{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T07:05:39Z","timestamp":1784185539149,"version":"3.55.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T00:00:00Z","timestamp":1779408000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T00:00:00Z","timestamp":1784160000000},"content-version":"vor","delay-in-days":55,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Imaging"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Small and low-contrast liver tumors remain challenging targets for contrast-enhanced CT segmentation because of severe class imbalance and limited long-range contextual modeling in conventional CNN encoders.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We developed OF-TransUNet, a minimalist hybrid that differs from parameter-heavy TransUNet-style variants by inserting a single lightweight mid-level Conv-Transformer block at encoder stage 3 (\u00d78 downsampling) within an otherwise unchanged 2D nnU-Net, together with an output-focused progressive unfreezing schedule intended to improve adaptation stability. This design was motivated by unstable and poorly reproducible optimization observed under immediate full fine-tuning in internal ablation experiments. A public dataset (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009104) was used descriptively for architecture and schedule selection. The pre-specified primary endpoint was the external per-patient tumor Dice difference versus a standardized 2D nnU-Net baseline on an independent cohort (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200942). A pre-defined secondary lesion-level analysis focused on medium-sized tumors (10\u201350\u2009mm).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      On the external cohort, OF-TransUNet showed a numerically higher per-patient tumor Dice than nnU-Net (0.2788\u2009\u00b1\u20090.2575 vs 0.2400\u2009\u00b1\u20090.2426), with a mean paired difference of +0.0388 (95% CI 0.0029 to 0.0748). Because paired differences were non-normal, the pre-specified Wilcoxon signed-rank test was retained as the primary inferential analysis and was borderline (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.0553); a supplementary paired t-test yielded nominal significance (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.0347). In the pre-defined medium-lesion analysis (10\u201350\u2009mm;\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u200984), detection increased from 0.190 to 0.286 at the pre-specified 10% overlap threshold (McNemar exact\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.021; GEE OR 1.97, 95% CI 1.15\u20133.35). Post hoc sensitivity analyses using 5% and 15% overlap thresholds preserved the directional advantage. Relative to baseline, OF-TransUNet increased parameters by 8.4% and FLOPs by 18.3%, with no measurable latency penalty and only minimal memory increase.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>In this single-center external validation cohort, a single mid-level Conv-Transformer insertion plus output-focused progressive unfreezing was associated with a numerically higher per-patient tumor Dice and a statistically supported improvement in the pre-defined medium-lesion detection analysis, while preserving a lightweight computational profile. Because the pre-specified non-parametric primary patient-level analysis was borderline and did not reach conventional significance, the Dice finding should be interpreted cautiously. Tumor HD95 was numerically higher in OF-TransUNet, indicating a possible recall-boundary trade-off that requires further boundary-focused evaluation. Overall, this minimally invasive modification supports further multi-center validation rather than definitive claims of superiority. A supplementary controlled benchmark on the public LiTS dataset, limited to a single pre-fixed validation fold because only 131 public cases have released annotations for local evaluation, provided directionally consistent contextual evidence under an identical pipeline.