External Email - Use Caution I've just exposed the option to the user. It might take some days before it will be available in the development version.
@sudeepti: In the new development version, if you add to your samseg command the following flag "--do-not-use-shape-model", the lesion shape model (VAE) will not be used. This will most probably produce a lesion segmentation with more true positives *and* more false positives. Please double-check the results if you're using this option. Stefano On Fri, Jan 5, 2024 at 11:20 AM Koen Van Leemput <leem...@gmail.com> wrote: > External Email - Use Caution > > Hi Stefano, > > For samseg isn't there also an option to disable the VAE shape model? I > forgot the details, but if false positives are not an issue maybe that > could also help? > > Koen > > On Friday, January 5, 2024, Stefano Cerri <ste.45....@gmail.com> wrote: > >> External Email - Use Caution >> >> Hi, >> >> For SAMSEG: >> >> Are you using the --lesion-mask-pattern flag with the value "1" on the >> FLAIR scan? You can try to relax the masking by excluding darker than WM >> mean intensities voxels rather than darker than GM ones, i.e., by adding to >> your command: --lesion-mask-structure "White" >> >> For WMH-SynthSeg: >> >> It looks like a memory error (the process was killed). On the Wiki: >> *MailScanner >> has detected a possible fraud attempt from "secure-web.cisco.com" claiming >> to be* >> https://secure-web.cisco.com/1n6HHxGODqkOuO4bNnigMhWKnI-nKae-t26hw5s_Sdz9GzWiUDG_AtQ_j3y3ivmY1bmsnhBUnuuvFPcgoa2Ua5qxVd2xrLqy1F6WaQqEFMV2oyQt1k1XiINNYLrPrgl_55cjqyYyK-0u0uTe8FglkHsn4QxDt9cGdw6DVTpcrCn1Djm11J3BMY7juusRHnx7T1Ifog1C9FbOf_lSU9arBqg8dq0W6qyObwIZs4mXMO62bnn-LGm7gFX80Hl5jA_A5WtNdmQ2Fvkp1nzKkDTXPxhQYUxdWzBikOu49wbIrBb0nSjwVccUy7pV40H2YjjLnI276nbbmJAPQapRw3FHrRw/https%3A%2F%2Fsurfer.nmr.mgh.harvard.edu%2Ffswiki%2FWMH-SynthSeg >> <https://secure-web.cisco.com/1HuCfTaru0pjBRImg5FBdnCDAClGBp2QhQDG_ONxySiD4aBpb8dX_9OWokS_PrsTYfMYUj6Dub6piUJi2g2Zpl7rhqLNDkcwSORd5hQ3SUk7_fYeGPCEOrfp3QjhjjHebnuj-k3zV_yc_wRKAI-jbX5BHqaNgPByMMc7-bhmMcBGophr1_lP4tmBxmq-SvMcZ0iWerp81-cOXMxo4NtbhS5gIUIhprFiFtLhcXjlwCtPcMIaIHbmTzL5XjtfzOLAg-22R7Awi6o7400qTCzIKXxyS473rB0txewIziNjlNmHT6MgPBPh5iwHokUj3naGQ_jEESDEujufpSbUwtVxLbA/https%3A%2F%2Fsurfer.nmr.mgh.harvard.edu%2Ffswiki%2FWMH-SynthSeg> >> they recommend 32GB of RAM. Do you have access to a machine with more RAM? >> >> Stefano >> >> [Freesurfer] WMH-SynthSeg vs. SAMSEG for WM lesions >> <https://secure-web.cisco.com/10UF5Sfsck6gBiuQyh4tRFtvmnzLpFEUi-WgbbCbj9UG2boB9N5XjVjTMWP2Y5j0lQtS3keltoGD7fPWDgtVe4_5zwOh3es5NY-BMN0A-JNk3wH3si-segJF_xIACeMG_YaMeVT-mTgyjusr2X32cUZsjuXj60HXiGVdQp0SfFDc9lQHUzFNKP3zkFwCj3pM52K3KI10F1CmH4AxI-FtLil2AAV-fRw1C8_HdbId3ZjXeXMyJ7gC8DUXEWapUSmiRGZACymUMayzcIvfmH1L1S2za6QCGAGCsPoM8UG7wXCdJkTPJuWZKCpJPNYKouK85kbjGj8LeyF54sUq5M5VR-A/https%3A%2F%2Fwww.mail-archive.com%2Fsearch%3Fl%3Dfreesurfer%40nmr.mgh.harvard.edu%26q%3Dsubject%3A%2522%255C%255BFreesurfer%255C%255D%2BWMH%255C-SynthSeg%2Bvs.%2BSAMSEG%2Bfor%2BWM%2Blesions%2522%26o%3Dnewest> >> >> SudEEpti >> <https://secure-web.cisco.com/1oJN1ySIU6hTF6KozyWDOxPUxnfQT6NbHWVuqvL4RV_PNw-mjuH5HUIQ_4CrcrA2nB92UzWiqt0sldQoX7neyVBIx5YQ_ClIloJhwjfN3Wr-65IptS-tt7ZRgYRK4ptYQGQfsFX5B8cKOsc0-XY7SOZxDPnLT5_SQDK_zbCwXForrAFt6h-C4TbVXo15OSdI9A8_Wa4dkPrebnymfACMnEVmCmQyBjnkS71J2FBFdGJ1m8j_Gmkg7V-5nKiYy-Loc0f8uI6uvcCDH2wkofUf0wC8tT9K0feA_coqMJR_k3brvE_FKWAKCcp4TEUfmxhx39s2jcXEa0Kk6Ko5v93TwIA/https%3A%2F%2Fwww.mail-archive.com%2Fsearch%3Fl%3Dfreesurfer%40nmr.mgh.harvard.edu%26q%3Dfrom%3A%2522SudEEpti%2522> >> Thu, 