Neural architecture search (NAS) can automate medical image segmentation network design, but costly candidate evaluation limits the supervision available for evolutionary selection. Since replacement decisions depend on relative candidate quality, learning architecture preferences directly can provide guidance under constrained training budgets. In this paper, we propose Ranking-Aware Predictor-Assisted Differential Evolution (R-PADE) for U-Net-style architecture search. Specifically, a predictor trained with pairwise ranking supervision and contrastive regularization directly determines trial–target replacement in discrete differential evolution. Aggregated pairwise preferences prioritize candidates for proxy training, whose observations subsequently update the predictor. This connects evolutionary selection with selective candidate evaluation, reducing reliance on direct training for replacement decisions. Structured encoding and feasibility repair maintain valid architectures during the search. Experiments on CHAOS, BUSI, and ISIC demonstrate competitive segmentation performance with compact architectures. Compared with EU-Net, R-PADE reduces search GPU time by 35.6% while achieving higher Dice scores on CHAOS and BUSI. The ablation experiments compare the implemented predictor formulations and evaluate the contribution of contrastive regularization using matched search settings and proxy-evaluation budgets.
- Open Access
- Article
R-PADE: Ranking-Guided Evolutionary Neural Architecture Search forMedical Image Segmentation
- Tian Zhang 1,
- Jianlun Ma 2,
- Aohan Mei 2,
- Nan Li 3,
- Dong Ge 2,4,
- Huiyan Jiang 2,
- Dong Li 4 and
- Jianhui Lv 5,*
Author Information
Received: 02 July 2026 | Revised: 24 October 2026 | Accepted: 29 October 2026 | Published: 09 November 2026
Abstract
Keywords
neural architecture search | medical image segmentation | differential evolution | ranking predictor
References
- 1.
Zhang, T.; Cheng, J.; Miao, L.; et al. Multi-Hop Reasoning with Relation Based Node Quality Evaluation for Sparse Medical Knowledge Graph. IEEE Trans. Emerg. Top. Comput. Intell. 2024, 9, 1805–1816. https://doi.org/10.1109/tetci.2024.3452748.
- 2.
Wang, M.; Jiang, H.; Shi, T.; et al. SCL-Net: Structured Collaborative Learning for PET/CT Based Tumor Segmentation. IEEE J. Biomed. Health Informatics 2022, 27, 1048–1059. https://doi.org/10.1109/jbhi.2022.3226475.
- 3.
Ronneberger, O.; Fischer, P.; Brox, T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015; Springer: Cham, Switzerland, 2015; pp. 234–241. https://doi.org/10.1007/978-3-319-24574-4_28.
- 4.
Wang, M.; Jiang, H.; Shi, T.; et al. HD-RDS-UNet: Leveraging Spatial-Temporal Correlation Between the Decoder Feature Maps for Lymphoma Segmentation. IEEE J. Biomed. Health Informatics 2021, 26, 1116–1127. https://doi.org/10.1109/jbhi.2021.3102612.
- 5.
Li, N.; Ma, L.; Xing, T.; et al. Automatic design of machine learning via evolutionary computation: A survey. Appl. Soft Comput. 2023, 143, 110412. https://doi.org/10.1016/j.asoc.2023.110412.
- 6.
Guo, L.; Li, N.; Zhang, T. EEG-based emotion recognition via improved evolutionary convolutional neural network. Int. J. Bio-Inspired Comput. 2024, 23, 203–213. https://doi.org/10.1504/ijbic.2024.139268.
- 7.
Zhang, T.; Ma, L.; Cheng, S.; et al. Automatic prompt design via particle swarm optimization driven LLM for efficient medical information extraction. Swarm Evol. Comput. 2025, 95, 101922. https://doi.org/10.1016/j.swevo.2025.101922.
- 8.
Ma, L.; Li, N.; Yu, G.; et al. Pareto-Wise Ranking Classifier for Multiobjective Evolutionary Neural Architecture Search. IEEE Trans. Evol. Comput. 2023, 28, 570–581. https://doi.org/10.1109/tevc.2023.3314766.
- 9.
