LungEvaty: A Scalable, Open-Source Transformer-based Deep Learning Model for Lung Cancer Risk Prediction in LDCT Screening

TL;DR

LungEvaty is a scalable, open-source transformer model that predicts lung cancer risk from entire LDCT scans, leveraging large datasets without region annotations, and can be refined with anatomically informed attention.

Contribution

The paper introduces LungEvaty, a fully transformer-based framework that processes whole-lung LDCT scans for risk prediction, eliminating the need for pixel-level annotations and enabling scalable analysis.

Findings

Matches state-of-the-art performance

Trained on over 90,000 CT scans

Open-source and extensible framework

Abstract

Lung cancer risk estimation is gaining increasing importance as more countries introduce population-wide screening programs using low-dose CT (LDCT). As imaging volumes grow, scalable methods that can process entire lung volumes efficiently are essential to tap into the full potential of these large screening datasets. Existing approaches either over-rely on pixel-level annotations, limiting scalability, or analyze the lung in fragments, weakening performance. We present LungEvaty, a fully transformer-based framework for predicting 1-6 year lung cancer risk from a single LDCT scan. The model operates on whole-lung inputs, learning directly from large-scale screening data to capture comprehensive anatomical and pathological cues relevant for malignancy risk. Using only imaging data and no region supervision, LungEvaty matches state-of-the-art performance, refinable by an optional Anatomically Informed Attention Guidance (AIAG) loss that encourages anatomically focused attention. In total, LungEvaty was trained on more than 90,000 CT scans, including over 28,000 for fine-tuning and 6,000 for evaluation. The framework offers a simple, data-efficient, and fully open-source solution that provides an extensible foundation for future research in longitudinal and multimodal lung cancer risk prediction.