Assessing the probability of metastatic mediastinal lymph node involvement in patients with non small cell lung cancer using convolutional neural networks on chest computed tomography

Capa

Citar

Texto integral

Resumo

BACKGROUND: Lung cancer is the second most common cancer worldwide, accounting for approximately 20% of all cancer related deaths and having a <10% 5 year survival rate for very late stage cases. For the prevalent non small cell lung cancer (NSCLC), recent guidelines advise staging based on the 8th edition of the TNM classification, highlighting the importance of mediastinal lymph node involvement. While noninvasive methods are generally accurate, they often lack sensitivity, and invasive methods may not be suitable for all patients. Advances in deep learning present potential in solving such problems. However, most research focuses on algorithm development more than clinical relevance. Moreover, none of them addressed individual lymph node malignancies, limiting comprehensive analysis and interpretability and leaving clinicians without sufficient means to validate the results effectively.

AIM: To develop a local data trained and validated algorithm for segmenting each mediastinal lymph node in chest computed tomography (CT) and assessing the probability of its involvement in metastasis.

MATERIALS AND METHODS: Initially, IASLC lymph node stations are segmented, providing a bounding box of the mediastinum for further processing. Next, the image is cropped to this box and passed through a second network to identify and mask all visible lymph nodes. Finally, each detected lymph node is extracted, stacked with its mask, and evaluated by a feed-forward network to determine malignancy probabilities.

RESULTS: The pipeline achieved an average recall and object Dice Score of 0.74±0.01 and 0.53±0.26 for the clinically relevant lymph node segmentation task. Further, it recorded a 0.73 ROC AUC for predicting a patient’s N-stage, outperforming traditional size based criteria.

CONCLUSIONS: The proposed algorithm enables new research algorithms to optimize the management of patients with nonenlarged intrathoracic lymph nodes, thus improving the quality of medical care for patients with cancer.

Sobre autores

Alexey Shevtsov

IRA Labs

Autor responsável pela correspondência
Email: a.shevtsov@ira-labs.com
ORCID ID: 0000-0003-3085-4325
Rússia, Moscow

Iaroslav Tominin

IRA Labs

Email: ya.tominin@ira-labs.com
ORCID ID: 0000-0002-7210-7208
Rússia, Moscow

Vladislav Tominin

IRA Labs

Email: v.tominin@ira-labs.com
ORCID ID: 0000-0001-5678-3452
Rússia, Moscow

Vsevolod Malevanniy

IRA Labs

Email: v.malevanniy@ira-labs.com
ORCID ID: 0009-0005-8804-2102
Rússia, Moscow

Yury Esakov

Moscow City Clinical Oncological Hospital № 1

Email: lungsurgery@mail.ru
ORCID ID: 0000-0002-5933-924X
Código SPIN: 8424-0756

MD, Cand. Sci. (Medicine)

Rússia, Moscow

Zurab Tukvadze

Moscow City Clinical Oncological Hospital № 1

Email: tukvadze.z.med@gmail.com
ORCID ID: 0000-0002-4550-6107
Rússia, Moscow

Andrey Nefedov

Saint-Petersburg State Research Institute of Phthisiopulmonology

Email: herurg78@mail.ru
ORCID ID: 0000-0001-6228-182X
Código SPIN: 2365-9458

MD, Cand. Sci. (Medicine)

Rússia, Saint Petersburg

Piotr Yablonskii

Saint-Petersburg State Research Institute of Phthisiopulmonology

Email: glhirurgb2@mail.ru
ORCID ID: 0000-0003-4385-9643
Código SPIN: 3433-2624

MD, Dr. Sci. (Medicine), Professor

Rússia, Saint Petersburg

Pavel Gavrilov

Saint-Petersburg State Research Institute of Phthisiopulmonology

Email: spbniifrentgen@mail.ru
ORCID ID: 0000-0003-3251-4084
Código SPIN: 7824-5374

MD, Cand. Sci. (Med.)

