{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T02:04:17Z","timestamp":1780020257561,"version":"3.53.1"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis. Comput. Ind. Biomed. Art"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Few-shot medical image classification is a highly challenging problem in computer-aided diagnosis, with the central difficulty being enabling deep models to learn discriminative features conducive to classification from limited labeled samples. Vision transformers (ViTs) have recently demonstrated outstanding performance across various visual tasks. However, owing to their large parameter counts and dependence on massive pretraining data, ViTs are prone to overfitting in sample-scarce scenarios typical of few-shot learning. Parameter-efficient fine-tuning (PEFT) techniques, such as low-rank adaptation (LoRA), have alleviated some of these issues. However, conventional PEFT approaches still encounter difficulties in complex medical image classification tasks. To address this, this study proposes a general fine-tuning framework called a hierarchical probing and fusion network (HPF-Net), which integrates three core innovations to allow smarter and more efficient adaptation for few-shot medical image classification. First, a Fisher information-driven layer selection strategy strengthens the layer-selection robustness in few-shot settings. Subsequently, the attention-guided multiscale fusion module aligns and improves the features drawn from the selected critical layers. Subsequently, LoRA is incorporated into this efficient fine-tuning pipeline to reduce the parameter overhead while improving the accuracy. Extensive experiments on the public few-shot medical image benchmark, the medical imaging meta-dataset, demonstrated that HPF-Net significantly outperformed baseline methods, and ablation studies validated the necessity of each proposed component. The source code will be released upon acceptance.<\/jats:p>","DOI":"10.1186\/s42492-026-00220-6","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T01:54:40Z","timestamp":1780019680000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multiscale feature fusion for few-shot medical image learning with fisher information-driven layer selection"],"prefix":"10.1186","volume":"9","author":[{"given":"Kai","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8444-0622","authenticated-orcid":false,"given":"Yanjun","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,29]]},"reference":[{"key":"220_CR1","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 (2023) The liver tumor segmentation benchmark (LiTS). Med Image Anal 84:102680. https:\/\/doi.org\/10.1016\/j.media.2022.102680","journal-title":"Med Image Anal"},{"issue":"1","key":"220_CR2","doi-asserted-by":"publisher","first-page":"180161","DOI":"10.1038\/sdata.2018.161","volume":"5","author":"P Tschandl","year":"2018","unstructured":"Tschandl P, Rosendahl C, Kittler H (2018) The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions. Sci DataSci Data 5(1):180161. https:\/\/doi.org\/10.1038\/sdata.2018.161","journal-title":"Sci DataSci Data"},{"issue":"5","key":"220_CR3","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","volume":"172","author":"DS Kermany","year":"2018","unstructured":"Kermany DS, Goldbaum M, Cai WJ, Valentim CCS, Liang HY, Baxter SL et al (2018) Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172(5):1122\u20131131.e9. https:\/\/doi.org\/10.1016\/j.cell.2018.02.010","journal-title":"Cell"},{"issue":"6","key":"220_CR4","doi-asserted-by":"publisher","first-page":"100512","DOI":"10.1016\/j.patter.2022.100512","volume":"3","author":"R Liu","year":"2022","unstructured":"Liu R, Wang X, Wu Q, Dai L, Fang X, Yan T et al (2022) DeepDRiD: diabetic retinopathy-grading and image quality estimation challenge. Patterns 3(6):100512. https:\/\/doi.org\/10.1016\/j.patter.2022.100512","journal-title":"Patterns"},{"key":"220_CR5","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M et al (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60\u201388. https:\/\/doi.org\/10.1016\/j.media.2017.07.005","journal-title":"Med Image Anal"},{"key":"220_CR6","doi-asserted-by":"publisher","first-page":"102802","DOI":"10.1016\/j.media.2023.102802","volume":"88","author":"F Shamshad","year":"2023","unstructured":"Shamshad F, Khan S, Zamir SW, Khan MH, Hayat M, Khan FS et al (2023) Transformers in medical imaging: a survey. Med Image