Ma, L.; Li, N.; Zhu, P.; et al. A Novel Fuzzy Neural Network Architecture Search Framework for Defect Recognition with Uncertainties. IEEE Trans. Fuzzy Syst. 2024, 32, 3274–3285. https://doi.org/10.1109/tfuzz.2024.3373792.
- 10.
Ma, L.; Kang, H.; Yu, G.; et al. Single-Domain Generalized Predictor for Neural Architecture Search System. IEEE Trans. Comput. 2024, 73, 1400–1413. https://doi.org/10.1109/tc.2024.3365949.
- 11.
Li, N.; Ma, L.; Wang, R.; et al. Listwise ranking predictor for evolutionary neural architecture search. Swarm Evol. Comput. 2025, 96, 101956. https://doi.org/10.1016/j.swevo.2025.101956.
- 12.
Yu, C.; Wang, Y.; Tang, C.; et al. EU-Net: Automatic U-Net neural architecture search with differential evolutionary algorithm for medical image segmentation. Comput. Biol. Med. 2023, 167, 107579. https://doi.org/10.1016/j.compbiomed.2023.107579.
- 13.
Sun, X.X.; Wang, H.; Song, P.C. Compact Training-Free NAS with Alternating Evolution Game for Medical Image Segmentation. In Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Daejeon, Republic of Korea, 23–27 September 2025; pp. 108–118. https://doi.org/10.1007/978-3-032-05325-1_11.
- 14.
Li, N.; Xue, B.; Ma, L.; et al. Transferable Relativistic Predictor: Mitigating Cross-Task Cold-Start Issue in NAS. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, Montreal, QC, Canada, 16–22 August 2025; pp. 5625–5633. https://doi.org/10.24963/ijcai.2025/626.
- 15.
Li, N.; He, M.; Mei, A.; et al. Ranking-Aware Predictor-Assisted Automatic Architecture Design for Biomedical Image Segmentation. In Proceedings of the 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Wuhan, China, 15–18 December 2025; pp. 1–8. https://doi.org/10.1109/bibm66473.2025.11389832.
- 16.
Punn, N.S.; Agarwal, S. Modality specific U-Net variants for biomedical image segmentation: a survey. Artif. Intell. Rev. 2022, 55, 5845–5889. https://doi.org/10.1007/s10462-022-10152-1.
- 17.
Wang, H.; Cao, P.; Wang, J.; et al. UCTransNet: rethinking the skip connections in u-net from a channel-wise perspective with transformer. Proc. AAAI Conf. Artif. Intell. 2022, 36, 2441–2449.
- 18.
Chen, J.; Lu, Y.; Yu, Q.; et al. TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation. arXiv 2021, arXiv:2102.04306.
- 19.
Hatamizadeh, A.; Tang, Y.; Nath, V.; et al. UNETR: Transformers for 3D Medical Image Segmentation. In Proceedings of the 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, 3–8 January 2022; pp. 1748–1758. https://doi.org/10.1109/wacv51458.2022.00181.
- 20.
Cao, H.; Wang, Y.; Chen, J.; et al. Swin-Unet: Unet-Like Pure Transformer for Medical Image Segmentation. In Computer Vision—ECCV 2022 Workshops; Springer: Cham, Switzerland, 2022; pp. 205–218. https://doi.org/10.1007/978-3-031-25066-8_9.
- 21.
Hatamizadeh, A.; Nath, V.; Tang, Y.; et al. Swin UNETR: Swin Transformers for Semantic Segmentation of Brain Tumors in MRI Images. In Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries; Springer: Cham, Switzerland, 2022; pp. 272–284. https://doi.org/10.1007/978-3-031-08999-2_22.
- 22.
Chen, J.; Mei, J.; Li, X.; 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.
- 23.
Yılmaz, A.; Erkan, U.; Toktaş, A.; et al. AHIR: Deep learning-based autoencoder hashing image retrieval. Neurocomputing 2026, 671, 132639. https://doi.org/10.1016/j.neucom.2026.132639.
- 24.
Erkan, U.; Yılmaz, A.; Toktaş, A.; et al. Object detection-based deep autoencoder hashing image retrieval. Signal Process. Image Commun. 2025, 138, 117384. https://doi.org/10.1016/j.image.2025.117384.
- 25.
