Deep Learning for Adrenal Gland Segmentation: Comparing Accuracy and Efficiency Across Three Convolutional Neural Network Models
Source abstract
Abstract
Adrenal glands are vital endocrine organs whose accurate segmentation on CT imaging presents significant challenges due to their small size and variable morphology. This study evaluates the efficacy of deep learning approaches for automatic adrenal gland segmentation from multiphase CT scans. We implemented three convolutional neural network architectures (U-Net, SegNet, and NablaNet) and assessed their performance on a dataset comprising 868 adrenal glands from contrast-enhanced abdominal CT scans. Performance was evaluated using the Dice similarity coefficient (DSC), alongside practical implementation metrics including training and deployment time. U-Net demonstrated superior segmentation performance (DSC: 0.630 ± 0.05 for right, 0.660 ± 0.06 for left adrenal glands) compared to NablaNet (DSC: 0.552 ± 0.08 for right, 0.550 ± 0.07 for left) and SegNet (DSC: 0.320 ± 0.10 for right, 0.335 ± 0.09 for left). While all models achieved high specificity, boundary delineation accuracy remained challenging. Our findings demonstrate the feasibility of deep learning-based adrenal gland segmentation while highlighting the persistent challenges in achieving the segmentation quality observed with larger abdominal organs. U-Net provides the optimal balance between accuracy and computational requirements, establishing a foundation for further refinement of AI-assisted adrenal imaging tools.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Radiomics and Machine Learning in Medical Imaging · AI in cancer detection · Medical Imaging Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Doctoral Program Studies, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, Romania
Department of Fundamental Sciences, Faculty of Midwifery and Nursing, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, Romania
Department of Clinical Laboratory of Radiology and Medical Imaging, Clinical Hospital “Prof. Dr. Theodor Burghele”, 050664 Bucharest, Romania
Clinical Laboratory of Medical Microbiology, Marius Nasta Institute of Pneumology, 050159 Bucharest, Romania
Department of Urology, Clinical Hospital “Prof. Dr. Theodor Burghele”, Faculty of Medicine, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, Romania
Department of Urology, Clinical Hospital “Prof. Dr. Theodor Burghele”, 050664 Bucharest, Romania
Medical Sciences Section, Academy of Romanian Scientists, 050085 Bucharest, Romania
References (51)
Show source-provided references
1. Adrenal development and disease
2. The molecular biology, biochemistry, and physiology of human steroidogenesis and its disorders10.1210/er.2010-0013 ↗
3. Functional zonation of the rat adrenal cortex: The development and maintenance10.2183/pjab.90.163 ↗
4. Imaging techniques for adrenal lesion characterization10.1016/j.rcl.2008.01.003 ↗
5. Imaging of adrenal masses10.1016/S0720-048X(01)00444-2 ↗
6. Torresan, F., Ceccato, F., Barbot, M., and Scaroni, C. (2021). Adrenal venous sampling: Technique, indications, and limitations. Front. Endocrinol., 12.
7. Adrenal imaging: Current status and future perspectives
8. Management of adrenal incidentalomas: European Society of Endocrinology Clinical Practice Guideline in collaboration with the European Network for the Study of Adrenal Tumors10.1530/EJE-16-0467 ↗
9. Prevalence of adrenal incidentaloma in a contemporary computerized tomography series10.1007/BF03344099 ↗
10. Incidentally discovered adrenal masses
11. Minor morphologic abnormalities of adrenal glands at CT: Prognostic importance in patients with lung cancer10.1148/radiol.2352031708 ↗
12. Incidental adrenal lesions: Principles, techniques, and algorithms for imaging characterization10.1148/radiol.2493070976 ↗
13. Adrenal imaging with multidetector CT: Evidence-based protocol optimization and interpretative practice10.1148/rg.295095026 ↗
14. State-of-the-art MR imaging of the adrenal gland
15. Distinguishing benign from malignant adrenal masses: Multi-detector row CT protocol with 10-minute delay10.1148/radiol.2382041514 ↗
16. Current methods in medical image segmentation10.1146/annurev.bioeng.2.1.315 ↗
17. Can established CT attenuation and washout criteria for adrenal adenoma accurately exclude pheochromocytoma?10.2214/AJR.12.9620 ↗
18. Imaging of adrenal incidentalomas: Current status10.2214/ajr.179.3.1790559 ↗
19. Adrenal imaging10.1046/j.1464-410X.2000.00588.x ↗
20. A survey on deep learning in medical image analysis10.1016/j.media.2017.07.005 ↗
21. Deep learning techniques for medical image segmentation: Achievements and challenges10.1007/s10278-019-00227-x ↗
22. Ourselin, S., Joskowicz, L., Sabuncu, M., Unal, G., and Wells, W. (2016). Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields. Medical Image Computing and Computer-Assisted Intervention—MICCAI 2016, Springer.10.1007/978-3-319-46726-9_73 ↗
23. Heller, N., Sathianathen, N., Kalapara, A., Walczak, E., Moore, K., Kaluzniak, H., Rosenberg, J., Blake, P., Rengel, Z., and Oestreich, M. (2019). The KiTS19 challenge data: 300 kidney tumor cases with clinical context, CT semantic segmentations, and surgical outcomes. arXiv.
24. nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation10.1038/s41592-020-01008-z ↗
25. Navab, N., Hornegger, J., Wells, W., and Frangi, A. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Springer.10.1007/978-3-319-24571-3 ↗
26. Attention gated networks: Learning to leverage salient regions in medical images10.1016/j.media.2019.01.012 ↗
27. TransUNet: Transformers make strong encoders for medical image segmentation
28. Karlinsky, L., Michaeli, T., and Nishino, K. (2023). Swin-Unet: Unet-Like Pure Transformer for Medical Image Segmentation. Computer Vision—ECCV 2022 Workshops. ECCV 2022, Springer.10.1007/978-3-031-25063-7 ↗
29. Abdominal multi-organ segmentation with organ-attention networks and statistical fusion10.1016/j.media.2019.04.005 ↗
30. Automatic multi-organ segmentation on abdominal CT with dense v-networks10.1109/TMI.2018.2806309 ↗
31. SegNet: A deep convolutional encoder-decoder architecture for image segmentation10.1109/TPAMI.2016.2644615 ↗
32. Joint optic disc and cup segmentation based on multi-label deep network and polar transformation10.1109/TMI.2018.2791488 ↗
33. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv.
34. Multi-Scale Three-Path Network (MSTP-Net): A new architecture for retinal vessel segmentation
35. A review of cancer data fusion methods based on deep learning
36. Isensee, F., and Maier-Hein, K.H. (2019). An attempt at beating the 3D U-Net. arXiv.10.24926/548719.001 ↗
37. Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D., and Duchesne, S. (2017). A Fixed-Point Model for Pancreas Segmentation in Abdominal CT Scans. Medical Image Computing and Computer Assisted Intervention−MICCAI 2017, Springer.10.1007/978-3-319-66179-7 ↗
38. Deep semantic segmentation of natural and medical images: A review10.1007/s10462-020-09854-1 ↗
39. Humpire-Mamani, G.E., Setio, A.A.A., van Ginneken, B., and Jacobs, C. (2018). Efficient organ localization using multi-task convolutional neural networks in thorax-abdomen CT scans. Phys. Med. Biol., 63.10.1088/1361-6560/aab4b3 ↗
40. A novel MRI segmentation method using CNN-based correction network for MRI-guided adaptive radiotherapy10.1002/mp.13221 ↗
41. Navab, N., Hornegger, J., Wells, W., and Frangi, A. (2015). DeepOrgan: Multi-level Deep Convolutional Networks for Automated Pancreas Segmentation. Medical Image Computing and Computer-Assisted Intervention--MICCAI 2015, Springer.
42. Characterization of adrenal masses (<5 cm) by use of chemical shift MR imaging: Observer performance versus quantitative measures10.2214/ajr.165.1.7785642 ↗
43. Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N., and Kainz, B. (2018). Attention U-Net: Learning Where to Look for the Pancreas. arXiv.
44. TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers10.1016/j.media.2024.103280 ↗
45. Crimi, A., Bakas, S., Kuijf, H., Menze, B., and Reyes, M. (2018). Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation. Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2017, Springer.10.1007/978-3-319-75238-9 ↗
46. Position paper on COVID-19 imaging and AI: From the clinical needs and technological challenges to initial AI solutions at the lab and national level towards a new era for AI in healthcare10.1016/j.media.2020.101800 ↗
47. A roadmap for foundational research on artificial intelligence in medical imaging: From the 2018 NIH/RSNA/ACR/The Academy Workshop10.1148/radiol.2019190613 ↗
48. Krähenbühl, P., and Koltun, V. (2011, January 12–15). Efficient inference in fully connected CRFs with Gaussian edge potentials. Proceedings of the Advances in Neural Information Processing Systems—NeurIPS 2011, Granada, Spain.
49. Classification of Pancreatic Cysts in Computed Tomography Images Using a Random Forest and Convolutional Neural Network Ensemble
50. Li, W., Lin, Z., Zhou, K., Qi, L., Wang, Y., and Jia, J. (2022, January 18–24). MAT: Mask-aware Transformer for Large Hole Image Inpainting. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.01049 ↗
51. Self-supervised learning for medical image analysis using image context restoration