{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T13:57:48Z","timestamp":1788962268557,"version":"build-2803163510"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"vor","delay-in-days":60,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["101073222"],"award-info":[{"award-number":["101073222"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Neoadjuvant chemotherapy is a standard clinical practice for tumor downsizing in breast cancer, with\n                    <jats:inline-formula>\n                      <jats:tex-math>$$^{18}$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    F-FDG Positron Emission Tomography (PET) being an essential tool for predicting complete pathological response and monitoring treatment. Our work aims to leverage PET imaging for automated segmentation of breast lesions and biomarker analysis before and after the first course of chemotherapy. We developed a system to segment primary tumor regions and extract biomarkers reflecting tumor evolution. A total of 243 baseline and 180 follow-up\n                    <jats:inline-formula>\n                      <jats:tex-math>$$^{18}$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    F-FDG PET scans were acquired. Ground truth annotations were generated semi-automatically for all baseline scans and manually for 12 test cases. A deep learning-based segmentation method was developed and evaluated using various architectures. The optimal baseline model, trained on baseline exams, was fine-tuned on 15 follow-up scans using active learning to segment tumors in follow-up exams. The pipeline extracts maximum standardized uptake value (SUV\n                    <jats:inline-formula>\n                      <jats:tex-math>$$_{max}$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    ), metabolic tumor volume (MTV), and total lesion glycolysis (TLG) to assess tumor response. Quality control procedures were used to exclude outliers. Among the tested approaches, nnUNet achieved the best tumor segmentation on PET baseline scans, with a Dice similarity coefficient of\n                    <jats:inline-formula>\n                      <jats:tex-math>$$0.89 \\pm 0.04$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    and a Hausdorff distance of\n                    <jats:inline-formula>\n                      <jats:tex-math>$$3.52 \\pm 0.76$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    mm on the test set. After fine-tuning, performance on follow-up exams reached a Dice similarity coefficient of\n                    <jats:inline-formula>\n                      <jats:tex-math>$$0.78 \\pm 0.03$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    and Hausdorff distance of\n                    <jats:inline-formula>\n                      <jats:tex-math>$$4.95 \\pm 0.12$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    mm. Biomarker analysis showed strong correlations between manual and automatic segmentations. The average\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\Delta SUV_{max}$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    ,\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\Delta MTV$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    , and\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\Delta TLG$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    between 12 baseline and follow-up scans used for testing were\n                    <jats:inline-formula>\n                      <jats:tex-math>$$-6.02 \\pm 1.55$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    (p=0.002),\n                    <jats:inline-formula>\n                      <jats:tex-math>$$-9.30 \\pm 2.33$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    cm\n                    <jats:inline-formula>\n                      <jats:tex-math>$$^3$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    (p=0.007), and\n                    <jats:inline-formula>\n                      <jats:tex-math>$$-14.09 \\pm 6.33$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    cm\n                    <jats:inline-formula>\n                      <jats:tex-math>$$^3$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    (p=0.010), respectively. The proposed method provides an effective automated system for breast tumor segmentation from\n                    <jats:inline-formula>\n                      <jats:tex-math>$$^{18}$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    F-FDG PET. Thanks to biomarkers extracted from the automatic segmentations on both baseline and follow-up exams, our method enables the automatic assessment of cancer progression.