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

Table 1.

Summary of the TCIA BREAST-DIAGNOSIS dataset characteristics.

More »

Table 1 Expand

Fig 1.

Collection of breast MRI scans, categorized into Benign and Malignant cases.

More »

Fig 1 Expand

Fig 2.

AIN Development Process - Sequential four-step development of Adaptive Involution Network for breast MRI tumor classification: introducing SAIL layers, integrating CWAM mechanisms, combining with CNN architecture, and achieving final AIN model.

More »

Fig 2 Expand

Fig 3.

SAIL Architecture Overview - Diagram showing the key components of Spatially-Adaptive Involution Layers, including adaptive kernel generation, spatial feature unfolding, involution operations, channel projection, and parallel convolution across multi-scale feature maps.

More »

Fig 3 Expand

Fig 4.

CWAM Three-Step Process - Channel-Wise Attention Mechanism showing global context aggregation, channel dependency modeling through bottleneck transformation, and feature recalibration with attention weights.

More »

Fig 4 Expand

Fig 5.

Adaptive Residual Block Flow - Circular process showing ARB components: feature extraction through SAIL/convolutions, batch normalization, ReLU activation, dropout regularization, additional convolution, CWAM recalibration, and shortcut connection.

More »

Fig 5 Expand

Fig 6.

AIN Sequential Architecture - Gear-based diagram showing AIN processing stages from feature extraction stem through four ARB stages (SAIL-based stages 1-2, convolution-based stages 3-4), global average pooling, to classification head.

More »

Fig 6 Expand

Table 2.

Complete list of training hyperparameters used for the proposed AIN model.

More »

Table 2 Expand

Fig 7.

Training and Validation History - Folds 1-3 - Performance plots showing model accuracy and loss progression over training epochs for each fold during cross-validation.

More »

Fig 7 Expand

Fig 8.

Training and Validation History - Folds 4-5 and Overall Performance - Performance plots showing model accuracy and loss progression over training epochs for the remaining cross-validation folds plus overall performance summary.

More »

Fig 8 Expand

Table 3.

Classification report summary.

More »

Table 3 Expand

Table 4.

Summary of classification metrics across five folds.

More »

Table 4 Expand

Fig 9.

Detailed confusion matrices for breast cancer classification showing individual fold performance (a-e) and aggregated results across all folds (f), demonstrating model consistency and overall classification accuracy.

More »

Fig 9 Expand

Fig 10.

Calibration curves illustrating the reliability of predicted probabilities for different models within a five-fold cross-validation framework.

Subfigures (a)–(e) show individual fold results, while (f) presents the overall calibration.

More »

Fig 10 Expand

Table 5.

Ablation study on the contribution of SAIL, CWAM (SE), and the hybrid layering strategy.

All models are trained for a maximum of 50 epochs with early stopping (patience = 15).

More »

Table 5 Expand

Fig 11.

Qualitative analysis of model predictions.

More »

Fig 11 Expand

Table 6.

Performance comparison of AdaptiveInvolutionNet with state-of-the-art methods for breast cancer classification.

More »

Table 6 Expand