Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Comparison of recognition results with conventional affinity and graph affinity method.

A: conventional affinity method. B: graph-based affinity methods.

More »

Fig 1 Expand

Fig 2.

Overview of the proposed weakly supervised semantic segmentation method.

More »

Fig 2 Expand

Table 1.

The annotated classification of the lung cavity size and quantity in a patient’s CT scan across three datasets. The “Class” column indicates the numerical index corresponding to each classification category.

More »

Table 1 Expand

Table 2.

Patient-level data distribution under 5-fold cross-validation.

For each dataset, a fixed test set is held out and excluded from cross-validation. Five-fold CV is performed only on the training pool at the patient level.

More »

Table 2 Expand

Table 3.

Statistical evaluation protocol for segmentation performance.

More »

Table 3 Expand

Fig 3.

Impact of parameter variations and module ablation on lung cavity segmentation under weak supervision.

More »

Fig 3 Expand

Table 4.

Design of ablation study modules with different loss components used in our weakly supervised method.

More »

Table 4 Expand

Table 5.

The contribution of various ablation components to the lung cavity semantic segmentation task in the proposed weakly supervised method.

More »

Table 5 Expand

Fig 4.

Performance of conventional affinity and our graph affinity method.

A: conventional affinity method. B: graph-based affinity methods.

More »

Fig 4 Expand

Fig 5.

Recognition results of class activation mapping for M-1 to M-5 ablation methods.

More »

Fig 5 Expand

Fig 6.

Training and validation losses of methods M-1 to M-5 and ROC curve performance for lung cavity attribute classification.

More »

Fig 6 Expand

Fig 7.

Confusion matrices for M-1 to M-5 ablation classification experiments.

More »

Fig 7 Expand

Table 6.

Benchmark configuration and fairness comparison across weakly supervised semantic segmentation methods.

All methods are re-trained under identical settings with a patch size of and optimized using AdamW.

More »

Table 6 Expand

Table 7.

Quantitative results of various 3D medical weakly supervised (lung cavity) semantic segmentation methods.

More »

Table 7 Expand

Fig 8.

Semantic segmentation results of lung cavities using various methods.

C1 - C7 sequentially represent the methods from [36], [19], [37], [15], [24], [38], and [39].

More »

Fig 8 Expand

Table 8.

Subgroup analysis by cavity size and quantity.

Average DSC (%) across different lesion subgroups.

More »

Table 8 Expand

Table 9.

Qualitative performance analysis by lesion location.

More »

Table 9 Expand

Table 10.

Subgroup analysis by cavity morphology.

More »

Table 10 Expand