Anal 88:102802. https:\/\/doi.org\/10.1016\/j.media.2023.102802","journal-title":"Med Image Anal"},{"key":"220_CR7","unstructured":"Bommasani R, Hudson DA, Adeli E, Altman R, Arora S, Von Arx S et al (2021) On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258"},{"key":"220_CR8","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai XH, Unterthiner T et al (2021) An image is worth 16x16 words: transformers for image recognition at scale. In: Proceedings of the 9th international conference on learning representations, ICLR, Virtual, 3\u20137 May 2021"},{"key":"220_CR9","unstructured":"Radford A, Kim JW, Hallacy C, Ramesh A, Goh G, Agarwal S et al (2021) Learning transferable visual models from natural language supervision. In: Proceedings of the 38th international conference on machine learning, PMLR, Virtual, 18\u201324 July 2021"},{"key":"220_CR10","unstructured":"Touvron H, Cord M, Douze M, Massa F, Sablayrolles A, J\u00e9gou H (2021) Training data-efficient image transformers & distillation through attention. In: Proceedings of the 38th international conference on machine learning, PMLR, Virtual, 18\u201324 July 2021"},{"key":"220_CR11","doi-asserted-by":"publisher","unstructured":"He KM, Chen XL, Xie SN, Li YH, Dollar P, Girshick R (2022) Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, IEEE, New Orleans, 18\u201324 June 2022. https:\/\/doi.org\/10.1109\/CVPR52688.2022.01553","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"220_CR12","doi-asserted-by":"publisher","unstructured":"He KM, Zhang XY, Ren SQ, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, IEEE, Las Vegas, 27\u201330 June 2016. https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"220_CR13","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd international conference on machine learning, PMLR, Lille, 6\u201311 July 2015"},{"key":"220_CR14","doi-asserted-by":"publisher","unstructured":"Deng J, Dong W, Socher R, Li LJ, Kai Li N, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. In: Proceedings of the 2009 IEEE conference on computer vision and pattern recognition, IEEE, Miami, 20\u201325 June 2009. https:\/\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"220_CR15","doi-asserted-by":"publisher","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D et al (2014) Microsoft COCO: common objects in context. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision \u2013 ECCV 2014. 13th European conference, Zurich, Switzerland, September 2014. Lecture notes in computer science, vol 8693. Springer, Cham, pp 740\u2013755. https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"220_CR16","unstructured":"Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? In: Proceedings of the 28th international conference on neural information processing systems, MIT Press, Montreal, 8\u201313 December 2014"},{"key":"220_CR17","unstructured":"Finn C, Abbeel P, Levine S (2017) Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the 34th international conference on machine learning, PMLR, Sydney, 6\u201311 August 2017"},{"key":"220_CR18","unstructured":"Snell J, Swersky K, Zemel R (2017) Prototypical networks for few-shot learning. In: Proceedings of the 31st international conference on neural information processing systems, Curran Associates Inc., Long Beach, 4\u20139 December 2017"},{"issue":"3","key":"220_CR19","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1145\/3386252","volume":"53","author":"YQ Wang","year":"2021","unstructured":"Wang YQ, Yao QM, Kwok JT, Ni LM (2021) Generalizing from a few examples: a survey on few-shot learning. ACM Comput Surv 53(3):63. https:\/\/doi.org\/10.1145\/3386252","journal-title":"ACM Comput Surv"},{"issue":"3","key":"220_CR20","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1038\/s42256-023-00626-4","volume":"5","author":"N Ding","year":"2023","unstructured":"Ding N, Qin YJ, Yang G, Wei FC, Yang ZH, Su YS et al (2023) Parameter-efficient fine-tuning of large-scale pre-trained language models. Nat Mach Intell 5(3):220\u2013235. https:\/\/doi.org\/10.1038\/s42256-023-00626-4","journal-title":"Nat Mach Intell"},{"key":"220_CR21","unstructured":"Hu EJ, Shen YL, Wallis P, Allen-Zhu Z, Li YZ, Wang SA et al (2022) LoRA: low-rank adaptation of large language models. In: Proceedings of the 10th international conference on learning representations, ICLR, Virtual, 25\u201329 April 2022"},{"key":"220_CR22","unstructured":"Howard AG, Zhu ML, Chen