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-50945-w","type":"journal-article","created":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T09:26:24Z","timestamp":1779096384000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Automatic computation of breast cancer biomarkers from multiple $$^{18}$$ F-FDG PET image segmentation"],"prefix":"10.1038","volume":"16","author":[{"given":"Tewele W.","family":"Tareke","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neree","family":"Payan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandre","family":"Cochet","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laurent","family":"Arnould","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beno\u00eet","family":"Presles","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jean-Marc","family":"Vrigneaud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabrice","family":"Meriaudeau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alain","family":"Lalande","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,18]]},"reference":[{"key":"50945_CR1","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/S0039-6257(00)00165-X","volume":"343","author":"P Lichtenstein","year":"2000","unstructured":"Lichtenstein, P. et al. Environmental and heritable factors in the causation of cancer\u2013analyses of cohorts of twins from Sweden, Denmark, and Finland. N. Engl. J. Med. 343, 78\u201385. https:\/\/doi.org\/10.1016\/S0039-6257(00)00165-X (2000).","journal-title":"N. Engl. J. Med."},{"key":"50945_CR2","doi-asserted-by":"publisher","first-page":"2572","DOI":"10.1093\/annonc\/mds071","volume":"23","author":"O Humbert","year":"2012","unstructured":"Humbert, O. et al. Changes in 18f-fdg tumor metabolism after a first course of neoadjuvant chemotherapy in breast cancer: influence of tumor subtypes. Ann. Oncol. 23, 2572\u20132577. https:\/\/doi.org\/10.1093\/annonc\/mds071 (2012).","journal-title":"Ann. Oncol."},{"key":"50945_CR3","doi-asserted-by":"publisher","first-page":"452","DOI":"10.1016\/10.6004\/jnccn.2020.0016","volume":"18","author":"WJ Gradishar","year":"2020","unstructured":"Gradishar, W. J. et al. Breast cancer, version 3.2020, nccn clinical practice guidelines in oncology. J. Natl. Compr. Cancer Netw. 18, 452\u2013478. https:\/\/doi.org\/10.1016\/10.6004\/jnccn.2020.0016 (2020).","journal-title":"J. Natl. Compr. Cancer Netw."},{"key":"50945_CR4","doi-asserted-by":"publisher","first-page":"1796","DOI":"10.1200\/JCO.2011.38.8","volume":"30","author":"G Von Minckwitz","year":"2012","unstructured":"Von Minckwitz, G. et al. Definition and impact of pathologic complete response on prognosis after neoadjuvant chemotherapy in various intrinsic breast cancer subtypes. J. Clin. Oncol. 30, 1796\u20131804. https:\/\/doi.org\/10.1200\/JCO.2011.38.8 (2012).","journal-title":"J. Clin. Oncol."},{"key":"50945_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11307-018-1181-3","volume":"21","author":"K Paydary","year":"2019","unstructured":"Paydary, K. et al. The evolving role of fdg-pet\/ct in the diagnosis, staging, and treatment of breast cancer. Mol. Imaging Biol. 21, 1\u201310. https:\/\/doi.org\/10.1007\/s11307-018-1181-3 (2019).","journal-title":"Mol. Imaging Biol."},{"key":"50945_CR6","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1634\/theoncologist.2014-0342","volume":"20","author":"O Humbert","year":"2015","unstructured":"Humbert, O. et al. Role of positron emission tomography for the monitoring of response to therapy in breast cancer. The Oncologist 20, 94\u2013104. https:\/\/doi.org\/10.1634\/theoncologist.2014-0342 (2015).","journal-title":"The Oncologist"},{"key":"50945_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13058-020-01350-2","volume":"22","author":"S Han","year":"2020","unstructured":"Han, S. & Choi, J. Y. Prognostic value of 18 f-fdg pet and pet\/ct for assessment of treatment response to neoadjuvant chemotherapy in breast cancer: a systematic review and meta-analysis. Breast Cancer Res. 22, 1\u201315. https:\/\/doi.org\/10.1186\/s13058-020-01350-2 (2020).","journal-title":"Breast Cancer Res."