Automated volumetric assessment of pituitary adenoma
© 2023. The Author(s)..
PURPOSE: Assessment of pituitary adenoma (PA) volume and extent of resection (EOR) through manual segmentation is time-consuming and likely suffers from poor interrater agreement, especially postoperatively. Automated tumor segmentation and volumetry by use of deep learning techniques may provide more objective and quick volumetry.
METHODS: We developed an automated volumetry pipeline for pituitary adenoma. Preoperative and three-month postoperative T1-weighted, contrast-enhanced magnetic resonance imaging (MRI) with manual segmentations were used for model training. After adequate preprocessing, an ensemble of convolutional neural networks (CNNs) was trained and validated for preoperative and postoperative automated segmentation of tumor tissue. Generalization was evaluated on a separate holdout set.
RESULTS: In total, 193 image sets were used for training and 20 were held out for validation. At validation using the holdout set, our models (preoperative / postoperative) demonstrated a median Dice score of 0.71 (0.27) / 0 (0), a mean Jaccard score of 0.53 ± 0.21/0.030 ± 0.085 and a mean 95th percentile Hausdorff distance of 3.89 ± 1.96./12.199 ± 6.684. Pearson's correlation coefficient for volume correlation was 0.85 / 0.22 and -0.14 for extent of resection. Gross total resection was detected with a sensitivity of 66.67% and specificity of 36.36%.
CONCLUSIONS: Our volumetry pipeline demonstrated its ability to accurately segment pituitary adenomas. This is highly valuable for lesion detection and evaluation of progression of pituitary incidentalomas. Postoperatively, however, objective and precise detection of residual tumor remains less successful. Larger datasets, more diverse data, and more elaborate modeling could potentially improve performance.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:83 |
---|---|
Enthalten in: |
Endocrine - 83(2024), 1 vom: 11. Jan., Seite 171-177 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Da Mutten, Raffaele [VerfasserIn] |
---|
Links: |
---|
Themen: |
Deep learning |
---|
Anmerkungen: |
Date Completed 24.01.2024 Date Revised 15.03.2024 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1007/s12020-023-03529-x |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM362457654 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM362457654 | ||
003 | DE-627 | ||
005 | 20240315232750.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1007/s12020-023-03529-x |2 doi | |
028 | 5 | 2 | |a pubmed24n1330.xml |
035 | |a (DE-627)NLM362457654 | ||
035 | |a (NLM)37749388 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Da Mutten, Raffaele |e verfasserin |4 aut | |
245 | 1 | 0 | |a Automated volumetric assessment of pituitary adenoma |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 24.01.2024 | ||
500 | |a Date Revised 15.03.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2023. The Author(s). | ||
520 | |a PURPOSE: Assessment of pituitary adenoma (PA) volume and extent of resection (EOR) through manual segmentation is time-consuming and likely suffers from poor interrater agreement, especially postoperatively. Automated tumor segmentation and volumetry by use of deep learning techniques may provide more objective and quick volumetry | ||
520 | |a METHODS: We developed an automated volumetry pipeline for pituitary adenoma. Preoperative and three-month postoperative T1-weighted, contrast-enhanced magnetic resonance imaging (MRI) with manual segmentations were used for model training. After adequate preprocessing, an ensemble of convolutional neural networks (CNNs) was trained and validated for preoperative and postoperative automated segmentation of tumor tissue. Generalization was evaluated on a separate holdout set | ||
520 | |a RESULTS: In total, 193 image sets were used for training and 20 were held out for validation. At validation using the holdout set, our models (preoperative / postoperative) demonstrated a median Dice score of 0.71 (0.27) / 0 (0), a mean Jaccard score of 0.53 ± 0.21/0.030 ± 0.085 and a mean 95th percentile Hausdorff distance of 3.89 ± 1.96./12.199 ± 6.684. Pearson's correlation coefficient for volume correlation was 0.85 / 0.22 and -0.14 for extent of resection. Gross total resection was detected with a sensitivity of 66.67% and specificity of 36.36% | ||
520 | |a CONCLUSIONS: Our volumetry pipeline demonstrated its ability to accurately segment pituitary adenomas. This is highly valuable for lesion detection and evaluation of progression of pituitary incidentalomas. Postoperatively, however, objective and precise detection of residual tumor remains less successful. Larger datasets, more diverse data, and more elaborate modeling could potentially improve performance | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Deep learning | |
650 | 4 | |a Endocrinology | |
650 | 4 | |a Extent of resection | |
650 | 4 | |a Machine learning | |
650 | 4 | |a Neurosurgery | |
650 | 4 | |a Pituitary | |
700 | 1 | |a Zanier, Olivier |e verfasserin |4 aut | |
700 | 1 | |a Ciobanu-Caraus, Olga |e verfasserin |4 aut | |
700 | 1 | |a Voglis, Stefanos |e verfasserin |4 aut | |
700 | 1 | |a Hugelshofer, Michael |e verfasserin |4 aut | |
700 | 1 | |a Pangalu, Athina |e verfasserin |4 aut | |
700 | 1 | |a Regli, Luca |e verfasserin |4 aut | |
700 | 1 | |a Serra, Carlo |e verfasserin |4 aut | |
700 | 1 | |a Staartjes, Victor E |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Endocrine |d 1995 |g 83(2024), 1 vom: 11. Jan., Seite 171-177 |w (DE-627)NLM091795540 |x 1559-0100 |7 nnns |
773 | 1 | 8 | |g volume:83 |g year:2024 |g number:1 |g day:11 |g month:01 |g pages:171-177 |
856 | 4 | 0 | |u http://dx.doi.org/10.1007/s12020-023-03529-x |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 83 |j 2024 |e 1 |b 11 |c 01 |h 171-177 |