Multi-Annotator Consensus Network with Adaptive Preprocessing for Lung Nodule Segmentation: A Deep Learning Framework for Clinical Decision Support
Received: 28 May 2025 | Revised: 23 June 2025, 19 July 2025 and 29 July 2025 | Accepted: 1 August 2025 | Online: 17 October 2025
Corresponding author: S. Venkatesh
Abstract
Accurate lung nodule segmentation remains a challenging task as inter-observer variability among radiological experts limits diagnostic consistency. This study introduces Multi-Annotator Consensus Network with Adaptive Preprocessing (MACN-AP), a deep learning framework learning from multiple expert annotations simultaneously. The architecture incorporates adaptive preprocessing for optimal image enhancement, multi-annotator attention mechanisms for expert-specific features, consensus formation layers, and Bayesian uncertainty quantification. Evaluation was conducted on the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset comprising 875 patients and 1,575 nodules, each with complete four-expert annotations. Through systematic slice-level sampling, we derived 1,600 training samples from 800 patients and 150 validation samples from 75 held-out patients using stratified hold-out validation. MACN-AP achieved exceptional validation performance, with a Dice coefficient of 0.99 and an Intersection of Union (IoU) of 0.98, converging within 10 epochs. Uncertainty analysis revealed a strong inverse correlation with segmentation accuracy (r = -0.87), enabling reliable confidence assessment. Moreover, the clinical decision support framework successfully stratified cases into auto-approve (Dice > 0.98, uncertainty < 0.1), uncertain review, and manual assessment categories. These findings demonstrate that MACN-AP effectively integrates multi-expert knowledge while providing interpretable uncertainty estimates, establishing a robust foundation for automated, trustworthy lung nodule diagnosis workflows through intelligent case routing and evidence-based clinical decision support.
Keywords:
lung nodule segmentation, multi-annotator learning, adaptive preprocessing, clinical decision support, deep learning, medical imagingDownloads
References
X. Yao, X. Wang, S.-H. Wang, and Y.-D. Zhang, "A comprehensive survey on convolutional neural network in medical image analysis," Multimedia Tools and Applications, vol. 81, no. 29, pp. 41361–41405, Dec. 2022. DOI: https://doi.org/10.1007/s11042-020-09634-7
L. Azour et al., "Inter-Reader Variability of Volumetric Subsolid Pulmonary Nodule Radiomic Features," Academic Radiology, vol. 29, pp. S98–S107, Feb. 2022. DOI: https://doi.org/10.1016/j.acra.2021.01.026
W. Huang, H. Zhang, X. Quan, and J. Wang, "A Two-Level Dynamic Adaptive Network for Medical Image Fusion," IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1–17, 2022. DOI: https://doi.org/10.1109/TIM.2022.3169546
S. T. Vemula, M. Sreevani, P. Rajarajeswari, K. Bhargavi, J. M. R. S. Tavares, and S. Alankritha, "Deep Learning Techniques for Lung Cancer Recognition," Engineering, Technology & Applied Science Research, vol. 14, no. 4, pp. 14916–14922, Aug. 2024. DOI: https://doi.org/10.48084/etasr.7510
S. G. Armato et al., "The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT Scans," Medical Physics, vol. 38, no. 2, pp. 915–931, Feb. 2011.
N. Siddique, S. Paheding, C. P. Elkin, and V. Devabhaktuni, "U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications," IEEE Access, vol. 9, pp. 82031–82057, 2021. DOI: https://doi.org/10.1109/ACCESS.2021.3086020
F. Guo, M. Ng, G. Kuling, and G. Wright, "Cardiac MRI segmentation with sparse annotations: Ensembling deep learning uncertainty and shape priors," Medical Image Analysis, vol. 81, Oct. 2022, Art. no. 102532. DOI: https://doi.org/10.1016/j.media.2022.102532
H. Li, Y. Nan, J. Del Ser, and G. Yang, "Region-based evidential deep learning to quantify uncertainty and improve robustness of brain tumor segmentation," Neural Computing and Applications, vol. 35, no. 30, pp. 22071–22085, Oct. 2023. DOI: https://doi.org/10.1007/s00521-022-08016-4
S. Wang et al., "Annotation-efficient deep learning for automatic medical image segmentation," Nature Communications, vol. 12, no. 1, Oct. 2021, Art. no. 5915. DOI: https://doi.org/10.1038/s41467-021-26216-9
M. P. Schilling et al., "Automated Annotator Variability Inspection for Biomedical Image Segmentation," IEEE Access, vol. 10, pp. 2753–2765, 2022. DOI: https://doi.org/10.1109/ACCESS.2022.3140378
