search

mist-medical / MIST

MIST: A simple, scalable, and end-to-end framework for 3D medical imaging segmentation.
Apache License 2.0
28 stars 11 forks source link

MIST Issue #25

Closed CMSantos1 closed 3 months ago

CMSantos1 commented 3 months ago

The labels in my data do not correspond to the labels I assigned in the dataset.json files

Steps to reproduce the behavior: convert data to csv format, update config.json file and run data

The expected behavior is to train my data and run a 5-fold cross validation.

Screenshot 2024-07-17 132401

Environment details

aecelaya commented 3 months ago

Thanks for submitting an issue! A couple of things:

1) What are the labels in your dataset? Please post a screenshot of your dataset.json file.

2) Next time please use a more descriptive title for the issue.

CMSantos1 commented 3 months ago

Noted! Thank you.
I have attached a screenshot of the dataset.json file.

Screenshot 2024-07-19 090350
CMSantos1 commented 3 months ago

Noted. Thank you.

Best Regards, Chimamanda Santos-Obi

From: Adrian Celaya @.> Sent: Thursday, July 18, 2024 5:52 PM To: mist-medical/MIST @.> Cc: Santos-Obi,Chimamanda Mary-Jane @.>; Author @.> Subject: [EXTERNAL] Re: [mist-medical/MIST] MIST Issue (Issue #25)

SLOW DOWN! - EXTERNAL SENDER: @.**@.>

Be suspicious of tone, urgency, and formatting. Do not click/open links or attachments on a mobile device. Wait until you are at a computer to confirm you are absolutely certain it is a trusted source. If you are at all uncertain use the Report Phish button and our Cybersecurity team will investigate.

Thanks for submitting an issue! A couple of things:

  1. What are the labels in your dataset? Please post a screenshot of your dataset.json file.
  2. Next time please use a more descriptive title for the issue.

— Reply to this email directly, view it on GitHubhttps://urldefense.com/v3/__https:/github.com/mist-medical/MIST/issues/25*issuecomment-2237747192__;Iw!!PfbeBCCAmug!my5qzyYfXVlNliQ1sR-LxMvF1KYVr56Svp8YIC4vL6DrJH7hwsWjXo-aZoz7D8zJZdvUlCt1j6-fyDB5QuuTPWrdjwED$, or unsubscribehttps://urldefense.com/v3/__https:/github.com/notifications/unsubscribe-auth/BJ6B672EKEUL7WQUIRCDSOLZNBBKDAVCNFSM6AAAAABLCZGX2GVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDEMZXG42DOMJZGI__;!!PfbeBCCAmug!my5qzyYfXVlNliQ1sR-LxMvF1KYVr56Svp8YIC4vL6DrJH7hwsWjXo-aZoz7D8zJZdvUlCt1j6-fyDB5QuuTPQ34G-BJ$. You are receiving this because you authored the thread.Message ID: @.**@.>>

The information contained in this e-mail message may be privileged, confidential, and/or protected from disclosure. This e-mail message may contain protected health information (PHI); dissemination of PHI should comply with applicable federal and state laws. If you are not the intended recipient, or an authorized representative of the intended recipient, any further review, disclosure, use, dissemination, distribution, or copying of this message or any attachment (or the information contained therein) is strictly prohibited. If you think that you have received this e-mail message in error, please notify the sender by return e-mail and delete all references to it and its contents from your systems.

aecelaya commented 3 months ago

Do you know what labels are in your dataset? There seems to be a mismatch between the labels you specified [0, 1] in the dataset.json file and what's in the dataset. You may need to write a script to loop through the masks in the dataset and get their unique values.

CMSantos1 commented 3 months ago

Thank you for your response. No, I don’t know the labels in my dataset. What script can I use to loop through the masks in the dataset and get their unique values.

Best,

Chimamanda Santos-Obi

From: Adrian Celaya @.> Sent: Friday, July 19, 2024 11:01 AM To: mist-medical/MIST @.> Cc: Santos-Obi,Chimamanda Mary-Jane @.>; Author @.> Subject: [EXTERNAL] Re: [mist-medical/MIST] MIST Issue (Issue #25)

SLOW DOWN! - EXTERNAL SENDER: @.**@.>

Be suspicious of tone, urgency, and formatting. Do not click/open links or attachments on a mobile device. Wait until you are at a computer to confirm you are absolutely certain it is a trusted source. If you are at all uncertain use the Report Phish button and our Cybersecurity team will investigate.

Do you know what labels are in your dataset? There seems to be a mismatch between the labels you specified [0, 1] in the dataset.json file and what's in the dataset. You may need to write a script to loop through the masks in the dataset and get their unique values.

— Reply to this email directly, view it on GitHubhttps://urldefense.com/v3/__https:/github.com/mist-medical/MIST/issues/25*issuecomment-2239512990__;Iw!!PfbeBCCAmug!nWV2qXTTIUPr10HqdSELhjO8sa54PKIKbJ9_pipgBb8GbfuFALb79qYRYUpxxwW88Ac_PPWFDMCji6VnbLoSVy44_DOp$, or unsubscribehttps://urldefense.com/v3/__https:/github.com/notifications/unsubscribe-auth/BJ6B674IWZNJYAXKRVVT3GDZNEZ4LAVCNFSM6AAAAABLCZGX2GVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDEMZZGUYTEOJZGA__;!!PfbeBCCAmug!nWV2qXTTIUPr10HqdSELhjO8sa54PKIKbJ9_pipgBb8GbfuFALb79qYRYUpxxwW88Ac_PPWFDMCji6VnbLoSVw1om7kq$. You are receiving this because you authored the thread.Message ID: @.**@.>>

The information contained in this e-mail message may be privileged, confidential, and/or protected from disclosure. This e-mail message may contain protected health information (PHI); dissemination of PHI should comply with applicable federal and state laws. If you are not the intended recipient, or an authorized representative of the intended recipient, any further review, disclosure, use, dissemination, distribution, or copying of this message or any attachment (or the information contained therein) is strictly prohibited. If you think that you have received this e-mail message in error, please notify the sender by return e-mail and delete all references to it and its contents from your systems.

aecelaya commented 3 months ago

That's something that you'll need to write outside of MIST.

