DALSA : domain adaptation for supervised learning from sparsely annotated MR images / Michael Goetz, Christian Weber, Franciszek Binczyk, Joanna Polanska, Rafal Tarnawski, Barbara Bobek-Billewicz, Ullrich Koethe, Jens Kleesiek, Bram Stieltjes, and Klaus H. Maier-Hein
We propose a new method that employs transfer learning techniques to effectively correct sampling selection errors introduced by sparse annotations during supervised learning for automated tumor segmentation. The practicality of current learning-based automated tissue classification approaches is severely impeded by their dependency on manually segmented training databases that need to be recreated for each scenario of application, site, or acquisition setup. The comprehensive annotation of reference datasets can be highly labor-intensive, complex, and error-prone. The proposed method derives high-quality classifiers for the different tissue classes from sparse and unambiguous annotations and employs domain adaptation techniques for effectively correcting sampling selection errors introduced by the sparse sampling. The new approach is validated on labeled, multi-modal MR images of 19 patients with malignant gliomas and by comparative analysis on the BraTS 2013 challenge data sets. Compared to training on fully labeled data, we reduced the time for labeling and training by a factor greater than 70 and 180 respectively without sacrificing accuracy. This dramatically eases the establishment and constant extension of large annotated databases in various scenarios and imaging setups and thus represents an important step towards practical applicability of learning-based approaches in tissue classification..
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
Jan. 2016 2016 |
---|---|
Erschienen: |
Jan. 2016 |
Enthalten in: |
Zur Gesamtaufnahme - volume:35 |
---|---|
Enthalten in: |
IEEE transactions on medical imaging - 35(2016), 1, Seite 184-196 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Götz, Michael [VerfasserIn] |
---|
Links: |
Volltext [lizenzpflichtig] |
---|
Anmerkungen: |
Gesehen am 25.06.2020 |
---|
Umfang: |
13 |
---|
doi: |
10.1109/TMI.2015.2463078 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
1702179869 |
---|
LEADER | 01000caa a2200265 4500 | ||
---|---|---|---|
001 | 1702179869 | ||
003 | DE-627 | ||
005 | 20230427045019.0 | ||
007 | cr uuu---uuuuu | ||
008 | 200625s2016 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1109/TMI.2015.2463078 |2 doi | |
035 | |a (DE-627)1702179869 | ||
035 | |a (DE-599)KXP1702179869 | ||
035 | |a (OCoLC)1341341868 | ||
040 | |a DE-627 |b ger |c DE-627 |e rda | ||
041 | |a eng | ||
100 | 1 | |a Götz, Michael |e verfasserin |0 (DE-588)119554541X |0 (DE-627)1677564326 |4 aut | |
245 | 1 | 0 | |a DALSA |b domain adaptation for supervised learning from sparsely annotated MR images |c Michael Goetz, Christian Weber, Franciszek Binczyk, Joanna Polanska, Rafal Tarnawski, Barbara Bobek-Billewicz, Ullrich Koethe, Jens Kleesiek, Bram Stieltjes, and Klaus H. Maier-Hein |
264 | 1 | |c Jan. 2016 | |
300 | |a 13 | ||
336 | |a Text |b txt |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Gesehen am 25.06.2020 | ||