Rússia, Saint Petersburg

Vadim Kozlov

Novosibirsk Regional Clinical Oncology Dispensary

Email: vadimkozlov80@mail.ru
ORCID ID: 0000-0003-3211-5139
Código SPIN: 8045-4286

MD, Cand. Sci. (Medicine)

Rússia, Novosibirsk

Mariya Blokhina

AstraZeneca Pharmaceuticals LLC

Email: mariya.blokhina@astrazeneca.com
ORCID ID: 0009-0002-9008-9485

MD

Rússia, Moscow

Elena Nalivkina

AstraZeneca Pharmaceuticals LLC

Email: elena.nalivkina@astrazeneca.com
ORCID ID: 0009-0003-5412-9643
Rússia, Moscow

Victor Gombolevskiy

IRA Labs; Artificial Intelligence Research Institute

Email: gombolevskii@gmail.com
ORCID ID: 0000-0003-1816-1315
Código SPIN: 6810-3279

MD, Cand. Sci. (Med.)

Rússia, Moscow; Moscow

Yuriy Vasilev

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: VasilevYA1@zdrav.mos.ru
ORCID ID: 0000-0002-5283-5961
Código SPIN: 4458-5608

MD, Dr. Sci. (Medicine)

Rússia, Moscow

Mariya Dugova

IRA Labs

Email: m.dugova@ira-labs.com
ORCID ID: 0009-0004-5586-8015

MD

Rússia, Moscow

Valeria Chernina

IRA Labs

Email: v.chernina@ira-labs.com
ORCID ID: 0000-0002-0302-293X
Código SPIN: 8896-8051

MD

Rússia, Moscow

Olga Omelyanskaya

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: OmelyanskayaOV@zdrav.mos.ru
ORCID ID: 0000-0002-0245-4431
Código SPIN: 8948-6152
Rússia, Moscow

Roman Reshetnikov

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: reshetnikov@fbb.msu.ru
ORCID ID: 0000-0002-9661-0254
Código SPIN: 8592-0558

Cand. Sci. (Physics and Mathematics)

Rússia, Moscow

Ivan Blokhin

Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies

Email: BlokhinIA@zdrav.mos.ru
ORCID ID: 0000-0002-2681-9378
Código SPIN: 3306-1387

MD, Cand. Sci. (Medicine)

Rússia, Moscow

Mikhail Belyaev

IRA Labs

Email: belyaevmichel@gmail.com
ORCID ID: 0000-0001-9906-6453
Código SPIN: 2406-1772

Cand. Sci. (Physics and Mathematics)