},{"key":"50945_CR8","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1007\/s00259-007-0459-5","volume":"34","author":"A Berriolo-Riedinger","year":"2007","unstructured":"Berriolo-Riedinger, A. et al. [18 f] fdg-pet predicts complete pathological response of breast cancer to neoadjuvant chemotherapy. Eur. J. Nuclear Med. Mol. Imaging 34, 1915\u20131924. https:\/\/doi.org\/10.1007\/s00259-007-0459-5 (2007).","journal-title":"Eur. J. Nuclear Med. Mol. Imaging"},{"key":"50945_CR9","doi-asserted-by":"publisher","first-page":"428","DOI":"10.1007\/s00259-013-2595-4","volume":"41","author":"A Cochet","year":"2014","unstructured":"Cochet, A. et al. 18 f-fdg pet\/ct provides powerful prognostic stratification in the primary staging of large breast cancer when compared with conventional explorations. Eur. J. Nuclear Med. Mol. Imaging 41, 428\u2013437. https:\/\/doi.org\/10.1007\/s00259-013-2595-4 (2014).","journal-title":"Eur. J. Nuclear Med. Mol. Imaging"},{"key":"50945_CR10","doi-asserted-by":"publisher","first-page":"512","DOI":"10.2967\/jnumed.111.096834","volume":"53","author":"A Cochet","year":"2012","unstructured":"Cochet, A. et al. Evaluation of breast tumor blood flow with dynamic first-pass 18f-fdg pet\/ct: comparison with angiogenesis markers and prognostic factors. J. Nuclear Med. 53, 512\u2013520. https:\/\/doi.org\/10.2967\/jnumed.111.096834 (2012).","journal-title":"J. Nuclear Med."},{"key":"50945_CR11","doi-asserted-by":"publisher","first-page":"1682","DOI":"10.1007\/s00259-015-3110-x","volume":"42","author":"D Groheux","year":"2015","unstructured":"Groheux, D. et al. Do clinical, histological or immunohistochemical primary tumour characteristics translate into different 18 f-fdg pet\/ct volumetric and heterogeneity features in stage ii\/iii breast cancer?. Eur. J. Nuclear Med. Mol. Imaging 42, 1682\u20131691. https:\/\/doi.org\/10.1007\/s00259-015-3110-x (2015).","journal-title":"Eur. J. Nuclear Med. Mol. Imaging"},{"key":"50945_CR12","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.remn.2021.02.010","volume":"41","author":"C Can","year":"2022","unstructured":"Can, C. et al. The prognostic role of baseline 18f-fdg pet\/ct suvmax and suvmax change in patients with node-positive breast cancer receiving neoadjuvant chemotherapy. Rev. Esp. Med. Nuclear Imagen Mol. (Engl. Ed.) 41, 3\u201310. https:\/\/doi.org\/10.1016\/j.remn.2021.02.010 (2022).","journal-title":"Rev. Esp. Med. Nuclear Imagen Mol. (Engl. Ed.)"},{"key":"50945_CR13","doi-asserted-by":"publisher","DOI":"10.1007\/s00259-019-04422-4","author":"N Payan","year":"2020","unstructured":"Payan, N. et al. Biological correlates of tumor perfusion and its heterogeneity in newly diagnosed breast cancer using dynamic first-pass 18 f-fdg pet\/ct. Eur. J. Nuclear Med. Mol. Imaging https:\/\/doi.org\/10.1007\/s00259-019-04422-4 (2020).","journal-title":"Eur. J. Nuclear Med. Mol. Imaging"},{"key":"50945_CR14","doi-asserted-by":"publisher","first-page":"1525","DOI":"10.1007\/s00259-014-2739-1","volume":"41","author":"O Humbert","year":"2014","unstructured":"Humbert, O. et al. Her2-positive breast cancer: 18 f-fdg pet for early prediction of response to trastuzumab plus taxane-based neoadjuvant chemotherapy. Eur. J. Nuclear Med. Mol. Imaging 41, 1525\u20131533. https:\/\/doi.org\/10.1007\/s00259-014-2739-1 (2014).","journal-title":"Eur. J. Nuclear Med. Mol. Imaging"},{"key":"50945_CR15","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1200\/JCO.2008.17.2650","volume":"27","author":"J Schwarz-Dose","year":"2009","unstructured":"Schwarz-Dose, J. et al. Monitoring primary systemic therapy of large and locally advanced breast cancer by using sequential positron emission tomography imaging with [18f] fluorodeoxyglucose. J. Clin. Oncol. 27, 535\u2013541. https:\/\/doi.org\/10.1200\/JCO.2008.17.2650 (2009).","journal-title":"J. Clin. Oncol."