MIST only checks to see if your labels match or are a subset of what's specified in the dataset.json file.

CMSantos1 commented 3 months ago

Thank you so much. Please how do I do that? I’m unsure of how to write the code.

From: Adrian Celaya @.> Sent: Tuesday, July 23, 2024 12:23 AM To: mist-medical/MIST @.> Cc: Santos-Obi,Chimamanda Mary-Jane @.>; Author @.> Subject: [EXTERNAL] Re: [mist-medical/MIST] MIST Issue (Issue #25)

SLOW DOWN! - EXTERNAL SENDER: @.**@.>

Be suspicious of tone, urgency, and formatting. Do not click/open links or attachments on a mobile device. Wait until you are at a computer to confirm you are absolutely certain it is a trusted source. If you are at all uncertain use the Report Phish button and our Cybersecurity team will investigate.

That's something that you'll need to write outside of MIST.

MIST only checks to see if your labels match or are a subset of what's specified in the dataset.json file.

— Reply to this email directly, view it on GitHubhttps://urldefense.com/v3/__https:/github.com/mist-medical/MIST/issues/25*issuecomment-2244276546__;Iw!!PfbeBCCAmug!m1b8ZQiiKJrt2GW3BEU2kCcZmYj4yc2lr1g5zVJZpi_oeU7-DJ0KT_qWLFeGmx95mcjyMU-pn9k3LeCNlKNWMl_bhfqp$, or unsubscribehttps://urldefense.com/v3/__https:/github.com/notifications/unsubscribe-auth/BJ6B672YZ7STEKBRK2VTWO3ZNXSCLAVCNFSM6AAAAABLCZGX2GVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDENBUGI3TMNJUGY__;!!PfbeBCCAmug!m1b8ZQiiKJrt2GW3BEU2kCcZmYj4yc2lr1g5zVJZpi_oeU7-DJ0KT_qWLFeGmx95mcjyMU-pn9k3LeCNlKNWMgNHl6CF$. You are receiving this because you authored the thread.Message ID: @.**@.>>

The information contained in this e-mail message may be privileged, confidential, and/or protected from disclosure. This e-mail message may contain protected health information (PHI); dissemination of PHI should comply with applicable federal and state laws. If you are not the intended recipient, or an authorized representative of the intended recipient, any further review, disclosure, use, dissemination, distribution, or copying of this message or any attachment (or the information contained therein) is strictly prohibited. If you think that you have received this e-mail message in error, please notify the sender by return e-mail and delete all references to it and its contents from your systems.

aecelaya commented 3 months ago

Write a for loop that loads each mask and updates a running list with its unique values. Once the loop is done, use something like numpy's np.unique to find the final set of unique values.

Because this is not a MIST bug, I'm going to close this issue. Please refer to antspyx and numpy's documentation for this.

CMSantos1 commented 3 months ago

Alright. Thank you so much

From: Adrian Celaya @.> Sent: Wednesday, July 24, 2024 1:36 AM To: mist-medical/MIST @.> Cc: Santos-Obi,Chimamanda Mary-Jane @.>; Author @.> Subject: [EXTERNAL] Re: [mist-medical/MIST] MIST Issue (Issue #25)

SLOW DOWN! - EXTERNAL SENDER: @.**@.>

Be suspicious of tone, urgency, and formatting. Do not click/open links or attachments on a mobile device. Wait until you are at a computer to confirm you are absolutely certain it is a trusted source. If you are at all uncertain use the Report Phish button and our Cybersecurity team will investigate.

Write a for loop that loads each mask and updates a running list with its unique values. Once the loop is done, use something like numpy's np.unique to find the final set of unique values.

Because this is not a MIST bug, I'm going to close this issue. Please refer to antspyx and numpy's documentation for this.

— Reply to this email directly, view it on GitHubhttps://urldefense.com/v3/__https:/github.com/mist-medical/MIST/issues/25*issuecomment-2247019107__;Iw!!PfbeBCCAmug!krn4A4G5KLGD6OPxMwhQf7UtKRrtI7V-IgdHFHz742XkqEh1TzEpxoOPfPTjRJfj5asulvxh-bVOx_XHnbUtk8uYuz5Q$, or unsubscribehttps://urldefense.com/v3/__https:/github.com/notifications/unsubscribe-auth/BJ6B67ZDW6CEPDGTLFGL2F3ZN5DMZAVCNFSM6AAAAABLCZGX2GVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZDENBXGAYTSMJQG4__;!!PfbeBCCAmug!krn4A4G5KLGD6OPxMwhQf7UtKRrtI7V-IgdHFHz742XkqEh1TzEpxoOPfPTjRJfj5asulvxh-bVOx_XHnbUtk_na0P4r$. You are receiving this because you authored the thread.Message ID: @.**@.>>

The information contained in this e-mail message may be privileged, confidential, and/or protected from disclosure. This e-mail message may contain protected health information (PHI); dissemination of PHI should comply with applicable federal and state laws. If you are not the intended recipient, or an authorized representative of the intended recipient, any further review, disclosure, use, dissemination, distribution, or copying of this message or any attachment (or the information contained therein) is strictly prohibited. If you think that you have received this e-mail message in error, please notify the sender by return e-mail and delete all references to it and its contents from your systems.