The full dataset viewer is not available (click to read why). Only showing a preview of the rows.
Error code: DatasetGenerationCastError
Exception: DatasetGenerationCastError
Message: An error occurred while generating the dataset
All the data files must have the same columns, but at some point there are 2 new columns ({'question_id', 'answer'}) and 2 missing columns ({'id', 'conversations'}).
This happened while the json dataset builder was generating data using
hf://datasets/introvoyz041/SurgMLLMBench/SurgMLLMBench/AutoLaparo/test/autolaparo_phase_test_answer.jsonl (at revision 9cbf0eb830a7003e1f44e8a50e1bb59aeb0f59bf)
Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)
Traceback: Traceback (most recent call last):
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1831, in _prepare_split_single
writer.write_table(table)
File "/usr/local/lib/python3.12/site-packages/datasets/arrow_writer.py", line 714, in write_table
pa_table = table_cast(pa_table, self._schema)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2272, in table_cast
return cast_table_to_schema(table, schema)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/table.py", line 2218, in cast_table_to_schema
raise CastError(
datasets.table.CastError: Couldn't cast
question_id: int64
image: string
answer: string
to
{'id': Value('string'), 'image': Value('string'), 'conversations': List({'from': Value('string'), 'value': Value('string')})}
because column names don't match
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 1339, in compute_config_parquet_and_info_response
parquet_operations = convert_to_parquet(builder)
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/src/services/worker/src/worker/job_runners/config/parquet_and_info.py", line 972, in convert_to_parquet
builder.download_and_prepare(
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 894, in download_and_prepare
self._download_and_prepare(
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 970, in _download_and_prepare
self._prepare_split(split_generator, **prepare_split_kwargs)
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1702, in _prepare_split
for job_id, done, content in self._prepare_split_single(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/lib/python3.12/site-packages/datasets/builder.py", line 1833, in _prepare_split_single
raise DatasetGenerationCastError.from_cast_error(
datasets.exceptions.DatasetGenerationCastError: An error occurred while generating the dataset
All the data files must have the same columns, but at some point there are 2 new columns ({'question_id', 'answer'}) and 2 missing columns ({'id', 'conversations'}).
This happened while the json dataset builder was generating data using
hf://datasets/introvoyz041/SurgMLLMBench/SurgMLLMBench/AutoLaparo/test/autolaparo_phase_test_answer.jsonl (at revision 9cbf0eb830a7003e1f44e8a50e1bb59aeb0f59bf)
Please either edit the data files to have matching columns, or separate them into different configurations (see docs at https://hf.co/docs/hub/datasets-manual-configuration#multiple-configurations)Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
id
string | image
string | conversations
list |
|---|---|---|
c22dba20-10b3-47ae-9f46-a3015cb5b51b
|
01/01_frame0001.jpg
|
[
{
"from": "human",
"value": "<image>\nCould you specify the surgical phase shown here?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
a6362fb8-0acc-4c1d-b75b-2dfa0b7d93e6
|
01/01_frame0002.jpg
|
[
{
"from": "human",
"value": "<image>\nCould you specify the surgical phase shown here?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
34538c5b-575d-4763-97fe-615185f0ca59
|
01/01_frame0003.jpg
|
[
{
"from": "human",
"value": "<image>\nCould you specify the surgical phase shown here?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
ed7f2e30-4d0f-428d-ad62-8e173695dd79
|
01/01_frame0004.jpg
|
[
{
"from": "human",
"value": "What surgical phase does this image depict?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
fc36a2e1-60b3-4a1f-a949-ad952326e5dd
|
01/01_frame0005.jpg
|
[
{
"from": "human",
"value": "<image>\nWhich phase of surgery is presented in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
360cc0f2-fa5f-45bc-9b4a-75e2642ae5de
|
01/01_frame0006.jpg
|
[
{
"from": "human",
"value": "<image>\nCan you determine the surgical phase from this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
4e10dc50-52ad-4469-b146-eabb311c938c
|
01/01_frame0007.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat surgical phase does this image depict?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
