Computer-aided diagnosis for screening of lower extremity lymphedema in pelvic computed tomography images using deep learning.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
27 09 2023
27 09 2023
Historique:
received:
25
05
2023
accepted:
25
09
2023
medline:
29
9
2023
pubmed:
28
9
2023
entrez:
27
9
2023
Statut:
epublish
Résumé
Lower extremity lymphedema (LEL) is a common complication after gynecological cancer treatment, which significantly reduces the quality of life. While early diagnosis and intervention can prevent severe complications, there is currently no consensus on the optimal screening strategy for postoperative LEL. In this study, we developed a computer-aided diagnosis (CAD) software for LEL screening in pelvic computed tomography (CT) images using deep learning. A total of 431 pelvic CT scans from 154 gynecological cancer patients were used for this study. We employed ResNet-18, ResNet-34, and ResNet-50 models as the convolutional neural network (CNN) architecture. The input image for the CNN model used a single CT image at the greater trochanter level. Fat-enhanced images were created and used as input to improve classification performance. Receiver operating characteristic analysis was used to evaluate our method. The ResNet-34 model with fat-enhanced images achieved the highest area under the curve of 0.967 and an accuracy of 92.9%. Our CAD software enables LEL diagnosis from a single CT image, demonstrating the feasibility of LEL screening only on CT images after gynecologic cancer treatment. To increase the usefulness of our CAD software, we plan to validate it using external datasets.
Identifiants
pubmed: 37758908
doi: 10.1038/s41598-023-43503-1
pii: 10.1038/s41598-023-43503-1
pmc: PMC10533488
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
16214Informations de copyright
© 2023. Springer Nature Limited.
Références
Grada, A. A. & Phillips, T. J. Lymphedema: Diagnostic workup and management. J. Am. Acad. Dermatol. 77, 995–1006 (2017).
doi: 10.1016/j.jaad.2017.03.021
pubmed: 29132859
Grada, A. A. & Phillips, T. J. Lymphedema: Pathophysiology and clinical manifestations. J. Am. Acad. Dermatol. 77, 1009–1020 (2017).
doi: 10.1016/j.jaad.2017.03.022
pubmed: 29132848
Manrique, O. J. et al. Overview of lymphedema for physicians and other clinicians: A review of fundamental concepts. Mayo Clin. Proc. 97, 1920–1935 (2022).
doi: 10.1016/j.mayocp.2020.01.006
pubmed: 32829905
Kim, W. J., Kim, J., Kang, M., Park, D. H. & Jeon, J. Y. Usefulness of computed tomography venography in gynecologic cancer patients with lower extremity edema. Medicine. 99, e21818 (2020).
doi: 10.1097/MD.0000000000021818
pubmed: 32925718
pmcid: 7489682
Wong, M. et al. The prevalence of undiagnosed postoperative lower limb lymphedema among gynecological oncology patients. Eur. J. Surg. Oncol. 48, 1167–1172 (2022).
doi: 10.1016/j.ejso.2021.12.464
pubmed: 34980543
Bona, A. F., Ferreira, K. R., Carvalho, R. B. M., Thuler, L. C. S. & Bergmann, A. Incidence, prevalence, and factors associated with lymphedema after treatment for cervical cancer: A systematic review. Int. J. Gynecol. Cancer 30, 1697–1704 (2020).
doi: 10.1136/ijgc-2020-001682
pubmed: 32863276
Bowman, C., Piedalue, K. A., Baydoun, M. & Carlson, L. E. The quality of life and psychosocial implications of cancer-related lower-extremity lymphedema: A systematic review of the literature. J. Clin. Med. 9, 3200 (2020).
doi: 10.3390/jcm9103200
pubmed: 33023211
pmcid: 7601061
Hu, H., Fu, M., Huang, X., Huang, J. & Gao, J. Risk factors for lower extremity lymphedema after cervical cancer treatment: A systematic review and meta-analysis. Transl. Cancer Res. 11, 1713–1721 (2022).
