Merge pull request #105 from Hendrik-code/development_robert

Development robert

Author: Hendrik-code

TPTBox/core/bids_constants.py

@@ -163,6 +163,8 @@
     "localizer",
     "difference",
     "labels",
+    "report",
+    "pet",
 ]
 # https://bids-specification.readthedocs.io/en/stable/appendices/entity-table.html
 formats_relaxed = [*formats, "t2", "t1", "t2c", "t1c", "mr", "snapshot", "t1dixon", "dwi", "ctb"]
@@ -221,7 +223,7 @@
     "OPT": "Ophthalmic Tomography",
     "OPV": "Ophthalmic Visual Field",
     "OSS": "Optical Surface Scan",
-    "OT": "Other ",
+    "OT": "Other",
     "PLAN": "Plan",
     "PR": "Presentation State",
     "PT": "Positron emission tomography (PET)",

TPTBox/core/bids_files.py

@@ -687,7 +687,7 @@ def get_changed_bids(
         auto_add_run_id=False,
         additional_folder: str | None = None,
         dataset_path: str | None = None,
-        make_parent=True,
+        make_parent=False,
         non_strict_mode=False,
     ):
         ds = dataset_path if dataset_path is not None else self.get_path_decomposed()[0]

TPTBox/core/dicom/dicom_extract.py

@@ -190,7 +190,68 @@ def dicom_to_nifti_multiframe(ds, nii_path):
     return nii_path
 
 
-def _convert_to_nifti(dicom_out_path, nii_path):
+def _export_pdf_from_dicom(dcm_path, out_pdf):
+    assert len(dcm_path) == 1, dcm_path
+    ds = dcm_path[0]
+
+    # verify modality / SOP class
+    if ds.Modality.upper() != "PDF":
+        raise ValueError("Not a PDF DICOM")
+
+    if "EncapsulatedDocument" not in ds:
+        raise ValueError("No embedded PDF found")
+
+    pdf_bytes = ds.EncapsulatedDocument
+
+    out_pdf = Path(out_pdf)
+    out_pdf.write_bytes(pdf_bytes)
+
+
+def _collect_text(ds, txt_lines: list[str] | None = None):
+    if txt_lines is None:
+        txt_lines = []
+
+    def _help_collect_text(content_sequence, level: int = 0):
+        for item in content_sequence:
+            prefix = "  " * level
+
+            concept = ""
+
+            if hasattr(item, "ConceptNameCodeSequence"):
+                try:
+                    concept = item.ConceptNameCodeSequence[0].CodeMeaning
+                except Exception:
+                    pass
+
+            value = None
+
+            for attr in ["TextValue", "CodeMeaning", "NumericValue"]:
+                if hasattr(item, attr):
+                    value = getattr(item, attr)
+                    break
+
+            if concept or value is not None:
+                txt_lines.append(f"{prefix}{concept}: {value}")
+
+            if hasattr(item, "ContentSequence"):
+                _help_collect_text(
+                    item.ContentSequence,
+                    level + 1,
+                )
+
+    if hasattr(ds, "ContentSequence"):
+        _help_collect_text(ds.ContentSequence)
+    return txt_lines
+
+
+def _extract_txt_from_dicom(dcm_path, out_txt):
+    lines = []
+    for p in dcm_path:
+        lines = _collect_text(p, lines)
+    Path(out_txt).write_text("\n".join(lines))
+
+
+def _extract_nii_from_dicom(dicom_out_path, nii_path):
     """
     Convert DICOM files to NIfTI format and handle common conversion errors.
 
@@ -206,6 +267,7 @@ def _convert_to_nifti(dicom_out_path, nii_path):
         FunctionTimedOut: Raised if the DICOM-to-NIfTI conversion times out.
         ValueError: Raised for generic validation failures.
     """
+
     try:
         if isinstance(dicom_out_path, list):
             try:
@@ -217,6 +279,7 @@ def _convert_to_nifti(dicom_out_path, nii_path):
                     return True
             except Exception as e:
                 logger.on_debug("Multi-Frame DICOM did not work:", e)
+            ## The PDF dicom lands here
             convert_dicom.dicom_array_to_nifti(dicom_out_path, nii_path, True)
         else:
             # func_timeout(10, dicom2nifti.dicom_series_to_nifti, (dicom_out_path, nii_path, True))
@@ -246,6 +309,9 @@ def _convert_to_nifti(dicom_out_path, nii_path):
         logger.print_error()
 
