An automated surgical decision-making framework for partial or radical nephrectomy based on 3D-CT multi-level anatomical features in renal cell carcinoma
Tóm tắt
To determine whether 3D-CT multi-level anatomical features can provide a more accurate prediction of surgical decision-making for partial or radical nephrectomy in renal cell carcinoma. This is a retrospective study based on multi-center cohorts. A total of 473 participants with pathologically proved renal cell carcinoma were split into the internal training and the external testing set. The training set contains 412 cases from five open-source cohorts and two local hospitals. The external testing set includes 61 participants from another local hospital. The proposed automatic analytic framework contains the following modules: a 3D kidney and tumor segmentation model constructed by 3D-UNet, a multi-level feature extractor based on the region of interest, and a partial or radical nephrectomy prediction classifier by XGBoost. The fivefold cross-validation strategy was used to get a robust model. A quantitative model interpretation method called the Shapley Additive Explanations was conducted to explore the contribution of each feature. In the prediction of partial versus radical nephrectomy, the combination of multi-level features achieved better performance than any single-level feature. For the internal validation, the AUROC was 0.93 ± 0.1, 0.94 ± 0.1, 0.93 ± 0.1, 0.93 ± 0.1, and 0.93 ± 0.1, respectively, as determined by the fivefold cross-validation. The AUROC from the optimal model was 0.82 ± 0.1 in the external testing set. The tumor shape Maximum 3D Diameter plays the most vital role in the model decision. The automated surgical decision framework for partial or radical nephrectomy based on 3D-CT multi-level anatomical features exhibits robust performance in renal cell carcinoma. The framework points the way towards guiding surgery through medical images and machine learning. We proposed an automated analytic framework that can assist surgeons in partial or radical nephrectomy decision-making. The framework points the way towards guiding surgery through medical images and machine learning.
• The 3D-CT multi-level anatomical features provide a more accurate prediction of surgical decision-making for partial or radical nephrectomy in renal cell carcinoma.
• The data from multicenter study and a strict fivefold cross-validation strategy, both internal validation set and external testing set, can be easily transferred to different tasks of new datasets.
• The quantitative decomposition of the prediction model was conducted to explore the contribution of each extracted feature.
Tài liệu tham khảo
Ljungberg B, Albiges L, Abu-Ghanem Y et al (2022) European Association of Urology Guidelines on Renal Cell Carcinoma: The 2022 Update. Eur Urol.https://doi.org/10.1016/j.eururo.2022.03.006:399-410
Moch H, Cubilla AL, Humphrey PA, Reuter VE, Ulbright TM (2016) The 2016 WHO Classification of Tumours of the Urinary System and Male Genital Organs-Part A: renal, penile, and testicular tumours. Eur Urol 70:93–105
Rouprêt M, Babjuk M, Burger M et al (2021) European Association of Urology guidelines on upper urinary tract urothelial carcinoma: 2020 update. Eur Urol 79:62–79
Klett DE, Tsivian M, Packiam VT et al (2021) Partial versus radical nephrectomy in clinical T2 renal masses. Int J Urol 28:1149–1154
Castro-Porras LV, Rojas-Russell ME, Villanueva-Sanchez J, Lopez-Cervantes M (2019) An anthropometry-based equation of fat mass percentage as a valid discriminator of obesity. Public Health Nutr 22:1250–1258
Capitanio U, Terrone C, Antonelli A et al (2015) Nephron-sparing techniques independently decrease the risk of cardiovascular events relative to radical nephrectomy in patients with a T1a–T1b renal mass and normal preoperative renal function. Eur Urol 67:683–689
MacLennan S, Imamura M, Lapitan MC et al (2012) Systematic review of oncological outcomes following surgical management of localised renal cancer. Eur Urol 61:972–993
Semko S, Pikul M, Voylenko O et al (2021) Life quality among patients with kidney cancer depending on the surgery type. Eur Radiol 79:776–776
Rossi SH, Prezzi D, Kelly-Morland C, Goh V (2018) Imaging for the diagnosis and response assessment of renal tumours. World J Urol 36:1927–1942
Motzer RJ, Jonasch E, Boyle S et al (2020) NCCN guidelines insights: kidney cancer, version 1.2021: featured updates to the NCCN guidelines. J Natl Compr Canc Netw 18:1160–1170
Buffi N, Lista G, Larcher A et al (2012) Margin, ischemia, and complications (MIC) score in partial nephrectomy: a new system for evaluating achievement of optimal outcomes in nephron-sparing surgery. Eur Urol 62:617–618
