Loss functions¶

Segmentation Losses¶

DiceLoss¶

class monai.losses.DiceLoss(include_background=True, to_onehot_y=False, sigmoid=False, softmax=False, other_act=None, squared_pred=False, jaccard=False, reduction=<LossReduction.MEAN: 'mean'>)[source]¶

Compute average Dice loss between two tensors. It can support both multi-classes and multi-labels tasks. Input logits input (BNHW[D] where N is number of classes) is compared with ground truth target (BNHW[D]). Axis N of input is expected to have logit predictions for each class rather than being image channels, while the same axis of target can be 1 or N (one-hot format). The smooth parameter is a value added to the intersection and union components of the inter-over-union calculation to smooth results and prevent divide by 0, this value should be small. The include_background class attribute can be set to False for an instance of DiceLoss to exclude the first category (channel index 0) which is by convention assumed to be background. If the non-background segmentations are small compared to the total image size they can get overwhelmed by the signal from the background so excluding it in such cases helps convergence.

Milletari, F. et. al. (2016) V-Net: Fully Convolutional Neural Networks forVolumetric Medical Image Segmentation, 3DV, 2016.

Parameters

include_background (bool) – if False channel index 0 (background category) is excluded from the calculation.
to_onehot_y (bool) – whether to convert y into the one-hot format. Defaults to False.
sigmoid (bool) – if True, apply a sigmoid function to the prediction.
softmax (bool) – if True, apply a softmax function to the prediction.
other_act (Optional[Callable]) – if don’t want to use sigmoid or softmax, use other callable function to execute other activation layers, Defaults to None. for example: other_act = torch.tanh.
squared_pred (bool) – use squared versions of targets and predictions in the denominator or not.
jaccard (bool) – compute Jaccard Index (soft IoU) instead of dice or not.
reduction (Union[LossReduction, str]) –
{"none", "mean", "sum"} Specifies the reduction to apply to the output. Defaults to "mean".
- "none": no reduction will be applied.
- "mean": the sum of the output will be divided by the number of elements in the output.
- "sum": the output will be summed.

Raises

TypeError – When other_act is not an Optional[Callable].
ValueError – When more than 1 of [sigmoid=True, softmax=True, other_act is not None]. Incompatible values.

forward(input, target, smooth=1e-05)[source]¶

Parameters

input (Tensor) – the shape should be BNH[WD].
target (Tensor) – the shape should be BNH[WD].
smooth (float) – a small constant to avoid nan.

Raises

ValueError – When self.reduction is not one of [“mean”, “sum”, “none”].

Return type

Tensor

monai.losses.Dice¶: alias of monai.losses.dice.DiceLoss

monai.losses.dice¶: alias of monai.losses.dice.DiceLoss

MaskedDiceLoss¶

class monai.losses.MaskedDiceLoss(include_background=True, to_onehot_y=False, sigmoid=False, softmax=False, other_act=None, squared_pred=False, jaccard=False, reduction=<LossReduction.MEAN: 'mean'>)[source]¶

Add an additional masking process before DiceLoss, accept a binary mask ([0, 1]) indicating a region, input and target will be masked by the region: region with mask 1 will keep the original value, region with 0 mask will be converted to 0. Then feed input and target to normal DiceLoss computation. This has the effect of ensuring only the masked region contributes to the loss computation and hence gradient calculation.

Parameters

include_background (bool) – if False channel index 0 (background category) is excluded from the calculation.
to_onehot_y (bool) – whether to convert y into the one-hot format. Defaults to False.
sigmoid (bool) – if True, apply a sigmoid function to the prediction.
softmax (bool) – if True, apply a softmax function to the prediction.
other_act (Optional[Callable]) – if don’t want to use sigmoid or softmax, use other callable function to execute other activation layers, Defaults to None. for example: other_act = torch.tanh.
squared_pred (bool) – use squared versions of targets and predictions in the denominator or not.
jaccard (bool) – compute Jaccard Index (soft IoU) instead of dice or not.
reduction (Union[LossReduction, str]) –
{"none", "mean", "sum"} Specifies the reduction to apply to the output. Defaults to "mean".
- "none": no reduction will be applied.
- "mean": the sum of the output will be divided by the number of elements in the output.
- "sum": the output will be summed.

Raises

TypeError – When other_act is not an Optional[Callable].
ValueError – When more than 1 of [sigmoid=True, softmax=True, other_act is not None]. Incompatible values.

forward(input, target, smooth=1e-05, mask=None)[source]¶

Parameters

input (Tensor) – the shape should be BNH[WD].
target (Tensor) – the shape should be BNH[WD].
smooth (float) – a small constant to avoid nan.
mask (Optional[Tensor]) – the shape should B1H[WD] or 11H[WD].

GeneralizedDiceLoss¶

class monai.losses.GeneralizedDiceLoss(include_background=True, to_onehot_y=False, sigmoid=False, softmax=False, other_act=None, w_type=<Weight.SQUARE: 'square'>, reduction=<LossReduction.MEAN: 'mean'>)[source]¶

Compute the generalised Dice loss defined in:

Sudre, C. et. al. (2017) Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations. DLMIA 2017.