},{"key":"50945_CR16","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1007\/s10334-017-0610-7","volume":"30","author":"F Gallivanone","year":"2017","unstructured":"Gallivanone, F. et al. Biomarkers from in vivo molecular imaging of breast cancer: pretreatment 18 f-fdg pet predicts patient prognosis, and pretreatment dwi-mr predicts response to neoadjuvant chemotherapy. Magn. Reson. Mater. Phys. Biol. Med. 30, 359\u2013373. https:\/\/doi.org\/10.1007\/s10334-017-0610-7 (2017).","journal-title":"Magn. Reson. Mater. Phys. Biol. Med."},{"key":"50945_CR17","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1109\/TMI.2010.2083681","volume":"30","author":"A-S Dewalle-Vignion","year":"2010","unstructured":"Dewalle-Vignion, A.-S. et al. A new method for volume segmentation of pet images, based on possibility theory. IEEE Trans. Med. Imaging 30, 409\u2013423. https:\/\/doi.org\/10.1109\/TMI.2010.2083681 (2010).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"50945_CR18","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.1016\/S0039-6257(00)00165-X","volume":"46","author":"U Nestle","year":"2005","unstructured":"Nestle, U. et al. Comparison of different methods for delineation of 18f-fdg pet-positive tissue for target volume definition in radiotherapy of patients with non-small cell lung cancer. J. Nuclear Med. 46, 1342\u20131348. https:\/\/doi.org\/10.1016\/S0039-6257(00)00165-X (2005).","journal-title":"J. Nuclear Med."},{"key":"50945_CR19","doi-asserted-by":"publisher","first-page":"1989","DOI":"10.1007\/s00259-008-0875-1","volume":"35","author":"A Schaefer","year":"2008","unstructured":"Schaefer, A. et al. A contrast-oriented algorithm for fdg-pet-based delineation of tumour volumes for the radiotherapy of lung cancer: derivation from phantom measurements and validation in patient data. Eur. J. Nuclear Med. Mol. Imaging 35, 1989\u20131999. https:\/\/doi.org\/10.1007\/s00259-008-0875-1 (2008).","journal-title":"Eur. J. Nuclear Med. Mol. Imaging"},{"key":"50945_CR20","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1118\/1.2870215","volume":"35","author":"M Brambilla","year":"2008","unstructured":"Brambilla, M. et al. Threshold segmentation for pet target volume delineation in radiation treatment planning: the role of target-to-background ratio and target size. Med. Phys. 35, 1207\u20131213. https:\/\/doi.org\/10.1118\/1.2870215 (2008).","journal-title":"Med. Phys."},{"key":"50945_CR21","doi-asserted-by":"publisher","first-page":"5969","DOI":"10.1088\/0031-9155\/50\/24\/014","volume":"50","author":"B Yaremko","year":"2005","unstructured":"Yaremko, B. et al. Thresholding in pet images of static and moving targets. Phys. Med. Biol. 50, 5969. https:\/\/doi.org\/10.1088\/0031-9155\/50\/24\/014 (2005).","journal-title":"Phys. Med. Biol."},{"key":"50945_CR22","doi-asserted-by":"publisher","first-page":"2764","DOI":"10.3390\/cancers13112764","volume":"13","author":"XY Liew","year":"2021","unstructured":"Liew, X. Y., Hameed, N. & Clos, J. A review of computer-aided expert systems for breast cancer diagnosis. Cancers 13, 2764. https:\/\/doi.org\/10.3390\/cancers13112764 (2021).","journal-title":"Cancers"},{"key":"50945_CR23","doi-asserted-by":"publisher","first-page":"4855","DOI":"10.1088\/0031-9155\/61\/13\/4855","volume":"61","author":"B Berthon","year":"2016","unstructured":"Berthon, B., Marshall, C., Evans, M. & Spezi, E. Atlaas: an automatic decision tree-based learning algorithm for advanced image segmentation in positron emission tomography. Phys. Med. Biol. 61, 4855. https:\/\/doi.org\/10.1088\/0031-9155\/61\/13\/4855 (2016).","journal-title":"Phys. Med. Biol."},{"key":"50945_CR24","doi-asserted-by":"publisher","first-page":"3711","DOI":"10.1118\/1.2956713","volume":"35","author":"H Li","year":"2008","unstructured":"Li, H. et al. A novel pet tumor delineation method based on adaptive region-growing and dual-front active contours. Med. Phys. 35, 3711\u20133721. https:\/\/doi.org\/10.1118\/1.2956713 (2008).","journal-title":"Med. Phys."},{"key":"50945_CR25","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1109\/TITB.2006.874192","volume":"10","author":"J Kim","year":"2006","unstructured":"Kim, J., Cai, W., Feng, D. & Eberl, S. Segmentation of voi from multidimensional dynamic pet images by integrating spatial and temporal features. IEEE Trans. Inf. Technol. Biomed. 