ee5310aa-d261-41d8-bfcd-4ab4a3b7e9f3
|
01/01_frame0008.jpg
|
[
{
"from": "human",
"value": "Could you specify the surgical phase shown here?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
63c7821d-eec9-446c-b142-99da3456ff4a
|
01/01_frame0009.jpg
|
[
{
"from": "human",
"value": "Can you determine the surgical phase from this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
ed17dce2-69f3-4c17-92ce-e768479d9b1f
|
01/01_frame0010.jpg
|
[
{
"from": "human",
"value": "Could you specify the surgical phase shown here?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
e1325e6a-c997-441f-b2e6-d01e86382f1e
|
01/01_frame0011.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat is the current surgical phase visible in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
400a0af2-0b96-416c-9ca9-66650fb7d8fd
|
01/01_frame0012.jpg
|
[
{
"from": "human",
"value": "What surgical phase does this image depict?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
439cb587-5c07-41bd-af74-f3e0bdc6eb0c
|
01/01_frame0013.jpg
|
[
{
"from": "human",
"value": "What is the current surgical phase visible in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
db5c2d7c-1b2a-403b-894b-c58d625efb82
|
01/01_frame0014.jpg
|
[
{
"from": "human",
"value": "<image>\nCould you specify the surgical phase shown here?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
264639e6-712c-4ae5-ad52-7ba4336cb761
|
01/01_frame0015.jpg
|
[
{
"from": "human",
"value": "Which phase of surgery is presented in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
2c566d31-d954-4b20-89ba-406467fd9374
|
01/01_frame0016.jpg
|
[
{
"from": "human",
"value": "Can you determine the surgical phase from this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
98f70111-e1aa-4799-9bd2-fc054883b015
|
01/01_frame0017.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat is the current surgical phase visible in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
3969e19a-b84e-4a5b-9c85-b502fdf65e1a
|
01/01_frame0018.jpg
|
[
{
"from": "human",
"value": "Could you specify the surgical phase shown here?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
eec292f8-0a17-46ce-bb54-3ade198c5957
|
01/01_frame0019.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat is the current surgical phase visible in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
51f724bf-b7fd-4a3c-9ff8-7655e465cb3e
|
01/01_frame0020.jpg
|
[
{
"from": "human",
"value": "Could you specify the surgical phase shown here?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
503c85ec-d12f-4115-9aba-d8b1f8ef3c79
|
01/01_frame0021.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat surgical phase does this image depict?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
f19e7b2f-d1a5-428b-8d50-31fce131b3ef
|
01/01_frame0022.jpg
|
[
{
"from": "human",
"value": "Which phase of surgery is presented in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
032f717e-1d70-4d52-bb34-2a52f3f7a1e2
|
01/01_frame0023.jpg
|
[
{
"from": "human",
"value": "<image>\nCan you determine the surgical phase from this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
da9813c8-b24e-4f75-a50c-33dfc9b0e59e
|
01/01_frame0024.jpg
|
[
{
"from": "human",
"value": "Which phase of surgery is presented in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
38bf8d83-d93e-4796-a3a3-ddfe2860403b
|
01/01_frame0025.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat is the current surgical phase visible in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
0852ed72-44e7-4e9f-8026-e03842b2a0bb
|
01/01_frame0026.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat is the current surgical phase visible in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
127e2da1-d1b7-473c-9fa9-3915b55f592e
|
01/01_frame0027.jpg
|
[
{
"from": "human",
"value": "Could you specify the surgical phase shown here?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
61ea7bb3-9e1c-492a-8741-71b563cfcef0
|
01/01_frame0028.jpg
|
[
{
"from": "human",
"value": "What is the current surgical phase visible in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
9ccd04cc-e3ad-403d-a355-a84b1b355403
|
01/01_frame0029.jpg
|
[
{
"from": "human",
"value": "Which phase of surgery is presented in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
daa04461-e48f-4fbe-96c6-d0471e9807b7
|
01/01_frame0030.jpg
|
[
{
"from": "human",
"value": "<image>\nWhich phase of surgery is presented in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
11e8e7a2-a1e9-4fed-8bbc-e97dc1c4c9b7
|
01/01_frame0031.jpg
|
[
{
"from": "human",
