{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T06:26:05Z","timestamp":1782887165202,"version":"3.54.5"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2024,5,25]],"date-time":"2024-05-25T00:00:00Z","timestamp":1716595200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,5,25]],"date-time":"2024-05-25T00:00:00Z","timestamp":1716595200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Milcom Funding","award":["Convention 017-10470"],"award-info":[{"award-number":["Convention 017-10470"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>\n                           <jats:bold>Purpose<\/jats:bold>\n                        <\/jats:title>\n                <jats:p>Segmenting ultrasound images is important for precise area and\/or volume calculations, ensuring reliable diagnosis and effective treatment evaluation for diseases. Recently, many segmentation methods have been proposed and shown impressive performance. However, currently, there is no deeper understanding of how networks segment target regions or how they define the boundaries. In this paper, we present a new approach that analyzes ultrasound segmentation networks in terms of learned borders because border delimitation is challenging in ultrasound.\n<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>\n                           <jats:bold>Methods<\/jats:bold>\n                        <\/jats:title>\n                <jats:p>We propose a way to split the boundaries for ultrasound images into distinct and completed. By exploiting the Grad-CAM of the split borders, we analyze the areas each network pays attention to. Further, we calculate the ratio of correct predictions for distinct and completed borders. We conducted experiments on an in-house leg ultrasound dataset (LEG-3D-US) as well as on two additional public datasets of thyroid, nerves, and one private for prostate.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>\n                           <jats:bold>Results<\/jats:bold>\n                        <\/jats:title>\n                <jats:p>Quantitatively, the networks exhibit around 10% improvement in handling completed borders compared to distinct borders. Similar to doctors, the network struggles to define the borders in less visible areas. Additionally, the Seg-Grad-CAM analysis underscores how completion uses distinct borders and landmarks, while distinct focuses mainly on the shiny structures. We also observe variations depending on the attention mechanism of each architecture.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>\n                           <jats:bold>Conclusion<\/jats:bold>\n                        <\/jats:title>\n                <jats:p>In this work, we highlight the importance of studying ultrasound borders differently than other modalities such as MRI or CT. We split the borders into distinct and completed, similar to clinicians, and show the quality of the network-learned information for these two types of borders. Additionally, we open-source a 3D leg ultrasound dataset to the community <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/Al3xand1a\/segmentation-border-analysis\">https:\/\/github.com\/Al3xand1a\/segmentation-border-analysis<\/jats:ext-link>.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1007\/s11548-024-03170-7","type":"journal-article","created":{"date-parts":[[2024,5,25]],"date-time":"2024-05-25T03:31:57Z","timestamp":1716607917000},"page":"1419-1427","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Ultrasound segmentation analysis via distinct and completed anatomical borders"],"prefix":"10.1007","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2149-6581","authenticated-orcid":false,"given":"Vanessa Gonzalez","family":"Duque","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandra","family":"Marquardt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yordanka","family":"Velikova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lilian","family":"Lacourpaille","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antoine","family":"Nordez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marion","family":"Crouzier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong Joo","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diana","family":"Mateus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,25]]},"reference":[{"issue":"4\u20136","key":"3170_CR1","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1159\/000086997","volume":"68","author":"YS Oh","year":"2005","unstructured":"Oh YS, Early DS, Azar RR (2005) Clinical applications of endoscopic ultrasound to oncology. Oncology 68(4\u20136):526\u2013537","journal-title":"Oncology"},{"issue":"8","key":"3170_CR2","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1109\/TMI.2006.877092","volume":"25","author":"JA Noble","year":"2006","unstructured":"Noble JA, Boukerroui D (2006) Ultrasound image segmentation: a survey. IEEE TMI 25(8):987\u20131010. https:\/\/doi.org\/10.1109\/TMI.2006.877092","journal-title":"IEEE TMI"},{"key":"3170_CR3","unstructured":"Duque VG, Alchanti D, Crouzier M, Nordez A, Lacourpaille L, Mateus D (2020) Low-limb muscles segmentation in 3d freehand ultrasound using non-learning methods and label transfer. In: 16th SIPAIM, vol 11583, pp 154\u2013163"},{"key":"3170_CR4","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-cam: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE ICCV conference, pp 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"key":"3170_CR5","doi-asserted-by":"crossref","unstructured":"Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2016) Learning deep features for discriminative localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2921\u20132929","DOI":"10.1109\/CVPR.2016.319"},{"key":"3170_CR6","first-page":"9505","volume":"31","author":"J Adebayo","year":"2018","unstructured":"Adebayo J, Gilmer J, Muelly M, Goodfellow I, Hardt M, Kim B (2018) Sanity checks for saliency maps. Adv Neural Inf Process Syst 31:9505","journal-title":"Adv Neural Inf Process Syst"},{"key":"3170_CR7","first-page":"20040","volume":"34","author":"Y Zhang","year":"2021","unstructured":"Zhang Y, Khakzar A, Li Y, Farshad A, Kim ST, Navab N (2021) Fine-grained neural network explanation by identifying input features with predictive information. Adv Neural Inf Process Syst 34:20040\u201320051","journal-title":"Adv Neural Inf Process Syst"},{"issue":"1","key":"3170_CR8","doi-asserted-by":"publisher","first-page":"17024","DOI":"10.1038\/s41598-022-20653-2","volume":"12","author":"Y Jung","year":"2022","unstructured":"Jung Y, Kim T, Han M-R, Kim S, Kim G, Lee S, Choi YJ (2022) Ovarian tumor diagnosis using deep convolutional neural networks and a denoising convolutional autoencoder. Sci Rep 12(1):17024","journal-title":"Sci Rep"},{"key":"3170_CR9","first-page":"32","volume":"8","author":"R Du","year":"2022","unstructured":"Du R, Chen Y, Li T, Shi L, Fei Z, Li Y (2022) Discrimination of breast cancer based on ultrasound images and convolutional neural network. J Oncol 8:32","journal-title":"J Oncol"},{"key":"3170_CR10","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention\u201418th MICCAI conference. Springer, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3170_CR11","unstructured":"Oktay O, Schlemper J, Folgoc LL, Lee M, Heinrich M, Misawa K, Mori K, McDonagh S, Hammerla NY, Kainz B, Glocker B, Rueckert D (2018) Attention u-net: learning where to look for the pancreas. MIDL conference"},{"key":"3170_CR12","doi-asserted-by":"crossref","unstructured":"Hatamizadeh A, Tang Y, Nath V, Yang D, Myronenko A, Landman B, Roth HR, Xu D (2022) Unetr: transformers for 3d medical image segmentation. In: Proceedings of the IEEE\/CVF conference, pp 574\u2013584","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"3170_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2022.102372","volume":"132","author":"RL Draelos","year":"2022","unstructured":"Draelos RL, Carin L (2022) Explainable multiple abnormality classification of chest CT volumes. Artif Intell Med 132:102372","journal-title":"Artif Intell Med"},{"key":"3170_CR14","doi-asserted-by":"crossref","unstructured":"Jamil MS, Banik SP, Rahaman GA, Saha S (2023) Advanced gradcam++: improved visual explanations of CNN decisions in diabetic retinopathy. In: Computer vision and image analysis for industry 4.0, pp 64\u201375","DOI":"10.1201\/9781003256106-6"},{"key":"3170_CR15","first-page":"1","volume":"6","author":"H Zhang","year":"2023","unstructured":"Zhang H, Hu L, Liang W, Li Z, Yuan M, Ye Y, Wang Z, Ren Y, Li X (2023) BCT-OFD: bridging CNN and transformer via online feature distillation for covid-19 image recognition. Int J Mach Learn Cybern 6:1\u201320","journal-title":"Int J Mach Learn Cybern"},{"key":"3170_CR16","unstructured":"Lee S, Lee J, Lee J, Park C-K, Yoon S (2018) Robust tumor localization with pyramid grad-cam. CoRR"},{"key":"3170_CR17","doi-asserted-by":"crossref","unstructured":"Jiang H, Xu J, Shi R, Yang K, Zhang D, Gao M, Ma H, Qian W (2020) A multi-label deep learning model with interpretable grad-cam for diabetic retinopathy classification. In: 2020 42nd Annual international conference of the IEEE engineering in medicine and biology society (EMBC). IEEE, pp 1560\u20131563","DOI":"10.1109\/EMBC44109.2020.9175884"},{"key":"3170_CR18","doi-asserted-by":"crossref","unstructured":"Xiao M, Zhang L, Shi W, Liu J, He W, Jiang Z (2021) A visualization method based on the grad-cam for medical image segmentation model. In: 2021 EIECS conference. IEEE, pp 242\u2013247","DOI":"10.1109\/EIECS53707.2021.9587953"},{"key":"3170_CR19","doi-asserted-by":"crossref","unstructured":"Hasany SN, Petitjean C, M\u00e9riaudeau F (2023) SEG-XRES-CAM: explaining spatially local regions in image segmentation. In: Proceedings of the IEEE\/CVF CVPR conference, pp 3732\u20133737","DOI":"10.1109\/CVPRW59228.2023.00384"},{"issue":"7","key":"3170_CR20","doi-asserted-by":"publisher","first-page":"0268550","DOI":"10.1371\/journal.pone.0268550","volume":"17","author":"M Kronke","year":"2022","unstructured":"Kronke M, Eilers C, Dimova D, Kohler M, Buschner G, Schweiger L, Konstantinidou L, Makowski M, Nagarajah J, Navab N, Weber W, Wendler T (2022) Tracked 3d ultrasound and deep neural network-based thyroid segmentation reduce interobserver variability in thyroid volumetry. Plos One 17(7):0268550","journal-title":"Plos One"},{"issue":"22","key":"3170_CR21","doi-asserted-by":"publisher","first-page":"7741","DOI":"10.3390\/s21227741","volume":"21","author":"CA Jimenez-Casta\u00f1o","year":"2021","unstructured":"Jimenez-Casta\u00f1o CA, \u00c1lvarez-Meza AM, Aguirre-Ospina OD, C\u00e1rdenas-Pe\u00f1a DA, Orozco-Guti\u00e9rrez \u00c1A (2021) Random Fourier features-based deep learning improvement with class activation interpretability for nerve structure segmentation. Sensors 21(22):7741","journal-title":"Sensors"},{"issue":"21","key":"3170_CR22","doi-asserted-by":"publisher","DOI":"10.1242\/jeb.187260","volume":"221","author":"M Crouzier","year":"2018","unstructured":"Crouzier M, Lacourpaille L, Nordez A, Tucker K, Hug F (2018) Neuromechanical coupling within the human triceps surae and its consequence on individual force-sharing strategies. J Exp Biol 221(21):187260","journal-title":"J Exp Biol"},{"issue":"2","key":"3170_CR23","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1259\/bjr\/80676194","volume":"77","author":"A Gee","year":"2004","unstructured":"Gee A, Prager R, Treece G, Cash C, Berman L (2004) Processing and visualizing three-dimensional ultrasound data. Br J Radiol 77(2):186\u2013193","journal-title":"Br J Radiol"},{"key":"3170_CR24","unstructured":"Cardoso MJ, Li W, Brown R, Ma N, Kerfoot E, Wang Y, Murrey B, Myronenko A, Zhao C, Yang D, Feng A (2022) Monai: an open-source framework for deep learning in healthcare. arXiv preprint arXiv:2211.02701"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-024-03170-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-024-03170-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-024-03170-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,25]],"date-time":"2024-11-25T10:06:39Z","timestamp":1732529199000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-024-03170-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,25]]},"references-count":24,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["3170"],"URL":"https:\/\/doi.org\/10.1007\/s11548-024-03170-7","relation":{},"ISSN":["1861-6429"],"issn-type":[{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,25]]},"assertion":[{"value":"7 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The experimental procedures were approved by the local ethics committee (Rennes Ouest V, CPP-MIP-010), and all procedures adhered to the Declaration of Helsinki.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate and publish"}}]}}