ADALORA-QAT

Model Card for AdaLoRA-QAT

AdaLoRA-QAT is an efficient, compact foundation model variant designed for accurate chest X-ray (CXR) lung segmentation. It adapts the Segment Anything Model (SAM) to meet strict clinical computational constraints by combining adaptive low-rank parameter fine-tuning with quantization-aware training.

Model Details

Model Description

AdaLoRA-QAT introduces a two-stage fine-tuning framework for medical image segmentation. Stage 1 utilizes Adaptive Low-Rank Adaptation (AdaLoRA) to dynamically allocate rank capacity to task-relevant transformer layers in full precision. Stage 2 implements full-model quantization-aware fine-tuning (QAT) using a selective mixed-precision strategy, achieving INT8 precision for select layers while preserving fine structural fidelity.

Model Sources

• Repository: https://github.com/prantik-pdeb/ADALORA-QAT
• Project Page: https://prantik-pdeb.github.io/adaloraqat.github.io/
• Paper: AdaLoRA-QAT: Adaptive Low-Rank and Quantization-Aware Segmentation

Uses

Direct Use

• Accurate lung field segmentation for isolating pulmonary parenchyma.
• Enhancing abnormality visibility and enabling quantitative analysis in chest radiographs.
• Improving the reliability of computer-aided diagnosis (CAD) systems.
• Enabling deployable foundation models on resource-constrained clinical hardware.

Sample Usage

To run inference using the provided scripts in the repository:

python -u inference/inference.py \
--image_path sample_data/images/C19RD_COVID-29.png \
--checkpoint_path "best_model_stage2_int8.pth" \
--bbox 0 0 511 511 --save_mask --visualize \
--output_mask_path ./inf_res.png \
--save_overlay ./overlay

Training Details

Training Data

• The model was trained on 64,590 chest X-rays spanning diverse thoracic pathologies.
• The data sources include JSRT, QaTa-COV19, COVID-19 Radiography, Chest X-Ray Pneumothorax, and COVID-QU-Ex datasets.

Speeds, Sizes, Times

• The model yields a 2.24x model compression compared to base-SAM fine-tuning.
• Trainable parameters are reduced by 16.6x, down to 5.4M.

Evaluation

Testing Data, Factors & Metrics

Testing Data

• The 64,590 CXR dataset was divided using an 80:10:10 split for experiments.

Metrics

• Dice Score (DSC).
• Intersection over Union (IOU).
• Normalized Surface Distance (NSD).
• Structural Similarity Index (SSIM).
• Wilcoxon signed-rank test for statistical significance assessment.

Results

• AdaLoRA-QAT achieves a 95.6% Dice score.
• The model matches full-precision SAM decoder fine-tuning accuracy.
• Statistical analysis confirms that full INT8 quantization preserves segmentation accuracy without significant degradation.
• SSIM analysis exhibits strong structural agreement along lung boundaries and vascular regions.

Model Examination

• Quantization error analysis shows that FP32-INT8 quantization noise follows an approximately zero-mean Gaussian distribution.
• There is a strong linear correlation between FP32 and INT8 weights.
• Errors are uniformly distributed across weight magnitudes, confirming preserved numerical fidelity under low-bit quantization.

Hardware

• NVIDIA RTX A6000 GPUs (48 GB).

Citation

@inproceedings{deb2026adalora,
  title={ADALORA-QAT: Adaptive Low Rank and Quantization Aware Segmentation},
  author={Deb, Prantik and Dhondy, Srimanth and Ramakrishna, N and Kapoor, Anu and Bapi, Raju S and Chakraborti, Tapabrata},
  booktitle={2026 IEEE 23rd International Symposium on Biomedical Imaging (ISBI)},
  pages={1--4},
  year={2026},
  organization={IEEE}
}

Model Card Authors

Prantik Deb, Srimanth Dhondy, N. Ramakrishna, Anu Kapoor, Raju S. Bapi, Tapabrata Chakraborti.