doi: 10.21037/tcr-22-1256
pubmed: 35836533
pmcid: 9273676
Zhang, H. et al. Current status and progress in the treatment of lower limb lymphedema after treatment of gynecological oncology. Lymphat. Res. Biol. 20, 308–314 (2022).
doi: 10.1089/lrb.2021.0035
pubmed: 34698556
Russo, S. et al. Standardization of lower extremity quantitative lymphedema measurements and associated patient-reported outcomes in gynecologic cancers. Gynecol. Oncol. 160, 625–632 (2021).
doi: 10.1016/j.ygyno.2020.10.026
pubmed: 33158510
Pani, S. P., Vanamail, P. & Yuvaraj, J. Limb circumference measurement for recording edema volume in patients with filarial lymphedema. Lymphology. 28, 57–63 (1995).
pubmed: 7564492
Cornish, B. H. et al. Early diagnosis of lymphedema using multiple frequency bioimpedance. Lymphology 34, 2–11 (2001).
pubmed: 11307661
Carter, J. et al. GOG 244: The lymphedema and gynecologic cancer (LEG) study: The association between the gynecologic cancer lymphedema questionnaire (GCLQ) and lymphedema of the lower extremity (LLE). Gynecol. Oncol. 155, 452–460 (2019).
doi: 10.1016/j.ygyno.2019.09.027
pubmed: 31679787
pmcid: 6900449
Szuba, A., Shin, W. S., Strauss, H. W. & Rockson, S. The third circulation: radionuclide lymphoscintigraphy in the evaluation of lymphedema. J. Nucl. Med. 44, 43–57 (2003).
pubmed: 12515876
Yamamoto, T. et al. The earliest finding of indocyanine green lymphography in asymptomatic limbs of lower extremity lymphedema patients secondary to cancer treatment: The modified dermal backflow stage and concept of subclinical lymphedema. Plast. Reconstr. Surg. 128, 314e–321e (2011).
doi: 10.1097/PRS.0b013e3182268da8
pubmed: 21921744
Akita, S. et al. Noninvasive screening test for detecting early stage lymphedema using follow-up computed tomography imaging after cancer treatment and results of treatment with lymphaticovenular anastomosis. Microsurgery 37, 910–916 (2017).
doi: 10.1002/micr.30188
pubmed: 28621805
Litjens, G. et al. A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60–88 (2017).
doi: 10.1016/j.media.2017.07.005
pubmed: 28778026
Sahiner, B. et al. Deep learning in medical imaging and radiation therapy. Med. Phys. 46, e1–e36 (2019).
doi: 10.1002/mp.13264
pubmed: 30367497
Fujita, H. AI-based computer-aided diagnosis (AI-CAD): The latest review to read first. Radiol. Phys. Technol. 13, 6–19 (2020).
doi: 10.1007/s12194-019-00552-4
pubmed: 31898014
Kim, W. H., Kim, C. G. & Kim, D. W. Optimal CT number range for adipose tissue when determining lean body mass in whole-body F-18 FDG PET/CT studies. Nucl. Med. Mol. Imaging. 46, 294–299 (2012).
doi: 10.1007/s13139-012-0175-3
pubmed: 24900077
pmcid: 4043057
He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. ArXiv. http://arxiv.org/abs/1512.03385 (2015).
Obuchowski, N. A. ROC analysis. AJR Am. J. Roentgenol. 184, 364–372 (2005).
doi: 10.2214/ajr.184.2.01840364
pubmed: 15671347
Fawcett, T. An introduction to ROC analysis. Pattern Recog. Lett. 27, 861–874 (2006).
doi: 10.1016/j.patrec.2005.10.010
Youden, W. J. Index for rating diagnostic tests. Cancer 3, 32–35 (1950).
doi: 10.1002/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3
pubmed: 15405679
Selvaraju, R. R. et al. Grad-CAM: Visual explanations from deep networks via gradient-based localization. in Proceeding of 2017 IEEE International Conference on Computer Vision (ICCV), 618–626 (2017).
