An Adaptive Preprocessing Pipeline for the Enhancement of Camouflaged Lung Tumor Detection in Whole-Body PET-CT Images
Received: 10 December 2025 | Revised: 9 January 2026 and 22 January 2026 | Accepted: 2 February 2026 | Online: 4 April 2026
Corresponding author: N. Manju
Abstract
Lung cancer is the leading cause of cancer-related mortality worldwide; therefore, its early detection and accurate delineation are important for effective clinical management. A very helpful tool for the diagnosis of lung cancer and its staging is whole-body Positron Emission Tomography Computed Tomography (PET-CT); however, the interpretation of these images is often challenging due to low Signal to Noise Ratios (SNRs), limited contrast, and physiological uptake patterns. As a result, small or low-uptake tumors may become camouflaged within surrounding tissues, potentially delaying diagnosis and increasing uncertainty in clinical decision-making. This study proposes an adaptive image preprocessing framework for whole-body PET-CT to enhance the visibility of camouflaged lung tumors and improve overall image quality for downstream analysis. This framework consists of three self-tuning modules: i) the Adaptive Non-Local Means Denoising (ANLMD), which suppresses noise while preserving structural edges; ii) the Camouflage Aware Contrast Enhancement (CACE), which selectively amplifies low-contrast tumor regions; and iii) the Selective Background Attenuation (SBA), which suppresses physiologically high uptake in non-tumor organs using CT-guided anatomical masking. Contrary to deep-learning-based preprocessing approaches, the proposed approach is fully interpretable, modular, and does not require training or retraining across scanners. Quantitative evaluation revealed significant enhancements in image quality, including a Peak Signal to Noise Ratio (PSNR) of 37.26 dB, a Structural Similarity Index Measure (SSIM) of 0.956, and a Contrast to Noise Ratio (CNR) of 4.55, validating that the proposed methodology produces PET-CT images assisting radiologists for much more accurate interpretation by reducing the camouflage effects and enhancing diagnostic clarity.
Keywords:
lung cancer, PET-CT, camouflaged tumors, denoising, contrast enhancement, background attenuationDownloads
References
R. L. Siegel, K. D. Miller, N. S. Wagle, and A. Jemal, "Cancer statistics, 2023," CA: A Cancer Journal for Clinicians, vol. 73, no. 1, pp. 17–48, Jan. 2023. DOI: https://doi.org/10.3322/caac.21763
H. AL-Jahdali, A. N. Khan, S. Loutfi, and A. S. Al-Harbi, "Guidelines for the role of FDG-PET/CT in lung cancer management," Journal of Infection and Public Health, vol. 5, pp. S35–S40, Dec. 2012. DOI: https://doi.org/10.1016/j.jiph.2012.09.003
J. Qi and R. M. Leahy, "Iterative reconstruction techniques in emission computed tomography," Physics in Medicine and Biology, vol. 51, no. 15, pp. R541–R578, Aug. 2006. DOI: https://doi.org/10.1088/0031-9155/51/15/R01
X. Fu, L. Bi, A. Kumar, M. Fulham, and J. Kim, "Multimodal Spatial Attention Module for Targeting Multimodal PET-CT Lung Tumor Segmentation," IEEE Journal of Biomedical and Health Informatics, vol. 25, no. 9, pp. 3507–3516, Sept. 2021. DOI: https://doi.org/10.1109/JBHI.2021.3059453
R. C. Gonzalez and R. E. Woods, Digital image processing, Fourth, Global edition. New York, New York: Pearson Education, 2018.
