What question did this study set out to answer?

The goal is to enhance the detection and segmentation of lung nodules in CT scans using a unified deep learning approach.

February 11, 2026Electronics0 citationsOpen Access

Multi-Task Deep Learning for Lung Nodule Detection and Segmentation in CT Scans

RLRunhan LiCentre for Life BABarmak Honarvar Shakibaei Asli

Key Points

The goal is to enhance the detection and segmentation of lung nodules in CT scans using a unified deep learning approach.
Developed a multi-task learning framework using Mask R-CNN architecture.
Implemented preprocessing steps like Hounsfield Unit normalization and lung parenchyma masking.
Introduced an auxiliary RoI classifier to boost detection sensitivity for ambiguous nodules.
Aggregated slice-wise predictions across the z-axis for comprehensive evaluation.
Achieved a favorable trade-off between detection and segmentation performance.
Demonstrated improvement in accuracy for small or ambiguous nodules.
Showcased the effectiveness of integrated MTL in advancing computer-aided diagnosis systems.

Abstract

The early detection of pulmonary nodules in chest CT scans is critical for improving lung cancer outcomes. While existing computer-aided diagnosis (CAD) systems have shown promise, most treat detection and segmentation as separate tasks, leading to fragmented pipelines and limited representation sharing. This study proposes a 2.5D multi-task learning (MTL) framework that integrates both tasks within a unified Mask R-CNN architecture. The framework incorporates a tailored preprocessing pipeline—including Hounsfield Unit (HU) normalisation, CLAHE enhancement, and lung parenchyma masking—to improve input consistency and task-relevant contrast characteristics. To enhance sensitivity for small or ambiguous nodules, an auxiliary RoI classifier is introduced. Additionally, a nodule-level evaluation strategy aggregates slice-wise predictions across the z-axis, supporting a clinically meaningful assessment that approximates 3D diagnostic workflows. Experiments on the LUNA16 dataset demonstrate that the proposed framework achieves a favourable trade-off between detection and segmentation performance under a unified 2.5D multi-task setting. These results highlight the potential of integrated MTL approaches to advance CAD systems for early lung cancer screening.

问 AI

Bookmark

View Full Paper