{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T23:53:43Z","timestamp":1781740423688,"version":"3.54.5"},"reference-count":61,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100007567","name":"City University of Hong Kong","doi-asserted-by":"publisher","award":["9229503"],"award-info":[{"award-number":["9229503"]}],"id":[{"id":"10.13039\/100007567","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004000","name":"Guangzhou Municipal Science and Technology Program key projects","doi-asserted-by":"publisher","award":["2024A04J6413"],"award-info":[{"award-number":["2024A04J6413"]}],"id":[{"id":"10.13039\/501100004000","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023B1515020004"],"award-info":[{"award-number":["2023B1515020004"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002402","name":"Sun Yat-sen University","doi-asserted-by":"publisher","award":["24xkjc013"],"award-info":[{"award-number":["24xkjc013"]}],"id":[{"id":"10.13039\/501100002402","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFA1011900"],"award-info":[{"award-number":["2024YFA1011900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003452","name":"Innovation and Technology Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003452","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376291"],"award-info":[{"award-number":["62376291"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.eswa.2026.132368","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T20:24:07Z","timestamp":1776111847000},"page":"132368","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Multi-sequence parotid gland lesion segmentation via expert text-guided segment anything model"],"prefix":"10.1016","volume":"323","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7149-5763","authenticated-orcid":false,"given":"Zhongyuan","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1861-3599","authenticated-orcid":false,"given":"Chuan-Xian","family":"Ren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6731-6518","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2322-9092","authenticated-orcid":false,"given":"Xiaohua","family":"Ban","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3966-7502","authenticated-orcid":false,"given":"Jianning","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2224-0887","authenticated-orcid":false,"given":"Xiaohui","family":"Duan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.132368_bib0001","unstructured":"Achiam, J., Adler, S., & Agarwal, S. (2023). Gpt-4 technical report. arXiv preprint arXiv: 2303.08774."},{"key":"10.1016\/j.eswa.2026.132368_bib0002","series-title":"European conference on computer vision workshops","first-page":"205","article-title":"Swin-unet: UNet-like pure transformer for medical image segmentation","author":"Cao","year":"2022"},{"key":"10.1016\/j.eswa.2026.132368_bib0003","doi-asserted-by":"crossref","unstructured":"Chen, C., Miao, J., & Wu, D. (2024a). Ma-sam: Modality-agnostic sam adaptation for 3d medical image segmentation. Medical Image Analysis, 98, 103310. 10.1016\/j.media.2024.103310.","DOI":"10.1016\/j.media.2024.103310"},{"key":"10.1016\/j.eswa.2026.132368_bib0004","unstructured":"Chen, J., Lu, Y., & Yu, Q. (2021). TransUNet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv: 2102.04306."},{"key":"10.1016\/j.eswa.2026.132368_bib0005","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision workshops","first-page":"3367","article-title":"Sam-adapter: Adapting segment anything in underperformed scenes","author":"Chen","year":"2023"},{"issue":"3","key":"10.1016\/j.eswa.2026.132368_bib0006","doi-asserted-by":"crossref","first-page":"1375","DOI":"10.1007\/s11263-024-02246-w","article-title":"Bi-VLGM: Bi-level class-severity-aware vision-language graph matching for text guided medical image segmentation","volume":"133","author":"Chen","year":"2024","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.eswa.2026.132368_bib0007","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"3511","article-title":"Unleashing the potential of SAM for medical adaptation via hierarchical decoding","author":"Cheng","year":"2024"},{"key":"10.1016\/j.eswa.2026.132368_bib0008","series-title":"Findings of the association for computational linguistics: EACL 2023","first-page":"1181","article-title":"Pubmedclip: How much does clip benefit visual question answering in the medical domain?","author":"Eslami","year":"2023"},{"key":"10.1016\/j.eswa.2026.132368_bib0009","series-title":"European conference on computer vision","first-page":"108","article-title":"Cc-sam: Sam with cross-feature attention and context for ultrasound image segmentation","author":"Gowda","year":"2024"},{"issue":"9","key":"10.1016\/j.eswa.2026.132368_bib0010","doi-asserted-by":"crossref","first-page":"3756","DOI":"10.1109\/TMI.2025.3564976","article-title":"Mscpt: