Compute complex conjugate of an/a array/tensor. Supports Ndim inputs with last dim equal to 2 (real/imaginary channels) Args: x: Inp

First compute the difference in the complex domain, then get the absolute value and take the mse Args: x, y - B, 2, H, W real va

Compute complex-valued multiplication. Supports Ndim inputs with last dim equal to 2 (real/imaginary channels) Args: x: Input array/

Compute COCO metrics Args: results_list (list[dict[int, dict[str, np.ndarray]]]): list with results per image (in list)

Compute the matched indices between anchors and ground truth (gt) boxes in targets. output[k][i] represents the matched gt index for

This function is used to compute the Average Surface Distance from `y_pred` to `y` under the default setting. In addition, if sets ``symm

Compute box regression losses. Args: box_regression: box regression results, sized (B, sum(HWA), 2*self.spatial_dims)

Compute per-component Dice for a single batch item. Args: y_pred (torch.Tensor): Predictions with shape (1, 2, D, H, W)

Compute the dice metric for binary inputs which have only spatial dimensions. This method is called separately for each batch item an

Compute classification losses. Args: cls_logits: classification logits, sized (B, sum(HW(D)A), self.num_classes)

Compute false positive and true positive probabilities for tumor detection, by comparing the model outputs with the prepared ground t

The Frechet distance between multivariate normal distributions.

Compute the Hausdorff distance. Args: y_pred: input data to compute, typical segmentation model output. It must be one-h

This method computes identifies Isolated Tumor Cells (ITC) and return their labels. Args: tumor_mask: the tumor mask. thresh

Compute losses. Args: head_outputs_reshape: reshaped head_outputs. ``head_output_reshape[self.cls_key]`` is a Tensor

Compute the actual feature map with input tensor `x`. Args: x: input to `nn_module`. class_idx: index of the

Compute Mean Absolute Percentage Error. Args: y_pred: predicted values y: ground truth values epsilon: small value t

Compute matches Args: boxes: bounding boxes, Nx4 or Nx6 torch tensor or ndarray. The box mode is assumed to be ``Standar

Compute matches according to ATTS for a single image Adapted from (https://github.com/sfzhang15/ATSS/blob/79dfb28bd1/atss_cor

Args: y: first sample (e.g., the reference image). Its shape is (B,C,W,H) for 2D data and (B,C,W,H,D) for 3D. y_pred: second samp

Args: y_pred: Predicted image. It must be a 2D or 3D batch-first tensor [B,C,H,W] or [B,C,H,W,D]. y: Reference image.

This method computes the segmentation mask according to the binary tumor mask. Args: mask: the binary mask array threshold:

dynamically compute the pad width according to the spatial shape. Args: spatial_shape: spatial shape of the original ima

Voronoi assignment to connected components (CPU, single EDT) without cc3d. Returns the ID of the nearest component for each voxel. Args:

Compute confidence map Args: img (NDArray): Processed image. seeds (NDArray): Seeds for the random walks framework. T

Compute 6-Connected Laplacian for confidence estimation problem Args: padded_index (NDArray): The index matrix of the image with

Converts an axis-aligned bounding box to points. Args: mode: The mode specifying how to interpret the bounding box. bbox: Bo

Convert and make a copy the dataset to meet the requirements of nnU-Net workflow.

Convert nnUNet model checkpoints and configuration to MONAI bundle format. Parameters ---------- nnunet_config : dict Config

Convert point label based on its class prompt. For special classes defined in special index, the positive/negative point label will b

Converts points to an axis-aligned bounding box. Args: points: Points representing the corners of the bounding box. Shape (N, 8, 3)

Utility to export a model into a TensorRT engine-based TorchScript model with optional input / output data verification. There are two ways

Calculate the slices to copy a sliced area of array in `src_shape` into array in `dest_shape`. The area has dimensions `dims` (use 0 or None

Convert the given box corners to the bounding boxes of the current mode. Args: corners: corners of boxes, 4-element or 6

Create an Nifti1Image object from ``data_array``. This method assumes a 'channel-last' ``data_array``. Args: data_array:

Create a PIL object from ``data_array``. Args: data_array: input data array. dtype: output data type.