"value": "Could you specify the surgical phase shown here?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
60fb3e4d-d073-4e17-8610-ba6862cd18ea
|
01/01_frame0032.jpg
|
[
{
"from": "human",
"value": "Could you specify the surgical phase shown here?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
54e11cbd-51dd-499b-88f9-d42adbb339b0
|
01/01_frame0033.jpg
|
[
{
"from": "human",
"value": "<image>\nCan you determine the surgical phase from this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
50e640ce-bbef-42ab-9e02-662c9e5b779e
|
01/01_frame0034.jpg
|
[
{
"from": "human",
"value": "What surgical phase does this image depict?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
d6dc40ce-42ea-4f1d-a9db-f7225c2a6e1c
|
01/01_frame0035.jpg
|
[
{
"from": "human",
"value": "Could you specify the surgical phase shown here?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
5324b622-944c-4aaf-aeae-7b2cd5abfdd2
|
01/01_frame0036.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat surgical phase does this image depict?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
e3dbc531-a2c6-43a7-98de-7692257a96b1
|
01/01_frame0037.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat is the current surgical phase visible in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
6029b1ee-f3d9-4d53-9b33-7d07fd234c83
|
01/01_frame0038.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat is the current surgical phase visible in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
b1356d84-9e0a-40a3-8fc5-8a0d91606e78
|
01/01_frame0039.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat surgical phase does this image depict?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
a6464a5a-53d7-49a3-ba40-5a9520b13c21
|
01/01_frame0040.jpg
|
[
{
"from": "human",
"value": "<image>\nCan you determine the surgical phase from this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
2f1fedb8-559b-4cae-b786-6f8dbd8f2944
|
01/01_frame0041.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat surgical phase does this image depict?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
841cca9b-00cd-4094-aa08-cce15bfd207d
|
01/01_frame0042.jpg
|
[
{
"from": "human",
"value": "<image>\nWhich phase of surgery is presented in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
4b6fd6ee-2bc3-44c9-a35f-25c60cfa1a3a
|
01/01_frame0043.jpg
|
[
{
"from": "human",
"value": "What is the current surgical phase visible in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
0e72d6f0-d161-491f-aa55-39602324558b
|
01/01_frame0044.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat surgical phase does this image depict?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
cf859484-9cc7-47a1-9fef-6f0d8b80d5bb
|
01/01_frame0045.jpg
|
[
{
"from": "human",
"value": "<image>\nCould you specify the surgical phase shown here?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
6b65930d-4cd4-4df8-b4c0-a41c6cde116d
|
01/01_frame0046.jpg
|
[
{
"from": "human",
"value": "<image>\nWhich phase of surgery is presented in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
0d92a3ab-2316-4e71-bf1e-f08b43708424
|
01/01_frame0047.jpg
|
[
{
"from": "human",
"value": "<image>\nCan you determine the surgical phase from this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
a355173f-9a8d-4e2f-bccf-16c89bfb1f4e
|
01/01_frame0048.jpg
|
[
{
"from": "human",
"value": "Could you specify the surgical phase shown here?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
854717a6-410d-4c90-95c2-f690ba25bf0e
|
01/01_frame0049.jpg
|
[
{
"from": "human",
"value": "What is the current surgical phase visible in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
1aab63d4-226b-4293-9439-9458b4679d64
|
01/01_frame0050.jpg
|
[
{
"from": "human",
"value": "Which phase of surgery is presented in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
5d17c296-f027-4aa1-b4b4-2eb0275d4811
|
01/01_frame0051.jpg
|
[
{
"from": "human",
"value": "<image>\nCould you specify the surgical phase shown here?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
794d0724-fa34-42a2-adb6-59e2744ca269
|
01/01_frame0052.jpg
|
[
{
"from": "human",
"value": "<image>\nCould you specify the surgical phase shown here?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
99b3877d-9dab-4d9f-b2c0-532afe1ce493
|
01/01_frame0053.jpg
|
[
{
"from": "human",
"value": "<image>\nCould you specify the surgical phase shown here?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
c188bb10-dda5-48e8-9dca-0197f873c4bd
|
01/01_frame0054.jpg
|
[
{
"from": "human",
"value": "Could you specify the surgical phase shown here?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