Lista G, Buffi NM, Lughezzani G et al (2015) Margin, ischemia, and complications system to report perioperative outcomes of robotic partial nephrectomy: a European Multicenter Observational Study (EMOS project). Urology 85:589–595
Teishima J, Hayashi T, Kitano H et al (2020) Impact of radiological morphology of clinical T1 renal cell carcinoma on the prediction of upstaging to pathological T3. Jpn J Clin Oncol 50:473–478
Schiavina R, Borghesi M, Chessa F, Rizzi S, Martorana G (2014) Predictors of positive surgical margins after nephron-sparing surgery for renal cell carcinoma: retrospective analysis on 298 consecutive patients. Urologia 81:40–45
Luo S, Wei R, Lu S et al (2022) Fuhrman nuclear grade prediction of clear cell renal cell carcinoma: influence of volume of interest delineation strategies on machine learning-based dynamic enhanced CT radiomics analysis. Eur Radiol 32:2340–2350
Wu K, Wu P, Yang K et al (2022) A comprehensive texture feature analysis framework of renal cell carcinoma: pathological, prognostic, and genomic evaluation based on CT images. Eur Radiol 32:2255–2265
Demirjian NL, Varghese BA, Cen SY et al (2022) CT-based radiomics stratification of tumor grade and TNM stage of clear cell renal cell carcinoma. Eur Radiol 32:2552–2563
Healy GM, Salinas-Miranda E, Jain R et al (2022) Pre-operative radiomics model for prognostication in resectable pancreatic adenocarcinoma with external validation. Eur Radiol 32:2492–2505
Zhang G, Wu Z, Zhang X et al (2022) CT-based radiomics to predict muscle invasion in bladder cancer. Eur Radiol 32:3260–3268
McGovern A, Lagerquist R, Gagne DJ et al (2019) Making the black box more transparent: understanding the physical implications of machine learning. Bull Am Meteor Soc 100:2175–2199
Watson DS, Krutzinna J, Bruce IN et al (2019) Clinical applications of machine learning algorithms: beyond the black box. BMJ 364:1886
Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH (2021) nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18:203–211
Chen T, Guestrin C (2016) Xgboost: a scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. 785–794
Lundberg SM, Erion G, Chen H et al (2020) From local explanations to global understanding with explainable AI for trees. Nat Mach Intell 2:56–67
Kutikov A, Uzzo RG (2009) The R.E.N.A.L. nephrometry score: a comprehensive standardized system for quantitating renal tumor size, location and depth. J Urol 182:844–853
Ficarra V, Novara G, Secco S et al (2009) Preoperative aspects and dimensions used for an anatomical (PADUA) classification of renal tumours in patients who are candidates for nephron-sparing surgery. Eur Urol 56:786–793
Veccia A, Antonelli A, Uzzo RG et al (2020) Predictive value of nephrometry scores in nephron-sparing surgery: a systematic review and meta-analysis. Eur Urol Focus 6:490–504
Benadiba S, Verin AL, Pignot G et al (2015) Are urologists and radiologists equally effective in determining the RENAL Nephrometry score? Ann Surg Oncol 22:1618–1624
Hickman SE, Woitek R, Le EPV et al (2022) Machine learning for workflow applications in screening mammography: systematic review and meta-analysis. Radiology 302:88–104
Fan M, Cui Y, You C et al (2022) Radiogenomic signatures of oncotype DX recurrence score enable prediction of survival in estrogen receptor–positive breast cancer: a multicohort study. Radiology 302:516–524
Hou R, Grimm LJ, Mazurowski MA et al (2022) Prediction of upstaging in ductal carcinoma in situ based on mammographic radiomic features. Radiology 303:54–62
Pease M, Arefan D, Barber J et al (2022) Outcome prediction in patients with severe traumatic brain injury using deep learning from head CT scans. Radiology 304:385–394
Zhao Y, Liu G, Sun Q, Zhai G, Wu G, Li Z-C (2021) Validation of CT radiomics for prediction of distant metastasis after surgical resection in patients with clear cell renal cell carcinoma: exploring the underlying signaling pathways. Eur Radiol 31:5032–5040
Visvikis D, Cheze Le Rest C, Jaouen V, Hatt M (2019) Artificial intelligence, machine (deep) learning and radio(geno)mics: definitions and nuclear medicine imaging applications. Eur J Nucl Med Mol Imaging 46:2630–2637
Litjens G, Kooi T, Bejnordi BE et al (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88
Napel S, Mu W, Jardim-Perassi BV, Aerts H, Gillies RJ (2018) Quantitative imaging of cancer in the postgenomic era: radio(geno)mics, deep learning, and habitats. Cancer 124:4633–4649
Yang W, Huang H, Zhang Z, Chen X, Huang K, Zhang S (2019) Towards rich feature discovery with class activation maps augmentation for person re-identificationProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 1389–1398