Rússia, Moscow

Bibliografia

  1. Thandra KCh, Barsouk A, Saginala K, et al. Epidemiology of lung cancer. Contemporary Oncology. 2021;25(1):45–52. doi: 10.5114/wo.2021.103829
  2. Goldstraw P, Chansky K, Crowley J, et al. The IASLC lung cancer staging project: Proposals for revision of the TNM stage groupings in the forthcoming (Eighth) edition of the TNM classification for lung cancer. J Thorac Oncol. 2016;11(1):39–51. doi: 10.1016/j.jtho.2015.09.009
  3. Tanoue LT, Tanner NT, Gould MK, Silvestri GA. Lung cancer screening. Am J Respir Crit Care Med. 2015;191(1):19–33. doi: 10.1164/rccm.201410-1777CI
  4. Ettinger DS, Wood DE, Aggarwal C, et al. NCCN guidelines insights: Non small cell lung cancer, version 1. 2020. J Natl Compr Canc Netw. 2019;17(12):1464–1472. doi: 10.6004/jnccn.2019.0059
  5. Planchard D, Popat S, Kerr K, et al. Metastatic non small cell lung cancer: ESMO clin-ical practice guidelines for diagnosis, treatment and follow up [published correction appears in Ann Oncol. 2019;30(5):863–870. doi: 10.1093/annonc/mdy474]. Ann Oncol. 2018;29(Suppl 4):iv192–iv237. doi: 10.1093/annonc/mdy275
  6. Heleno B, Siersma V, Brodersen J. Estimation of overdiagnosis of lung cancer in low dose computed tomography screening: A secondary analysis of the danish lung cancer screening trial. JAMA Intern Med. 2018;178(10):1420–1422. doi: 10.1001/jamainternmed.2018.3056
  7. Lopes Pegna A, Picozzi G, Falaschi F, et al. Four year results of low dose CT screen ing and nodule management in the ITALUNG trial. J Thorac Oncol. 2013;8(7):866–875. doi: 10.1097/JTO.0b013e31828f68d6
  8. Infante M, Cavuto S, Lutman FR, et al. Long term follow up results of the DANTE trial, a randomized study of lung cancer screening with spiral computed tomography. Am J Respir Crit Care Med. 2015;191(10):1166–1175. doi: 10.1164/rccm.201408-1475OC
  9. De Koning H, van der Aalst C, de Jong P. Reduced lung cancer mortality with volume CT screening in a randomized trial. N Engl J Med. 2020;382(6):503–513. doi: 10.1056/NEJMoa1911793
  10. Pastorino U, Silva M, Sestini S, et al. Prolonged lung cancer screening reduced 10-year mortality in the MILD trial: new confirmation of lung cancer screening efficacy. Ann Oncol. 2019;30(10):1672. doi: 10.1093/annonc/mdz169
  11. Baldwin DR, Duffy SW, Wald NJ, et al. UK Lung Screen (UKLS) nodule management protocol: modelling of a single screen randomised controlled trial of low dose CT screening for lung cancer. Thorax. 2011;66(4):308–313. doi: 10.1136/thx.2010.152066
  12. Detterbeck FC, Boffa DJ, Kim AW, Tanoue LT. The eighth edition lung cancer stage classification. Chest. 2017;151(1):193–203. doi: 10.1016/j.chest.2016.10.010
  13. Nakajima T, Yasufuku K, Yoshino I. Current status and perspective of EBUS-TBNA. Gen Thorac Cardiovasc Surg. 2013;61(7):390–396. doi: 10.1007/s11748-013-0224-6
  14. Hartert M, Tripsky J, Huertgen M. Video-assisted mediastinoscopic lymphadenecto-my (VAMLA) for staging & treatment of non small cell lung cancer (NSCLC). Mediastinum. 2020;4:3. doi: 10.21037/med.2019.09.06
  15. Ettinger DS, Wood DE, Aisner DL, et al. Non small cell lung cancer, version 5.2017, NCCN clinical practice guidelines in oncology. J Natl Compr Canc Netw. 2017;15(4):504–535. doi: 10.6004/jnccn.2017.0050
  16. Roberts PF, Follette DM, von Haag D, et al. Factors associated with false positive staging of lung cancer by positron emission tomography. Ann Thorac Surg. 2000;70(4):1154–1160. doi: 10.1016/s0003-4975(00)01769-0
  17. Kanzaki R, Higashiyama M, Fujiwara A, et al. Occult mediastinal lymph node metas-tasis in NSCLC patients diagnosed as clinical N0-1 by preoperative integrated FDG-PET/CT and CT: risk factors, pattern, and histopathological study. Lung Cancer. 2011;71(3):333–337. doi: 10.1016/j.lungcan.2010.06.008
  18. Verduzco-Aguirre HC, Lopes G, Soto Perez De Celis E. Implementation of diagnostic resources for cancer in developing countries: a focus on PET/CT. Ecancermedical science. 2019;13:ed87. doi: 10.3332/ecancer.2019.ed87
  19. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436–444. doi: 10.1038/nature14539
  20. Guo D, Ye X, Ge J, et al. Deepstationing: thoracic lymph node station parsing in CT scans using anatomical context encoding and key organ auto search. In: International Conference on Medical Image Computing and Computer Assisted Intervention; 2021 September 27–October 1; Strasbourg. Available from: https://miccai2021.org/openaccess/paperlinks/2021/09/01/140-Paper0015.html
  21. Iuga AI, Carolus H, Höink AJ, et al. Automated detection and segmentation of thorac ic lymph nodes from CT using 3D foveal fully convolutional neural networks. BMC Med Imaging. 2021;21(1):69. doi: 10.1186/s12880-021-00599-z
  22. Iuga AI, Lossau T, Caldeira LL, et al. Automated mapping and N-staging of thoracic lymph nodes in contrast-enhanced CT scans of the chest using a fully convolutional neural network. Eur J Radiol. 2021;139:109718. doi: 10.1016/j.ejrad.2021.109718
  23. Zhong Y, Yuan M, Zhang T, et al. Radiomics approach to prediction of occult medi astinal lymph node metastasis of lung adenocarcinoma. AJR Am J Roentgenol. 2018;211(1):109–113. doi: 10.2214/AJR.17.19074
  24. Liu Y, Kim J, Balagurunathan Y, et al. Prediction of pathological nodal involvement by CT-based Radiomic features of the primary tumor in patients with clinically node negative pe ripheral lung adenocarcinomas. Med Phys. 2018;45(6):2518–2526. doi: 10.1002/mp.12901