132cba5a-e7ea-44d5-9f85-295d8f5d38bb
|
01/01_frame0055.jpg
|
[
{
"from": "human",
"value": "What surgical phase does this image depict?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
acd1252e-614e-4272-8d2c-8d3b9f068f6f
|
01/01_frame0056.jpg
|
[
{
"from": "human",
"value": "<image>\nCan you determine the surgical phase from this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
f6e7ce39-5e4d-4e8f-808f-75301164ec9a
|
01/01_frame0057.jpg
|
[
{
"from": "human",
"value": "What is the current surgical phase visible in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
037cedd1-b823-4ac2-b4ce-fbaac695b4a9
|
01/01_frame0058.jpg
|
[
{
"from": "human",
"value": "Which phase of surgery is presented in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
5e8f8540-1d9b-4ec7-a738-0b0a729f8ca7
|
01/01_frame0059.jpg
|
[
{
"from": "human",
"value": "Which phase of surgery is presented in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
527a4004-6ef2-4b7f-9ef5-def941ac0f9c
|
01/01_frame0060.jpg
|
[
{
"from": "human",
"value": "<image>\nWhich phase of surgery is presented in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
7e389969-37c6-42f6-aa20-433c7ff948a7
|
01/01_frame0061.jpg
|
[
{
"from": "human",
"value": "Can you determine the surgical phase from this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
f5889121-c07d-4dd5-9e6f-10effadc052b
|
01/01_frame0062.jpg
|
[
{
"from": "human",
"value": "Which phase of surgery is presented in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
654711dc-c145-451c-a442-614df1a04670
|
01/01_frame0063.jpg
|
[
{
"from": "human",
"value": "What surgical phase does this image depict?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
2a8c3888-905f-4261-91ce-ee5ba82b01ea
|
01/01_frame0064.jpg
|
[
{
"from": "human",
"value": "<image>\nWhich phase of surgery is presented in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
a65400ad-af39-49a5-b4f4-3e03621b8253
|
01/01_frame0065.jpg
|
[
{
"from": "human",
"value": "Can you determine the surgical phase from this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
1047f013-308d-4800-a4e0-b16422c91d46
|
01/01_frame0066.jpg
|
[
{
"from": "human",
"value": "Which phase of surgery is presented in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
eb48c61b-0829-416b-bdd3-4490915f2a43
|
01/01_frame0067.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat surgical phase does this image depict?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
e9eead1a-2483-44c4-8370-82dbd54b2a5b
|
01/01_frame0068.jpg
|
[
{
"from": "human",
"value": "Can you determine the surgical phase from this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
86601ae0-312a-4623-8d12-83cdb3393665
|
01/01_frame0069.jpg
|
[
{
"from": "human",
"value": "<image>\nCould you specify the surgical phase shown here?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
681a1ca1-4c42-4594-8c9a-36c0bc9863ad
|
01/01_frame0070.jpg
|
[
{
"from": "human",
"value": "Could you specify the surgical phase shown here?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
b7d88d54-aa3a-4d0e-b98c-fa0c6a2adbfc
|
01/01_frame0071.jpg
|
[
{
"from": "human",
"value": "<image>\nWhich phase of surgery is presented in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
70154b5f-8aaa-4d82-8d1e-0f8c60d76fb5
|
01/01_frame0072.jpg
|
[
{
"from": "human",
"value": "What is the current surgical phase visible in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
fcad8367-e7c6-489c-b06b-488268cada95
|
01/01_frame0073.jpg
|
[
{
"from": "human",
"value": "<image>\nCan you determine the surgical phase from this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
6dd719df-f3fa-4823-b99d-97a7f47a2a89
|
01/01_frame0074.jpg
|
[
{
"from": "human",
"value": "<image>\nCould you specify the surgical phase shown here?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
2f7b7765-efc8-4180-8654-f5a1ab327582
|
01/01_frame0075.jpg
|
[
{
"from": "human",
"value": "<image>\nCan you determine the surgical phase from this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
6fdfd91b-4249-4786-92f4-65559fe278e9
|
01/01_frame0076.jpg
|
[
{
"from": "human",
"value": "What surgical phase does this image depict?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
6cd5f27a-117a-44b8-a033-324a124b93dc
|
01/01_frame0077.jpg
|
[
{
"from": "human",
"value": "Could you specify the surgical phase shown here?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
5177ee36-3d80-4803-a23e-e9b830a3a1ac
|
01/01_frame0078.jpg
|
[
{
"from": "human",
"value": "<image>\nWhich phase of surgery is presented in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