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12880-026-02406-z","type":"journal-article","created":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T17:04:46Z","timestamp":1779469486000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient transformer integration in nnU-Net for liver tumor segmentation: an external validation study"],"prefix":"10.1186","volume":"26","author":[{"given":"He","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoping","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,22]]},"reference":[{"key":"2406_CR1","doi-asserted-by":"publisher","unstructured":"Cao H, Wang Y, Chen J, Jiang D, Zhang X, Tian Q, et al. Unet-like pure transformer for medical image segmentation. European Conference on Computer Vision. 2022. https:\/\/doi.org\/10.1007\/978-3-031-25066-8_9.","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"2406_CR2","doi-asserted-by":"publisher","unstructured":"Chen J, Lu Y, Yu Q, Luo X, Adeli E, Wang Y, et al. Transunet: transformers make strong encoders for medical image segmentation. arXiv. 2021. https:\/\/doi.org\/10.48550\/arXiv.2102.04306.","DOI":"10.48550\/arXiv.2102.04306"},{"issue":"2","key":"2406_CR3","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021;18(2):203\u201311. https:\/\/doi.org\/10.1038\/s41592-020-01008-z.","journal-title":"Nat Methods"},{"key":"2406_CR4","doi-asserted-by":"publisher","unstructured":"Moawad AW, Morshid A, Khalaf AM, Elmohr MM, Hazle JD, Fuentes D, et al. Multimodality annotated hepatocellular carcinoma data set including pre- and post-TACE with imaging segmentation. Sci Data Sci Data. 2023;10(1). https:\/\/doi.org\/10.1038\/s41597-023-01928-3.","DOI":"10.1038\/s41597-023-01928-3"},{"issue":"3","key":"2406_CR5","doi-asserted-by":"publisher","first-page":"229","DOI":"10.3322\/caac.21834","volume":"74","author":"F Bray","year":"2024","unstructured":"Bray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clinicians. 2024;74(3):229\u201363. https:\/\/doi.org\/10.3322\/caac.21834.","journal-title":"CA Cancer J Clinicians"},{"key":"2406_CR6","doi-asserted-by":"publisher","unstructured":"Llovet JM, Kelley RK, Villanueva A, Singal AG, Pikarsky E, Roayaie S, et al. Author correction: hepatocellular carcinoma. Nat Rev Dis Primers. 2024;10(1). https:\/\/doi.org\/10.1038\/s41572-024-00500-6.","DOI":"10.1038\/s41572-024-00500-6"},{"issue":"3","key":"2406_CR7","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1080\/21681163.2022.2099300","volume":"11","author":"S Saha Roy","year":"2023","unstructured":"Saha Roy S, Roy S, Mukherjee P, Halder Roy A. An automated liver tumour segmentation and classification model by deep learning based approaches. Comput Methods Biomech Biomed Eng: Imag Visual. 2023;11(3):638\u201350. https:\/\/doi.org\/10.1080\/21681163.2022.2099300.","journal-title":"Comput Methods Biomech Biomed Eng: Imag Visual"},{"key":"2406_CR8","doi-asserted-by":"publisher","unstructured":"Pang Y, Liang J, Huang T, Chen H, Li Y, Li D, et al. Scale hybrid transformers to efficient 3D medical image segmentation under limited computational resources. IEEE Transactions on Medical Imaging. 2023. https:\/\/doi.org\/10.1109\/TMI.2023.3326188.","DOI":"10.1109\/TMI.2023.3326188"},{"key":"2406_CR9","doi-asserted-by":"publisher","first-page":"103295","DOI":"10.1016\/j.media.2024.103295","volume":"98","author":"T Liu","year":"2024","unstructured":"Liu T, Bai Q, Torigian DA, Tong Y, Udupa JK. VSmTrans: a hybrid paradigm integrating self-attention and convolution for 3D medical image segmentation. Med Image Anal. 2024;98:103295. https:\/\/doi.org\/10.1016\/j.media.2024.103295.","journal-title":"Med Image Anal"},{"key":"2406_CR10","doi-asserted-by":"publisher","unstructured":"Isensee F, Wald T, Ulrich C, Baumgartner M, Roy S, Maier-Hein K, et al. Nnu-net revisited: a call for rigorous validation in 3D medical image segmentation. International Conference on Medical Image Computing and Computer-Assisted Intervention. 