---
title: BTDNet Radiogenomic Classification
url: https://www.emergentmind.com/topics/btdnet
type: topic
---

# BTDNet Radiogenomic Classification

BTDNet is a multi-modal deep neural architecture for radiogenomic classification in brain tumor analysis, designed to address variable-length 3D MRI volume data and volume-level annotation. It leverages four complementary computational modules—advanced data augmentation, slice-wise 3D feature extraction via CNN-RNN, a routing/masking mechanism to handle input heterogeneity, and a late fusion scheme for multi-parametric MRI integration—providing state-of-the-art performance for prediction of MGMT promoter methylation status. BTDNet is distinct in its approach to both data-level and architectural challenges posed by multi-modal, volumetric medical imaging [2310.03485].

## 1. Architecture and Computational Components

BTDNet comprises four principal components:

**1. Data Augmentation:**  
Training and inference are both augmented at multiple levels. Random geometric transforms (slice-wise flips and rotations) as well as an “MixAugment” strategy (an extension of mixup) are used to generate convex combinations of volume-label pairs, facilitating virtual data synthesis. During inference, test-time augmentation (TTA) is employed by aggregating predictions across multiple transformed instances of each test case.

**2. 3D Analysis via CNN + RNN:**  
Each 3D MRI volume is processed as a sequence of 2D slices. A slice-wise 2D convolutional neural network (ResNet18, sans classifier) extracts per-slice features. These features feed into a uni-directional LSTM which encodes inter-slice dependencies, producing a sequence of hidden states per volume.

**3. Routing and Variable-Length Handling:**  
To accommodate variable slice counts, the RNN outputs are padded to a fixed maximum length and concatenated. A binary mask derived from the true (unpadded) length zeros out padded positions. This masked vector passes through a fully-connected block with batch normalization and GELU.

**4. Multi-Modal Fusion:**  
BTDNet employs four parallel CNN-RNN-routing pipelines for each MRI modality (FLAIR, T1w, T1wCE, T2), all sharing weights. The modality-specific 64-dimensional representations are concatenated (forming a 256-dimensional feature), embedded via a GELU-activated FC transform, and classified via softmax.

## 2. Mathematical Foundations

BTDNet's operations are precisely formulated as follows:

- **Slice-wise Geometric Transforms:**  
  $T(X) = \left(T_1(x_1), T_2(x_2), \dots, T_t(x_t)\right)$, with each $T_i$ randomly flipping or rotating $x_i$.

- **MixAugment:**  
Given two augmented volumes $T(X_i)$, $T(X_j)$, with labels $y_i$, $y_j$, and $\lambda \sim \mathrm{Beta}(\alpha, \alpha)$, construct  
$\tilde X = \lambda T(X_i) + (1-\lambda)T(X_j)$,  
$\tilde y = \lambda y_i + (1-\lambda)y_j$.

- **Test-Time Augmentation:**  
Aggregate logits  
$\text{logit}_{\mathrm{final}} = p^X + p^{F} + p^{R} + p^{FR}$  
from original, flipped, rotated, and combined augmented inputs.

- **2D CNN per slice:**  
For each layer $\ell$:  
$Y_\ell = \phi\left(W_\ell * X_{\ell-1} + b_\ell\right)$.

- **RNN with LSTM:**  
$h_t = \sigma(W_h f_t + U_h h_{t-1} + b_h)$  
across the $t$ slices.

- **Masking:**  
Concatenate $h_1, ..., h_{T_{\max}}$; mask with a binary vector $m$ indicating valid slices, then $F_\mathrm{mask} = M F_\mathrm{conc}$ (block-diagonal masking), and pass to  
$u = \mathrm{GELU}(\mathrm{BN}(W_d F_\mathrm{mask} + b_d))$.

- **Fusion:**  
Concatenate four modalities  
$U = [u^{\mathrm{FL}}, u^{\mathrm{T1}}, u^{\mathrm{T1CE}}, u^{\mathrm{T2}}]$,  
project to joint features  
$v = \mathrm{GELU}(W_f U + b_f)$,  
then classify  
$\hat{y} = \mathrm{softmax}(W_o v + b_o)$.