  25. Cong M, Yao H, Liu H, et al. Development and evaluation of a venous computed to mography radiomics model to predict lymph node metastasis from non small cell lung cancer. Medicine (Baltimore). 2020;99(18):e20074. doi: 10.1097/MD.0000000000020074
  26. Gu P, Zhao YZ, Jiang LY, et al. Endobronchial ultrasound guided transbronchial nee dle aspiration for staging of lung cancer: a systematic review and meta analysis. Eur J Cancer. 2009;45(8):1389–1396. doi: 10.1016/j.ejca.2008.11.043
  27. Brown G, Richards CJ, Bourne MW, et al. Morphologic predictors of lymph node sta tus in rectal cancer with use of high spatial resolution MR imaging with histopathologic comparison. Radiology. 2003;227(2):371–377. doi: 10.1148/radiol.2272011747
  28. Som PM. Lymph nodes of the neck. Radiology. 1987;165(3):593–600. doi: 10.1148/radiology.165.3.3317494
  29. Curtin HD, Ishwaran H, Mancuso AA, et al. Comparison of CT and MR imaging in staging of neck metastases. Radiology. 1998;207(1):123–130. doi: 10.1148/radiology.207.1.9530307
  30. Loch FN, Asbach P, Haas M, et al. Accuracy of various criteria for lymph node stag ing in ductal adenocarcinoma of the pancreatic head by computed tomography and magnetic reso nance imaging. World J Surg Oncol. 2020;18(1):213. doi: 10.1186/s12957-020-01951-3
  31. Elsholtz FH, Asbach P, Haas M, et al. Introducing the node reporting and data system 1.0 (Node-RADS): a concept for standardized assessment of lymph nodes in cancer Eur Radiol. 2021;31(8):7217. Eur Radiol. 2021;31(9):6116–6124. doi: 10.1007/s00330-020-07572-4 Сorrected and republished from: Eur Radiol. 2021;31(9): 7217. doi: 10.1007/s00330-021-07795-z
  32. Ceylan N, Doğan S, Kocaçelebi K, et al. Contrast enhanced CT versus integrated PET-CT in pre-operative nodal staging of non-small cell lung cancer. Diagn Interv Radiol. 2012;18(5):435–440. doi: 10.4261/1305-3825.DIR.5100-11.2
  33. Kamnitsas K, Ledig C, Newcombe VF, et al. Efficient multi-scale 3D CNN with fully connected CRF for accurate brain lesion segmentation. Med Image Anal. 2017;36:61–78. doi: 10.1016/j.media.2016.10.004
  34. Çiçek Ö, Abdulkadir A, Lienkamp SS, et al. 3D U-net: learning dense volumetric segmentation from sparse annotation. In: Medical Image Computing and Computer Assisted Inter vention (MICCAI 2016), Part II: 19th International Conference; 2016 October 17–21; Athens. P. 424–432.
  35. Milletari F, Navab N, Ahmadi SA. V-net: fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth international conference on 3D vision (3DV): proceedings article. 2016 October 25–28; California. P. 565–571. doi: 10.1109/3DV.2016.79
  36. Van Ginneken B, Armato SG, de Hoop B, et al. Comparing and combining algorithms for computer aided detection of pulmonary nodules in computed tomography scans: the ANODE09 study. Med Image Anal. 2010;14(6):707–722. doi: 10.1016/j.media.2010.05.005
  37. Bakas S, Reyes M, Jakab A, et al. Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge. The international multimodal brain tumor segmentation (BraTS) challenge. 2018. doi: 10.48550/arXiv.1811.02629
  38. Silva F, Pereira T, Frade J, et al. Pre training autoencoder for lung nodule malignancy assessment using CT images. Applied Sciences. 2020;10(21):7837. doi: 10.3390/app10217837
  39. Dubost F, Adams H, Yilmaz P, et al. Weakly supervised object detection with 2D and 3D regression neural networks. Med Image Anal. 2020;65:101767. doi: 10.1016/j.media.2020.101767
  40. Rusch VW, Asamura H, Watanabe H, et al. The IASLC lung cancer staging project: a proposal for a new international lymph node map in the forthcoming seventh edition of the TNM classification for lung cancer. J Thorac Oncol. 2009;4(5):568–577. doi: 10.1097/JTO.0b013e3181a0d82e
  41. Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer Assisted Intervention (MICCAI 2015): 18th International Conference; 2015 May; Munich; Р. 234–241. doi: 10.48550/arXiv.1505.04597
  42. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2016 June 27–30; Las Vegas. P. 770–778. doi: 10.48550/arXiv.1512.03385
  43. Ioffe S, Szegedy Ch. Batch normalization: accelerating deep network training by reducing internal covariate shift. ArXiv. 2015;1. doi: 10.48550/arXiv.1502.03167
  44. Nair V, Hinton GE. Rectified linear units improve restricted boltzmann machines. In: Conference: proceedings of the 27th International Conference on Machine Learning (ICML-10); 2010 June 21–24; Haifa. Available from: https://icml.cc/Conferences/2010/papers/432.pdf
  45. Nair V, Hinton GE. Rectified linear units improve restricted boltzmann machines. In: Conference: proceedings of the 27th International Conference on Machine Learning (ICML-10), June 21–24, 2010. Haifa, Israel; 2010. Р. 807–814.
  46. Roth HR, Lu L, Seff A, et al. A new 2.5D representation for lymph node detection using random sets of deep convolutional neural network observations. Med Image Comput Comput Assist Interv. 2014;17(1):520–527. doi: 10.1007/978-3-319-10404-1_65
  47. Goncharov M, Pisov M, Shevtsov A, et al. CT-based COVID-19 triage: deep multi-task learning improves joint identification and severity quantification. Med Image Anal. 2021;71:102054. doi: 10.1016/j.media.2021.102054