04 Jan 2024 23:54:04 -0800 >> <https://secure-web.cisco.com/1JsH5pJG8BzMI3v8LKsEGcmt1J0aRmNdo-KqIrQw8arF8BP4GEGTyt7o7BBWBpoBhFnf7H2f8hDDHgVlApzrrpJd2B6CFkE6_1l2GHF-la-9yG9VlF8r8WARQiwmJu8zcMm1Lo6NFMGySBH954XRq9sg_4lBw_KdBCO3c04OTsh4eiUGXUNVO4_ev_uGvK9CaGTT5qsKtJouRpJarF-2rJi15G4_C7HH3EQu1fTC-ZfCnZR_Iu-HmfT3RIgmWaGcMQ39UdoH5yjZTKXI60uUiVnYj8_pwvoQ1Je2JsEFnyBS_EBQIAzYniwh1Cqk6q8EevaCdjfZi-bisWeUEnjws8g/https%3A%2F%2Fwww.mail-archive.com%2Fsearch%3Fl%3Dfreesurfer%40nmr.mgh.harvard.edu%26q%3Ddate%3A20240104> >> >> External Email - Use Caution >> >> Hello Freesurfer >> >> I am reaching out for some advice on unsupervised WM lesion detection using >> SAMSEG and WMH-SynthSeg. >> >> *SAMSEG: * >> Our use case prioritizes maximizing true positives over minimizing false >> positives. However, even with a low threshold of 0.1, SAMSEG misses some >> areas (on FLAIR). Are there any strategies or parameters to force SAMSEG to >> be more "aggressive"? >> >> *WMH-SynthSeg:* >> Unfortunately, I have not been able to get WMH-SynthSeg to work. The error >> message is pasted below. Does this point to a memory issue (I have 24GB >> RAM)? >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> *Arguments seem correct; loading Python packages...Using cpuUsing 1 >> thread(s)Preparing model and loading weightsWorking on image 1 of 1: >> /home/localuser01/southekal/TEMP/101-001_3scans_FLAIR/101-001-1_reg.mgz >> Loading input volume and normalizing to [0,1] Upscaling to target >> resolution Pushing data through the CNNKilledreal 3m33.897suser >> 2m48.028ssys 0m32.337s* >> >> Any insights or suggestions would be greatly appreciated! Thank you in >> advance. >> >> _______________________________________________ >> Freesurfer mailing listfreesur...@nmr.mgh.harvard.edu*MailScanner has >> detected a possible fraud attempt from "secure-web.cisco.com" claiming to >> be* >> https://secure-web.cisco.com/1q0ftnds5Pjt7ZrNdNNEV2v0D2o_gXpcBeu43TMzmE4cYI2iSjFaarpe0ynDzr_ZP4TmxElHJWu7JN0Hd8Scra-7M4qlwoeIX4QbI4zrJV0Omv3yD9s_G1W2_MBxSoeRfnoi7go1bWknxjoaV_u-6NDDRAJRqSDtfiDbbqo1pJyKoolpYsfrD1YeD_AqheI2hBcNz1n01b3WhLyG9gmFRbScsFAUkhUDvopME09eFfzcoqRNA5bRtTuPybWIOrhEcb5o47v_AYvFAzeE9HII2fJbXVVwDzIkLnUIsm6h7hlabZZKwz6XGBev_B_QnVAXpxmqw3YGxSi0iCX96sBgD_w/https%3A%2F%2Fmail.nmr.mgh.harvard.edu%2Fmailman%2Flistinfo%2Ffreesurfer >> >> <https://secure-web.cisco.com/1L5bfw4JEkXOrhY8TbJ8DAIk6FHVJxNUWzVkU8Ueq6fQY5XqhPfvgjXxlg3X2muiBxW5BsnLz05HdvKtXjfwp2IXX4Hqn0PCfa7VynsizJ5YgIYDSZ1dc8AvYd7R3IA-NqcNwrwwTM0S3CFe1vKNaJbITTsCLRnLtzlyD8iXAZrCAG3nVCO8QZTi-RC1lQ9kx9ekO0eorj8dpx6oMQ62MMUtq-6-JKSkvH41LdhhA6JmH5BJpGemqfMjLr4wB8SUAKUINRO4TmZ7X18mVBtib09PBik62Pe9rvjtFS6J7Fi_R52V_O2hbGA0OLu5eZgVO-T698cN-xoglHC_x1hwB6g/https%3A%2F%2Fmail.nmr.mgh.harvard.edu%2Fmailman%2Flistinfo%2Ffreesurfer> >> 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. >> >> _______________________________________________ > Freesurfer mailing list > Freesurfer@nmr.mgh.harvard.edu > https://secure-web.cisco.com/1q0ftnds5Pjt7ZrNdNNEV2v0D2o_gXpcBeu43TMzmE4cYI2iSjFaarpe0ynDzr_ZP4TmxElHJWu7JN0Hd8Scra-7M4qlwoeIX4QbI4zrJV0Omv3yD9s_G1W2_MBxSoeRfnoi7go1bWknxjoaV_u-6NDDRAJRqSDtfiDbbqo1pJyKoolpYsfrD1YeD_AqheI2hBcNz1n01b3WhLyG9gmFRbScsFAUkhUDvopME09eFfzcoqRNA5bRtTuPybWIOrhEcb5o47v_AYvFAzeE9HII2fJbXVVwDzIkLnUIsm6h7hlabZZKwz6XGBev_B_QnVAXpxmqw3YGxSi0iCX96sBgD_w/https%3A%2F%2Fmail.nmr.mgh.harvard.edu%2Fmailman%2Flistinfo%2Ffreesurfer
_______________________________________________ Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer 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.
