Fix ValueError by removing [0] to properly unpack indexed data

[joshuacwnewton]

Description

This fixes a bug introduced in d87fa5b:

  File "/__w/spinalcordtoolbox/spinalcordtoolbox/spinalcordtoolbox/deepseg/inference.py", line 228, in segment_nnunet
    pred = predictor.predict_single_npy_array(
  File "/__w/spinalcordtoolbox/spinalcordtoolbox/python/envs/venv_sct/lib/python3.9/site-packages/nnunetv2/inference/predict_from_raw_data.py", line 442, in predict_single_npy_array
    dct = next(ppa)
  File "/__w/spinalcordtoolbox/spinalcordtoolbox/python/envs/venv_sct/lib/python3.9/site-packages/batchgenerators/dataloading/data_loader.py", line 126, in __next__
    return self.generate_train_batch()
  File "/__w/spinalcordtoolbox/spinalcordtoolbox/python/envs/venv_sct/lib/python3.9/site-packages/nnunetv2/inference/data_iterators.py", line 193, in generate_train_batch
    image, seg_prev_stage, props, ofname = self._data[idx][0]
ValueError: not enough values to unpack (expected 4, got 1)

By combining the indexes into a single line, I believe the previous commit needed to remove the [0] index in order for the indexed data to properly unpack.

Testing

I tested this PR with our downstream package in spinalcordtoolbox/spinalcordtoolbox#4448 (comment).

The specific command that we run that triggers this issue in the first place can be found here.

(I'm surprised that this wasn't caught by nnunetv2's test suite! I'm not sure if this issue is specific to predict_single_npy_array, but I would presume not? EDIT: Ah, I see now. The tests aren't set up to run on PRs...)

Related issues/PRs

Fixes #2112.

[FabianIsensee]

Thanks a lot! That one slipped through somehow 😅