neurotk 0.1.0__tar.gz

neurotk-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

neurotk-0.1.0/PKG-INFO

@@ -0,0 +1,83 @@
+Metadata-Version: 2.4
+Name: neurotk
+Version: 0.1.0
+Summary: Dataset validation toolkit for neurology brain imaging (NIfTI)
+Author-email: Sakshi Rathi <rathi036@umn.edu>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/SakshiRa/neurotk
+Project-URL: Source, https://github.com/SakshiRa/neurotk
+Project-URL: Issues, https://github.com/SakshiRa/neurotk/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Medical Science Apps.
+Classifier: License :: OSI Approved :: Apache Software License
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: nibabel
+Requires-Dist: scipy
+Requires-Dist: matplotlib
+Dynamic: license-file
+
+[![DOI](https://zenodo.org/badge/1134680274.svg)](https://doi.org/10.5281/zenodo.18252017)
+
+
+# NeuroTK: Dataset Validation for Neurology Brain Imaging
+
+## Motivation
+Neurology brain imaging datasets are heterogeneous and frequently contain inconsistencies. Geometry, spacing, orientation, and annotation issues occur commonly across CT and MRI collections. These problems often surface late in modeling, when remediation is costly and compromises reproducibility. NeuroTK surfaces issues early, explicitly, and reproducibly to support dataset hygiene prior to analysis.
+
+## Scope
+NeuroTK focuses on dataset quality assurance prior to downstream analysis. It provides dataset-level and file-level validation with structural and geometric consistency checks, and assessment of annotation presence and integrity.
+
+- Dataset-level and file-level validation
+- Structural and geometric consistency checks
+- Annotation presence and integrity assessment
+
+NeuroTK does not modify scientific data.
+
+## Installation
+```sh
+pip install neurotk
+```
+
+## Quickstart
+```sh
+neurotk validate --images imagesTr --labels labelsTr --out report.json
+```
+
+Inputs are expected as flat directories of NIfTI files, and filenames must match exactly for image–label pairing.
+
+```
+dataset/
+  imagesTr/
+    case_001.nii.gz
+    case_002.nii.gz
+  labelsTr/
+    case_001.nii.gz
+    case_002.nii.gz
+```
+
+## Output
+NeuroTK emits a JSON report containing a dataset-level summary, per-file diagnostics, and explicit listings of detected issues.
+
+```json
+{
+  "summary": {"num_images": 100, "files_with_issues": 7},
+  "files": {"case_001.nii.gz": {"issues": ["label_missing"]}}
+}
+```
+
+## Citation
+If you use NeuroTK in your research, please cite it as follows:
+
+```bibtex
+@software{neurotk,
+  title  = {NeuroTK: Dataset Validation for Neurology Brain Imaging},
+  author = {Sakshi Rathi},
+  year   = {2026},
+  url    = {https://github.com/SakshiRa/neurotk},
+  note   = {Open-source toolkit for dataset validation and quality assurance in neurology brain imaging}
+}
+```

neurotk-0.1.0/README.md

@@ -0,0 +1,61 @@
+[![DOI](https://zenodo.org/badge/1134680274.svg)](https://doi.org/10.5281/zenodo.18252017)
+
+
+# NeuroTK: Dataset Validation for Neurology Brain Imaging
+
+## Motivation
+Neurology brain imaging datasets are heterogeneous and frequently contain inconsistencies. Geometry, spacing, orientation, and annotation issues occur commonly across CT and MRI collections. These problems often surface late in modeling, when remediation is costly and compromises reproducibility. NeuroTK surfaces issues early, explicitly, and reproducibly to support dataset hygiene prior to analysis.
+
+## Scope
+NeuroTK focuses on dataset quality assurance prior to downstream analysis. It provides dataset-level and file-level validation with structural and geometric consistency checks, and assessment of annotation presence and integrity.
+
+- Dataset-level and file-level validation
+- Structural and geometric consistency checks
+- Annotation presence and integrity assessment
+
+NeuroTK does not modify scientific data.
+
+## Installation
+```sh
+pip install neurotk
+```
+
+## Quickstart
+```sh
+neurotk validate --images imagesTr --labels labelsTr --out report.json
+```
+
+Inputs are expected as flat directories of NIfTI files, and filenames must match exactly for image–label pairing.
+
+```
+dataset/
+  imagesTr/
+    case_001.nii.gz
+    case_002.nii.gz
+  labelsTr/
+    case_001.nii.gz
+    case_002.nii.gz
+```
+
+## Output
+NeuroTK emits a JSON report containing a dataset-level summary, per-file diagnostics, and explicit listings of detected issues.
+
+```json
+{
+  "summary": {"num_images": 100, "files_with_issues": 7},
+  "files": {"case_001.nii.gz": {"issues": ["label_missing"]}}
+}
+```
+
+## Citation
+If you use NeuroTK in your research, please cite it as follows:
+
+```bibtex
+@software{neurotk,
+  title  = {NeuroTK: Dataset Validation for Neurology Brain Imaging},
+  author = {Sakshi Rathi},
+  year   = {2026},
+  url    = {https://github.com/SakshiRa/neurotk},
+  note   = {Open-source toolkit for dataset validation and quality assurance in neurology brain imaging}
+}
+```