2024. https:\/\/doi.org\/10.1007\/978-3-031-72114-4_47.","DOI":"10.1007\/978-3-031-72114-4_47"},{"key":"2406_CR11","doi-asserted-by":"publisher","first-page":"103280","DOI":"10.1016\/j.media.2024.103280","volume":"97","author":"J Chen","year":"2024","unstructured":"Chen J, Mei J, Li X, Lu Y, Yu Q, Wei Q, et al. TransUNet: rethinking the U-Net architecture design for medical image segmentation through the lens of transformers. Med Image Anal. 2024;97:103280. https:\/\/doi.org\/10.1016\/j.media.2024.103280.","journal-title":"Med Image Anal"},{"key":"2406_CR12","doi-asserted-by":"publisher","unstructured":"Zhou HY, Guo J, Zhang Y, Han X, Yu L, Wang L, et al. nnFormer: volumetric medical image segmentation via a 3D transformer. IEEE Transactions on Image Processing. 2023. https:\/\/doi.org\/10.1109\/TIP.2023.3293771.","DOI":"10.1109\/TIP.2023.3293771"},{"key":"2406_CR13","doi-asserted-by":"publisher","first-page":"112841","DOI":"10.1016\/j.asoc.2025.112841","volume":"173","author":"Y Gao","year":"2025","unstructured":"Gao Y, Zhang S, Shi L, Zhao G, Shi Y. Collaborative transformer U-shaped network for medical image segmentation. Appl Soft Comput. 2025;173:112841. https:\/\/doi.org\/10.1016\/j.asoc.2025.112841.","journal-title":"Appl. Soft Comput"},{"key":"2406_CR14","doi-asserted-by":"publisher","unstructured":"Wang Y, Yu X, Yang Y, Zeng S, Xu Y, Feng R. Ftunet: a feature-enhanced network for medical image segmentation based on the combination of U-shaped network and vision transformer. Neural Process Lett. 2024;56(2). https:\/\/doi.org\/10.1007\/s11063-024-11533-z.","DOI":"10.1007\/s11063-024-11533-z"},{"key":"2406_CR15","doi-asserted-by":"publisher","unstructured":"Valanarasu JMJ, Patel VM. Unext: mlp-based rapid medical image segmentation network. International Conference on Medical Image Computing and Computer-Assisted Intervention. 2022. https:\/\/doi.org\/10.1007\/978-3-031-16443-9_3.","DOI":"10.1007\/978-3-031-16443-9_3"},{"key":"2406_CR16","unstructured":"Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, et al. Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res. 2020. https:\/\/jmlr.org\/papers\/v21\/20-074.html."},{"key":"2406_CR17","doi-asserted-by":"publisher","unstructured":"Azad R, Aghdam EK, Rauland A, Jia Y, Avval AH, Bozorgpour A, et al. Medical image segmentation review: the success of u-net. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024. https:\/\/doi.org\/10.1109\/TPAMI.2024.3435571.","DOI":"10.1109\/TPAMI.2024.3435571"},{"key":"2406_CR18","doi-asserted-by":"publisher","unstructured":"Huang X, Deng Z, Li D, Yuan X. Missformer: an effective medical image segmentation transformer. arXiv. 2021. https:\/\/doi.org\/10.48550\/arXiv.2109.07162.","DOI":"10.48550\/arXiv.2109.07162"},{"key":"2406_CR19","doi-asserted-by":"publisher","unstructured":"Hatamizadeh A, Xu Z, Yang D, Li W, Roth H, Xu D. Unetformer: a unified vision transformer model and pre-training framework for 3D medical image segmentation. arXiv. 2022. https:\/\/doi.org\/10.48550\/arXiv.2204.00631.","DOI":"10.48550\/arXiv.2204.00631"},{"key":"2406_CR20","doi-asserted-by":"publisher","unstructured":"Dutt R, Ericsson L, Sanchez P, Tsaftaris SA, Hospedales T. Parameter-efficient fine-tuning for medical image analysis: the missed opportunity. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2305.08252.","DOI":"10.48550\/arXiv.2305.08252"},{"key":"2406_CR21","doi-asserted-by":"publisher","first-page":"102918","DOI":"10.1016\/j.media.2023.102918","volume":"89","author":"MA Mazurowski","year":"2023","unstructured":"Mazurowski MA, Dong H, Gu H, Yang J, Konz N, Zhang Y. Segment anything model for medical image analysis: an experimental study. Med Image Anal. 2023;89:102918. https:\/\/doi.org\/10.1016\/j.media.2023.102918.","journal-title":"Med Image Anal"},{"key":"2406_CR22","unstructured":"Li J, Liu C, Cheng S, Arcucci R, Hong S. Frozen language model helps ecg zero-shot learning. Med Imag Deep Learn. 