PAnQnJX6I4Cl4Q0ET_kF2QuivsdvaRRLnKGUY3-p9v8vRR-YtaT47YWeAJwR7cvWfk9HLDY3ninRU7SRlACRb9gf2xr4m3_cvdcb01Mkixcxdqur8fPlcUevmMl_UedfbZ7AfamE7MOmv4LOSo3F80ZVCWW6Ag9IjPMWiHAmC-pr3DJ4lyDxk8adwWkRbcbABEj0E6MBEoWChyxIszaQWb9zgG_gaDaSlF0WrtDGGGutc_Qa1Q9JlvByRARNCt6T_00GOWSxfalQgU/http%3A%2F%2Fwww.jeiglesias.com

From: freesurfer-bounces@nmr.mgh.harvard.edumailto:freesurfer-bounces@nmr.mgh.harvard.edu <freesurfer-bounces@nmr.mgh.harvard.edumailto:freesurfer-bounces@nmr.mgh.harvard.edu> on behalf of r04458005@ntu.edu.twmailto:r04458005@ntu.edu.tw <r04458005@ntu.edu.twmailto:r04458005@ntu.edu.tw> Date: Sunday, March 31, 2024 at 3:55 AM To: freesurfer@nmr.mgh.harvard.edumailto:freesurfer@nmr.mgh.harvard.edu <freesurfer@nmr.mgh.harvard.edumailto:freesurfer@nmr.mgh.harvard.edu> Subject: [Freesurfer] Easyreg > cortical parcels missing after SynthSeg with --parc option ?

   External Email - Use Caution

Hello Freesurfer Developpers,

I attempted to run mri_easyreg (Freesurfer 7.4) between two images.

After I ran mri-easyreg adding these images (--ref_seg

--flo_reg), I get again the > no cortical parcels.

The following is the command I used and the error code.

What did I do wong?

Any hints?

Thanks in advance for your help.

Best,

Edward

mri_easyreg --ref /home/chang/GBM_Data/T1_template/Template_MNI_Normal122_sc_age19-40_tirq_1.0mm_T1_scalp_trip.nii --flo /home/chang/GBM_Data/GBM_original/20231223_1/Pre/Kuo/Brain_only/pre_042_0000.nii.gz --ref_seg /home/chang/GBM_Data/T1_template/Template_MNI_Normal122_sc_age19-40_tirq_1.0mm_T1_scalp_trip_synthseg.nii --flo_seg /home/chang/GBM_Data/GBM_original/20231223_1/Pre/Kuo/Brain_only_synthseg/042/pre_042_0000_synthseg.nii.gz --ref_reg /home/chang/GBM_Data/GBM_original/20231223_1/Pre/Kuo/Brain_only_synthseg/042/pre_042_ref_reg.nii.gz --flo_reg /home/chang/GBM_Data/GBM_original/20231223_1/Pre/Kuo/Brain_only_synthseg/042/pre_042_flo_reg.nii.gz --fwd_field /home/chang/GBM_Data/GBM_original/20231223_1/Pre/Kuo/Brain_only_synthseg/042/pre_042_FWF.nii.gz --bak_field /home/chang/GBM_Data/GBM_original/20231223_1/Pre/Kuo/Brain_only_synthseg/042/pre_042_BWF.nii.gz

2024-03-31 15:50:23.731218: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used. 2024-03-31 15:50:23.752531: I tensorflow/tsl/cuda/cudart_stub.cc:28] Could not find cuda drivers on your machine, GPU will not be used. 2024-03-31 15:50:23.752807: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2024-03-31 15:50:24.041622: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT using 1 thread Segmentation of reference image already exists; reading from disk Error: No cortical labels found; does the segmentation include cortical parcels?

---

Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://secure-web.cisco.com/1yHEkeBnbAAzb8GXeE9RJC5tvBqLBv6ecNOIKAr7wnWNuqV... The information in this e-mail is intended only for the person to whom it is addressed. If you believe this e-mail was sent to you in error and the e-mail contains patient information, please contact the Mass General Brigham Compliance HelpLine at https://secure-web.cisco.com/1cxev3tGRl_8H4xhcSP0NnuH2I_siEF3gsYZU67UQRSvyzy... https://secure-web.cisco.com/1cxev3tGRl_8H4xhcSP0NnuH2I_siEF3gsYZU67UQRSvyzyrvMmBCQCY35Pg28byQDOvYEpcmgqtgfk9PV8BwpYzE0uNrf2UKDiB0zDuCkhnoMcTxLeh7Nrz6mlvpFvXI0jlaupScnsdaDk-Ht_vMfBjOtF3bXeXKwIeSvzOPCnhmPhcrmqyUqwYE2lm8kNZTKvZI-Fwv6mi7nMWLVamAHFGJAi75EJ-J8nkhu2l3NEZdXBHIGPsDVTuAcnCceQ5Pmrm5rCKVwy92Z4QZZ7-M2-RYfZyV8g1MAhlRbsjsHP2VWrLfmIOfWXYsJdexePxZTO3KoL_IrCJ-9dRdUzKzPw/https%3A%2F%2Fwww.massgeneralbrigham.org%2Fcomplianceline . Please note that this e-mail is not secure (encrypted). If you do not wish to continue communication over unencrypted e-mail, please notify the sender of this message immediately. Continuing to send or respond to e-mail after receiving this message means you understand and accept this risk and wish to continue to communicate over unencrypted e-mail.