10, 637\u2013646. https:\/\/doi.org\/10.1109\/TITB.2006.874192 (2006).","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"50945_CR26","doi-asserted-by":"publisher","first-page":"414","DOI":"10.2967\/jnumed.113.129858","volume":"55","author":"F Orlhac","year":"2014","unstructured":"Orlhac, F. et al. Tumor texture analysis in 18f-fdg pet: relationships between texture parameters, histogram indices, standardized uptake values, metabolic volumes, and total lesion glycolysis. J. Nuclear Med. 55, 414\u2013422. https:\/\/doi.org\/10.2967\/jnumed.113.129858 (2014).","journal-title":"J. Nuclear Med."},{"key":"50945_CR27","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.compbiomed.2014.04.014","volume":"50","author":"B Foster","year":"2014","unstructured":"Foster, B., Bagci, U., Mansoor, A., Xu, Z. & Mollura, D. J. A review on segmentation of positron emission tomography images. Comput. Biol. Med. 50, 76\u201396. https:\/\/doi.org\/10.1016\/j.compbiomed.2014.04.014 (2014).","journal-title":"Comput. Biol. Med."},{"issue":"1","key":"50945_CR28","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1186\/s41824-025-00274-4","volume":"9","author":"L Alonzo","year":"2025","unstructured":"Alonzo, L. et al. Molecular imaging in the diagnostic process of neuroendocrine tumors: A systematic review on unknown primary origin and suspected nets. EJNMMI Rep. 9(1), 38 (2025).","journal-title":"EJNMMI Rep."},{"key":"50945_CR29","doi-asserted-by":"crossref","unstructured":"Canfora, I. et al. A predictive system to classify preoperative grading of rectal cancer using radiomics features. In International Conference on Image Analysis and Processing, 431\u2013440 (Springer, 2022).","DOI":"10.1007\/978-3-031-13321-3_38"},{"key":"50945_CR30","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5\u20139, 2015 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"50945_CR31","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1016\/j.future.2019.11.021","volume":"108","author":"S Qamar","year":"2020","unstructured":"Qamar, S., Jin, H., Zheng, R., Ahmad, P. & Usama, M. A variant form of 3d-unet for infant brain segmentation. Future Gener. Comput. Syst. 108, 613\u2013623. https:\/\/doi.org\/10.1016\/j.future.2019.11.021 (2020).","journal-title":"Future Gener. Comput. Syst."},{"key":"50945_CR32","doi-asserted-by":"publisher","first-page":"203","DOI":"10.48550\/arXiv.1809.10486","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee, F., Jaeger, P. F., Kohl, S. A., Petersen, J. & Maier-Hein, K. H. nnu-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat. methods 18, 203\u2013211. https:\/\/doi.org\/10.48550\/arXiv.1809.10486 (2021).","journal-title":"Nat. methods"},{"key":"50945_CR33","doi-asserted-by":"publisher","unstructured":"Robin, M., John, J. & Ravikumar, A. Breast tumor segmentation using u-net. In 2021 5th International Conference on Computing Methodologies and Communication (ICCMC), 1164\u20131167 (IEEE, 2021). https:\/\/doi.org\/10.1109\/ICCMC51019.2021.9418447.","DOI":"10.1109\/ICCMC51019.2021.9418447"},{"key":"50945_CR34","doi-asserted-by":"publisher","first-page":"853","DOI":"10.1007\/s00158-009-0460-7","volume":"41","author":"RT Marler","year":"2010","unstructured":"Marler, R. T. & Arora, J. S. The weighted sum method for multi-objective optimization: new insights. Struct. Multidiscip. Optim. 41, 853\u2013862. https:\/\/doi.org\/10.1007\/s00158-009-0460-7 (2010).","journal-title":"Struct. Multidiscip. Optim."},{"key":"50945_CR35","doi-asserted-by":"crossref","unstructured":"Salehi, S. S. M., Erdogmus, D. & Gholipour, A. Tversky loss function for image segmentation using 3d fully convolutional deep networks. In International Workshop on Machine Learning in Medical Imaging, 379\u2013387 (Springer, 2017).","DOI":"10.1007\/978-3-319-67389-9_44"},{"key":"50945_CR36","doi-asserted-by":"publisher","DOI":"10.30534\/ijatcse\/2020\/175942020","author":"U Ruby","year":"2020","unstructured":"Ruby, U. & Yendapalli, V. Binary cross entropy with deep learning technique for image classification. Trends Comput. Sci. Eng. https:\/\/doi.org\/10.30534\/ijatcse\/2020\/175942020 (2020).","journal-title":"Trends Comput. Sci. Eng."