Few-shot whole slide image classification with multi-scale and context-focused prompt tuning","volume":"44","author":"Han","year":"2025","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.1016\/j.eswa.2026.132368_bib0011","series-title":"International conference on machine learning","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019"},{"issue":"2","key":"10.1016\/j.eswa.2026.132368_bib0012","first-page":"3","article-title":"LoRA: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"10.1016\/j.eswa.2026.132368_bib0013","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"3942","article-title":"Gloria: A multimodal global-local representation learning framework for label-efficient medical image recognition","author":"Huang","year":"2021"},{"key":"10.1016\/j.eswa.2026.132368_bib0014","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"9779","article-title":"P2SAM: Probabilistically prompted SAMs are efficient segmentator for ambiguous medical images","author":"Huang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132368_bib0015","doi-asserted-by":"crossref","unstructured":"Huang, Y., Yang, X., & Liu, L. (2024b). Segment anything model for medical images?Medical Image Analysis, 92, 103061. 10.1016\/j.media.2023.103061.","DOI":"10.1016\/j.media.2023.103061"},{"issue":"12","key":"10.1016\/j.eswa.2026.132368_bib0016","doi-asserted-by":"crossref","first-page":"2003","DOI":"10.1016\/j.joms.2022.08.007","article-title":"Survival outcome of salivary gland carcinoma: A 50-year retrospective study with long-term follow-up","volume":"80","author":"Jia","year":"2022","journal-title":"Journal of Oral and Maxillofacial Surgery"},{"key":"10.1016\/j.eswa.2026.132368_bib0017","series-title":"European conference on computer vision","first-page":"167","article-title":"Generalized sam: Efficient fine-tuning of sam for variable input image sizes","author":"Kato","year":"2024"},{"key":"10.1016\/j.eswa.2026.132368_bib0018","doi-asserted-by":"crossref","unstructured":"Ke, L., Ye, M., & Danelljan, M. (2023). Segment anything in high quality. Advances in Neural Information Processing Systems, 36, 29914\u201329934.","DOI":"10.52202\/075280-1303"},{"key":"10.1016\/j.eswa.2026.132368_bib0019","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.1016\/j.eswa.2026.132368_bib0020","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"20990","article-title":"Enhancing SAM with efficient prompting and preference optimization for semi-supervised medical image segmentation","author":"Konwer","year":"2025"},{"key":"10.1016\/j.eswa.2026.132368_bib0021","doi-asserted-by":"crossref","unstructured":"Lai, J., Wu, Z., Peng, L., & Liu, H. (2026). Prompting across perception and recognition: A unified CLIP-based visual-text prompt framework for zero-shot anomaly detection. Expert Systems with Applications, 299, 129936. 10.1016\/j.eswa.2025.129936.","DOI":"10.1016\/j.eswa.2025.129936"},{"key":"10.1016\/j.eswa.2026.132368_bib0022","doi-asserted-by":"crossref","unstructured":"Lei, Q., Wang, B., & Tan, R. (2024). Ez-hoi: Vlm adaptation via guided prompt learning for zero-shot hoi detection. Advances in Neural Information Processing Systems, 37, 55831\u201355857.","DOI":"10.52202\/079017-1775"},{"key":"10.1016\/j.eswa.2026.132368_bib0023","doi-asserted-by":"crossref","unstructured":"Li, C., Li, W., Liu, H., Liu, X., Xu, Q., Chen, Z., Huang, Y., & Yuan, Y. (2024). Flaws can be applause: Unleashing potential of segmenting ambiguous objects in SAM. Advances in Neural Information Processing Systems, 37, 45578\u201345599.","DOI":"10.52202\/079017-1449"},{"key":"10.1016\/j.eswa.2026.132368_bib0024","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6929","article-title":"Long-tailed visual recognition via Gaussian clouded logit adjustment","author":"Li","year":"2022"},{"key":"10.1016\/j.eswa.2026.132368_bib0025","doi-asserted-by":"crossref","unstructured":"Liang, X., Li, X., Li, F., Jiang, J., Dong, Q., Wang, W., Wang, K., Dong, S., Luo, G., & Li, S. (2025). MedFILIP: Medical fine-grained language-image pre-training. IEEE Journal of Biomedical and Health Informatics, 29(5), 3587\u20133597. 10.1109\/JBHI.2025.3528196.","DOI":"10.1109\/JBHI.2025.3528196"},{"key":"10.1016\/j.eswa.2026.132368_bib0026","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"22369","article-title":"Jarvisir: Elevating autonomous driving perception with intelligent image restoration","author":"Lin","year":"2025"},{"key":"10.1016\/j.eswa.2026.132368_bib0027","unstructured":"Lin, Y., Lin, Z., Lin, K., Bai, J., Pan, P., Li, C., Chen, H., Wang, Z., Ding, X., Li, W. et al. (2025b). Jarvisart: Liberating human artistic creativity via an intelligent photo retouching agent. arXiv preprint arXiv: 2506.17612."