         return False
+    except Exception:
+        print(nii_path)
+
     return True
 
 
@@ -264,7 +330,7 @@ def _get_paths(
 ):
     if keys is None:
         keys = {}
-    (mri_format, keys) = extract_keys_from_json(
+    (mri_format, keys, ending) = extract_keys_from_json(
         simp_json,
         dcm_data_l,
         use_session,
@@ -277,7 +343,7 @@ def _get_paths(
     json_file_name, json_bids_name = _generate_bids_path(
         dataset_nifti_dir, keys, mri_format, simp_json, make_subject_chunks=make_subject_chunks, parent=parent
     )
-    nii_path = str(json_file_name).replace(".json", "") + ".nii.gz"
+    nii_path = str(json_file_name).replace(".json", "") + ending
     return json_file_name, json_bids_name, nii_path
 
 
@@ -364,11 +430,17 @@ def _from_dicom_to_nii(
     if exist and Path(nii_path).exists():
         logger.print("already exists:", json_file_name, ltype=Log_Type.STRANGE, verbose=verbose)
         return nii_path
-    suc = _convert_to_nifti(dcm_data_l, nii_path)
+    add_grid = False
+    if nii_path.endswith(".pdf"):
+        _export_pdf_from_dicom(dcm_data_l, nii_path)
+    elif nii_path.endswith(".txt"):
+        _extract_txt_from_dicom(dcm_data_l, nii_path)
+    else:
+        add_grid = _extract_nii_from_dicom(dcm_data_l, nii_path)
 
-    if suc:
+    if add_grid:
         _add_grid_info_to_json(nii_path, json_file_name)
-    return nii_path if suc else None
+    return nii_path if add_grid else None
 
 
 def _add_grid_info_to_json(nii_path: Path | str, simp_json: Path | str, force_update=False, add=True):
@@ -390,7 +462,7 @@ def _add_grid_info_to_json(nii_path: Path | str, simp_json: Path | str, force_up
     return json_dict
 
 
-def _find_all_files(dcm_dirs: Path | list[Path]):
+def _find_all_files(dcm_dirs: Path | list[Path],verbose=False):
     """
     Recursively find all DICOM directories or files in the given paths.
 
@@ -400,6 +472,9 @@ def _find_all_files(dcm_dirs: Path | list[Path]):
     Yields:
         Path: Paths to directories or individual DICOM files found during the search.
     """
+    if verbose:
+        logger.on_neutral("Start file searching")
+        i = 0
     yield dcm_dirs
     dcm_dirs = dcm_dirs if isinstance(dcm_dirs, list) else [dcm_dirs]
     for dcm_dir in dcm_dirs:
@@ -408,9 +483,15 @@ def _find_all_files(dcm_dirs: Path | list[Path]):
                 file = ""
                 for file in files:
                     if Path(file).is_file():  # str(file).endswith(".dcm") or str(file).endswith(".ima")
+                        if verbose:
+                            logger.on_neutral("File ",i,end="\r")
+                            i += 1
                         yield Path(root, file).absolute().parent
                         break
                     else:
+                        if verbose:
+                            logger.on_neutral("File ",i,end="\r")
+                            i += 1
                         yield Path(root, file)
                 # if "." not in str(file):
                 #    yield Path(root, file).absolute().parent
@@ -606,7 +687,7 @@ def extract_dicom_folder(
         convert_dicom.settings.disable_validate_slice_increment()
     outs = {}
 
-    for p in _find_all_files(dicom_folder):
+    for p in _find_all_files(dicom_folder,verbose=verbose):
         dicom_path = p
 
         if str(dicom_path).endswith(".pkl"):
@@ -672,6 +753,7 @@ def process_series(key, files, parts):
             p, Path("/media/data/robert/datasets", "dataset-Durchleuchtung222"), False, False, validate_slice_increment=False
         )
 
+
     sys.exit()
     # s = "/home/robert/Downloads/bein/dataset-oberschenkel/rawdata/sub-1-3-46-670589-11-2889201787-2305829596-303261238-2367429497/mr/sub-1-3-46-670589-11-2889201787-2305829596-303261238-2367429497_sequ-406_mr.nii.gz"
     # nii2 = NII.load(s, False)

