Enhanced Detection Performance of Acute Vertebral Compression Fractures Using a Hybrid Deep Learning and Traditional Quantitative Measurement Approach: Beyond the Limitations of Genant Classification
Objective: This study evaluated the applicability of the classical method, height loss ratio (HLR), for identifying major acute compression fractures in clinical practice and compared its performance with deep learning (DL)-based VCF detection methods. Additionally, it examined whether combining the...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/12/1/64 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589082226589696 |
|---|---|
| author | Jemyoung Lee Minbeom Kim Heejun Park Zepa Yang Ok Hee Woo Woo Young Kang Jong Hyo Kim |
| author_facet | Jemyoung Lee Minbeom Kim Heejun Park Zepa Yang Ok Hee Woo Woo Young Kang Jong Hyo Kim |
| author_sort | Jemyoung Lee |
| collection | DOAJ |
| description | Objective: This study evaluated the applicability of the classical method, height loss ratio (HLR), for identifying major acute compression fractures in clinical practice and compared its performance with deep learning (DL)-based VCF detection methods. Additionally, it examined whether combining the HLR with DL approaches could enhance performance, exploring the potential integration of classical and DL methodologies. Methods: End-to-End VCF Detection (EEVD), Two-Stage VCF Detection with Segmentation and Detection (TSVD_SD), and Two-Stage VCF Detection with Detection and Classification (TSVD_DC). The models were evaluated on a dataset of 589 patients, focusing on sensitivity, specificity, accuracy, and precision. Results: TSVD_SD outperformed all other methods, achieving the highest sensitivity (84.46%) and accuracy (95.05%), making it particularly effective for identifying true positives. The complementary use of DL methods with HLR further improved detection performance. For instance, combining HLR-negative cases with TSVD_SD increased sensitivity to 87.84%, reducing missed fractures, while combining HLR-positive cases with EEVD achieved the highest specificity (99.77%), minimizing false positives. Conclusion: These findings demonstrated that DL-based approaches, particularly TSVD_SD, provided robust alternatives or complements to traditional methods, significantly enhancing diagnostic accuracy for acute VCFs in clinical practice. |
| format | Article |
| id | doaj-art-e1c8701c41084a4680c8adfed7d3a3e0 |
| institution | Kabale University |
| issn | 2306-5354 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj-art-e1c8701c41084a4680c8adfed7d3a3e02025-01-24T13:23:08ZengMDPI AGBioengineering2306-53542025-01-011216410.3390/bioengineering12010064Enhanced Detection Performance of Acute Vertebral Compression Fractures Using a Hybrid Deep Learning and Traditional Quantitative Measurement Approach: Beyond the Limitations of Genant ClassificationJemyoung Lee0Minbeom Kim1Heejun Park2Zepa Yang3Ok Hee Woo4Woo Young Kang5Jong Hyo Kim6Department of Applied Bioengineering, Graduate School of Convergence Science and Technology, Seoul National University, Seoul 08826, Republic of KoreaClariPi Research, ClariPi Inc., Seoul 03088, Republic of KoreaDepartment of Radiology, Korea University Guro Hospital, Seoul 08308, Republic of KoreaDepartment of Radiology, Korea University Guro Hospital, Seoul 08308, Republic of KoreaDepartment of Radiology, Korea University Guro Hospital, Seoul 08308, Republic of KoreaDepartment of Radiology, Korea University Guro Hospital, Seoul 08308, Republic of KoreaDepartment of Applied Bioengineering, Graduate School of Convergence Science and Technology, Seoul National University, Seoul 08826, Republic of KoreaObjective: This study evaluated the applicability of the classical method, height loss ratio (HLR), for identifying major acute compression fractures in clinical practice and compared its performance with deep learning (DL)-based VCF detection methods. Additionally, it examined whether combining the HLR with DL approaches could enhance performance, exploring the potential integration of classical and DL methodologies. Methods: End-to-End VCF Detection (EEVD), Two-Stage VCF Detection with Segmentation and Detection (TSVD_SD), and Two-Stage VCF Detection with Detection