520 | |a We propose a new method that employs transfer learning techniques to effectively correct sampling selection errors introduced by sparse annotations during supervised learning for automated tumor segmentation. The practicality of current learning-based automated tissue classification approaches is severely impeded by their dependency on manually segmented training databases that need to be recreated for each scenario of application, site, or acquisition setup. The comprehensive annotation of reference datasets can be highly labor-intensive, complex, and error-prone. The proposed method derives high-quality classifiers for the different tissue classes from sparse and unambiguous annotations and employs domain adaptation techniques for effectively correcting sampling selection errors introduced by the sparse sampling. The new approach is validated on labeled, multi-modal MR images of 19 patients with malignant gliomas and by comparative analysis on the BraTS 2013 challenge data sets. Compared to training on fully labeled data, we reduced the time for labeling and training by a factor greater than 70 and 180 respectively without sacrificing accuracy. This dramatically eases the establishment and constant extension of large annotated databases in various scenarios and imaging setups and thus represents an important step towards practical applicability of learning-based approaches in tissue classification. | ||
650 | 4 | |a Algorithms | |
650 | 4 | |a automated tissue classification | |
650 | 4 | |a automated tumor segmentation | |
650 | 4 | |a Automatic multi-modal segmentation | |
650 | 4 | |a biomedical MRI | |
650 | 4 | |a Brain Neoplasms | |
650 | 4 | |a brain tumor segmentation | |
650 | 4 | |a compressed sensing | |
650 | 4 | |a DALSA | |
650 | 4 | |a Decision Trees | |
650 | 4 | |a domain adaptation | |
650 | 4 | |a domain adaptation techniques | |
650 | 4 | |a domain-adaptation-for-supervised-learning-from-sparsely-annotation | |
650 | 4 | |a glioma | |
650 | 4 | |a Glioma | |
650 | 4 | |a Humans | |
650 | 4 | |a image classification | |
650 | 4 | |a Image Processing, Computer-Assisted | |
650 | 4 | |a image segmentation | |
650 | 4 | |a Image segmentation | |
650 | 4 | |a Labeling | |
650 | 4 | |a learning-based approach | |
650 | 4 | |a Machine Learning | |
650 | 4 | |a Magnetic Resonance Imaging | |
650 | 4 | |a malignant gliomas | |
650 | 4 | |a medical image processing | |
650 | 4 | |a MR Images | |
650 | 4 | |a Noise | |
650 | 4 | |a random forest | |
650 | 4 | |a sampling selection errors | |
650 | 4 | |a sparse annotations | |
650 | 4 | |a sparse sampling | |
650 | 4 | |a tissue classes | |
650 | 4 | |a Training | |
650 | 4 | |a Training data | |
650 | 4 | |a transfer learning | |
650 | 4 | |a transfer learning techniques | |
650 | 4 | |a Tumors | |
650 | 4 | |a tumours | |
650 | 4 | |a Vegetation | |
700 | 1 | |a Weber, Christian |e verfasserin |4 aut | |
700 | 1 | |a Binczyk, Franciszek |e verfasserin |4 aut | |
700 | 1 | |a Polanska, Joanna |e verfasserin |4 aut | |
700 | 1 | |a Tarnawski, Rafal |e verfasserin |4 aut | |
700 | 1 | |a Bobek-Billewicz, Barbara |e verfasserin |4 aut | |
700 | 1 | |a Köthe, Ullrich |e verfasserin |0 (DE-588)123963435 |0 (DE-627)594480884 |0 (DE-576)304484520 |4 aut | |
700 | 1 | |a Kleesiek, Jens Philipp |d 1977- |e verfasserin |0 (DE-588)132998076 |0 (DE-627)530080745 |0 (DE-576)299554465 |4 aut | |
700 | 1 | |a Stieltjes, Bram |e verfasserin |4 aut | |
700 | 1 | |a Maier-Hein, Klaus H. |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |a Institute of Electrical and Electronics Engineers |t IEEE transactions on medical imaging |d New York, NY : Institute of Electrical and Electronics Engineers, 1982 |g 35(2016), 1, Seite 184-196 |h Online-Ressource |w (DE-627)341354759 |w (DE-600)2068206-2 |w (DE-576)105283061 |x 1558-254X |7 nnns |