},{"key":"10.1016\/j.eswa.2026.132368_bib0028","unstructured":"Liu, A., Feng, B., & Xue, B. (2024a). Deepseek-v3 technical report. arXiv preprint arXiv: 2412.19437."},{"key":"10.1016\/j.eswa.2026.132368_bib0029","unstructured":"Liu, P., Li, C., Li, Z., Wu, Y., Li, W., Yang, Z., Zhang, Z., Lin, Y., Han, S., & Feng, B. Y. (2025). Ir3d-bench: Evaluating vision-language model scene understanding as agentic inverse rendering. arXiv preprint arXiv: 2506.23329."},{"key":"10.1016\/j.eswa.2026.132368_bib0030","doi-asserted-by":"crossref","unstructured":"Liu, S., Zeng, Z., & Ren, T. (2024b). Grounding DINO: Marrying dino with grounded pre-training for open-set object detection. (pp. 38\u201355). 10.1007\/978-3-031-72970-6_3.","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"10.1016\/j.eswa.2026.132368_bib0031","doi-asserted-by":"crossref","unstructured":"Ma, J., He, Y., & Li, F. (2024). Segment anything in medical images. Nature Communications, 15, 654. 10.1038\/s41467-024-44824-z.","DOI":"10.1038\/s41467-024-44824-z"},{"key":"10.1016\/j.eswa.2026.132368_bib0032","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"14788","article-title":"Vila-m3: Enhancing vision-language models with medical expert knowledge","author":"Nath","year":"2025"},{"key":"10.1016\/j.eswa.2026.132368_bib0033","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"4515","article-title":"Sam-parser: Fine-tuning sam efficiently by parameter space reconstruction","volume":"vol. 38","author":"Peng","year":"2024"},{"key":"10.1016\/j.eswa.2026.132368_bib0034","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"2984","article-title":"Silvar-med: A speech-driven visual language model for explainable abnormality detection in medical imaging","author":"Pham","year":"2025"},{"issue":"8","key":"10.1016\/j.eswa.2026.132368_bib0035","doi-asserted-by":"crossref","first-page":"1467","DOI":"10.3390\/diagnostics11081467","article-title":"Current trends and controversies in the management of warthin tumor of the parotid gland","volume":"11","author":"Quer","year":"2021","journal-title":"Diagnostics"},{"key":"10.1016\/j.eswa.2026.132368_bib0036","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.eswa.2026.132368_bib0037","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"11769","article-title":"Emcad: Efficient multi-scale convolutional attention decoding for medical image segmentation","author":"Rahman","year":"2024"},{"key":"10.1016\/j.eswa.2026.132368_bib0038","doi-asserted-by":"crossref","unstructured":"Ren, C.-X., Xu, G.-X., & Dai, D.-Q. (2024). Cross-site prognosis prediction for nasopharyngeal carcinoma from incomplete multi-modal data. Medical Image Analysis, 93, 103103. 10.1016\/j.media.2024.103103.","DOI":"10.1016\/j.media.2024.103103"},{"key":"10.1016\/j.eswa.2026.132368_bib0039","series-title":"International conference on medical image computing and computer-assisted intervention","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"10.1016\/j.eswa.2026.132368_bib0040","doi-asserted-by":"crossref","unstructured":"Shan, D., Li, Z., Li, Y., Li, Q., Tian, J., & Hong, Q. (2025). Stpnet: Scale-aware text prompt network for medical image segmentation. IEEE Transactions on Image Processing. 10.1109\/TIP.2025.3571672.","DOI":"10.1109\/TIP.2025.3571672"},{"key":"10.1016\/j.eswa.2026.132368_bib0041","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23565","article-title":"Vrp-sam: Sam with visual reference prompt","author":"Sun","year":"2024"},{"key":"10.1016\/j.eswa.2026.132368_bib0042","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"30271","article-title":"Prototype-based image prompting for weakly supervised histopathological image segmentation","author":"Tang","year":"2025"},{"key":"10.1016\/j.eswa.2026.132368_bib0043","series-title":"International conference on medical image computing and computer-assisted intervention","first-page":"23","article-title":"Unext: Mlp-based rapid medical image segmentation network","author":"Valanarasu","year":"2022"},{"key":"10.1016\/j.eswa.2026.132368_bib0044","series-title":"Proceedings of the conference on empirical methods in natural language processing. conference on empirical methods in natural language processing","first-page":"3876","article-title":"Medclip: Contrastive learning from unpaired medical images and text","volume":"vol. 2022","author":"Wang","year":"2022"},{"key":"10.1016\/j.eswa.2026.132368_bib0045","doi-asserted-by":"crossref","unstructured":"Wu, J., Wang, Z., & Hong, M. (2025). Medical SAM adapter: Adapting segment anything model for medical image segmentation. Medical Image Analysis, 102, 103547. 