and Classification (TSVD_DC). The models were evaluated on a dataset of 589 patients, focusing on sensitivity, specificity, accuracy, and precision. Results: TSVD_SD outperformed all other methods, achieving the highest sensitivity (84.46%) and accuracy (95.05%), making it particularly effective for identifying true positives. The complementary use of DL methods with HLR further improved detection performance. For instance, combining HLR-negative cases with TSVD_SD increased sensitivity to 87.84%, reducing missed fractures, while combining HLR-positive cases with EEVD achieved the highest specificity (99.77%), minimizing false positives. Conclusion: These findings demonstrated that DL-based approaches, particularly TSVD_SD, provided robust alternatives or complements to traditional methods, significantly enhancing diagnostic accuracy for acute VCFs in clinical practice.https://www.mdpi.com/2306-5354/12/1/64acute vertebral compression fracturegenant classificationdeep learningcomputed tomographyspine |
| spellingShingle | Jemyoung Lee Minbeom Kim Heejun Park Zepa Yang Ok Hee Woo Woo Young Kang Jong Hyo Kim Enhanced Detection Performance of Acute Vertebral Compression Fractures Using a Hybrid Deep Learning and Traditional Quantitative Measurement Approach: Beyond the Limitations of Genant Classification Bioengineering acute vertebral compression fracture genant classification deep learning computed tomography spine |
| title | Enhanced Detection Performance of Acute Vertebral Compression Fractures Using a Hybrid Deep Learning and Traditional Quantitative Measurement Approach: Beyond the Limitations of Genant Classification |
| title_full | Enhanced Detection Performance of Acute Vertebral Compression Fractures Using a Hybrid Deep Learning and Traditional Quantitative Measurement Approach: Beyond the Limitations of Genant Classification |
| title_fullStr | Enhanced Detection Performance of Acute Vertebral Compression Fractures Using a Hybrid Deep Learning and Traditional Quantitative Measurement Approach: Beyond the Limitations of Genant Classification |
| title_full_unstemmed | Enhanced Detection Performance of Acute Vertebral Compression Fractures Using a Hybrid Deep Learning and Traditional Quantitative Measurement Approach: Beyond the Limitations of Genant Classification |
| title_short | Enhanced Detection Performance of Acute Vertebral Compression Fractures Using a Hybrid Deep Learning and Traditional Quantitative Measurement Approach: Beyond the Limitations of Genant Classification |
| title_sort | enhanced detection performance of acute vertebral compression fractures using a hybrid deep learning and traditional quantitative measurement approach beyond the limitations of genant classification |
| topic | acute vertebral compression fracture genant classification deep learning computed tomography spine |
| url | https://www.mdpi.com/2306-5354/12/1/64 |
| work_keys_str_mv | AT jemyounglee enhanceddetectionperformanceofacutevertebralcompressionfracturesusingahybriddeeplearningandtraditionalquantitativemeasurementapproachbeyondthelimitationsofgenantclassification AT minbeomkim enhanceddetectionperformanceofacutevertebralcompressionfracturesusingahybriddeeplearningandtraditionalquantitativemeasurementapproachbeyondthelimitationsofgenantclassification AT heejunpark enhanceddetectionperformanceofacutevertebralcompressionfracturesusingahybriddeeplearningandtraditionalquantitativemeasurementapproachbeyondthelimitationsofgenantclassification AT zepayang enhanceddetectionperformanceofacutevertebralcompressionfracturesusingahybriddeeplearningandtraditionalquantitativemeasurementapproachbeyondthelimitationsofgenantclassification AT okheewoo enhanceddetectionperformanceofacutevertebralcompressionfracturesusingahybriddeeplearningandtraditionalquantitativemeasurementapproachbeyondthelimitationsofgenantclassification AT wooyoungkang enhanceddetectionperformanceofacutevertebralcompressionfracturesusingahybriddeeplearningandtraditionalquantitativemeasurementapproachbeyondthelimitationsofgenantclassification AT jonghyokim enhanceddetectionperformanceofacutevertebralcompressionfracturesusingahybriddeeplearningandtraditionalquantitativemeasurementapproachbeyondthelimitationsofgenantclassification |