Merge branch 'dev' of github.com:Project-MONAI/MONAI into fix-6056-wsireader-defaults

Author: bhashemian

README.md

@@ -51,6 +51,10 @@ Examples and notebook tutorials are located at [Project-MONAI/tutorials](https:/
 
 Technical documentation is available at [docs.monai.io](https://docs.monai.io).
 
+## Citation
+
+If you have used MONAI in your research, please cite us! The citation can be exported from: https://arxiv.org/abs/2211.02701.
+
 ## Model Zoo
 [The MONAI Model Zoo](https://github.com/Project-MONAI/model-zoo) is a place for researchers and data scientists to share the latest and great models from the community.
 Utilizing [the MONAI Bundle format](https://docs.monai.io/en/latest/bundle_intro.html) makes it easy to [get started](https://github.com/Project-MONAI/tutorials/tree/main/model_zoo) building workflows with MONAI.

docs/requirements.txt

@@ -1,6 +1,6 @@
 -f https://download.pytorch.org/whl/cpu/torch-1.12.1%2Bcpu-cp37-cp37m-linux_x86_64.whl
 torch>=1.8
-pytorch-ignite==0.4.10
+pytorch-ignite==0.4.11
 numpy>=1.20
 itk>=5.2
 nibabel

docs/source/MONAI-logo-color.png

@@ -116,7 +116,7 @@ def generate_apidocs(*args):
     "collapse_navigation": True,
     "navigation_depth": 3,
     "show_toc_level": 1,
-    "footer_items": ["copyright"],
+    "footer_start": ["copyright"],
     "navbar_align": "content",
     "logo": {"image_light": "MONAI-logo-color.png", "image_dark": "MONAI-logo-color.png"},
 }

docs/source/conf.py

@@ -88,6 +88,21 @@ Generic Interfaces
 .. autoclass:: RandomOrder
     :members:
 
+Functionals
+-----------
+
+Crop and Pad (functional)
+^^^^^^^^^^^^^^^^^^^^^^^^^
+.. automodule:: monai.transforms.croppad.functional
+    :members:
+
+Spatial (functional)
+^^^^^^^^^^^^^^^^^^^^
+.. automodule:: monai.transforms.spatial.functional
+    :members:
+
+.. currentmodule:: monai.transforms
+
 Vanilla Transforms
 ------------------
 

docs/source/transforms.rst

@@ -52,7 +52,7 @@ def compute_isolated_tumor_cells(tumor_mask: np.ndarray, threshold: float) -> li
             A region with the longest diameter less than this threshold is considered as an ITC.
     """
     max_label = np.amax(tumor_mask)
-    properties = measure.regionprops(tumor_mask, coordinates="rc")
+    properties = measure.regionprops(tumor_mask)
     itc_list = [i + 1 for i in range(max_label) if properties[i].major_axis_length < threshold]
 
     return itc_list

monai/apps/pathology/utils.py

@@ -58,13 +58,15 @@ def get_logger(
     (https://docs.python.org/3/library/logging.html#formatter-objects).
     `logger_handler` can be used to add an additional handler.
     """
+    adds_stdout_handler = module_name is not None and module_name not in logging.root.manager.loggerDict
     logger = logging.getLogger(module_name)
     logger.propagate = False
     logger.setLevel(logging.INFO)
-    handler = logging.StreamHandler(sys.stdout)
-    formatter = logging.Formatter(fmt=fmt, datefmt=datefmt)
-    handler.setFormatter(formatter)
-    logger.addHandler(handler)
+    if adds_stdout_handler:  # don't add multiple stdout or add to the root
+        handler = logging.StreamHandler(sys.stdout)
+        formatter = logging.Formatter(fmt=fmt, datefmt=datefmt)
+        handler.setFormatter(formatter)
+        logger.addHandler(handler)
     if logger_handler is not None:
         logger.addHandler(logger_handler)
     return logger

monai/apps/utils.py

@@ -617,7 +617,7 @@ def run(
     **override: Any,
 ) -> list:
     """
-    Specify `meta_file` and `config_file` to run monai bundle components and workflows.
+    Specify `config_file` to run monai bundle components and workflows.
 
     Typical usage examples:
 
@@ -642,10 +642,12 @@ def run(
     Args:
         runner_id: ID name of the expected config expression to run, can also be a list of IDs to run in order.
         meta_file: filepath of the metadata file, if it is a list of file paths, the content of them will be merged.
+            Default to "configs/metadata.json", which is commonly used for bundles in MONAI model zoo.
         config_file: filepath of the config file, if `None`, must be provided in `args_file`.
             if it is a list of file paths, the content of them will be merged.
-        logging_file: config file for `logging` module in the program, default to `None`. for more details:
+        logging_file: config file for `logging` module in the program. for more details:
             https://docs.python.org/3/library/logging.config.html#logging.config.fileConfig.
+            Default to "configs/logging.conf", which is commonly used for bundles in MONAI model zoo.
         tracking: enable the experiment tracking feature at runtime with optionally configurable and extensible.
             if "mlflow", will add `MLFlowHandler` to the parsed bundle with default logging settings,
             if other string, treat it as file path to load the logging settings, if `dict`,
@@ -719,18 +721,30 @@ def run(
         warnings.warn("`config_file` not provided for 'monai.bundle run'.")
     _log_input_summary(tag="run", args=_args)
     config_file_, meta_file_, runner_id_, logging_file_, tracking_ = _pop_args(
-        _args, config_file=None, meta_file=None, runner_id="", logging_file=None, tracking=None
+        _args,
+        config_file=None,
+        meta_file="configs/metadata.json",
+        runner_id="",
+        logging_file="configs/logging.conf",
+        tracking=None,
     )
     if logging_file_ is not None:
         if not os.path.exists(logging_file_):
-            raise FileNotFoundError(f"can't find the logging config file: {logging_file_}.")
-        logger.info(f"set logging properties based on config: {logging_file_}.")
-        fileConfig(logging_file_, disable_existing_loggers=False)
+            if logging_file_ == "configs/logging.conf":
+                warnings.warn("default logging file in 'configs/logging.conf' not exists, skip logging.")
+            else:
+                raise FileNotFoundError(f"can't find the logging config file: {logging_file_}.")
+        else:
+            logger.info(f"set logging properties based on config: {logging_file_}.")
+            fileConfig(logging_file_, disable_existing_loggers=False)
 
