Key Research Publications Featuring AVIEW in 2024

In 2024, Coreline Soft’s AI-powered imaging analysis solution, AVIEW, received increased attention across the global medical research community. With 108 published studies citing AVIEW—up significantly from 80 in 2023—the solution has shown consistent validation in areas such as lung cancer screening, coronary artery calcium scoring, emphysema analysis, and metastasis detection using CT scans.

The following five research highlights showcase AVIEW’s clinical utility, diagnostic accuracy, and its growing role as a trusted AI software in radiology workflows.

Feasibility of AI as First Reader in the 4-IN-THE-LUNG-RUN Lung Cancer Screening Trial: Impact on Negative-Misclassifications and Clinical Referral Rate

This study assessed AVIEW-LCS as a First Reader in a large-scale lung cancer screening initiative. Among 3,678 participants, AVIEW recorded only 0.8% false negatives (31 cases) compared to 11.1% (407 cases) by radiologists.

Furthermore, the clinical referral rate due to false negatives (* NM referral) was 2.9% for AVIEW versus 11.8% for radiologists.
While AVIEW showed a slightly higher false positive rate (5.7% vs. 0.5%), the overall reduction in workload was estimated at 71.2%, highlighting AVIEW’s potential to optimize radiology workflows while maintaining diagnostic safety.

* NM: False negative classification on first reading
* NM Referrel: False negative classification on final reading

Coronary calcium score and emphysema extent on different CT radiation dose protocols in lung cancer screening

This study explored AVIEW’s performance in quantifying coronary artery calcium (CAC) and emphysema in both low-dose (LDCT) and ultra-low-dose CT (ULDCT) scans during lung cancer screening.

With 361 participants, AVIEW showed strong agreement for CAC quantification between LDCT and ULDCT (ICC = 0.86, 84% overlap).
In contrast, emphysema analysis had a moderate agreement level (ICC = 0.57), with ULDCT tending to overestimate. The findings support the use of ULDCT with AVIEW for cardiovascular evaluation in lung cancer screening contexts.

Comparison of AI software tools for automated detection, quantification and categorization of pulmonary nodules in the HANSE LCS trial

This comparative study analyzed AVIEW (Coreline Soft, Korea) and ChestCTExplore (Siemens Healthineers, Germany) in a cohort of 946 LDCT scans from the HANSE LCS program.

Both tools showed a high correlation (r > 0.95) in measuring nodule volumes. However, AVIEW (S1) outperformed its counterpart (S2) in sensitivity, PPV, and agreement with radiologists’ readings.
Notably, AVIEW showed 75% agreement in Lung-RADS categorization, compared to 55% by the Siemens tool, and in 38% of cases, AI-driven scores diverged, indicating the potential impact on patient management decisions. The study emphasizes the importance of consistency and expert oversight in AI-supported screening.

Artificial intelligence system for identification of overlooked lung metastasis in abdominopelvic computed tomography scans of patients with malignancy

This study evaluated AVIEW as a Second Reader to identify missed pulmonary metastases in abdominal CT scans. AVIEW achieved an AUC of 0.911 and sensitivity up to 92.3%.

Although the initial false positive rate was 27.6%, it was reduced to as low as 2.4%–12.6% upon radiographer reassessment.
The study highlights AVIEW’s value in reducing diagnostic errors and minimizing unnecessary review cycles, especially in oncology follow-ups.

 

Development and multi-institutional validation of estimating forced vital capacity in pulmonary fibrosis using quantitative chest CT data

Presented at RSNA 2024, this multi-institutional study led by Coreline Soft's Clinical Research Lead, Ryoungwoo Jang, introduced a model to estimate forced vital capacity (FVC) using AVIEW’s lung texture analysis.

The results showed a correlation coefficient of 0.68 in the full dataset and 0.77 among non-IPF patients, suggesting that quantitative CT data can be used as a potential predictor of functional decline in pulmonary fibrosis.

Clinical Validation of AVIEW Across Diverse Use Cases

These 2024 studies collectively reinforce AVIEW’s credibility and versatility as a clinically validated AI-based CT analysis software. These studies and studies suggest:
 

1. The potential for real-world clinical integration of healthcare AI software
   The potential for real-world clinical integration of healthcare AI software AVIEW has the performance and quantitative accuracy to go beyond research and into real-world clinical practice, especially for screening programs to be both efficient and accurate.
    

2. Contributing to the redesign of radiology workflows
   When AI is engaged as a first or second reader, the potential for optimization across the diagnostic process is identified, including reduced radiologist fatigue and improved work focus.
    

3. Demonstrated multi-institutional/multi-country applicability of AVIEW
   The international nature of the authors and institutions, including European (iDNA, Parma, HANSE, etc.) and Korean hospitals, means that AVIEW is a trusted solution that can be accepted in global clinical settings.
    

From screening efficiency to functional prediction, AVIEW demonstrates how AI can bring quantifiable value to diagnostic imaging. Coreline Soft remains committed to advancing clinical partnerships and technology innovation to reshape the standards of diagnosis.
 

• Interested in reading more research? Visit our Publications Page

• Want to experience AVIEW in action? Book a Demo