neurotk-0.1.0/neurotk/__init__.py

@@ -0,0 +1,6 @@
+"""NeuroTK package."""
+
+from __future__ import annotations
+
+__all__ = ["__version__"]
+__version__ = "0.1.0"

neurotk-0.1.0/neurotk/cli.py

@@ -0,0 +1,135 @@
+"""Command-line interface for dataset validation."""
+
+from __future__ import annotations
+
+import argparse
+import json
+from pathlib import Path
+from typing import Dict, List, Optional, Tuple
+
+from .report import build_summary
+from .utils import nifti_stem
+from .validate import validate_image, validate_label
+
+
+def _is_nifti(path: Path) -> bool:
+    name = path.name.lower()
+    return name.endswith(".nii") or name.endswith(".nii.gz")
+
+
+def list_nifti_files(directory: Path) -> List[Path]:
+    return sorted([p for p in directory.rglob("*") if p.is_file() and _is_nifti(p)])
+
+
+def _build_label_index(label_files: List[Path]) -> Dict[str, Path]:
+    index: Dict[str, Path] = {}
+    for path in label_files:
+        index[nifti_stem(path.name)] = path
+    return index
+
+
+def _parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(prog="neurotk validate")
+    parser.add_argument("--images", required=True, type=Path)
+    parser.add_argument("--labels", required=False, type=Path)
+    parser.add_argument("--out", required=True, type=Path)
+    parser.add_argument("--max-samples", required=False, type=int, default=None)
+    return parser.parse_args()
+
+
+def run() -> int:
+    args = _parse_args()
+    images_dir: Path = args.images
+    labels_dir: Optional[Path] = args.labels
+
+    if not images_dir.exists() or not images_dir.is_dir():
+        raise SystemExit(f"Images directory not found: {images_dir}")
+
+    image_files = list_nifti_files(images_dir)
+    if args.max_samples is not None:
+        image_files = image_files[: max(args.max_samples, 0)]
+
+    label_files: List[Path] = []
+    if labels_dir is not None:
+        if not labels_dir.exists() or not labels_dir.is_dir():
+            raise SystemExit(f"Labels directory not found: {labels_dir}")
+        label_files = list_nifti_files(labels_dir)
+
+    label_index = _build_label_index(label_files)
+
+    files_report: Dict[str, Dict[str, object]] = {}
+    warnings: List[str] = []
+    shapes: List[Tuple[int, int, int]] = []
+    spacings: List[Tuple[float, float, float]] = []
+    orientations: List[Tuple[str, str, str]] = []
+    missing_labels: List[str] = []
+
+    for image_path in image_files:
+        image_info, image_issues = validate_image(image_path)
+
+        shape = image_info.get("shape")
+        image_shape = None
+        if isinstance(shape, list) and len(shape) == 3:
+            image_shape = tuple(shape)
+            shapes.append(image_shape)
+        spacing = image_info.get("spacing")
+        if isinstance(spacing, list) and len(spacing) == 3:
+            spacings.append(tuple(float(x) for x in spacing))
+        orientation = image_info.get("orientation")
+        if isinstance(orientation, list) and len(orientation) == 3:
+            orientations.append(tuple(str(x) for x in orientation))
+
+        label_info = None
+        label_issues: List[str] = []
+        if labels_dir is not None:
+            stem = nifti_stem(image_path.name)
+            label_path = label_index.get(stem)
+            if label_path is None:
+                missing_labels.append(image_path.name)
+            label_info, label_issues = validate_label(
+                label_path, image_shape
+            )
+
+        issues = image_issues + label_issues
+        files_report[image_path.name] = {
+            "image": image_info,
+            "label": label_info,
+            "issues": issues,
+        }
+
+    label_stems = {nifti_stem(p.name) for p in label_files}
+    image_stems = {nifti_stem(p.name) for p in image_files}
+    missing_images = sorted(list(label_stems - image_stems))
+
+    files_with_issues = sum(
+        1 for v in files_report.values() if v.get("issues")
+    )
+
+    summary = build_summary(
+        image_count=len(image_files),
+        label_count=len(label_files),
+        missing_labels=missing_labels,
+        missing_images=missing_images,
+        shapes=shapes,
+        spacings=spacings,
+        orientations=orientations,
+        files_with_issues=files_with_issues,
+    )
+
+    report = {"summary": summary, "files": files_report, "warnings": warnings}
+
+    args.out.parent.mkdir(parents=True, exist_ok=True)
+    with args.out.open("w", encoding="utf-8") as f:
+        json.dump(report, f, indent=2)
+
+    print("Validation complete")
+    return 0
+
+
+def main() -> None:
+    """CLI entrypoint."""
+    raise SystemExit(run())
+
+
+if __name__ == "__main__":
+    main()

