HoVerNet

class HoVerNet(num_input_channels=3, num_types=None, mode='original')[source]

HoVer-Net Architecture.

Parameters

  • num_input_channels (int) – Number of channels in input.

  • num_types (int) – Number of nuclei types within the predictions. Once define, a branch dedicated for typing is created. By default, no typing (num_types=None) is used.

  • mode (str) – To use architecture defined in as in original paper (original) or the one used in PanNuke paper (fast).

References

Graham, Simon, et al. “Hover-net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images.” Medical Image Analysis 58 (2019): 101563.

Gamper, Jevgenij, et al. “PanNuke dataset extension, insights and baselines.” arXiv preprint arXiv:2003.10778 (2020).

Methods

forward

Logic for using layers defined in init.

infer_batch

Run inference on an input batch.

postproc

Post processing script for image tiles.

Attributes

forward(imgs)[source]

Logic for using layers defined in init.

This method defines how layers are used in forward operation.

Parameters

imgs (torch.Tensor) – Input images, the tensor is in the shape of NCHW.

Returns

A dictionary containing the inference output.

The expected format os {decoder_name: prediction}.

Return type

output (dict)

static infer_batch(model, batch_data, on_gpu)[source]

Run inference on an input batch.

This contains logic for forward operation as well as batch i/o aggregation.

Parameters

  • model (nn.Module) – PyTorch defined model.

  • batch_data (ndarray) – a batch of data generated by torch.utils.data.DataLoader.

  • on_gpu (bool) – Whether to run inference on a GPU.

Returns

List of output from each head, each head is expected to contain N predictions for N input patches. There are two cases, one with 2 heads (Nuclei Pixels np and Hover hv) or with 2 heads (np, hv, and Nuclei Types tp).

static postproc(raw_maps)[source]

Post processing script for image tiles.

Parameters

raw_maps (list(ndarray)) – list of prediction output of each head and assumed to be in the order of [np, hv, tp] (match with the output of infer_batch).

Returns

pixel-wise nuclear instance segmentation

prediction.

inst_dict (dict): a dictionary containing a mapping of each instance

within inst_map instance information. It has following form

inst_info = {

box: number[], centroids: number[], contour: number[][], type: number, prob: number,

} inst_dict = {[inst_uid: number] : inst_info}

and inst_uid is an integer corresponds to the instance having the same pixel value within inst_map.

Return type

inst_map (ndarray)

Examples

>>> from tiatoolbox.models.architecture.hovernet import HoVerNet
>>> import torch
>>> import numpy as np
>>> batch = torch.from_numpy(image_patch)[None]
>>> # image_patch is a 256x256x3 numpy array
>>> weights_path = "A/weights.pth"
>>> pretrained = torch.load(weights_path)
>>> model = HoVerNet(num_types=6, mode="fast")
>>> model.load_state_dict(pretrained)
>>> output = model.infer_batch(model, batch, on_gpu=False)
>>> output = [v[0] for v in output]
>>> output = model.postproc(output)