fdf09ddd-64de-43bb-9350-d0a99022ae6a
|
01/01_frame0079.jpg
|
[
{
"from": "human",
"value": "What is the current surgical phase visible in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
581813a3-5ac1-49df-aec3-8600657612cc
|
01/01_frame0080.jpg
|
[
{
"from": "human",
"value": "What surgical phase does this image depict?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
77da7ba7-ebde-43fb-b290-69f522b39020
|
01/01_frame0081.jpg
|
[
{
"from": "human",
"value": "What is the current surgical phase visible in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
ca88b100-e244-4703-9ade-4718848b0689
|
01/01_frame0082.jpg
|
[
{
"from": "human",
"value": "What is the current surgical phase visible in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
d0b8c3c5-897e-4d1e-ac3a-6beb13fa6049
|
01/01_frame0083.jpg
|
[
{
"from": "human",
"value": "<image>\nWhich phase of surgery is presented in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
77a2cdde-bc8f-4ef8-a707-0f9d43cb712b
|
01/01_frame0084.jpg
|
[
{
"from": "human",
"value": "Which phase of surgery is presented in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
d643cbcc-7032-426f-844c-65f4ee9ec290
|
01/01_frame0085.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat is the current surgical phase visible in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
efe313be-4903-43d7-8242-cffbbc3ab2f5
|
01/01_frame0086.jpg
|
[
{
"from": "human",
"value": "Which phase of surgery is presented in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
3c9c5fff-3427-4836-8bbb-bf2890c08a56
|
01/01_frame0087.jpg
|
[
{
"from": "human",
"value": "What is the current surgical phase visible in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
603509e5-f8a9-4a0e-b64e-5226280dac22
|
01/01_frame0088.jpg
|
[
{
"from": "human",
"value": "What is the current surgical phase visible in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
5c402d2a-2a5f-43bf-9f8b-12d4a615cb18
|
01/01_frame0089.jpg
|
[
{
"from": "human",
"value": "What is the current surgical phase visible in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
d29e4509-7cc6-470b-8fd8-3497c9bad6a8
|
01/01_frame0090.jpg
|
[
{
"from": "human",
"value": "<image>\nCould you specify the surgical phase shown here?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
020fdf00-f624-41f4-ba1a-11a547694e68
|
01/01_frame0091.jpg
|
[
{
"from": "human",
"value": "What is the current surgical phase visible in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
3294db3b-60a3-4438-b1fb-009afc846560
|
01/01_frame0092.jpg
|
[
{
"from": "human",
"value": "What is the current surgical phase visible in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
646bbf8a-0869-42d5-9b21-93c0fe48cabe
|
01/01_frame0093.jpg
|
[
{
"from": "human",
"value": "<image>\nWhich phase of surgery is presented in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
ed08ee41-a5f9-4162-ab03-6d0394f152d2
|
01/01_frame0094.jpg
|
[
{
"from": "human",
"value": "Can you determine the surgical phase from this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
44059f8a-4149-402a-bfb5-4d354f2de87d
|
01/01_frame0095.jpg
|
[
{
"from": "human",
"value": "What is the current surgical phase visible in this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
8febd006-a526-47da-a833-150439c476dc
|
01/01_frame0096.jpg
|
[
{
"from": "human",
"value": "<image>\nWhat is the current surgical phase visible in this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
c7a45568-f6fa-4746-985f-0cbea2949bb9
|
01/01_frame0097.jpg
|
[
{
"from": "human",
"value": "<image>\nCould you specify the surgical phase shown here?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
f47bd9f7-1fee-4490-88be-7b0b03f0dda5
|
01/01_frame0098.jpg
|
[
{
"from": "human",
"value": "<image>\nCould you specify the surgical phase shown here?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
69d10c8b-a057-4668-adea-9d6359f84d8c
|
01/01_frame0099.jpg
|
[
{
"from": "human",
"value": "<image>\nCan you determine the surgical phase from this image?"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
ec29819e-5d1f-4c77-8990-58ed513ce820
|
01/01_frame0100.jpg
|
[
{
"from": "human",
"value": "Can you determine the surgical phase from this image?\n<image>"
},
{
"from": "gpt",
"value": "Dividing Ligament and Peritoneum"
}
] |
SurgMLLMBench: A Multimodal Large Language Model Benchmark Dataset for Surgical Scene Understanding
This dataset was presented in the paper: SurgMLLMBench: A Multimodal Large Language Model Benchmark Dataset for Surgical Scene Understanding.