neurotk-0.1.0/neurotk/io.py

@@ -0,0 +1,17 @@
+"""NIfTI input helpers."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Tuple
+
+import nibabel as nib
+import numpy as np
+
+
+def load_nifti(path: Path) -> Tuple[nib.Nifti1Image, np.ndarray, np.dtype]:
+    """Load a NIfTI file and return image, float data, and original dtype."""
+    img = nib.load(str(path))
+    data = img.get_fdata(dtype=np.float64)
+    dtype = np.asarray(img.dataobj).dtype
+    return img, data, dtype

neurotk-0.1.0/neurotk/report.py

@@ -0,0 +1,65 @@
+"""Dataset-level aggregation and report formatting."""
+
+from __future__ import annotations
+
+from collections import Counter
+from typing import Dict, Iterable, List, Optional, Tuple
+
+import numpy as np
+
+
+def _modal(values: Iterable[Tuple]) -> Optional[Tuple]:
+    items = list(values)
+    if not items:
+        return None
+    return Counter(items).most_common(1)[0][0]
+
+
+def build_summary(
+    image_count: int,
+    label_count: int,
+    missing_labels: List[str],
+    missing_images: List[str],
+    shapes: List[Tuple[int, int, int]],
+    spacings: List[Tuple[float, float, float]],
+    orientations: List[Tuple[str, str, str]],
+    files_with_issues: int,
+) -> Dict[str, object]:
+    modal_shape = _modal(shapes)
+    shape_deviation_count = 0
+    if modal_shape is not None:
+        shape_deviation_count = sum(1 for s in shapes if s != modal_shape)
+
+    spacing_mean = None
+    spacing_std = None
+    if spacings:
+        spacing_arr = np.array(spacings, dtype=float)
+        spacing_mean = spacing_arr.mean(axis=0).tolist()
+        spacing_std = spacing_arr.std(axis=0).tolist()
+
+    orientation_modal = _modal(orientations)
+    orientation_deviation_count = 0
+    orientation_counts = None
+    if orientations:
+        orientation_counts = {
+            ",".join(k): v for k, v in Counter(orientations).items()
+        }
+        if orientation_modal is not None:
+            orientation_deviation_count = sum(
+                1 for o in orientations if o != orientation_modal
+            )
+
+    return {
+        "num_images": image_count,
+        "num_labels": label_count,
+        "missing_label_images": missing_labels,
+        "missing_image_labels": missing_images,
+        "modal_shape": list(modal_shape) if modal_shape else None,
+        "shape_deviation_count": shape_deviation_count,
+        "spacing_mean": spacing_mean,
+        "spacing_std": spacing_std,
+        "orientation_modal": list(orientation_modal) if orientation_modal else None,
+        "orientation_counts": orientation_counts,
+        "orientation_deviation_count": orientation_deviation_count,
+        "files_with_issues": files_with_issues,
+    }