Lee, K. S., Ryu, J. J., Jang, H. S., Lee, D. Y. & Jung, S. K. Deep convolutional neural networks based analysis of cephalometric radiographs for differential diagnosis of orthognathic surgery indications. Appl. Sci. 10, 2124 (2020).
doi: 10.3390/app10062124
Kim, Y. H. et al. Influence of the depth of the convolutional neural networks on an artificial intelligence model for diagnosis of orthognathic surgery. J. Pers. Med. 11, 356 (2021).
doi: 10.3390/jpm11050356
pubmed: 33946874
pmcid: 8145139
Akita, S. et al. Suitable therapy options for sub-clinical and early-stage lymphoedema patients. J. Plast. Reconstr. Aesthet. Surg. 67, 520–525 (2014).
doi: 10.1016/j.bjps.2013.12.056
pubmed: 24480651
NCCN Guidelines for Cervical Cancer. National Comprehensive Cancer Network. https://www.nccn.org/professionals/physician_gls/pdf/cervical.pdf (2023).
NCCN Guidelines for Uterine Neoplasms. National Comprehensive Cancer Network. https://www.nccn.org/professionals/physician_gls/pdf/uterine.pdf (2023).
NCCN Guidelines for Ovarian Cancer. National Comprehensive Cancer Network. https://www.nccn.org/professionals/physician_gls/pdf/ovarian.pdf (2023).
Colombo, N. et al. ESMO-ESGO consensus conference recommendations on ovarian cancer: Pathology and molecular biology, early and advanced stages, borderline tumours and recurrent disease. Ann. Oncol. 30, 672–705 (2019).
doi: 10.1093/annonc/mdz062
pubmed: 31046081
Fu, M. R. et al. Machine learning for detection of lymphedema among breast cancer survivors. Mhealth 4, 17 (2018).
doi: 10.21037/mhealth.2018.04.02
pubmed: 29963562
pmcid: 5994440
Wei, X. et al. Developing and validating a prediction model for lymphedema detection in breast cancer survivors. Eur. J. Oncol. Nurs. 54, 102023 (2021).
doi: 10.1016/j.ejon.2021.102023
pubmed: 34500318
Hosseinzadeh, M. et al. Prediction of cognitive decline in Parkinson’s disease using clinical and DAT SPECT imaging features, and hybrid machine learning systems. Diagnostics. 13, 1691 (2023).
doi: 10.3390/diagnostics13101691
pubmed: 37238175
pmcid: 10217464
Salmanpour, M. R., Rezaeijo, S. M., Hosseinzadeh, M. & Rahmim, A. Deep versus handcrafted tensor radiomics features: Prediction of survival in head and neck cancer using machine learning and fusion techniques. Diagnostics. 13, 1696 (2023).
doi: 10.3390/diagnostics13101696
pubmed: 37238180
pmcid: 10217462
Wang, H., Shikano, K., Nakajima, T., Nomura, Y. & Nakaguchi, T. Peripheral pulmonary lesions classification using endobronchial ultrasonography images based on bagging ensemble learning and down-sampling technique. Appl. Sci. 13, 8403 (2023).
doi: 10.3390/app13148403
Chen, X. et al. Recent advances and clinical applications of deep learning in medical image analysis. Med. Image Anal. 79, 102444 (2022).
doi: 10.1016/j.media.2022.102444
pubmed: 35472844
pmcid: 9156578
Shamshad, F. et al. Transformers in medical imaging: A survey. Med. Image Anal. 88, 102802 (2023).
doi: 10.1016/j.media.2023.102802
pubmed: 37315483
Bergstra, J. & Bengio, Y. Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13, 281–305 (2012).
Prechelt, L. in Neural Networks: Tricks of the Trade: Second Edition (eds G. Montavon, G. B. Orr, & K.-R. Müller), 53–67 (Springer, 2012).
Paszke, A. et al. PyTorch: An imperative style, high-performance deep learning library. http://arxiv.org/abs/1912.01703 (2019).