773 | 1 | 8 | |g volume:35 |g year:2016 |g number:1 |g pages:184-196 |g extent:13 |
856 | 4 | 0 | |u https://doi.org/10.1109/TMI.2015.2463078 |x Verlag |x Resolving-System |z lizenzpflichtig |3 Volltext |
912 | |a GBV_USEFLAG_U | ||
912 | |a GBV_ILN_2013 | ||
912 | |a ISIL_DE-16-250 | ||
912 | |a SYSFLAG_1 | ||
912 | |a GBV_KXP | ||
912 | |a SSG-OLC-PHA | ||
912 | |a GBV_ILN_20 | ||
912 | |a GBV_ILN_22 | ||
912 | |a GBV_ILN_23 | ||
912 | |a GBV_ILN_24 | ||
912 | |a GBV_ILN_31 | ||
912 | |a GBV_ILN_32 | ||
912 | |a GBV_ILN_40 | ||
912 | |a GBV_ILN_60 | ||
912 | |a GBV_ILN_62 | ||
912 | |a GBV_ILN_70 | ||
912 | |a GBV_ILN_95 | ||
912 | |a GBV_ILN_100 | ||
912 | |a GBV_ILN_101 | ||
912 | |a GBV_ILN_105 | ||
912 | |a GBV_ILN_120 | ||
912 | |a GBV_ILN_161 | ||
912 | |a GBV_ILN_187 | ||
912 | |a GBV_ILN_285 | ||
912 | |a GBV_ILN_293 | ||
912 | |a GBV_ILN_702 | ||
912 | |a GBV_ILN_2001 | ||
912 | |a GBV_ILN_2003 | ||
912 | |a GBV_ILN_2005 | ||
912 | |a GBV_ILN_2006 | ||
912 | |a GBV_ILN_2009 | ||
912 | |a GBV_ILN_2010 | ||
912 | |a GBV_ILN_2011 | ||
912 | |a GBV_ILN_2014 | ||
912 | |a GBV_ILN_2015 | ||
912 | |a GBV_ILN_2020 | ||
912 | |a GBV_ILN_2021 | ||
912 | |a GBV_ILN_2027 | ||
912 | |a GBV_ILN_2034 | ||
912 | |a GBV_ILN_2048 | ||
912 | |a GBV_ILN_2050 | ||
912 | |a GBV_ILN_2055 | ||
912 | |a GBV_ILN_2057 | ||
912 | |a GBV_ILN_2059 | ||
912 | |a GBV_ILN_2061 | ||
912 | |a GBV_ILN_2064 | ||
912 | |a GBV_ILN_2068 | ||
912 | |a GBV_ILN_2088 | ||
912 | |a GBV_ILN_2106 | ||
912 | |a GBV_ILN_2108 | ||
912 | |a GBV_ILN_2110 | ||
912 | |a GBV_ILN_2111 | ||
912 | |a GBV_ILN_2112 | ||
912 | |a GBV_ILN_2113 | ||
912 | |a GBV_ILN_2118 | ||
912 | |a GBV_ILN_2119 | ||
912 | |a GBV_ILN_2129 | ||
912 | |a GBV_ILN_2153 | ||
912 | |a GBV_ILN_2190 | ||
912 | |a GBV_ILN_2232 | ||
912 | |a GBV_ILN_2472 | ||
912 | |a GBV_ILN_2522 | ||
912 | |a GBV_ILN_4046 | ||
912 | |a GBV_ILN_4112 | ||
912 | |a GBV_ILN_4125 | ||
912 | |a GBV_ILN_4126 | ||
912 | |a GBV_ILN_4242 | ||
912 | |a GBV_ILN_4246 | ||
912 | |a GBV_ILN_4249 | ||
912 | |a GBV_ILN_4251 | ||
912 | |a GBV_ILN_4306 | ||
912 | |a GBV_ILN_4307 | ||
912 | |a GBV_ILN_4313 | ||
912 | |a GBV_ILN_4323 | ||
912 | |a GBV_ILN_4324 | ||
912 | |a GBV_ILN_4328 | ||
912 | |a GBV_ILN_4333 | ||
912 | |a GBV_ILN_4335 | ||
912 | |a GBV_ILN_4336 | ||
912 | |a GBV_ILN_4338 | ||
912 | |a GBV_ILN_4700 | ||
936 | u | w | |d 35 |j 2016 |e 1 |h 184-196 |g 13 |
951 | |a AR | ||
952 | |d 35 |j 2016 |e 1 |h 184-196 |g 13 | ||
980 | |2 2013 |1 01 |x DE-16-250 |b 3691143784 |c 00 |f --%%-- |d --%%-- |e --%%-- |j --%%-- |y l01 |z 25-06-20 | ||
982 | |2 2013 |1 01 |x DE-16-250 |8 00 |s s |a hd2016 | ||
982 | |2 2013 |1 01 |x DE-16-250 |8 01 |s s |0 (DE-627)1410508463 |a wissenschaftlicher Artikel (Zeitschrift) | ||
982 | |2 2013 |1 01 |x DE-16-250 |8 02 |s s |a per_10 | ||
982 | |2 2013 |1 01 |x DE-16-250 |8 03 |s s |a s_13 | ||
982 | |2 2013 |1 01 |x DE-16-250 |8 04 |s p |0 (DE-627)1469076551 |a Köthe, Ullrich | ||
982 | |2 2013 |1 01 |x DE-16-250 |8 04 |s k |0 (DE-627)147113900X |a Heidelberg Collaboratory for Image Processing (HCI) | ||
982 | |2 2013 |1 01 |x DE-16-250 |8 04 |s s |0 (DE-627)1410501914 |a Verfasser | ||
982 | |2 2013 |1 01 |x DE-16-250 |8 04 |s s |a pos_7 | ||
982 | |2 2013 |1 01 |x DE-16-250 |8 05 |s p |0 (DE-627)150004220X |a Kleesiek, Jens Philipp | ||
982 | |2 2013 |1 01 |x DE-16-250 |8 05 |s k |0 (DE-627)1416466967 |a Medizinische Fakultät Heidelberg | ||
982 | |2 2013 |1 01 |x DE-16-250 |8 05 |s s |0 (DE-627)1410501914 |a Verfasser | ||
982 | |2 2013 |1 01 |x DE-16-250 |8 05 |s s |a pos_8 |