TPTBox/core/dicom/dicom_header_to_keys.py

@@ -165,7 +165,15 @@ def extract_keys_from_json(  # noqa: C901
     def _get(key, default=None):
         if key not in simp_json:
             return keys.get(key, default)
-        return str(simp_json[key]).replace("_", "-").replace(" ", "-").replace(".", "-")
+        value = str(simp_json[key]).replace("_", "-").replace(" ", "-").replace(".", "-")
+        # remove invalid filename characters
+        value = re.sub(r'[<>:"/\\|?*\x00-\x1F]', "", value)
+        # collapse repeated dashes
+        value = re.sub(r"-+", "-", value)
+        # strip leading/trailing dots and dashes
+        value = value.strip(".-")
+
+        return value
 
     """Extract keys from JSON based on study and series descriptions."""
     #### NAKO FIXED ####
@@ -174,25 +182,28 @@ def _get(key, default=None):
         series_description = _get("SeriesDescription", "unnamed")
         """Determine the MRI format based on the series description."""
         if "T2_TSE" in series_description:
-            return "T2w", {"acq": "sag", "chunk": series_description.split("_")[-1], "sequ": simp_json["SeriesNumber"], **keys}
+            return "T2w", {"acq": "sag", "chunk": series_description.split("_")[-1], "sequ": simp_json["SeriesNumber"], **keys}, ".nii.gz"
         elif "3D_GRE_TRA" in series_description:
-            return "vibe", {
-                "acq": "ax",
-                "part": dixon_mapping[series_description.split("_")[-1].lower()],
-                "chunk": _get("ProtocolName", "unnamed").split("_")[-1],
-                **keys,
-            }
+            return (
+                "vibe",
+                {
+                    "acq": "ax",
+                    "part": dixon_mapping[series_description.split("_")[-1].lower()],
+                    "chunk": _get("ProtocolName", "unnamed").split("_")[-1],
+                    **keys,
+                },
+                ".nii.gz",
+            )
         elif "ME_vibe" in series_description:
-            return "mevibe", {
-                "acq": "ax",
-                "part": dixon_mapping[series_description.split("_")[-1].lower()],
-                "sequ": simp_json["SeriesNumber"],
-                **keys,
-            }
+            return (
+                "mevibe",
+                {"acq": "ax", "part": dixon_mapping[series_description.split("_")[-1].lower()], "sequ": simp_json["SeriesNumber"], **keys},
+                ".nii.gz",
+            )
         elif "PD" in series_description:
-            return "pd", {"acq": "iso", **keys}
+            return "pd", {"acq": "iso", **keys}, ".nii.gz"
         elif "T2_HASTE" in series_description:
-            return "T2haste", {"acq": "ax", **keys}
+            return "T2haste", {"acq": "ax", **keys}, ".nii.gz"
         else:
             raise NotImplementedError(series_description)
     # GENERAL
@@ -268,6 +279,8 @@ def _get(key, default=None):
         found = False
         if modality == "ct":
             mri_format = "ct"
+        elif modality.lower() == "pt":
+            mri_format = "pet"
         elif modality == "xa":  # Angiography
             biplane = False
             if "BIPLANE A" in image_type or "SINGLE A" in image_type:
@@ -319,9 +332,14 @@ def _get(key, default=None):
                     " km " in series_description.lower() or series_description.startswith("km") or series_description.endswith("km")
                 ) and keys.get("ce") is None:
                     keys["ce"] = "ContrastAgent"
+        elif modality.lower() == "pdf":
+            return "report", keys, ".pdf"
+        elif modality.lower() == "sr":
+            keys["desc"] = _get("SeriesDescription", None)
+            return "report", keys, ".txt"
         else:
-            raise NotImplementedError(f"modality='{modality.upper()}', ({modalities.get(modality.upper())})")
+            raise NotImplementedError(f"modality='{modality}', ({modalities.get(modality.upper(), 'Non Standard Modality key')})")
 
             # ".*sub.*t1.*": "subtraktion",
         # "subtraktion.*t1.*": "subtraktion",
-        return mri_format, keys
+        return mri_format, keys, ".nii.gz"