neurotk-0.1.0/neurotk/utils.py

@@ -0,0 +1,55 @@
+"""Utility helpers for validation."""
+
+from __future__ import annotations
+
+from typing import Dict, Iterable, List, Optional, Tuple
+
+import nibabel as nib
+import numpy as np
+
+
+def nifti_stem(path_name: str) -> str:
+    """Return filename stem without NIfTI extensions."""
+    if path_name.endswith(".nii.gz"):
+        return path_name[:-7]
+    if path_name.endswith(".nii"):
+        return path_name[:-4]
+    return path_name.rsplit(".", 1)[0]
+
+
+def orientation_codes(affine: np.ndarray) -> Optional[Tuple[str, str, str]]:
+    """Return orientation codes from affine, or None on failure."""
+    try:
+        codes = nib.orientations.aff2axcodes(affine)
+    except Exception:
+        return None
+    return codes
+
+
+def safe_stats(data: np.ndarray) -> Dict[str, Optional[float]]:
+    """Compute stats on finite values; return None when unavailable."""
+    finite = np.isfinite(data)
+    if not np.any(finite):
+        return {"min": None, "max": None, "mean": None, "std": None}
+    vals = data[finite]
+    return {
+        "min": float(np.min(vals)),
+        "max": float(np.max(vals)),
+        "mean": float(np.mean(vals)),
+        "std": float(np.std(vals)),
+    }
+
+
+def spacing_from_header(img: nib.Nifti1Image) -> Optional[Tuple[float, float, float]]:
+    """Extract voxel spacing for the first three axes."""
+    zooms = img.header.get_zooms()
+    if len(zooms) < 3:
+        return None
+    return (float(zooms[0]), float(zooms[1]), float(zooms[2]))
+
+
+def to_list(values: Optional[Iterable]) -> Optional[List]:
+    """Convert iterable to list, preserving None."""
+    if values is None:
+        return None
+    return list(values)