},{"key":"50945_CR37","doi-asserted-by":"publisher","unstructured":"Cappabianco, F. A., Ribeiro, P. F., De Miranda, P. A. & Udupa, J. K. A general and balanced region-based metric for evaluating medical image segmentation algorithms. In 2019 IEEE International Conference on Image Processing (ICIP), 1525\u20131529 (IEEE, 2019). https:\/\/doi.org\/10.1109\/ICIP.2019.8803083.","DOI":"10.1109\/ICIP.2019.8803083"},{"key":"50945_CR38","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1080\/07038992.1998.10874685","volume":"24","author":"M Beauchemin","year":"1998","unstructured":"Beauchemin, M., Thomson, K. P. & Edwards, G. On the Hausdorff distance used for the evaluation of segmentation results. Can. J. Remote Sens. 24, 3\u20138. https:\/\/doi.org\/10.1080\/07038992.1998.10874685 (1998).","journal-title":"Can. J. Remote Sens."},{"key":"50945_CR39","doi-asserted-by":"publisher","first-page":"733","DOI":"10.1002\/cyto.a.20896","volume":"77","author":"J Adler","year":"2010","unstructured":"Adler, J. & Parmryd, I. Quantifying colocalization by correlation: the Pearson correlation coefficient is superior to the Mander\u2019s overlap coefficient. Cytom. Part A 77, 733\u2013742. https:\/\/doi.org\/10.1002\/cyto.a.20896 (2010).","journal-title":"Cytom. Part A"},{"issue":"8476","key":"50945_CR40","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1016\/S0140-6736(86)90837-8","volume":"327","author":"JM Bland","year":"1986","unstructured":"Bland, J. M. & Altman, D. Statistical methods for assessing agreement between two methods of clinical measurement. The Lancet 327(8476), 307\u2013310 (1986).","journal-title":"The Lancet"},{"key":"50945_CR41","doi-asserted-by":"publisher","first-page":"101","DOI":"10.3390\/cancers14010101","volume":"14","author":"N Moreau","year":"2021","unstructured":"Moreau, N. et al. Automatic segmentation of metastatic breast cancer lesions on 18f-fdg pet\/ct longitudinal acquisitions for treatment response assessment. Cancers 14, 101. https:\/\/doi.org\/10.3390\/cancers14010101 (2021).","journal-title":"Cancers"},{"key":"50945_CR42","doi-asserted-by":"publisher","unstructured":"Myronenko, A., Siddiquee, M. M. R., Yang, D., He, Y. & Xu, D. Automated head and neck tumor segmentation from 3D pet\/ct hecktor 2022 challenge report. In 3D Head and Neck Tumor Segmentation in PET\/CT Challenge, 31\u201337 (2022). https:\/\/doi.org\/10.1007\/978-3-031-27420-6_2","DOI":"10.1007\/978-3-031-27420-6_2"},{"key":"50945_CR43","doi-asserted-by":"publisher","unstructured":"Moreau, N. et al. Deep learning approaches for bone and bone lesion segmentation on 18fdg pet\/ct imaging in the context of metastatic breast cancer. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 1532\u20131535 (IEEE, 2020). https:\/\/doi.org\/10.1109\/EMBC44109.2020.9175904.","DOI":"10.1109\/EMBC44109.2020.9175904"},{"key":"50945_CR44","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s00259-016-3427-0","volume":"44","author":"M Hatt","year":"2017","unstructured":"Hatt, M. et al. Characterization of pet\/ct images using texture analysis: the past, the present... any future?. Eur. J. Nuclear Med. Mol. Imaging 44, 151\u2013165. https:\/\/doi.org\/10.1007\/s00259-016-3427-0 (2017).","journal-title":"Eur. J. Nuclear Med. Mol. Imaging"},{"key":"50945_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/10.1186\/s41747-019-0096-3","volume":"3","author":"W-D Vogl","year":"2019","unstructured":"Vogl, W.-D. et al. Automatic segmentation and classification of breast lesions through identification of informative multiparametric pet\/mri features. Eur. Radiol. Exp. 3, 1\u201313. https:\/\/doi.org\/10.1016\/10.1186\/s41747-019-0096-3 (2019).","journal-title":"Eur. Radiol. Exp."},{"key":"50945_CR46","doi-asserted-by":"publisher","first-page":"3261","DOI":"10.1109\/JBHI.2022.3164570","volume":"26","author":"X Qiao","year":"2022","unstructured":"Qiao, X. et al. Improving breast tumor segmentation in pet via attentive transformation based normalization. IEEE J. Biomed. Health Inform. 26, 3261\u20133271. https:\/\/doi.org\/10.1109\/JBHI.2022.3164570 (2022).","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"50945_CR47","doi-asserted-by":"publisher","first-page":"21149","DOI":"10.1038\/s41598-020-77875-5","volume":"10","author":"JH Choi","year":"2020","unstructured":"Choi, J. H. et al. Early prediction of neoadjuvant chemotherapy response for advanced breast cancer using pet\/mri image deep learning. Sci. Rep. 10, 21149 (2020).","journal-title":"Sci. Rep."