K. P. Das and J. Chandra, "A Review on Preprocessing Techniques for Noise Reduction in PET-CT Images for Lung Cancer," in Congress on Intelligent Systems, vol. 111, M. Saraswat, H. Sharma, K. Balachandran, J. H. Kim, and J. C. Bansal, Eds. Singapore: Springer Nature Singapore, 2022, pp. 455–475. DOI: https://doi.org/10.1007/978-981-16-9113-3_34
A. Buades, B. Coll, and J.-M. Morel, "A Non-Local Algorithm for Image Denoising," in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), 2005, vol. 2, pp. 60–65. DOI: https://doi.org/10.1109/CVPR.2005.38
J. Cui et al., "PET image denoising using unsupervised deep learning," European Journal of Nuclear Medicine and Molecular Imaging, vol. 46, no. 13, pp. 2780–2789, Dec. 2019. DOI: https://doi.org/10.1007/s00259-019-04468-4
Y. Lu, J. Lin, S. Chen, H. He, and Y. Cai, "Automatic Tumor Segmentation by Means of Deep Convolutional U-Net With Pre-Trained Encoder in PET Images," IEEE Access, vol. 8, pp. 113636–113648, 2020. DOI: https://doi.org/10.1109/ACCESS.2020.3003138
B. Yu, S. Ozdemir, Y. Dong, W. Shao, K. Shi, and K. Gong, "PET Image Denoising Based on 3D Denoising Diffusion Probabilistic Model: Evaluations on Total-Body Datasets," in Medical Image Computing and Computer Assisted Intervention – MICCAI 2024, vol. 15007, M. G. Linguraru, Q. Dou, A. Feragen, S. Giannarou, B. Glocker, K. Lekadir, and J. A. Schnabel, Eds. Cham: Springer Nature Switzerland, 2024, pp. 541–550. DOI: https://doi.org/10.1007/978-3-031-72104-5_52
I. Kruzhilov, S. Kudin, L. Vetoshkin, E. Sokolova, and V. Kokh, "Whole-body PET image denoising for reduced acquisition time," Frontiers in Medicine, vol. 11, Sept. 2024, Art. no. 1415058. DOI: https://doi.org/10.3389/fmed.2024.1415058
M. Carles et al., "Development and evaluation of two open-source nnU-Net models for automatic segmentation of lung tumors on PET and CT images with and without respiratory motion compensation," European Radiology, vol. 34, no. 10, pp. 6701–6711, Apr. 2024. DOI: https://doi.org/10.1007/s00330-024-10751-2
Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, "Image quality assessment: from error visibility to structural similarity," IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600–612, Apr. 2004. DOI: https://doi.org/10.1109/TIP.2003.819861
K. Zuiderveld, "Contrast Limited Adaptive Histogram Equalization," in Graphics Gems, Elsevier, 1994, pp. 474–485. DOI: https://doi.org/10.1016/B978-0-12-336156-1.50061-6
N. Otsu, "A Threshold Selection Method from Gray-Level Histograms," IEEE Transactions on Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62–66, Jan. 1979. DOI: https://doi.org/10.1109/TSMC.1979.4310076
T. Shepherd et al., "Comparative Study With New Accuracy Metrics for Target Volume Contouring in PET Image Guided Radiation Therapy," IEEE Transactions on Medical Imaging, vol. 31, no. 11, pp. 2006–2024, Nov. 2012. DOI: https://doi.org/10.1109/TMI.2012.2202322
A. De Biase et al., "Deep learning-based outcome prediction using PET/CT and automatically predicted probability maps of primary tumor in patients with oropharyngeal cancer," Computer Methods and Programs in Biomedicine, vol. 244, Feb. 2024, Art. no. 107939. DOI: https://doi.org/10.1016/j.cmpb.2023.107939
O. Ronneberger, P. Fischer, and T. Brox, "U-Net: Convolutional Networks for Biomedical Image Segmentation," in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, vol. 9351, N. Navab, J. Hornegger, W. M. Wells, and A. F. Frangi, Eds. Cham: Springer International Publishing, 2015, pp. 234–241. DOI: https://doi.org/10.1007/978-3-319-24574-4_28
Y. R. Habarnau and M. Namías, "A mirror-Unet architecture for PET/CT lesion segmentation." arXiv, Sept. 2023.
Ö. Çiçek, A. Abdulkadir, S. S. Lienkamp, T. Brox, and O. Ronneberger, "3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation," in Medical Image Computing and Computer-Assisted Intervention – MICCAI 2016, vol. 9901, S. Ourselin, L. Joskowicz, M. R. Sabuncu, G. Unal, and W. Wells, Eds. Cham: Springer International Publishing, 2016, pp. 424–432. DOI: https://doi.org/10.1007/978-3-319-46723-8_49
Z. Zhou, M. M. Rahman Siddiquee, N. Tajbakhsh, and J. Liang, "UNet++: A Nested U-Net Architecture for Medical Image Segmentation," in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, vol. 11045, D. Stoyanov, Z. Taylor, G. Carneiro, T. Syeda-Mahmood, A. Martel, L. Maier-Hein, J. M. R. S. Tavares, A. Bradley, J. P. Papa, V. Belagiannis, J. C. Nascimento, Z. Lu, S. Conjeti, M. Moradi, H. Greenspan, and A. Madabhushi, Eds. Cham: Springer International Publishing, 2018, pp. 3–11.