Adapted from:: https://github.com/NifTK/NiftyNet/blob/v0.6.0/niftynet/layer/loss_segmentation.py#L279

Parameters

include_background (bool) – If False channel index 0 (background category) is excluded from the calculation.
to_onehot_y (bool) – whether to convert y into the one-hot format. Defaults to False.
sigmoid (bool) – If True, apply a sigmoid function to the prediction.
softmax (bool) – If True, apply a softmax function to the prediction.
other_act (Optional[Callable]) – if don’t want to use sigmoid or softmax, use other callable function to execute other activation layers, Defaults to None. for example: other_act = torch.tanh.
squared_pred – use squared versions of targets and predictions in the denominator or not.
w_type (Union[Weight, str]) – {"square", "simple", "uniform"} Type of function to transform ground truth volume to a weight factor. Defaults to "square".
reduction (Union[LossReduction, str]) –
{"none", "mean", "sum"} Specifies the reduction to apply to the output. Defaults to "mean".
- "none": no reduction will be applied.
- "mean": the sum of the output will be divided by the number of elements in the output.
- "sum": the output will be summed.

Raises

TypeError – When other_act is not an Optional[Callable].
ValueError – When more than 1 of [sigmoid=True, softmax=True, other_act is not None]. Incompatible values.

forward(input, target, smooth=1e-05)[source]¶

Parameters

input (Tensor) – the shape should be BNH[WD].
target (Tensor) – the shape should be BNH[WD].
smooth (float) – a small constant to avoid nan.

Raises

ValueError – When self.reduction is not one of [“mean”, “sum”, “none”].

monai.losses.generalized_dice¶: alias of monai.losses.dice.GeneralizedDiceLoss

FocalLoss¶

class monai.losses.FocalLoss(gamma=2.0, weight=None, reduction=<LossReduction.MEAN: 'mean'>)[source]¶

Reimplementation of the Focal Loss described in:

“Focal Loss for Dense Object Detection”, T. Lin et al., ICCV 2017

“AnatomyNet: Deep learning for fast and fully automated whole‐volume segmentation of head and neck anatomy”, Zhu et al., Medical Physics 2018

Parameters

gamma (float) – value of the exponent gamma in the definition of the Focal loss.
weight (Optional[Tensor]) – weights to apply to the voxels of each class. If None no weights are applied. This corresponds to the weights lpha in [1].
reduction (Union[LossReduction, str]) –
{"none", "mean", "sum"} Specifies the reduction to apply to the output. Defaults to "mean".
- "none": no reduction will be applied.
- "mean": the sum of the output will be divided by the number of elements in the output.
- "sum": the output will be summed.

Example

import torch
from monai.losses import FocalLoss

pred = torch.tensor([[1, 0], [0, 1], [1, 0]], dtype=torch.float32)
grnd = torch.tensor([[0], [1], [0]], dtype=torch.int64)
fl = FocalLoss()
fl(pred, grnd)

forward(input, target)[source]¶

Parameters

input (Tensor) – the shape should be BCH[WD]. where C is the number of classes.
target (Tensor) – the shape should be B1H[WD] or BCH[WD]. If the target’s shape is B1H[WD], the target that this loss expects should be a class index in the range [0, C-1] where C is the number of classes.

Raises

ValueError – When target ndim differs from input.
ValueError – When target channel is not 1 and target shape differs from input.
ValueError – When self.reduction is not one of [“mean”, “sum”, “none”].

Return type

Tensor

TverskyLoss¶

class monai.losses.TverskyLoss(include_background=True, to_onehot_y=False, sigmoid=False, softmax=False, other_act=None, alpha=0.5, beta=0.5, reduction=<LossReduction.MEAN: 'mean'>)[source]¶

Compute the Tversky loss defined in:

Sadegh et al. (2017) Tversky loss function for image segmentation using 3D fully convolutional deep networks. (https://arxiv.org/abs/1706.05721)

Adapted from:: https://github.com/NifTK/NiftyNet/blob/v0.6.0/niftynet/layer/loss_segmentation.py#L631

Parameters

include_background (bool) – If False channel index 0 (background category) is excluded from the calculation.
to_onehot_y (bool) – whether to convert y into the one-hot format. Defaults to False.
sigmoid (bool) – If True, apply a sigmoid function to the prediction.
softmax (bool) – If True, apply a softmax function to the prediction.
other_act (Optional[Callable]) – if don’t want to use sigmoid or softmax, use other callable function to execute other activation layers, Defaults to None. for example: other_act = torch.tanh.
alpha (float) – weight of false positives
beta (float) – weight of false negatives
reduction (Union[LossReduction, str]) –
{"none", "mean", "sum"} Specifies the reduction to apply to the output. Defaults to "mean".
- "none": no reduction will be applied.
- "mean": the sum of the output will be divided by the number of elements in the output.
- "sum": the output will be summed.

Raises

TypeError – When other_act is not an Optional[Callable].
ValueError – When more than 1 of [sigmoid=True, softmax=True, other_act is not None]. Incompatible values.

forward(input, target, smooth=1e-05)[source]¶

Parameters

input (Tensor) – the shape should be BNH[WD].
target (Tensor) – the shape should be BNH[WD].
smooth (float) – a small constant to avoid nan.

Raises

ValueError – When self.reduction is not one of [“mean”, “sum”, “none”].

Return type

Tensor