Utility to create new Decathlon style datalist based on cross validation partition. Args: datalist: loaded list of dictionaries for

Creates an affine transformation for an ITK image based on the provided parameters. Args: image: The ITK image.

Create and organize a new copy of data to meet the requirements of nnU-Net V2 Args: test_key: key for test data in the data list .js

Create a new copy of dataset .json to meet the requirements of nnU-Net V2 Args: modality: image modality, could a string or a list o

Create pair of Ignite events from a event prefix name

Create simulated data using create_test_image_3d. Args: dataroot: data directory path that hosts the "nii.gz" image files. s

Create simulated data using create_test_image_3d. Args: dataroot: data directory path that hosts the "nii.gz" image files. s

Returns an array mapping neighbourhood code to the contour length. Adapted from https://github.com/deepmind/surface-distance In 2D, each

Returns an array mapping neighbourhood code to the surface elements area. Adapted from https://github.com/deepmind/surface-distance Note

Functional implementation of cropping a MetaTensor. This function operates eagerly or lazily according to ``lazy`` (default ``False``).

Crop the meshgrid so we only perform occlusion sensitivity on a subsection of the image.

`np.cumsum` with equivalent implementation for torch. Args: a: input data to compute cumsum. axis: expected axis to compute

Calculates the Damerau–Levenshtein distance between two strings for spelling correction. https://en.wikipedia.org/wiki/Damerau–Levenshtein_di

Decode network log_alpha_a/log_alpha_c using dijkstra shortest path algorithm. `[node_a, arch_code_a, arch_code_c, arch_code_a_max]`

From a set of original reference_boxes and encoded relative box offsets, Args: rel_codes: encoded boxes, Nx4 or Nx6 torc

Enumerate all slices defining ND patches of size `patch_size` from an `image_size` input image. Args: image_size: dimensions of imag

Dilate 2D/3D binary mask. Args: mask: input 2D/3D binary mask, [N,C,M,N] or [N,C,M,N,P] torch tensor or ndarray. filter_size

Dilate 2D/3D binary mask with data type as torch tensor. Args: mask_t: input 2D/3D binary mask, [N,C,M,N] or [N,C,M,N,P] torch tenso

TorchScript does not support torch.distributed.all_reduce. This function is a bypassing trick based on the example: https://pytorch.o

Do main VCS-independent setup function for installing Versioneer.

Git-specific installation logic for Versioneer. For Git, this means creating/changing .gitattributes to mark _version.py for export-subst key

Save all results to a csv file.

Encode a set of proposals with respect to some reference ground truth (gt) boxes. Args: gt_boxes: gt boxes, Nx4 or Nx6 torch tensor.

Utility to equalize input image based on the histogram. If `skimage` installed, will leverage `skimage.exposure.histogram`, otherwise, use

Erode 2D/3D binary mask with data type as torch tensor. Args: mask_t: input 2D/3D binary mask, [N,C,M,N] or [N,C,M,N,P] torch tensor

Evaluate the detection performance of a model based on the model probability map output, the ground truth tumor mask, and their assoc

Extracts the dataset fingerprint used for experiment planning. Args: fpe: [OPTIONAL] Name of the Dataset Fingerprint Ext

Fill the holes in the provided image. The label 0 will be treated as background and the enclosed holes will be set to the neighboring class

The configuration files defined when constructing this Algo instance might not have a complete training and validation pipelines. Som

Filter the patches and their locations according to a threshold. Args: image_np: a numpy.ndarray or torch.Tensor represe

Finalize the training or evaluation. Args: extra: Dict with additional information that can be provided by the FL system.

Recursively search all the content of input config item to get the ids of references. References mean: the IDs of other config items

Main forward method: Builds TRT engine if not available yet. Tries to run TRT engine If exception thrown and self.