2024. https:\/\/proceedings.mlr.press\/v227\/li24a.html."},{"key":"2406_CR23","doi-asserted-by":"publisher","unstructured":"Chen J, Mei J, Li X, Lu Y, Yu Q, Wei Q, et al. 3D transunet: advancing medical image segmentation through vision transformers. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2310.07781.","DOI":"10.48550\/arXiv.2310.07781"},{"key":"2406_CR24","doi-asserted-by":"publisher","first-page":"102078","DOI":"10.1016\/j.artmed.2021.102078","volume":"116","author":"D Karimi","year":"2021","unstructured":"Karimi D, Warfield SK, Gholipour A. Transfer learning in medical image segmentation: new insights from analysis of the dynamics of model parameters and learned representations. Artif Intell Med. 2021;116:102078. https:\/\/doi.org\/10.1016\/j.artmed.2021.102078.","journal-title":"Artif Intell Med"},{"key":"2406_CR25","doi-asserted-by":"publisher","unstructured":"Chen J, Liu Q, Wei Z, Luo X, Lai M, Chen H, et al. ETU-Net: efficient Transformer and convolutional U-style connected attention segmentation network applied to endoscopic image of epistaxis. Front Med. 2023;10. https:\/\/doi.org\/10.3389\/fmed.2023.1198054.","DOI":"10.3389\/fmed.2023.1198054"},{"key":"2406_CR26","doi-asserted-by":"publisher","first-page":"110233","DOI":"10.1016\/j.patcog.2023.110233","volume":"149","author":"Y Ni","year":"2024","unstructured":"Ni Y, Chen G, Feng Z, Cui H, Metaxas D, Zhang S, et al. DA-Tran: multiphase liver tumor segmentation with a domain-adaptive transformer network. Pattern Recognit. 2024;149:110233. https:\/\/doi.org\/10.1016\/j.patcog.2023.110233.","journal-title":"Pattern Recognit"},{"key":"2406_CR27","doi-asserted-by":"publisher","unstructured":"Ji Z, Chen Z, Ma X. Grouped multi-scale vision transformer for medical image segmentation. Sci Rep. 2025;15(1). https:\/\/doi.org\/10.1038\/s41598-025-95361-8.","DOI":"10.1038\/s41598-025-95361-8"},{"key":"2406_CR28","doi-asserted-by":"publisher","first-page":"125067","DOI":"10.1016\/j.eswa.2024.125067","volume":"258","author":"C Li","year":"2024","unstructured":"Li C, Wang R, He P, Chen W, Wu W, Wu Y. Segmentation prompts classification: a nnUnet-based 3D transfer learning framework with ROI tokenization and cross-task attention for esophageal cancer t-stage diagnosis. Expert Syst Appl. 2024;258:125067. https:\/\/doi.org\/10.1016\/j.eswa.2024.125067.","journal-title":"Expert Syst Appl"},{"key":"2406_CR29","doi-asserted-by":"publisher","unstructured":"Kirillov A, Mintun E, Ravi N, Mao H, Rolland C, Gustafson L, et al. Segment anything. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2023. https:\/\/doi.org\/10.48550\/arXiv.2304.02643.","DOI":"10.48550\/arXiv.2304.02643"},{"key":"2406_CR30","doi-asserted-by":"publisher","unstructured":"Ma J, He Y, Li F, Han L, You C, Wang B. Segment anything in medical images. Nat Commun. 2024;15(1). https:\/\/doi.org\/10.1038\/s41467-024-44824-z.","DOI":"10.1038\/s41467-024-44824-z"},{"key":"2406_CR31","doi-asserted-by":"publisher","first-page":"40290","DOI":"10.1109\/ACCESS.2024.3374108","volume":"12","author":"T Hussain","year":"2024","unstructured":"Hussain T, Shouno H. Magres-UNet: improved medical image segmentation through a deep learning paradigm of multi-attention gated residual U-Net. IEEE Access. 2024;12:40290\u2013310. https:\/\/doi.org\/10.1109\/ACCESS.2024.3374108.","journal-title":"IEEE Access"},{"key":"2406_CR32","doi-asserted-by":"publisher","first-page":"113233","DOI":"10.1016\/j.knosys.2025.113233","volume":"314","author":"T Hussain","year":"2025","unstructured":"Hussain T, Shouno H, Mohammed MA, Marhoon HA, Alam T. DCSSGA-UNet: biomedical image segmentation with DenseNet channel spatial and semantic guidance attention. Knowl-Based Syst. 2025;314:113233. https:\/\/doi.org\/10.1016\/j.knosys.2025.113233.","journal-title":"Knowl-Based Syst"},{"key":"2406_CR33","doi-asserted-by":"publisher","unstructured":"Hussain T, Shouno H, Hussain A, et al. EFFResNet-ViT: a fusion-based convolutional and vision transformer model for explainable medical image classification. IEEE Access. 