neurotk-0.1.0/neurotk/validate.py

@@ -0,0 +1,161 @@
+"""Per-file validation logic for NIfTI datasets."""
+
+from __future__ import annotations
+
+from pathlib import Path
+from typing import Dict, List, Optional, Tuple
+
+import numpy as np
+
+from .io import load_nifti
+from .utils import orientation_codes, safe_stats, spacing_from_header, to_list
+
+
+def _image_info_template(path: Path) -> Dict[str, object]:
+    return {
+        "path": str(path),
+        "readable": False,
+        "dimensionality": None,
+        "shape": None,
+        "spacing": None,
+        "orientation": None,
+        "affine_determinant": None,
+        "dtype": None,
+        "has_nan": None,
+        "has_inf": None,
+        "stats": None,
+    }
+
+
+def _label_info_template(path: Optional[Path]) -> Dict[str, object]:
+    return {
+        "path": str(path) if path else None,
+        "present": path is not None,
+        "readable": False,
+        "dimensionality": None,
+        "shape": None,
+        "shape_matches_image": None,
+        "integer_valued": None,
+        "unique_values": None,
+        "empty": None,
+    }
+
+
+def validate_image(path: Path) -> Tuple[Dict[str, object], List[str]]:
+    """Validate a single image file."""
+    info = _image_info_template(path)
+    issues: List[str] = []
+    try:
+        img, data, dtype = load_nifti(path)
+    except Exception as exc:
+        info["readable"] = False
+        info["error"] = f"{type(exc).__name__}: {exc}"
+        issues.append("image_not_readable")
+        return info, issues
+
+    info["readable"] = True
+    info["dtype"] = str(dtype)
+    info["dimensionality"] = int(img.ndim)
+    info["shape"] = to_list(img.shape)
+
+    if img.ndim != 3:
+        issues.append("image_dimensionality_not_3")
+
+    spacing = spacing_from_header(img)
+    info["spacing"] = to_list(spacing)
+    if spacing is None:
+        issues.append("image_spacing_missing")
+
+    orientation = orientation_codes(img.affine)
+    info["orientation"] = to_list(orientation)
+    if orientation is None:
+        issues.append("image_orientation_missing")
+
+    try:
+        det = float(np.linalg.det(img.affine))
+    except Exception as exc:
+        det = None
+        info["affine_error"] = f"{type(exc).__name__}: {exc}"
+    info["affine_determinant"] = det
+    if det is None or det == 0.0:
+        issues.append("image_affine_singular")
+
+    try:
+        info["has_nan"] = bool(np.isnan(data).any())
+        info["has_inf"] = bool(np.isinf(data).any())
+    except Exception as exc:
+        info["nan_inf_error"] = f"{type(exc).__name__}: {exc}"
+        issues.append("image_nan_inf_check_failed")
+
+    if info.get("has_nan"):
+        issues.append("image_contains_nan")
+    if info.get("has_inf"):
+        issues.append("image_contains_inf")
+
+    try:
+        info["stats"] = safe_stats(data)
+        if info["stats"]["min"] is None:
+            issues.append("image_stats_no_finite")
+    except Exception as exc:
+        info["stats_error"] = f"{type(exc).__name__}: {exc}"
+        issues.append("image_stats_failed")
+
+    return info, issues
+
+
+def validate_label(
+    path: Optional[Path], image_shape: Optional[Tuple[int, ...]]
+) -> Tuple[Dict[str, object], List[str]]:
+    """Validate a single label file."""
+    info = _label_info_template(path)
+    issues: List[str] = []
+    if path is None:
+        issues.append("label_missing")
+        return info, issues
+
+    try:
+        img, data, _dtype = load_nifti(path)
+    except Exception as exc:
+        info["readable"] = False
+        info["error"] = f"{type(exc).__name__}: {exc}"
+        issues.append("label_not_readable")
+        return info, issues
+
+    info["readable"] = True
+    info["dimensionality"] = int(img.ndim)
+    info["shape"] = to_list(img.shape)
+
+    if img.ndim != 3:
+        issues.append("label_dimensionality_not_3")
+
+    if image_shape is not None:
+        matches = tuple(img.shape) == tuple(image_shape)
+        info["shape_matches_image"] = matches
+        if not matches:
+            issues.append("label_shape_mismatch")
+
+    try:
+        finite = np.isfinite(data)
+        if not np.any(finite):
+            info["integer_valued"] = False
+            issues.append("label_no_finite_values")
+        else:
+            vals = data[finite]
+            info["integer_valued"] = bool(np.all(vals == np.round(vals)))
+            if not info["integer_valued"]:
+                issues.append("label_not_integer_valued")
+    except Exception as exc:
+        info["integer_error"] = f"{type(exc).__name__}: {exc}"
+        issues.append("label_integer_check_failed")
+
+    try:
+        unique_vals = np.unique(data)
+        info["unique_values"] = [int(v) for v in unique_vals.tolist()]
+        info["empty"] = bool(np.all(unique_vals == 0))
+        if info["empty"]:
+            issues.append("label_empty_mask")
+    except Exception as exc:
+        info["unique_error"] = f"{type(exc).__name__}: {exc}"
+        issues.append("label_unique_values_failed")
+
+    return info, issues