Dataset Overview
SurgMLLMBench is a multimodal benchmark designed for training and evaluating interactive multimodal large language models in surgical scene understanding. It integrates diverse surgical video datasetsβincluding laparoscopic surgery, robot-assisted surgery, and micro-surgical trainingβinto a unified framework with harmonized workflow labels, pixel-level instrument segmentation, and structured VQA annotations.
SurgMLLMBench integrates six surgical video datasets spanning multiple surgical domains:
- Cholec80 (Laparoscopic Surgery) β Download here
- EndoVis2018 (Robot-Assisted Surgery) β Download here
- AutoLaparo (Robot-Assisted Surgery) β Download here
- GraSP (Robot-Assisted Surgery) β Download here
- MISAW (Micro-Surgical Training) β Download here (Supplementary segmentation annotations β Download here)
- MAVIS (Micro-Surgical Training) β Download here (Newly collected dataset)
These datasets collectively cover over 112 hours of surgical video and more than 560K annotated frames, providing rich supervision across multiple domains and procedures.
Unified Annotation Schema
Because existing surgical datasets differ widely in taxonomy, task definitions, frame rates, resolutions, and annotation formats, SurgMLLMBench applies a comprehensive standardization pipeline:
Frame-level conversion: All videos are converted into frame-level images to unify temporal handling across datasets.
Harmonized metadata schema: A COCO-style metadata structure is used to represent workflow and segmentation labels in a consistent format.
Each frame is stored with the following unified fields:
- video_id
- frame_id
- stage
- phase
- step
- instrument_action
- segmentation
Missing labels are kept as empty fields to maintain structural consistency across datasets.
Multi-task Annotations
Across all datasets, SurgMLLMBench provides supervision for the following complementary tasks:
- Stage recognition
- Phase recognition
- Step recognition
- Instrument-centered action recognition
- Instrument segmentation (pixel-level)
These tasks capture global workflow, fine-grained procedural steps, and pixel-level spatial understanding, enabling multimodal LLMs to learn both semantic reasoning and visual grounding.
VQA Prompt Generation
SurgMLLMBench augments the structured annotations above with template-based VQA annotations to support interactive, conversation-style models. These provide questionβanswer pairs that are tightly coupled with the underlying workflow. Each frame can be paired with one or more VQA samples, drawn from four template families:
- Workflow queries
- Purpose: ask about stage, phase, and step for the current frame.
- Example template: βWhich stage, phase, and step are shown in this image?β
- Instrument count queries
- Purpose: ask how many tools are currently visible.
- Example template: βHow many surgical tools are visible in this image?β
- Instrument type queries
- Purpose: ask which instrument categories are present.
- Example template: βWhich instruments are present in this image?β
- Instrument action queries
- Purpose: ask about the functional action of one or more tools when action labels are available (e.g., in EndoVis2018, GraSP, MISAW).