2025. https:\/\/doi.org\/10.1109\/ACCESS.2025.3554184.","DOI":"10.1109\/ACCESS.2025.3554184"},{"issue":"03","key":"2406_CR34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1117\/1.JMI.5.3.036501","volume":"5","author":"K Yan","year":"2018","unstructured":"Yan K, Wang X, Lu L, Summers RM. DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning. J Med Imag. 2018;5(03):1. https:\/\/doi.org\/10.1117\/1.JMI.5.3.036501.","journal-title":"J Med Imag"},{"key":"2406_CR35","doi-asserted-by":"publisher","first-page":"102680","DOI":"10.1016\/j.media.2022.102680","volume":"84","author":"P Bilic","year":"2023","unstructured":"Bilic P, Christ P, Li HB, Vorontsov E, Ben-Cohen A, Kaissis G, et al. The liver tumor segmentation benchmark (LiTS). Med Image Anal. 2023;84:102680. https:\/\/doi.org\/10.1016\/j.media.2022.102680.","journal-title":"Med Image Anal"},{"key":"2406_CR36","doi-asserted-by":"publisher","unstructured":"Tabibian M, Razmpour T, Saha R. Diffusion models vs. DCGANs for class-imbalanced lung cancer CT classification: a comparative study. Intell Based Med. 2026;13. https:\/\/doi.org\/10.1016\/j.ibmed.2025.100336.","DOI":"10.1016\/j.ibmed.2025.100336"},{"key":"2406_CR37","doi-asserted-by":"publisher","unstructured":"Ye Y, Chipusu K, Zeng T, Chen Y, Ding B, Huang Y, et al. Multi-encoder U-Net benchmarking for LiTS17 liver\u2013tumor segmentation: accuracy\u2013efficiency trade-offs across training durations. Biomed Eng \/ Biomedizinische Tech. 2026. https:\/\/doi.org\/10.1515\/bmt-2026-0021.","DOI":"10.1515\/bmt-2026-0021"},{"key":"2406_CR38","doi-asserted-by":"publisher","unstructured":"Shin H, Han K, Lee S, Park H, Kim S, Kim J, et al. Deep learning-based liver tumor segmentation from computed tomography scans with a gradient-enhanced network. Diagnostics. 2026. https:\/\/doi.org\/10.3390\/diagnostics16030429.","DOI":"10.3390\/diagnostics16030429"},{"issue":"6","key":"2406_CR39","doi-asserted-by":"publisher","first-page":"1851","DOI":"10.3390\/s26061851","volume":"26","author":"Y Chen","year":"2026","unstructured":"Chen Y, Li X, Du Y, Jiang H, Liu X, Ma N, et al. SBM\u2013attention U-Net: a hybrid Transformer network for liver tumor segmentation in medical images. Sensors. 2026;26(6):1851. https:\/\/doi.org\/10.3390\/s26061851.","journal-title":"Sensors"}],"container-title":["BMC Medical Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12880-026-02406-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-026-02406-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12880-026-02406-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T06:31:52Z","timestamp":1784183512000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12880-026-02406-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,22]]},"references-count":39,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2406"],"URL":"https:\/\/doi.org\/10.1186\/s12880-026-02406-z","relation":{},"ISSN":["1471-2342"],"issn-type":[{"value":"1471-2342","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,22]]},"assertion":[{"value":"15 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This retrospective study was approved by the Ethics Committee of International Mongolian Hospital of Inner Mongolia. This committee belongs to the International Mongolian Medicine Hospital of Inner Mongolia Autonomous Region (affiliated with Inner Mongolia Medical University), Hohhot, China. Due to the retrospective and de-identified nature of the study, the requirement for informed consent was waived by the committee. The study was conducted in accordance with the Declaration of Helsinki. Use of the publicly available HCC-TACE dataset complied with its original data use license.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"356"}}