What does this research mean for the field?

The proposed XTC-Net model achieved 99.73% accuracy and 99.74% sensitivity in automated atelectasis detection from chest radiographs. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This research aims to develop an explainable hybrid model for detecting atelectasis in chest radiographs using deep learning techniques.

January 10, 2026Scientific Reports0 citationsOpen Access

XTC-Net: an explainable hybrid model for automated atelectasis detection from chest radiographs

RRReenu RajpootMaulana Azad National Institute of Technology SJSweta JainMaulana Azad National Institute of Technology VSVijay Bhaskar SemwalMaulana Azad National Institute of Technology

Key Result

The proposed XTC-Net model achieved 99.73% accuracy and 99.74% sensitivity in automated atelectasis detection from chest radiographs.

Key Points

This research aims to develop an explainable hybrid model for detecting atelectasis in chest radiographs using deep learning techniques.
Developed a hybrid model integrating Xception, Transformer, and Capsule Network components.
Employed a publicly accessible chest X-ray dataset for training and validation.
Conducted external validation using the NIH ChestX-ray dataset to assess generalizability.
Achieved 99.73% accuracy in detecting atelectasis.
Demonstrated 99.74% sensitivity and an F1 score of 99.73%.
Maintained consistent performance across different datasets, supporting clinical applicability.

Structured PICO

Does the XTC-Net hybrid deep learning model improve the automated detection of atelectasis from chest radiographs compared to existing models?

Population

Chest X-ray images from a publicly accessible dataset and the NIH ChestX-ray dataset for atelectasis detection

Intervention

XTC-Net (a three-stage hybrid deep learning model integrating Xception, Transformer, and Capsule Network components)

Comparator

Existing benchmark approaches (e.g., Xception, ResNet50, DenseNet169, VGG16, InceptionV3)

Outcome

Automated detection of atelectasis (measured by accuracy, sensitivity, and F1 score)surrogate

The XTC-Net hybrid deep learning model provides highly accurate and interpretable automated detection of atelectasis from chest radiographs.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

Atelectasis, characterized by partial or complete lung collapse, presents notable challenges in both diagnosis and treatment. Timely identification is essential to avoid further pulmonary complications and to facilitate early intervention. Leveraging artificial intelligence for the automated detection of atelectasis can significantly improve diagnostic efficiency, reduce clinical workload, and enhance patient care. This work presents an interpretable deep learning model that synergistically integrates Xception, Transformer, and Capsule Network components for the accurate detection of atelectasis from chest radiographs. The Xception module is employed to extract spatially rich features, while the Transformer component models long-range dependencies critical for understanding complex anatomical patterns. The Capsule Network further enhances the system's sensitivity to subtle structural variations associated with atelectatic regions. The training and validation of the model were conducted using a publicly accessible chest X-ray dataset, achieving impressive performance metrics: 99.73% accuracy, 99.74% sensitivity, and an F1 score of 99.73%. Furthermore, to evaluate the model's generalizability, external validation was performed using the NIH ChestX-ray dataset, which demonstrated consistent performance and highlighted the applicability of the proposed approach beyond the primary dataset. These results underscore the model's capability for reliable and interpretable automated diagnosis, supporting its future integration into clinical workflows.

Ask AI

Helpful

Bookmark

View Full Paper