# ILD-Slider: A Parameter-Efficient Model for Identifying Progressive Fibrosing Interstitial Lung Disease from Chest CT Slices

## TL;DR

This paper introduces ILD-Slider, a deep learning model that efficiently identifies progressive fibrosing interstitial lung disease from limited chest CT slices, enabling earlier diagnosis.

## Contribution

The novel contribution is a parameter-efficient framework using anatomy-based position markers and a slice-level adapter for accurate PF-ILD detection with minimal CT slices.

## Key findings

- ILD-Slider achieves an AUPRC of 0.790 and AUROC of 0.847 using only five representative CT slices per case.
- The model maintains high diagnostic accuracy while significantly reducing computational costs by selecting non-contiguous representative slices.

## Abstract

Progressive Fibrosing Interstitial Lung Disease (PF-ILD) is a severe phenotype of Interstitial Lung Disease (ILD) with a poor prognosis, typically requiring prolonged clinical observation and multiple CT examinations for diagnosis. Such requirements delay early detection and treatment initiation. To enable earlier identification of PF-ILD, we propose ILD-Slider, a parameter-efficient and lightweight deep learning framework that enables accurate PF-ILD identification from a limited number of CT slices. ILD-Slider introduces anatomy-based position markers (PMs) to guide the selection of representative slices (RSs). A PM extractor, trained via a multi-class classification model, achieves high PM detection accuracy despite severe class imbalance by leveraging a peak slice mining (PSM)-based strategy. Using the PM extractor, we automatically select three, five, or nine RSs per case, substantially reducing computational cost while maintaining diagnostic accuracy. The selected RSs are then processed by a slice-level 3D Adapter (Slider) for PF-ILD identification. Experiments on 613 cases from The University of Osaka Hospital (UOH) and the National Hospital Organization Osaka Toneyama Medical Center (OTMC) demonstrate the effectiveness of ILD-Slider, achieving an AUPRC of 0.790 (AUROC 0.847) using only five automatically extracted RSs. ILD-Slider further validates the feasibility of diagnosing PF-ILD from non-contiguous slices, which is particularly valuable for real-world and public datasets where contiguous volumes are often unavailable. These results highlight ILD-Slider as a practical and efficient solution for early PF-ILD identification.