Deep learning and atlas-based models to streamline the segmentation workflow of total marrow and lymphoid irradiation
© 2024. Italian Society of Medical Radiology..
PURPOSE: To improve the workflow of total marrow and lymphoid irradiation (TMLI) by enhancing the delineation of organs at risk (OARs) and clinical target volume (CTV) using deep learning (DL) and atlas-based (AB) segmentation models.
MATERIALS AND METHODS: Ninety-five TMLI plans optimized in our institute were analyzed. Two commercial DL software were tested for segmenting 18 OARs. An AB model for lymph node CTV (CTV_LN) delineation was built using 20 TMLI patients. The AB model was evaluated on 20 independent patients, and a semiautomatic approach was tested by correcting the automatic contours. The generated OARs and CTV_LN contours were compared to manual contours in terms of topological agreement, dose statistics, and time workload. A clinical decision tree was developed to define a specific contouring strategy for each OAR.
RESULTS: The two DL models achieved a median [interquartile range] dice similarity coefficient (DSC) of 0.84 [0.71;0.93] and 0.85 [0.70;0.93] across the OARs. The absolute median Dmean difference between manual and the two DL models was 2.0 [0.7;6.6]% and 2.4 [0.9;7.1]%. The AB model achieved a median DSC of 0.70 [0.66;0.74] for CTV_LN delineation, increasing to 0.94 [0.94;0.95] after manual revision, with minimal Dmean differences. Since September 2022, our institution has implemented DL and AB models for all TMLI patients, reducing from 5 to 2 h the time required to complete the entire segmentation process.
CONCLUSION: DL models can streamline the TMLI contouring process of OARs. Manual revision is still necessary for lymph node delineation using AB models.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:129 |
---|---|
Enthalten in: |
La Radiologia medica - 129(2024), 3 vom: 22. März, Seite 515-523 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Dei, Damiano [VerfasserIn] |
---|
Links: |
---|
Themen: |
Atlas-based |
---|
Anmerkungen: |
Date Completed 18.03.2024 Date Revised 18.03.2024 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1007/s11547-024-01760-8 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM367974436 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM367974436 | ||
003 | DE-627 | ||
005 | 20240318234206.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240203s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1007/s11547-024-01760-8 |2 doi | |
028 | 5 | 2 | |a pubmed24n1334.xml |
035 | |a (DE-627)NLM367974436 | ||
035 | |a (NLM)38308062 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Dei, Damiano |e verfasserin |4 aut | |
245 | 1 | 0 | |a Deep learning and atlas-based models to streamline the segmentation workflow of total marrow and lymphoid irradiation |
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 18.03.2024 | ||
500 | |a Date Revised 18.03.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2024. Italian Society of Medical Radiology. | ||
520 | |a PURPOSE: To improve the workflow of total marrow and lymphoid irradiation (TMLI) by enhancing the delineation of organs at risk (OARs) and clinical target volume (CTV) using deep learning (DL) and atlas-based (AB) segmentation models | ||
520 | |a MATERIALS AND METHODS: Ninety-five TMLI plans optimized in our institute were analyzed. Two commercial DL software were tested for segmenting 18 OARs. An AB model for lymph node CTV (CTV_LN) delineation was built using 20 TMLI patients. The AB model was evaluated on 20 independent patients, and a semiautomatic approach was tested by correcting the automatic contours. The generated OARs and CTV_LN contours were compared to manual contours in terms of topological agreement, dose statistics, and time workload. A clinical decision tree was developed to define a specific contouring strategy for each OAR | ||
520 | |a RESULTS: The two DL models achieved a median [interquartile range] dice similarity coefficient (DSC) of 0.84 [0.71;0.93] and 0.85 [0.70;0.93] across the OARs. The absolute median Dmean difference between manual and the two DL models was 2.0 [0.7;6.6]% and 2.4 [0.9;7.1]%. The AB model achieved a median DSC of 0.70 [0.66;0.74] for CTV_LN delineation, increasing to 0.94 [0.94;0.95] after manual revision, with minimal Dmean differences. Since September 2022, our institution has implemented DL and AB models for all TMLI patients, reducing from 5 to 2 h the time required to complete the entire segmentation process | ||
520 | |a CONCLUSION: DL models can streamline the TMLI contouring process of OARs. Manual revision is still necessary for lymph node delineation using AB models | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Atlas-based | |
650 | 4 | |a Deep learning | |
650 | 4 | |a Radiotherapy | |
650 | 4 | |a Segmentation | |
650 | 4 | |a Total marrow and lymphoid irradiation | |
650 | 4 | |a Total marrow irradiation | |
700 | 1 | |a Lambri, Nicola |e verfasserin |4 aut | |
700 | 1 | |a Crespi, Leonardo |e verfasserin |4 aut | |
700 | 1 | |a Brioso, Ricardo Coimbra |e verfasserin |4 aut | |
700 | 1 | |a Loiacono, Daniele |e verfasserin |4 aut | |
700 | 1 | |a Clerici, Elena |e verfasserin |4 aut | |
700 | 1 | |a Bellu, Luisa |e verfasserin |4 aut | |
700 | 1 | |a De Philippis, Chiara |e verfasserin |4 aut | |
700 | 1 | |a Navarria, Pierina |e verfasserin |4 aut | |
700 | 1 | |a Bramanti, Stefania |e verfasserin |4 aut | |
700 | 1 | |a Carlo-Stella, Carmelo |e verfasserin |4 aut | |
700 | 1 | |a Rusconi, Roberto |e verfasserin |4 aut | |
700 | 1 | |a Reggiori, Giacomo |e verfasserin |4 aut | |
700 | 1 | |a Tomatis, Stefano |e verfasserin |4 aut | |
700 | 1 | |a Scorsetti, Marta |e verfasserin |4 aut | |
700 | 1 | |a Mancosu, Pietro |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t La Radiologia medica |d 1947 |g 129(2024), 3 vom: 22. März, Seite 515-523 |w (DE-627)NLM000345326 |x 1826-6983 |7 nnns |
773 | 1 | 8 | |g volume:129 |g year:2024 |g number:3 |g day:22 |g month:03 |g pages:515-523 |
856 | 4 | 0 | |u http://dx.doi.org/10.1007/s11547-024-01760-8 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 129 |j 2024 |e 3 |b 22 |c 03 |h 515-523 |