},{"key":"50945_CR48","doi-asserted-by":"publisher","first-page":"5460","DOI":"10.1158\/1078-0432.CCR-15-0384","volume":"21","author":"O Humbert","year":"2015","unstructured":"Humbert, O. et al. Identification of biomarkers including 18fdg-pet\/ct for early prediction of response to neoadjuvant chemotherapy in triple-negative breast cancer. Clin. Cancer Res. 21, 5460\u20135468. https:\/\/doi.org\/10.1158\/1078-0432.CCR-15-0384 (2015).","journal-title":"Clin. Cancer Res."},{"key":"50945_CR49","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1093\/ajcp\/aqw045","volume":"145","author":"X Li","year":"2016","unstructured":"Li, X. et al. Biomarkers predicting pathologic complete response to neoadjuvant chemotherapy in breast cancer. Am. J. Clin. Pathol. 145, 871\u2013878. https:\/\/doi.org\/10.1093\/ajcp\/aqw045 (2016).","journal-title":"Am. J. Clin. Pathol."},{"key":"50945_CR50","doi-asserted-by":"publisher","first-page":"1357","DOI":"10.1038\/sj.bjc.6605310","volume":"101","author":"F V\u00e9gran","year":"2009","unstructured":"V\u00e9gran, F. et al. Gene expression profile and response to trastuzumab-docetaxel-based treatment in breast carcinoma. Br. J. Cancer 101, 1357\u20131364. https:\/\/doi.org\/10.1038\/sj.bjc.6605310 (2009).","journal-title":"Br. J. Cancer"},{"key":"50945_CR51","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/j.breast.2012.07.012","volume":"22","author":"S Guiu","year":"2013","unstructured":"Guiu, S. et al. Pathological response and survival after neoadjuvant therapy for breast cancer: a 30-year study. The Breast 22, 301\u2013308. https:\/\/doi.org\/10.1016\/j.breast.2012.07.012 (2013).","journal-title":"The Breast"},{"key":"50945_CR52","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s13550-024-01115-4","volume":"14","author":"N Payan","year":"2024","unstructured":"Payan, N. et al. Respective contribution of baseline clinical data, tumour metabolism and tumour blood-flow in predicting pcr after neoadjuvant chemotherapy in her2 and triple negative breast cancer. EJNMMI Res. 14, 60. https:\/\/doi.org\/10.1186\/s13550-024-01115-4 (2024).","journal-title":"EJNMMI Res."},{"issue":"4","key":"50945_CR53","doi-asserted-by":"publisher","first-page":"643","DOI":"10.2967\/jnumed.123.267048","volume":"65","author":"KH Leung","year":"2024","unstructured":"Leung, K. H. et al. Deep semisupervised transfer learning for fully automated whole-body tumor quantification and prognosis of cancer on pet\/ct. J. Nuclear Med. 65(4), 643\u2013650 (2024).","journal-title":"J. Nuclear Med."},{"issue":"1","key":"50945_CR54","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1186\/s13550-021-00795-6","volume":"11","author":"KH Leung","year":"2021","unstructured":"Leung, K. H., Rowe, S. P., Pomper, M. G. & Du, Y. A three-stage, deep learning, ensemble approach for prognosis in patients with Parkinson\u2019s disease. EJNMMI Res. 11(1), 52 (2021).","journal-title":"EJNMMI Res."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50945-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50945-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50945-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T22:44:49Z","timestamp":1784241889000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-50945-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":54,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["50945"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-50945-w","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,18]]},"assertion":[{"value":"4 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study adhered to the principles outlined in the Declaration of Helsinki and received approval from the institutional ethics committee of the Georges-Fran\u00e7ois Leclerc Center. Patient non-opposition was documented in source records by the medical team and served as the basis for informed consent.","order":2,"name":"Ethics","label":"Ethical approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"22432"}}