P.-H. Conze, G. Andrade-Miranda, V. K. Singh, V. Jaouen, and D. Visvikis, "Current and Emerging Trends in Medical Image Segmentation With Deep Learning," IEEE Transactions on Radiation and Plasma Medical Sciences, vol. 7, no. 6, pp. 545–569, Jul. 2023. DOI: https://doi.org/10.1109/TRPMS.2023.3265863
C. Huang, Z. Wang, G. Yuan, Z. Xiong, J. Hu, and Y. Tong, "PKSEA-Net: A prior knowledge supervised edge-aware multi-task network for retinal arteriolar morphometry," Computers in Biology and Medicine, vol. 172, Apr. 2024, Art. no. 108255. DOI: https://doi.org/10.1016/j.compbiomed.2024.108255
H. Jiang, L.-F. Li, X. Yang, X. Wang, and M.-X. Luo, "BSNet: a boundary-aware medical image segmentation network," The European Physical Journal Plus, vol. 140, no. 1, Jan. 2025, Art. no. 53. DOI: https://doi.org/10.1140/epjp/s13360-024-05960-z
R. Zahari, J. Cox, and B. Obara, "Uncertainty-aware image classification on 3D CT lung," Computers in Biology and Medicine, vol. 172, Apr. 2024, Art. no. 108324. DOI: https://doi.org/10.1016/j.compbiomed.2024.108324
P. M. Forooshani et al., "Deep Bayesian networks for uncertainty estimation and adversarial resistance of white matter hyperintensity segmentation," Human Brain Mapping, vol. 43, no. 7, pp. 2089–2108, May 2022. DOI: https://doi.org/10.1002/hbm.25784
A. Kurz et al., "Uncertainty Estimation in Medical Image Classification: Systematic Review," JMIR Medical Informatics, vol. 10, no. 8, Aug. 2022, Art. no. e36427. DOI: https://doi.org/10.2196/36427
T. Xia, T. Dang, J. Han, L. Qendro, and C. Mascolo, "Uncertainty-Aware Health Diagnostics via Class-Balanced Evidential Deep Learning," IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 11, pp. 6417–6428, Nov. 2024. DOI: https://doi.org/10.1109/JBHI.2024.3360002
X. Li et al., "Deep Learning Attention Mechanism in Medical Image Analysis: Basics and Beyonds," International Journal of Network Dynamics and Intelligence, pp. 93–116, Mar. 2023. DOI: https://doi.org/10.53941/ijndi0201006
B. Ghoshal, A. Tucker, B. Sanghera, and W. Lup Wong, "Estimating uncertainty in deep learning for reporting confidence to clinicians in medical image segmentation and diseases detection," Computational Intelligence, vol. 37, no. 2, pp. 701–734, May 2021. DOI: https://doi.org/10.1111/coin.12411
V. Trojani, M. C. Bassi, L. Verzellesi, and M. Bertolini, "Impact of Preprocessing Parameters in Medical Imaging-Based Radiomic Studies: A Systematic Review," Cancers, vol. 16, no. 15, Jul. 2024, Art. no. 2668. DOI: https://doi.org/10.3390/cancers16152668
T. Dhar, N. Dey, S. Borra, and R. S. Sherratt, "Challenges of Deep Learning in Medical Image Analysis—Improving Explainability and Trust," IEEE Transactions on Technology and Society, vol. 4, no. 1, pp. 68–75, Mar. 2023. DOI: https://doi.org/10.1109/TTS.2023.3234203
S. Ma, X. Li, J. Tang, and F. Guo, "Aggregate-aware model with bidirectional edge generation for medical image segmentation," Applied Soft Computing, vol. 163, Sep. 2024, Art. no. 111918. DOI: https://doi.org/10.1016/j.asoc.2024.111918
J. Wang, C. Zhou, and Y. Huang, "Contour-Aware Multi-Expert Model for Ambiguous Medical Image Segmentation," IEEE Transactions on Medical Imaging, vol. 44, no. 8, pp. 3284–3298, Aug. 2025. DOI: https://doi.org/10.1109/TMI.2025.3561117
L. Zhang et al., "Learning from multiple annotators for medical image segmentation," Pattern Recognition, vol. 138, Jun. 2023, Art. no. 109400. DOI: https://doi.org/10.1016/j.patcog.2023.109400
E. G. Lopez Molina, X. Huang, and Q. Zhang, "Disagreement attention: Let us agree to disagree on computed tomography segmentation," Biomedical Signal Processing and Control, vol. 84, Jul. 2023, Art. no. 104769. DOI: https://doi.org/10.1016/j.bspc.2023.104769
H. Yu, L. T. Yang, Q. Zhang, D. Armstrong, and M. J. Deen, "Convolutional neural networks for medical image analysis: State-of-the-art, comparisons, improvement and perspectives," Neurocomputing, vol. 444, pp. 92–110, Jul. 2021. DOI: https://doi.org/10.1016/j.neucom.2020.04.157
H. Arabi and H. Zaidi, "Single annotator versus multi-annotator: Challenge of segmenting two neighboring hippocampus head and body with high precision," Biomedical Signal Processing and Control, vol. 97, Art. no. 106667, Nov. 2024. DOI: https://doi.org/10.1016/j.bspc.2024.106667
Downloads
How to Cite
License
Copyright (c) 2025 S. Venkatesh, Jajjara Bhargav, L. Manjunath, V. Malathi, Anup Ingle, H. D. Aparna, J. Kavitha, J. Jaganpradeep
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