10.1016\/j.media.2025.103547.","DOI":"10.1016\/j.media.2025.103547"},{"key":"10.1016\/j.eswa.2026.132368_bib0046","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"24884","article-title":"Flair: Vlm with fine-grained language-informed image representations","author":"Xiao","year":"2025"},{"key":"10.1016\/j.eswa.2026.132368_bib0047","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16111","article-title":"Efficientsam: Leveraged masked image pretraining for efficient segment anything","author":"Xiong","year":"2024"},{"issue":"1","key":"10.1016\/j.eswa.2026.132368_bib0048","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1109\/TMI.2021.3104474","article-title":"Cross-site severity assessment of COVID-19 from CT images via domain adaptation","volume":"41","author":"Xu","year":"2022","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.1016\/j.eswa.2026.132368_bib0049","doi-asserted-by":"crossref","unstructured":"Xu, G.-X., Ren, C.-X., & Sun, Y. (2024a). Domain knowledge-driven encoder-decoder for nasopharyngeal carcinoma segmentation. Expert Systems with Applications, 258, 125208. 10.1016\/j.eswa.2024.125208.","DOI":"10.1016\/j.eswa.2024.125208"},{"key":"10.1016\/j.eswa.2026.132368_bib0050","unstructured":"Xu, Q., Li, J., He, X., Liu, Z., Chen, Z., Duan, W., Li, C., He, M. M., Tesema, F. B., Cheah, W. P. et al. (2024b). Esp-medsam: Efficient self-prompting sam for universal domain-generalized medical image segmentation. arXiv preprint arXiv: 2407.14153, 2(3)."},{"key":"10.1016\/j.eswa.2026.132368_bib0051","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"9112","article-title":"Sgtc: Semantic-guided triplet co-training for sparsely annotated semi-supervised medical image segmentation","volume":"vol. 39","author":"Yan","year":"2025"},{"key":"10.1016\/j.eswa.2026.132368_bib0052","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"21974","article-title":"Clip-cid: Efficient clip distillation via cluster-instance discrimination","volume":"Vol. 39","author":"Yang","year":"2025"},{"issue":"5","key":"10.1016\/j.eswa.2026.132368_bib0053","doi-asserted-by":"crossref","first-page":"2244","DOI":"10.1109\/TMI.2025.3530399","article-title":"DiffMIC-v2: Medical image classification via improved diffusion network","volume":"44","author":"Yang","year":"2025","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"10.1016\/j.eswa.2026.132368_bib0054","series-title":"European conference on computer vision","first-page":"251","article-title":"Attention prompting on image for large vision-language models","author":"Yu","year":"2024"},{"key":"10.1016\/j.eswa.2026.132368_bib0055","series-title":"European conference on computer vision","first-page":"310","article-title":"Long-clip: Unlocking the long-text capability of clip","author":"Zhang","year":"2024"},{"key":"10.1016\/j.eswa.2026.132368_bib0056","unstructured":"Zhang, C., Han, D., & Qiao, Y. (2023). Faster segment anything: Towards lightweight sam for mobile applications. arXiv preprint arXiv: 2306.14289."},{"key":"10.1016\/j.eswa.2026.132368_bib0057","doi-asserted-by":"crossref","unstructured":"Zhang, K., & Liu, D. (2023). Customized segment anything model for medical image segmentation. arXiv preprint arXiv: 2304.13785.","DOI":"10.2139\/ssrn.4495221"},{"key":"10.1016\/j.eswa.2026.132368_bib0058","unstructured":"Zhou, C., Ning, K., & Shen, Q. (2024). Sam-sp: Self-prompting makes sam great again. arXiv preprint arXiv: 2408.12364."},{"key":"10.1016\/j.eswa.2026.132368_bib0059","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Siddiquee, M. M. R., & Tajbakhsh, N. (2019). Unet++: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE Transactions on Medical Imaging. 10.1109\/tmi.2019.2959609.","DOI":"10.1109\/TMI.2019.2959609"},{"issue":"3","key":"10.1016\/j.eswa.2026.132368_bib0060","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1007\/s11263-024-02224-2","article-title":"Weakclip: Adapting clip for weakly-supervised semantic segmentation","volume":"133","author":"Zhu","year":"2025","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.eswa.2026.132368_bib0061","series-title":"Proceedings of the computer vision and pattern recognition conference","first-page":"29623","article-title":"Alignment, mining and fusion: Representation alignment with hard negative mining and selective knowledge fusion for medical visual question answering","author":"Zou","year":"2025"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426012819?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426012819?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T23:26:45Z","timestamp":1781738805000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426012819"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":61,"alternative-id":["S0957417426012819"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132368","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-sequence parotid gland lesion segmentation via expert text-guided segment anything model","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132368","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132368"}}