- Example template: βWhat action is the needle holder performing in this image?β
Dataset Source Metadata Injection
Instead of treating dataset identity as a separate VQA task, SurgMLLMBench embeds this information directly at the beginning of each question for files ending in "with_metadata.json": This ensures models receive explicit domain cues without needing a separate query category. Files without the suffix with_metadata contain pure template-driven VQA questions.
| Dataset | Metadata prefix |
|---|---|
| Cholec80 | This image is included in the cholec80 dataset. There is only phase information, so you answer step as None. |
| EndoVis2018 | This image is included in the endovis2018 dataset. |
| AutoLaparo(phase) | This image is included in the autolaparo dataset. There is only phase information, so you answer step as None. |
| AutoLaparo(tool) | This image is included in the autolaparo dataset. |
| GraSP | This image is included in the grasp dataset. |
| MISAW | This image is included in the misaw dataset. |
| MAVIS | This image is included in the mavis dataset. |
Note β AutoLaparo provides phase labels at 1 FPS, whereas tool annotations are derived from segmentation masks sampled at 25 FPS. Therefore, the phase test set and tool test set necessarily use different frame indices, resulting in separate test .jsonl files for phase and tool tasks.
File Naming Convention
Filenames follow a consistent structure:
| File Type | Meaning |
|---|---|
| *_phase_train.json | Phase-related VQA training samples |
| *_tool_train.json | Tool-type VQA training samples |
| *_segmentation_train.p | Segmentation training data |
| *_test_question.jsonl | Test questions |
| *_test_answer.jsonl | Test answers |
| *_with_metadata.json | Questions include dataset-source prefixes |
This naming scheme allows users to understand task, split, and metadata status directly from the filename.
Dataset Example
Dataset Structure
The dataset is structured as follows:
SurgMLLMBench/
βββ AutoLaparo/
β βββ train/
β β βββ autolaparo_phase_train.json
β β βββ autolaparo_tool_train.json
β β βββ autolaparo_segmentation_train.p
β β βββ ...
β β
β βββ test/
β βββ autolaparo_phase_test_question.jsonl
β βββ autolaparo_phase_test_answer.jsonl
β βββ autolaparo_segmentation_test.p
β βββ ...
β
βββ Cholec80/
β βββ train/
β β βββ cholec80_phase_train.json
β β βββ cholec80_tool_train.json
β β βββ ...
| |
β βββ test/
β βββ cholec80_test_question.jsonl
β βββ cholec80_test_answer.jsonl
β βββ ...
β
βββ EndoVis2018/
β βββ train/
β β βββ endovis2018_train.json
β β βββ endovis2018_train_with_metadata.json
β β βββ endovis2018_segmentation_train.p
| |
β βββ test/
β βββ endovis2018_test_question.jsonl
β βββ endovis2018_test_answer.jsonl
β βββ endovis2018_segmentation_test.p
β βββ ...
β
βββ GraSP/
β βββ train/
β β βββ grasp_phase_train.json
β β βββ grasp_tool_train.json
β | βββ grasp_segmentation_train.p
β | βββ ...
| |
β βββ test/
β βββ grasp_test_question.jsonl
β βββ grasp_test_answer.jsonl
β βββ grasp_segmentation_test.p
β βββ ...
β
βββ MAVIS/
β βββ train/
β β βββ mavis_phase_train.json
β β βββ mavis_tool_train.json
β β βββ mavis_segmentation_train.p
β β βββ ...
| |
β βββ test/
β βββ mavis_test_question.jsonl
β βββ mavis_test_answer.jsonl
β βββ mavis_segmentation_test.p
β βββ ...
β
βββ MISAW/
βββ train/
β βββ misaw_phase_train.json
β βββ misaw_tool_train.json
β βββ misaw_segmentation_train.p
β βββ ...
|
βββ test/
βββ misaw_test_question.jsonl
βββ misaw_test_answer.jsonl
βββ misaw_segmentation_test.p
βββ ...
Citation
If you use this dataset in your research, please cite:
@misc{choi2025surgmllmbenchmultimodallargelanguage,
title={SurgMLLMBench: A Multimodal Large Language Model Benchmark Dataset for Surgical Scene Understanding},
author={Tae-Min Choi and Tae Kyeong Jeong and Garam Kim and Jaemin Lee and Yeongyoon Koh and In Cheul Choi and Jae-Ho Chung and Jong Woong Park and Juyoun Park},
year={2025},
eprint={2511.21339},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2511.21339},
}
- Downloads last month
- 5