Vision metrics

---

source

calculate_dsc

 calculate_dsc (pred:torch.Tensor, targ:torch.Tensor)

MONAI compute_meandice

---

source

calculate_haus

 calculate_haus (pred:torch.Tensor, targ:torch.Tensor)

Compute 95th percentile Hausdorff distance (HD95) using MONAI.

HD95 is more robust than standard Hausdorff distance as it ignores the top 5% of outlier distances.

Args: pred: Binary prediction tensor [B, C, W, H, D]. targ: Binary target tensor [B, C, W, H, D].

Returns: HD95 values for each sample in batch.

---

source

binary_dice_score

 binary_dice_score (act:<built-
                    inmethodtensoroftypeobjectat0x7f0db213ecc0>,
                    targ:torch.Tensor)

Calculates the mean Dice score for binary semantic segmentation tasks.

Args: act: Activation tensor with dimensions [B, C, W, H, D]. targ: Target masks with dimensions [B, C, W, H, D].

Returns: Mean Dice score.

---

source

multi_dice_score

 multi_dice_score (act:torch.Tensor, targ:torch.Tensor)

Calculate the mean Dice score for each class in multi-class semantic segmentation tasks.

Args: act: Activation tensor with dimensions [B, C, W, H, D]. targ: Target masks with dimensions [B, C, W, H, D].

Returns: Mean Dice score for each class.

---

source

binary_hausdorff_distance

 binary_hausdorff_distance (act:torch.Tensor, targ:torch.Tensor)

Calculate the mean HD95 for binary semantic segmentation tasks.

Args: act: Activation tensor with dimensions [B, C, W, H, D]. targ: Target masks with dimensions [B, C, W, H, D].

Returns: Mean HD95.

---

source

multi_hausdorff_distance

 multi_hausdorff_distance (act:torch.Tensor, targ:torch.Tensor)

Calculate the mean HD95 for each class in multi-class semantic segmentation tasks.

Args: act: Activation tensor with dimensions [B, C, W, H, D]. targ: Target masks with dimensions [B, C, W, H, D].

Returns: Mean HD95 for each class.

Sensitivity and Precision

---

source

calculate_confusion_metrics

 calculate_confusion_metrics (pred:torch.Tensor, targ:torch.Tensor,
                              metric_name:str)

Calculate confusion matrix-based metric using MONAI.

Args: pred: Binary prediction tensor [B, C, W, H, D]. targ: Binary target tensor [B, C, W, H, D]. metric_name: One of “sensitivity”, “precision”, “specificity”, “f1 score”.

Returns: Metric values for each sample in batch.

---

source

binary_sensitivity

 binary_sensitivity (act:torch.Tensor, targ:torch.Tensor)

Calculate mean sensitivity (recall) for binary segmentation.

Sensitivity = TP / (TP + FN) - measures the proportion of actual positives that are correctly identified.

Args: act: Activation tensor [B, C, W, H, D]. targ: Target masks [B, C, W, H, D].

Returns: Mean sensitivity score.

---

source

multi_sensitivity

 multi_sensitivity (act:torch.Tensor, targ:torch.Tensor)

Calculate mean sensitivity for each class in multi-class segmentation.

Args: act: Activation tensor [B, C, W, H, D]. targ: Target masks [B, C, W, H, D].

Returns: Mean sensitivity for each class.

---

source

binary_precision

 binary_precision (act:torch.Tensor, targ:torch.Tensor)

Calculate mean precision for binary segmentation.

Precision = TP / (TP + FP) - measures the proportion of positive predictions that are actually correct.

Args: act: Activation tensor [B, C, W, H, D]. targ: Target masks [B, C, W, H, D].

Returns: Mean precision score.

---

source

multi_precision

 multi_precision (act:torch.Tensor, targ:torch.Tensor)

Calculate mean precision for each class in multi-class segmentation.

Args: act: Activation tensor [B, C, W, H, D]. targ: Target masks [B, C, W, H, D].

Returns: Mean precision for each class.

Lesion Detection Rate

---

source

calculate_lesion_detection_rate

 calculate_lesion_detection_rate (pred:torch.Tensor, targ:torch.Tensor)

Calculate lesion-wise detection rate.

For each connected component (lesion) in the target, check if there is any overlap with the prediction. A lesion is considered detected if at least one voxel overlaps.

Args: pred: Binary prediction tensor [B, C, W, H, D]. targ: Binary target tensor [B, C, W, H, D].

Returns: Detection rate (detected lesions / total lesions) for each sample.

---

source

binary_lesion_detection_rate

 binary_lesion_detection_rate (act:torch.Tensor, targ:torch.Tensor)

Calculate mean lesion detection rate for binary segmentation.

Args: act: Activation tensor [B, C, W, H, D]. targ: Target masks [B, C, W, H, D].

Returns: Mean lesion detection rate.

---

source

multi_lesion_detection_rate

 multi_lesion_detection_rate (act:torch.Tensor, targ:torch.Tensor)

Calculate mean lesion detection rate for each class in multi-class segmentation.

Args: act: Activation tensor [B, C, W, H, D]. targ: Target masks [B, C, W, H, D].

Returns: Mean lesion detection rate for each class.

Signed Relative Volume Error (RVE)

---

source

calculate_signed_rve

 calculate_signed_rve (pred:torch.Tensor, targ:torch.Tensor)

Calculate signed Relative Volume Error.

RVE = (pred_volume - targ_volume) / targ_volume

Positive values indicate over-segmentation (model predicts too large), negative values indicate under-segmentation (model predicts too small).

Args: pred: Binary prediction tensor [B, C, W, H, D]. targ: Binary target tensor [B, C, W, H, D].

Returns: Signed RVE for each sample in batch.

---

source

binary_signed_rve

 binary_signed_rve (act:torch.Tensor, targ:torch.Tensor)

Calculate mean signed RVE for binary segmentation.

Args: act: Activation tensor [B, C, W, H, D]. targ: Target masks [B, C, W, H, D].

Returns: Mean signed RVE.

---

source

multi_signed_rve

 multi_signed_rve (act:torch.Tensor, targ:torch.Tensor)

Calculate mean signed RVE for each class in multi-class segmentation.

Args: act: Activation tensor [B, C, W, H, D]. targ: Target masks [B, C, W, H, D].

Returns: Mean signed RVE for each class.