B, Kalenichenko D, Wang WJ, Weyand T et al (2017) MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861"},{"key":"220_CR23","unstructured":"Houlsby N, Giurgiu A, Jastrzebski S, Morrone B, De Laroussilhe Q, Gesmundo A et al (2019) Parameter-efficient transfer learning for NLP. In: Proceedings of the 36th international conference on machine learning, PMLR, Long Beach, 9\u201315 June 2019"},{"key":"220_CR24","doi-asserted-by":"publisher","unstructured":"Zaken EB, Goldberg Y, Ravfogel S (2022) BitFit: simple parameter-efficient fine-tuning for transformer-based masked language-models. In: Proceedings of the 60th annual meeting of the association for computational linguistics (volume 2: short papers), Association for Computational Linguistics, Dublin, Ireland, 22\u201327 May 2022. https:\/\/doi.org\/10.18653\/v1\/2022.acl-short.1","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"220_CR25","doi-asserted-by":"publisher","unstructured":"Lester B, Al-Rfou R, Constant N (2021) The power of scale for parameter-efficient prompt tuning. In: Proceedings of the 2021 conference on empirical methods in natural language processing, Association for Computational Linguistics, Punta Cana, 7\u201311 November 2021. https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.243","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"220_CR26","unstructured":"Liu SY, Wang CY, Yin HX, Molchanov P, Wang YCF, Cheng KT et al (2024) DoRA: weight-decomposed low-rank adaptation. In: Proceedings of the 41st international conference on machine learning, JMLR.org, Vienna, 21\u201327 July 2024"},{"key":"220_CR27","doi-asserted-by":"publisher","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WM, Frangi AF (eds) Medical image computing and computer-assisted intervention \u2013 MICCAI 2015. 18th international conference, Munich, Germany, October 2015. Lecture notes in computer science, vol 9351. Springer, Cham, pp 234\u2013241. https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"220_CR28","doi-asserted-by":"publisher","unstructured":"Zhou ZW, Siddiquee MMR, Tajbakhsh N, Liang JM (2018) Unet++: a nested U-Net architecture for medical image segmentation. In: Stoyanov D, Taylor Z, Carneiro G, Syeda-Mahmood T, Martel A, Maier-Hein L et al (eds) Deep learning in medical image analysis and multimodal learning for clinical decision support. 4th international workshop, DLMIA 2018, and 8th international workshop, ML-CDS 2018, held in conjunction with MICCAI 2018, Granada, Spain, September 2018. Lecture notes in computer science, vol 11045. Springer, Cham, pp 3\u201311. https:\/\/doi.org\/10.1007\/978-3-030-00889-5_1","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"220_CR29","unstructured":"Chen JN, Lu YY, Yu QH, Luo XD, Adeli E, Wang Y et al (2021) TransUNet: transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306"},{"issue":"1","key":"220_CR30","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1038\/s41597-025-04866-4","volume":"12","author":"S Woerner","year":"2025","unstructured":"Woerner S, Jaques A, Baumgartner CF (2025) A comprehensive and easy-to-use multi-domain multi-task medical imaging meta-dataset. Sci DataSci Data 12(1):666. https:\/\/doi.org\/10.1038\/s41597-025-04866-4","journal-title":"Sci DataSci Data"},{"key":"220_CR31","doi-asserted-by":"publisher","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: Fleet D, Pajdla T, Schiele B, Tuytelaars T (eds) Computer vision-ECCV 2014. 13th European conference, Zurich, Switzerland, September 2014. Lecture notes in computer science, vol 8689. Springer, Cham, pp 818\u2013833. https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"220_CR32","doi-asserted-by":"publisher","unstructured":"Mahendran A, Vedaldi A (2015) Understanding deep image representations by inverting them. In: Proceedings of the IEEE conference on computer vision and pattern recognition, IEEE, Boston, 7\u201312 June 2015. https:\/\/doi.org\/10.1109\/CVPR.2015.7299155","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"220_CR33","doi-asserted-by":"publisher","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 international conference on computer vision, IEEE, Venice, 22\u201329 October 2017. https:\/\/doi.org\/10.1109\/ICCV.2017.74","DOI":"10.1109\/ICCV.2017.74"},{"key":"220_CR34","unstructured":"Alain G, Bengio Y (2016) Understanding intermediate layers using linear classifier probes. In: Proceedings of the 5th international conference on