Statistics of a model. More...

#include <sb.h>

Collaboration diagram for sb_t_stat_model:

Data Fields
int	tp
	Count of True Positive. More...

int	tn
	Count of True Negative. More...

int	fp
	Count of False Positive. More...

int	fn
	Count of False Negative. More...

int	op
	Count of Optional Positive. More...

int	on
	Count of Optional Negative. More...

int	out_of_roi
	Count of Out Of ROI. More...

int	mod_disabled
	Count of samples with model disabled. More...

sb_t_range_flt	tp_weight
	Range of classification weight of the True Positive samples.

sb_t_range_flt	tn_weight
	Range of classification weight of the True Negative samples.

sb_t_range_flt	fp_weight
	Range of classification weight of the False Positive samples.

sb_t_range_flt	fn_weight
	Range of classification weight of the False Negative samples.

sb_t_range_flt	op_weight
	Range of classification weight of the Optional Positive samples.

sb_t_range_flt	on_weight
	Range of classification weight of the Optional Negative samples.

sb_t_range_flt	or_weight
	Range of classification weight of the out of the ROI samples.

sb_t_metrics	metrics
	Metrics. More...

float	score
	Level score. More...

Detailed Description

Statistics of a model.

Note: In multi-model case may happen that a FALSE NEGATIVE sample is associated with a FALSE POSITIVE sample. In this case the error weighs double in the statistics calculation.

See also: sb_t_stat.

Definition at line 12793 of file sb.h.

Field Documentation

◆ fn

int sb_t_stat_model::fn

Count of False Negative.

Retina, Deep Cortex: count of False Negative samples.
Surface, Deep Surface: count of False Negative blobs if blob analysis has been performed.
Deep Cortex: count of False Negative images.

Definition at line 12844 of file sb.h.

◆ fp

int sb_t_stat_model::fp

Count of False Positive.

Retina: count of False Positive samples.
Surface, Deep Surface: count of False Positive blobs if blob analysis has been performed.
Deep Cortex: count of False Positive images.

Definition at line 12834 of file sb.h.

◆ metrics

sb_t_metrics sb_t_stat_model::metrics

Metrics.

Metrics computed on counters

Definition at line 12893 of file sb.h.

◆ mod_disabled

int sb_t_stat_model::mod_disabled

Count of samples with model disabled.

Retina: count of samples with model disabled.
Deep Cortex, Surface, Deep Surface: not used.

Definition at line 12880 of file sb.h.

◆ on

int sb_t_stat_model::on

Count of Optional Negative.

Retina: count of Optional Negative samples.
Surface, Deep Surface: count of Optional Negative blobs if blob analysis has been performed.
Deep Cortex: not used.

Definition at line 12863 of file sb.h.

◆ op

int sb_t_stat_model::op

Count of Optional Positive.

Retina, Deep Cortex: count of Optional Positive samples.
Surface, Deep Surface: count of Optional Positive blobs if blob analysis has been performed.
Deep Cortex: not used.

Definition at line 12854 of file sb.h.

◆ out_of_roi

int sb_t_stat_model::out_of_roi

Count of Out Of ROI.

Retina: count of Out Of ROI samples.
Surface, Deep Surface: count of Out Of ROI blobs if blob analysis has been performed.
Deep Cortex: not used.

Definition at line 12872 of file sb.h.

◆ score

float sb_t_stat_model::score

Level score.

Score of the model on the processed level. It is computed only in SVL mode.
The range of the values is [0, 1]
Used only with Surface projects.

Definition at line 12901 of file sb.h.

◆ tn

int sb_t_stat_model::tn

Count of True Negative.

Retina: count of True Negative samples.
This parameter is used in different ways depending on whether the structure refers to global statistics or statistics per model. In particular in the case:
- global statistics: is incremented by 1 for each image that has no samples and no occurrences were found
- statistics per model, in this case there is a further difference depending on the value of the sb_t_par_model::num_occurrences parameter:
  - if = 0: it is always 0
  - if !=0: is increased by 1 for each sample with weight less than 0
Surface, Deep Surface: count of True Negative blobs if blob analysis has been performed.
Deep Cortex: count of True Negative images. This parameter is used in different ways depending on whether the structure refers to global statistics or statistics per model. In particular in the case:
- global statistics: is incremented by 1 for each image where all models have negative weight
- statistics per model: it is always equal to 0

Definition at line 12824 of file sb.h.

◆ tp

int sb_t_stat_model::tp

Count of True Positive.

Retina: count of True Positive samples.
Surface, Deep Surface: count of True Positive blobs if blob analysis has been performed.
Deep Cortex: count of True Positive images.

Definition at line 12803 of file sb.h.

The documentation for this struct was generated from the following file:

sb.h

Data Fields