An Intelligent Detection System for Pulmonary Nodules in Medical CT Images based on Deep Learning with a Voice Prompt System

Lung cancer is one of the malignant tumors with the highest mortality rate globally, and its high mortality is closely related to late-stage diagnosis. Low-dose computed tomography (LDCT) has been confirmed as an effective screening method to reduce lung cancer mortality in high-risk populations, but it significantly increases the workload and diagnostic pressure on radiologists. To address this challenge, this paper proposes and implements an integrated intelligent diagnostic system. The system combines a high-performance, two-stage deep learning model for the automated detection of pulmonary nodules and innovatively integrates a voice prompt module aimed at optimizing the workflow of radiologists and improving human-computer interaction efficiency. The detection model proposed in this paper adopts a 3D context-aware network architecture and includes a dedicated false-positive reduction module to enhance clinical utility. The main contributions of this study are: 1) designing and validating a high-precision pulmonary nodule detection model; and 2) exploring a novel paradigm for AI-assisted diagnostic interaction by introducing a voice prompt system, which aims to improve diagnostic efficiency and accuracy, providing new insights for the clinical translation of intelligent medical image analysis.