Peng, C.; Myronenko, A.; Hatamizadeh, A.; et al. HyperSegNAS: Bridging One-Shot Neural Architecture Search with 3D Medical Image Segmentation using HyperNet. In Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, 18–24 June 2022; pp. 20709–20719. https://doi.org/10.1109/cvpr52688.2022.02008.
- 26.
Huang, Z.; Wang, Z.; Yang, Z.; et al. AdwU-Net: Adaptive Depth and Width U-Net for Medical Image Segmentation by Differentiable Neural Architecture Search. In Proceedings of the International Conference on Medical Imaging with Deep Learning, Zürich, Switzerland, 6–8 July 2022; pp. 576–589.
- 27.
Ma, L.; Li, N.; Guo, Y.; et al. Learning to Optimize: Reference Vector Reinforcement Learning Adaption to Constrained Many-Objective Optimization of Industrial Copper Burdening System. IEEE Trans. Cybern. 2021, 52, 12698–12711. https://doi.org/10.1109/tcyb.2021.3086501.
- 28.
Chen, R.; Zhang, M.; Zheng, X.; et al. Thrifty Neural Architecture Search for Medical Image Segmentation (Student Abstract). Proc. AAAI Conf. Artif. Intell. 2022, 36, 12925–12926.
- 29.
Chollet, F. Xception: Deep Learning with Depthwise Separable Convolutions. In Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017; pp. 1800–1807. https://doi.org/10.1109/cvpr.2017.195.
- 30.
Gao, R. Rethinking Dilated Convolution for Real-time Semantic Segmentation. In Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Vancouver, BC, Canada, 17–24 June 2023; pp. 4675–4684. https://doi.org/10.1109/cvprw59228.2023.00493.
- 31.
Stergiou, A.; Poppe, R.W. AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling. IEEE Trans. Image Process. 2022, 32, 251–266. https://doi.org/10.1109/tip.2022.3227503.
- 32.
Paisitkriangkrai, S.; Shen, C.; van den Hengel, A. Pedestrian Detection with Spatially Pooled Features and Structured Ensemble Learning. IEEE Trans. Pattern Anal. Mach. Intell. 2015, 38, 1243–1257. https://doi.org/10.1109/tpami.2015.2474388.
- 33.
Gao, S.; Wu, R.; Liu, S.; et al. MSLID-TCN: multi-stage linear-index dilated temporal convolutional network for temporal action segmentation. Int. J. Mach. Learn. Cybern. 2025, 16, 567–581. https://doi.org/10.1007/s13042-024-02251-y.
- 34.
Kavur, A.E.; Gezer, N.S.; Barış, M.; et al. CHAOS Challenge—combined (CT-MR) healthy abdominal organ segmentation. Med. Image Anal. 2021, 69, 101950. https://doi.org/10.1016/j.media.2020.101950.
- 35.
Al-Dhabyani, W.; Gomaa, M.; Khaled, H.; et al. Dataset of breast ultrasound images. Data Brief 2020, 28, 104863. https://doi.org/10.1016/j.dib.2019.104863.
- 36.
Codella, N.; Rotemberg, V.M.; Tschandl, P.; et al. Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC). arXiv 2019, arXiv:1902.03368.
- 37.
Liu, L.; Wen, Z.; Liu, S.; et al. MixSearch: Searching for Domain Generalized Medical Image Segmentation Architectures. arXiv 2021, arXiv:2102.13280.
- 38.
Zhou, Q.; Wang, Q.; Bao, Y.; et al. LAEDNet: A Lightweight Attention Encoder–Decoder Network for ultrasound medical image segmentation. Comput. Electr. Eng. 2022, 99, 107777. https://doi.org/10.1016/j.compeleceng.2022.107777.
- 39.
He, Y.; Yang, D.; Roth, H.; et al. DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation. In Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 20–25 June 2021; pp. 5837–5846. https://doi.org/10.1109/cvpr46437.2021.00578.
- 40.
Yu, Q.; Yang, D.; Roth, H.; et al. C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 13–19 June 2020; pp. 4125–4134. https://doi.org/10.1109/cvpr42600.2020.00418.
This work is licensed under a Creative Commons Attribution 4.0 International License.