neurotk-0.1.0/neurotk.egg-info/PKG-INFO

@@ -0,0 +1,83 @@
+Metadata-Version: 2.4
+Name: neurotk
+Version: 0.1.0
+Summary: Dataset validation toolkit for neurology brain imaging (NIfTI)
+Author-email: Sakshi Rathi <rathi036@umn.edu>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/SakshiRa/neurotk
+Project-URL: Source, https://github.com/SakshiRa/neurotk
+Project-URL: Issues, https://github.com/SakshiRa/neurotk/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Medical Science Apps.
+Classifier: License :: OSI Approved :: Apache Software License
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: nibabel
+Requires-Dist: scipy
+Requires-Dist: matplotlib
+Dynamic: license-file
+
+[![DOI](https://zenodo.org/badge/1134680274.svg)](https://doi.org/10.5281/zenodo.18252017)
+
+
+# NeuroTK: Dataset Validation for Neurology Brain Imaging
+
+## Motivation
+Neurology brain imaging datasets are heterogeneous and frequently contain inconsistencies. Geometry, spacing, orientation, and annotation issues occur commonly across CT and MRI collections. These problems often surface late in modeling, when remediation is costly and compromises reproducibility. NeuroTK surfaces issues early, explicitly, and reproducibly to support dataset hygiene prior to analysis.
+
+## Scope
+NeuroTK focuses on dataset quality assurance prior to downstream analysis. It provides dataset-level and file-level validation with structural and geometric consistency checks, and assessment of annotation presence and integrity.
+
+- Dataset-level and file-level validation
+- Structural and geometric consistency checks
+- Annotation presence and integrity assessment
+
+NeuroTK does not modify scientific data.
+
+## Installation
+```sh
+pip install neurotk
+```
+
+## Quickstart
+```sh
+neurotk validate --images imagesTr --labels labelsTr --out report.json
+```
+
+Inputs are expected as flat directories of NIfTI files, and filenames must match exactly for image–label pairing.
+
+```
+dataset/
+  imagesTr/
+    case_001.nii.gz
+    case_002.nii.gz
+  labelsTr/
+    case_001.nii.gz
+    case_002.nii.gz
+```
+
+## Output
+NeuroTK emits a JSON report containing a dataset-level summary, per-file diagnostics, and explicit listings of detected issues.
+
+```json
+{
+  "summary": {"num_images": 100, "files_with_issues": 7},
+  "files": {"case_001.nii.gz": {"issues": ["label_missing"]}}
+}
+```
+
+## Citation
+If you use NeuroTK in your research, please cite it as follows:
+
+```bibtex
+@software{neurotk,
+  title  = {NeuroTK: Dataset Validation for Neurology Brain Imaging},
+  author = {Sakshi Rathi},
+  year   = {2026},
+  url    = {https://github.com/SakshiRa/neurotk},
+  note   = {Open-source toolkit for dataset validation and quality assurance in neurology brain imaging}
+}
+```

neurotk-0.1.0/neurotk.egg-info/SOURCES.txt

@@ -0,0 +1,15 @@
+LICENSE
+README.md
+pyproject.toml
+neurotk/__init__.py
+neurotk/cli.py
+neurotk/io.py
+neurotk/report.py
+neurotk/utils.py
+neurotk/validate.py
+neurotk.egg-info/PKG-INFO
+neurotk.egg-info/SOURCES.txt
+neurotk.egg-info/dependency_links.txt
+neurotk.egg-info/entry_points.txt
+neurotk.egg-info/requires.txt
+neurotk.egg-info/top_level.txt

neurotk-0.1.0/neurotk.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

neurotk-0.1.0/neurotk.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+neurotk = neurotk.cli:main

neurotk-0.1.0/neurotk.egg-info/requires.txt

@@ -0,0 +1,4 @@
+numpy
+nibabel
+scipy
+matplotlib

neurotk-0.1.0/neurotk.egg-info/top_level.txt

@@ -0,0 +1 @@
+neurotk

neurotk-0.1.0/pyproject.toml

@@ -0,0 +1,37 @@
+[build-system]
+requires = ["setuptools>=61.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "neurotk"
+version = "0.1.0"
+description = "Dataset validation toolkit for neurology brain imaging (NIfTI)"
+readme = "README.md"
+requires-python = ">=3.8"
+license = { text = "Apache-2.0" }
+
+authors = [
+  { name = "Sakshi Rathi", email = "rathi036@umn.edu" }
+]
+
+dependencies = [
+  "numpy",
+  "nibabel",
+  "scipy",
+  "matplotlib"
+]
+
+classifiers = [
+  "Programming Language :: Python :: 3",
+  "Intended Audience :: Science/Research",
+  "Topic :: Scientific/Engineering :: Medical Science Apps.",
+  "License :: OSI Approved :: Apache Software License"
+]
+
+[project.urls]
+Homepage = "https://github.com/SakshiRa/neurotk"
+Source = "https://github.com/SakshiRa/neurotk"
+Issues = "https://github.com/SakshiRa/neurotk/issues"
+
+[project.scripts]
+neurotk = "neurotk.cli:main"

neurotk-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+