Enhancing deep learning methods for brain metastasis detection through cross-technique annotations on SPACE MRI
Abstract Background Gadolinium-enhanced “sampling perfection with application-optimized contrasts using different flip angle evolution” (SPACE) sequence allows better visualization of brain metastases (BMs) compared to “magnetization-prepared rapid acquisition gradient echo” (MPRAGE). We hypothesize...
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-02-01
|
| Series: | European Radiology Experimental |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s41747-025-00554-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823863293607936000 |
|---|---|
| author | Tassilo Wald Benjamin Hamm Julius C. Holzschuh Rami El Shafie Andreas Kudak Balint Kovacs Irada Pflüger Bastian von Nettelbladt Constantin Ulrich Michael Anton Baumgartner Philipp Vollmuth Jürgen Debus Klaus H. Maier-Hein Thomas Welzel |
| author_facet | Tassilo Wald Benjamin Hamm Julius C. Holzschuh Rami El Shafie Andreas Kudak Balint Kovacs Irada Pflüger Bastian von Nettelbladt Constantin Ulrich Michael Anton Baumgartner Philipp Vollmuth Jürgen Debus Klaus H. Maier-Hein Thomas Welzel |
| author_sort | Tassilo Wald |
| collection | DOAJ |
| description | Abstract Background Gadolinium-enhanced “sampling perfection with application-optimized contrasts using different flip angle evolution” (SPACE) sequence allows better visualization of brain metastases (BMs) compared to “magnetization-prepared rapid acquisition gradient echo” (MPRAGE). We hypothesize that this better conspicuity leads to high-quality annotation (HAQ), enhancing deep learning (DL) algorithm detection of BMs on MPRAGE images. Methods Retrospective contrast-enhanced (gadobutrol 0.1 mmol/kg) SPACE and MPRAGE data of 157 patients with BM were used, either annotated on MPRAGE resulting in normal annotation quality (NAQ) or on coregistered SPACE resulting in HAQ. Multiple DL methods were developed with NAQ or HAQ using either SPACE or MRPAGE images and evaluated on their detection performance using positive predictive value (PPV), sensitivity, and F1 score and on their delineation performance using volumetric Dice similarity coefficient, PPV, and sensitivity on one internal and four additional test datasets (660 patients). Results The SPACE-HAQ model reached 0.978 PPV, 0.882 sensitivity, and 0.916 F1-score. The MPRAGE-HAQ reached 0.867, 0.839, and 0.840, the MPRAGE NAQ 0.964, 0.667, and 0.798, respectively (p ≥ 0.157). Relative to MPRAGE-NAQ, the MPRAGE-HAQ F1-score detection increased on all additional test datasets by 2.5–9.6 points (p < 0.016) and sensitivity improved on three datasets by 4.6–8.5 points (p < 0.001). Moreover, volumetric instance sensitivity improved by 3.6–7.6 points (p < 0.001). Conclusion HAQ improves DL methods without specialized imaging during application time. HAQ alone achieves about 40% of the performance improvements seen with SPACE images as input, allowing for fast and accurate, fully automated detection of small (< 1 cm) BMs. Relevance statement Training with higher-quality annotations, created using the SPACE sequence, improves the detection and delineation sensitivity of DL methods for the detection of brain metastases (BMs)on MPRAGE images. This MRI cross-technique transfer learning is a promising way to increase diagnostic performance. Key Points Delineating small BMs on SPACE MRI sequence results in higher quality annotations than on MPRAGE sequence due to enhanced conspicuity. Leveraging cross-technique ground truth annotations during training improved the accuracy of DL models in detecting and segmenting BMs. Cross-technique annotation may enhance DL models by integrating benefits from specialized, time-intensive MRI sequences while not relying on them. Further validation in prospective studies is needed. Graphical Abstract |
| format | Article |
| id | doaj-art-adb8424b13524459a840920269df331e |
| institution | Kabale University |
| issn | 2509-9280 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | European Radiology Experimental |
| spelling | doaj-art-adb8424b13524459a840920269df331e2025-02-09T12:11:21ZengSpringerOpenEuropean Radiology Experimental2509-92802025-02-019111410.1186/s41747-025-00554-5Enhancing deep learning methods for brain metastasis detection through cross-technique annotations on SPACE MRITassilo Wald0Benjamin Hamm1Julius C. Holzschuh2Rami El Shafie3Andreas Kudak4Balint Kovacs5Irada Pflüger6Bastian von Nettelbladt7Constantin Ulrich8Michael Anton Baumgartner9Philipp Vollmuth10Jürgen Debus11Klaus H. Maier-Hein12Thomas Welzel13German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image ComputingGerman Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image ComputingDivision of Radiology, German Cancer Research Center (DKFZ)Department of Radiation Oncology, Heidelberg University HospitalDepartment of Radiation Oncology, Heidelberg University HospitalGerman Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image ComputingDepartment of Neuroradiology, Heidelberg University HospitalDepartment of Radiation Oncology, Heidelberg University HospitalGerman Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image ComputingGerman Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image ComputingDepartment of Neuroradiology, Heidelberg University HospitalDepartment of Radiation Oncology, Heidelberg University HospitalGerman Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image ComputingDepartment of Radiation Oncology, Heidelberg University HospitalAbstract Background Gadolinium-enhanced “sampling perfection with application-optimized contrasts using different flip angle evolution” (SPACE) sequence allows better visualization of brain metastases (BMs) compared to “magnetization-prepared rapid acquisition gradient echo” (MPRAGE). We hypothesize that this better conspicuity leads to high-quality annotation (HAQ), enhancing deep learning (DL) algorithm detection of BMs on MPRAGE images. Methods Retrospective contrast-enhanced (gadobutrol 0.1 mmol/kg) SPACE and MPRAGE data of 157 patients with BM were used, either annotated on MPRAGE resulting in normal annotation quality (NAQ) or on coregistered SPACE resulting in HAQ. Multiple DL methods were developed with NAQ or HAQ using either SPACE or MRPAGE images and evaluated on their detection performance using positive predictive value (PPV), sensitivity, and F1 score and on their delineation performance using volumetric Dice similarity coefficient, PPV, and sensitivity on one internal and four additional test datasets (660 patients). Results The SPACE-HAQ model reached 0.978 PPV, 0.882 sensitivity, and 0.916 F1-score. The MPRAGE-HAQ reached 0.867, 0.839, and 0.840, the MPRAGE NAQ 0.964, 0.667, and 0.798, respectively (p ≥ 0.157). Relative to MPRAGE-NAQ, the MPRAGE-HAQ F1-score detection increased on all additional test datasets by 2.5–9.6 points (p < 0.016) and sensitivity improved on three datasets by 4.6–8.5 points (p < 0.001). Moreover, volumetric instance sensitivity improved by 3.6–7.6 points (p < 0.001). Conclusion HAQ improves DL methods without specialized imaging during application time. HAQ alone achieves about 40% of the performance improvements seen with SPACE images as input, allowing for fast and accurate, fully automated detection of small (< 1 cm) BMs. Relevance statement Training with higher-quality annotations, created using the SPACE sequence, improves the detection and delineation sensitivity of DL methods for the detection of brain metastases (BMs)on MPRAGE images. This MRI cross-technique transfer learning is a promising way to increase diagnostic performance. Key Points Delineating small BMs on SPACE MRI sequence results in higher quality annotations than on MPRAGE sequence due to enhanced conspicuity. Leveraging cross-technique ground truth annotations during training improved the accuracy of DL models in detecting and segmenting BMs. Cross-technique annotation may enhance DL models by integrating benefits from specialized, time-intensive MRI sequences while not relying on them. Further validation in prospective studies is needed. Graphical Abstracthttps://doi.org/10.1186/s41747-025-00554-5Brain neoplasmsDeep learningImage interpretation (computer-assisted)Image processing (computer-assisted)Magnetic resonance imaging |
| spellingShingle | Tassilo Wald Benjamin Hamm Julius C. Holzschuh Rami El Shafie Andreas Kudak Balint Kovacs Irada Pflüger Bastian von Nettelbladt Constantin Ulrich Michael Anton Baumgartner Philipp Vollmuth Jürgen Debus Klaus H. Maier-Hein Thomas Welzel Enhancing deep learning methods for brain metastasis detection through cross-technique annotations on SPACE MRI European Radiology Experimental Brain neoplasms Deep learning Image interpretation (computer-assisted) Image processing (computer-assisted) Magnetic resonance imaging |
| title | Enhancing deep learning methods for brain metastasis detection through cross-technique annotations on SPACE MRI |
| title_full | Enhancing deep learning methods for brain metastasis detection through cross-technique annotations on SPACE MRI |
| title_fullStr | Enhancing deep learning methods for brain metastasis detection through cross-technique annotations on SPACE MRI |
| title_full_unstemmed | Enhancing deep learning methods for brain metastasis detection through cross-technique annotations on SPACE MRI |
| title_short | Enhancing deep learning methods for brain metastasis detection through cross-technique annotations on SPACE MRI |
| title_sort | enhancing deep learning methods for brain metastasis detection through cross technique annotations on space mri |
| topic | Brain neoplasms Deep learning Image interpretation (computer-assisted) Image processing (computer-assisted) Magnetic resonance imaging |
| url | https://doi.org/10.1186/s41747-025-00554-5 |
| work_keys_str_mv | AT tassilowald enhancingdeeplearningmethodsforbrainmetastasisdetectionthroughcrosstechniqueannotationsonspacemri AT benjaminhamm enhancingdeeplearningmethodsforbrainmetastasisdetectionthroughcrosstechniqueannotationsonspacemri AT juliuscholzschuh enhancingdeeplearningmethodsforbrainmetastasisdetectionthroughcrosstechniqueannotationsonspacemri AT ramielshafie enhancingdeeplearningmethodsforbrainmetastasisdetectionthroughcrosstechniqueannotationsonspacemri AT andreaskudak enhancingdeeplearningmethodsforbrainmetastasisdetectionthroughcrosstechniqueannotationsonspacemri AT balintkovacs enhancingdeeplearningmethodsforbrainmetastasisdetectionthroughcrosstechniqueannotationsonspacemri AT iradapfluger enhancingdeeplearningmethodsforbrainmetastasisdetectionthroughcrosstechniqueannotationsonspacemri AT bastianvonnettelbladt enhancingdeeplearningmethodsforbrainmetastasisdetectionthroughcrosstechniqueannotationsonspacemri AT constantinulrich enhancingdeeplearningmethodsforbrainmetastasisdetectionthroughcrosstechniqueannotationsonspacemri AT michaelantonbaumgartner enhancingdeeplearningmethodsforbrainmetastasisdetectionthroughcrosstechniqueannotationsonspacemri AT philippvollmuth enhancingdeeplearningmethodsforbrainmetastasisdetectionthroughcrosstechniqueannotationsonspacemri AT jurgendebus enhancingdeeplearningmethodsforbrainmetastasisdetectionthroughcrosstechniqueannotationsonspacemri AT klaushmaierhein enhancingdeeplearningmethodsforbrainmetastasisdetectionthroughcrosstechniqueannotationsonspacemri AT thomaswelzel enhancingdeeplearningmethodsforbrainmetastasisdetectionthroughcrosstechniqueannotationsonspacemri |