F. Isensee, P. F. Jaeger, S. A. A. Kohl, J. Petersen, and K. H. Maier-Hein, "nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation," Nature Methods, vol. 18, no. 2, pp. 203–211, Feb. 2021. DOI: https://doi.org/10.1038/s41592-020-01008-z
D. Xiang, B. Zhang, Y. Lu, and S. Deng, "Modality-Specific Segmentation Network for Lung Tumor Segmentation in PET-CT Images," IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 3, pp. 1237–1248, Mar. 2023. DOI: https://doi.org/10.1109/JBHI.2022.3186275
A. Firouzian, M. D. Kelly, and J. M. Declerck, "Insight on automated lesion delineation methods for PET data," EJNMMI Research, vol. 4, no. 1, Dec. 2014, Art. no. 69. DOI: https://doi.org/10.1186/s13550-014-0069-8
S. Venkatesh et al., "Multi-Annotator Consensus Network with Adaptive Preprocessing for Lung Nodule Segmentation: A Deep Learning Framework for Clinical Decision Support," Engineering, Technology & Applied Science Research, vol. 15, no. 6, pp. 29566–29573, Dec. 2025. DOI: https://doi.org/10.48084/etasr.12408
S. Lalitha and P. Nimmagadda, "VASC-Net: A Novel AI Framework Combining CNN Architectures with SVM for Lung Cancer Detection," Engineering, Technology & Applied Science Research, vol. 15, no. 6, pp. 29722–29730, Dec. 2025. DOI: https://doi.org/10.48084/etasr.12243
M. Xia et al., "Anatomically and metabolically informed diffusion for unified denoising and segmentation in low-count PET imaging," Medical Image Analysis, vol. 107, Jan. 2026, Art. no. 103831. DOI: https://doi.org/10.1016/j.media.2025.103831
X. Lin et al., "Intratumoral and peritumoral PET/CT-based radiomics for non-invasively and dynamically predicting immunotherapy response in NSCLC," British Journal of Cancer, vol. 132, no. 6, pp. 558–568, Apr. 2025. DOI: https://doi.org/10.1038/s41416-025-02948-z
P. Taheri and A. Golden, "A prognostic PET radiomic model for risk stratification in non-small cell lung cancer: integrating radiogenomics and clinical features to predict survival and uncover tumor biology insights," Journal of Cancer Research and Clinical Oncology, vol. 151, no. 6, June 2025, Art. no. 180. DOI: https://doi.org/10.1007/s00432-025-06232-8
G. M. Alshmrani, Q. Ni, R. Jiang, and N. Muhammed, "Hyper-Dense_Lung_Seg: Multimodal-Fusion-Based Modified U-Net for Lung Tumour Segmentation Using Multimodality of CT-PET Scans," Diagnostics, vol. 13, no. 22, Nov. 2023, Art. no. 3481. DOI: https://doi.org/10.3390/diagnostics13223481
V. Balaji, T.-A. Song, M. Malekzadeh, P. Heidari, and J. Dutta, "Artificial Intelligence for PET and SPECT Image Enhancement," Journal of Nuclear Medicine, vol. 65, no. 1, pp. 4–12, Jan. 2024. DOI: https://doi.org/10.2967/jnumed.122.265000
S. Gatidis and T. Kuestner, "A whole-body FDG-PET/CT dataset with manually annotated tumor lesions (FDG-PET-CT-Lesions)." The Cancer Imaging Archive, 2022. DOI: https://doi.org/10.1038/s41597-022-01718-3
Downloads
How to Cite
License
Copyright (c) 2026 N. Shruthi, N. Manju
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.