     parser = ConfigParser()
     parser.read_config(f=config_file_)
     if meta_file_ is not None:
-        parser.read_meta(f=meta_file_)
+        if not os.path.exists(meta_file_):
+            warnings.warn("default meta file in 'configs/metadata.json' not exists.")
+        else:
+            parser.read_meta(f=meta_file_)
 
     # the rest key-values in the _args are to override config content
     parser.update(pairs=_args)

monai/bundle/scripts.py

@@ -1522,6 +1522,9 @@ class NrrdReader(ImageReader):
         dtype: dtype of the data array when loading image.
         index_order: Specify whether the returned data array should be in C-order (‘C’) or Fortran-order (‘F’).
             Numpy is usually in C-order, but default on the NRRD header is F
+        affine_lps_to_ras: whether to convert the affine matrix from "LPS" to "RAS". Defaults to ``True``.
+            Set to ``True`` to be consistent with ``NibabelReader``, otherwise the affine matrix is unmodified.
+
         kwargs: additional args for `nrrd.read` API. more details about available args:
             https://github.com/mhe/pynrrd/blob/master/nrrd/reader.py
 
@@ -1532,11 +1535,13 @@ def __init__(
         channel_dim: int | None = None,
         dtype: np.dtype | type | str | None = np.float32,
         index_order: str = "F",
+        affine_lps_to_ras: bool = True,
         **kwargs,
     ):
         self.channel_dim = channel_dim
         self.dtype = dtype
         self.index_order = index_order
+        self.affine_lps_to_ras = affine_lps_to_ras
         self.kwargs = kwargs
 
     def verify_suffix(self, filename: Sequence[PathLike] | PathLike) -> bool:
@@ -1590,7 +1595,10 @@ def get_data(self, img: NrrdImage | list[NrrdImage]) -> tuple[np.ndarray, dict]:
             if self.index_order == "C":
                 header = self._convert_f_to_c_order(header)
             header[MetaKeys.ORIGINAL_AFFINE] = self._get_affine(i)
-            header = self._switch_lps_ras(header)
+
+            if self.affine_lps_to_ras:
+                header = self._switch_lps_ras(header)
+
             header[MetaKeys.AFFINE] = header[MetaKeys.ORIGINAL_AFFINE].copy()
             header[MetaKeys.SPATIAL_SHAPE] = header["sizes"]
             [header.pop(k) for k in ("sizes", "space origin", "space directions")]  # rm duplicated data in header

monai/data/image_reader.py

@@ -461,7 +461,7 @@ def affine(self) -> torch.Tensor:
     @affine.setter
     def affine(self, d: NdarrayTensor) -> None:
         """Set the affine."""
-        self.meta[MetaKeys.AFFINE] = torch.as_tensor(d, device=torch.device("cpu"), dtype=torch.double)
+        self.meta[MetaKeys.AFFINE] = torch.as_tensor(d, device=torch.device("cpu"), dtype=torch.float64)
 
     @property
     def pixdim(self):
@@ -471,7 +471,10 @@ def pixdim(self):
         return affine_to_spacing(self.affine)
 
     def peek_pending_shape(self):
-        """Get the currently expected spatial shape as if all the pending operations are executed."""
+        """
+        Get the currently expected spatial shape as if all the pending operations are executed.
+        For tensors that have more than 3 spatial dimensions, only the shapes of the top 3 dimensions will be returned.
+        """
         res = None
         if self.pending_operations:
             res = self.pending_operations[-1].get(LazyAttr.SHAPE, None)
@@ -480,11 +483,13 @@ def peek_pending_shape(self):
 
     def peek_pending_affine(self):
         res = self.affine
+        r = len(res) - 1
         for p in self.pending_operations:
-            next_matrix = convert_to_tensor(p.get(LazyAttr.AFFINE))
+            next_matrix = convert_to_tensor(p.get(LazyAttr.AFFINE), dtype=torch.float64)
             if next_matrix is None:
                 continue
             res = convert_to_dst_type(res, next_matrix)[0]
+            next_matrix = monai.data.utils.to_affine_nd(r, next_matrix)
             res = monai.transforms.lazy.utils.combine_transforms(res, next_matrix)
         return res