Related Experiment Video
Updated: Jun 14, 2026
14:08
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
42.5K
Non-contrasted computed tomography (NCCT) based chronic thromboembolic pulmonary hypertension (CTEPH) automatic
Mayang Zhao1, Liming Song1, Jiarui Zhu1
1Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong Special Administrative Region of China, People's Republic of China.
Physics in Medicine and Biology
|August 27, 2024
Summary
A new AI model automatically diagnoses chronic thromboembolic pulmonary hypertension (CTEPH) using non-contrast CT scans. This method improves early detection and patient outcomes without needing extra scans or annotations.
Area of Science:
- Artificial Intelligence in Medical Imaging
- Radiology and Diagnostic Imaging
- Cardiovascular and Pulmonary Diseases
Background:
- Chronic thromboembolic pulmonary hypertension (CTEPH) diagnosis is challenging due to subtle symptoms and complex imaging requirements.
- Current diagnostic methods for CTEPH can be invasive or require contrast agents, increasing patient burden and cost.
- Automated diagnostic tools are needed to improve the efficiency and accuracy of CTEPH detection.
Purpose of the Study:
- To develop an automated diagnostic method for CTEPH using non-contrast computed tomography (NCCT) scans.
- To enable accurate CTEPH diagnosis without the need for precise lesion annotation.
- To improve the timeliness and accuracy of CTEPH detection for better patient outcomes.
Main Methods:
- A novel cascade network (CN) with multiple instance learning (CNMIL) framework was developed, integrating two Resnet-18 CNNs.
- Multiple instance learning (MIL) treated each 3D CT case as a 'bag' of slices, using attention to identify diagnostically relevant regions.
- The CNMIL framework was trained and evaluated on NCCT scans from 300 subjects (132 normal, 168 lung disease including 88 CTEPH).
Main Results:
- The CNMIL framework achieved a high diagnostic performance for CTEPH detection with an AUC of 0.807, accuracy of 0.833, sensitivity of 0.795, and specificity of 0.849.
- Ablation studies showed significant performance enhancement with MIL and CN integration, achieving an AUC of 0.978 and perfect sensitivity (1.000) for normal classification.
- The integrated CNMIL model outperformed other 3D network architectures, achieving the highest AUC of 0.8419 in comparative analysis.
Conclusions:
- The CNMIL network offers a non-invasive, annotation-free method for CTEPH diagnosis solely based on NCCT scans.
- This automated approach has the potential to significantly improve early and accurate detection of CTEPH.
- The developed method can lead to improved patient management and clinical outcomes for individuals with CTEPH.
Related Concept Videos
01:10Computed Tomography
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
01:28Imaging Studies for Cardiovascular System V: CT
Cardiac computed tomography (CT) scanning is an advanced cardiac imaging technique that utilizes CT technology, with or without intravenous (IV) contrast, to produce accurate cross-sectional virtual slices of specific areas of the heart, coronary circulation, and major blood vessels such as the aorta, pulmonary veins, and arteries. The computer processes these slices to generate three-dimensional images. Multidetector CT (MDCT) is a rapid form of CT scanning that captures multiple slices...
01:29Pulmonary Embolism II: Diagnostic Studies and Interprofessional Care
Diagnosing Pulmonary EmbolismDiagnosing pulmonary embolism (PE) involves clinical assessment and advanced imaging tests. The preferred diagnostic tool is the spiral (helical) CT scan or CT angiography (CTA), which uses intravenous contrast media to visualize the pulmonary vasculature and identify emboli.A ventilation-perfusion (V/Q) scan is an alternative for patients unable to receive contrast media. This scan includes both perfusion and ventilation scanning. Perfusion scanning involves...