## 3. Training Protocol, Loss, and Optimization

- **Loss:**  
A multi-class focal loss is used,  
$\mathcal{L}_\mathrm{FL} = -\alpha (1-p)^\gamma \log p - (1-\alpha)p^\gamma\log(1-p)$,  
where $p$ denotes prediction probability. This is extended across both real and synthetic (MixAugment-generated) volumes,  
$\mathcal{L}_\mathrm{total} = \mathcal{L}_\mathrm{FL}(r_i) + \mathcal{L}_\mathrm{FL}(r_j) + \mathcal{L}_\mathrm{FL}(v)$.

- **Optimizer:**  
Stochastic gradient descent with momentum 0.9, enhanced by Sharpness-Aware Minimization (SAM), is applied. Learning rates are $10^{-4}$ for training each modality stream from scratch and $10^{-5}$ for fine-tuning multi-modal integration. No explicit weight decay is used, apart from BatchNorm [2310.03485].

- **Pre-processing:**  
Volumes are skull-stripped, cropped to the brain ROI, and void slices are discarded. Slices are resized to $224 \times 224 \times 3$ and intensity-normalized to $[-1,1]$. Padding to fixed slice count is modality-specific: FLAIR and T2 to 250 slices, T1w and T1wCE to 200 slices. Batch size is four due to resource constraints.

## 4. Performance and Benchmark Analysis

BTDNet was evaluated on the RSNA-ASNR-MICCAI BraTS 2021 radiogenomics challenge dataset. The primary evaluation metric is macro F1 score.

| Method                        | Macro F1 (%)      | F1 Spread   |
|-------------------------------|-------------------|-------------|
| BTDNet                        | $\mathbf{66.2}$   | $\pm3.1$    |
| 3D-ResNet10-Trick (SOTA)      | $62.9$            | $\pm4.8$    |
| EfficientNet-LSTM-mpMRI       | $47.4$            | $\pm4.4$    |
| Other baselines               | $42.9$–$46.1$     | —           |

BTDNet outperforms the best previously published method by 3.3 percentage points in mean macro F1 and demonstrates lower cross-fold variance [2310.03485].

## 5. Ablation Study and Component Contributions

Extensive ablation studies were performed to quantify the effect of architectural, modal, and augmentation choices:

- **CNN backbone:** ResNet18 (66.2% F1) is preferred over deeper or alternative architectures, which yield lower F1.
- **RNN variant/size:** LSTM(128) is optimal; both smaller and larger sizes or GRU alternatives show slightly lower scores.
- **Routing/Mask layer:** Removing routing drops F1 to 60.9%, demonstrating the importance of explicit variable-length handling.
- **Modalities:** Single-modality models (FLAIR, T2, T1CE, T1) perform 1–3% worse than full four-modality fusion, confirming the utility of joint multimodal representation.
- **Data augmentation:** Removal of TTA (−1.0 F1), geometric transforms (−0.9), or MixAugment (−1.5) diminishes performance.
- **Loss:** Focal loss is superior (66.2%) compared to categorical (64.9%) or binary (64.5%) cross-entropy.

A plausible implication is that each architectural and data-centric intervention contributes additively to overall model robustness and generalization, with explicit handling of variable-length data and multi-modality being especially critical.

## 6. Implementation and Training Details

- **CNN configuration:** ResNet18, outputs 512-dim features per slice.
- **RNN:** Uni-directional LSTM, 128 units.
- **Routing dense:** 64 units, BatchNorm and GELU.
- **Fusion dense:** 128 units, GELU.
- **Batch protocol:** Padding per volume, batch size 4.
- **Training protocol:** Two-phase; independent pretraining of modality-specific streams, followed by multimodal fine-tuning. No regularizer other than BatchNorm is applied.

Preprocessing and network configuration are matched to the requirements of volumetric clinical MRI, maintaining strict separation between modalities until late fusion.

## 7. Significance and Distinctions

BTDNet demonstrates that aggressive, multi-granular data augmentation, explicit sequence modeling of slices, variable-length routing, and rigorous multi-modal integration significantly improve MGMT methylation prediction from MRI. Distinct from conventional architectures, BTDNet provides a robust template for handling variable-length, multi-volume, and weakly annotated medical imaging tasks [2310.03485]. Its modular design, coupled with rigorous benchmarking and ablation, underlines its practical and methodological significance for radiogenomic classification.

Source: https://www.emergentmind.com/topics/btdnet