learning representations, ICLR, Toulon, 24\u201326 April 2017"},{"key":"220_CR35","unstructured":"Gu QQ, Li ZH, Han JW (2011) Generalized fisher score for feature selection. In: Proceedings of the 27th conference on uncertainty in artificial intelligence, AUAI Press, Barcelona, 14\u201317 July 2011"},{"key":"220_CR36","unstructured":"Ba JL, Kiros JR, Hinton GE (2016) Layer normalization. arXiv preprint arXiv:1607.06450"},{"key":"220_CR37","doi-asserted-by":"publisher","unstructured":"Hendrycks D, Gimpel K (2016) Gaussian error linear units (GELUs). arXiv preprint arXiv:1606.08415. https:\/\/doi.org\/10.48550\/arXiv.1606.08415","DOI":"10.48550\/arXiv.1606.08415"},{"issue":"1","key":"220_CR38","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958","journal-title":"J Mach Learn Res"},{"issue":"11","key":"220_CR39","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1038\/s42256-019-0101-9","volume":"1","author":"C Matek","year":"2019","unstructured":"Matek C, Schwarz S, Spiekermann K, Marr C (2019) Human-level recognition of blast cells in acute myeloid leukaemia with convolutional neural networks. Nat Mach Intell 1(11):538\u2013544. https:\/\/doi.org\/10.1038\/s42256-019-0101-9","journal-title":"Nat Mach Intell"},{"key":"220_CR40","doi-asserted-by":"publisher","unstructured":"Chen SF, Ge CJ, Tong Z, Wang JL, Song YB, Wang J et al (2022) AdaptFormer: adapting vision transformers for scalable visual recognition. In: Proceedings of the 36th international conference on neural information processing systems, Curran Associates Inc., New Orleans, 28 November\u20139 December 2022. https:\/\/doi.org\/10.52202\/068431-1212","DOI":"10.52202\/068431-1212"},{"key":"220_CR41","doi-asserted-by":"publisher","unstructured":"Jia ML, Tang LM, Chen BC, Cardie C, Belongie S, Hariharan B et al (2022) Visual prompt tuning. In: Avidan S, Brostow G, Ciss\u00e9 M, Farinella GM, Hassner T (eds) Computer vision \u2013 ECCV 2022. 17th European conference, Tel Aviv, Israel, October 2022. Lecture notes in computer science, vol 13693. Springer, Cham, pp 709\u2013727. https:\/\/doi.org\/10.1007\/978-3-031-19827-4_41","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"220_CR42","doi-asserted-by":"publisher","first-page":"103258","DOI":"10.1016\/j.media.2024.103258","volume":"97","author":"W Zu","year":"2024","unstructured":"Zu W, Xie S, Zhao Q, Li G, Ma L (2024) Embedded prompt tuning: towards enhanced calibration of pretrained models for medical images. Med Image Anal 97:103258. https:\/\/doi.org\/10.1016\/j.media.2024.103258","journal-title":"Med Image Anal"},{"key":"220_CR43","unstructured":"Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: Proceedings of the 3rd international conference on learning representations, ICLR, San Diego, 7\u20139 May 2015"},{"key":"220_CR44","unstructured":"Loshchilov I, Hutter F (2019) Decoupled weight decay regularization. In: Proceedings of the 7th international conference on learning representations, ICLR, New Orleans, 6\u20139 May 2019"},{"key":"220_CR45","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton GE (2020) A simple framework for contrastive learning of visual representations. In: Proceedings of the 37th international conference on machine learning, PMLR, Virtual, 13\u201318 July 2020"}],"container-title":["Visual Computing for Industry, Biomedicine, and Art"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s42492-026-00220-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s42492-026-00220-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s42492-026-00220-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T01:54:51Z","timestamp":1780019691000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s42492-026-00220-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,29]]},"references-count":45,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["220"],"URL":"https:\/\/doi.org\/10.1186\/s42492-026-00220-6","relation":{},"ISSN":["2524-4442"],"issn-type":[{"value":"2524-4442","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,29]]},"assertion":[{"value":"9 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All datasets used in this study are publicly available and anonymized. Data usage follows the original licensing and data-use policies. This work involves no new human subjects or animal experiments and therefore did not require additional institutional ethics approval.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"9"}}