Arquivos suplementares

Arquivos suplementares
Ação
1. JATS XML
Baixar
2. Fig. 1. Three-stage algorithm for lymph node segmentation and metastasis classification: a, segmentation of lymph node groups; b, image coding based on the bounding box and processing using a second network; c, marking each identified lymph node, applying the respective mask, and assessment through a feedforward network. LN, lymph node.

Baixar (332KB)
Metadados
3. Fig. 2. Example of lymph node group annotation at different mediastinal levels.

Baixar (328KB)
Metadados
4. Fig. 3. Example of assigning the assessed statistical parameters to different connected components of the sample mask (a) and the respective logit mask (b); self-logit and hit-logit, personal statistics for each connected component; hit-dice, shared parameters for a pair of connected components with a positive value (с).

Baixar (148KB)
Metadados
5. Fig. 4. Accuracy of assigning lymph nodes to groups in accordance with the International Association for the Study of Lung Cancer (IASLC) guidelines.

Baixar (133KB)
Metadados
6. Fig. 5. Detection results during lymph node segmentation. FP, false positive; d, short axis diameter.

Baixar (97KB)
Metadados
7. Fig. 6. Comparison of baseline criteria derived from the short axis diameter for predicting patient status regarding the degree of regional lymph node involvement and the proposed algorithm. TPR, true positive rate; FPR, false posi-tive rate; SAD, short axis diameter.

Baixar (64KB)
Metadados
8. Fig. 7. Lymph nodes with the highest probability of metastasis for each patient. N0, no metastasis; N+, metastasis.

Baixar (232KB)
Metadados

Declaração de direitos autorais © Eco-Vector, 2024

Creative Commons License
Este artigo é disponível sob a Licença Creative Commons Atribuição–NãoComercial–SemDerivações 4.0 Internacional.

Согласие на обработку персональных данных с помощью сервиса «Яндекс.Метрика»

1. Я (далее – «Пользователь» или «Субъект персональных данных»), осуществляя использование сайта https://journals.rcsi.science/ (далее – «Сайт»), подтверждая свою полную дееспособность даю согласие на обработку персональных данных с использованием средств автоматизации Оператору - федеральному государственному бюджетному учреждению «Российский центр научной информации» (РЦНИ), далее – «Оператор», расположенному по адресу: 119991, г. Москва, Ленинский просп., д.32А, со следующими условиями.

2. Категории обрабатываемых данных: файлы «cookies» (куки-файлы). Файлы «cookie» – это небольшой текстовый файл, который веб-сервер может хранить в браузере Пользователя. Данные файлы веб-сервер загружает на устройство Пользователя при посещении им Сайта. При каждом следующем посещении Пользователем Сайта «cookie» файлы отправляются на Сайт Оператора. Данные файлы позволяют Сайту распознавать устройство Пользователя. Содержимое такого файла может как относиться, так и не относиться к персональным данным, в зависимости от того, содержит ли такой файл персональные данные или содержит обезличенные технические данные.

3. Цель обработки персональных данных: анализ пользовательской активности с помощью сервиса «Яндекс.Метрика».

4. Категории субъектов персональных данных: все Пользователи Сайта, которые дали согласие на обработку файлов «cookie».

5. Способы обработки: сбор, запись, систематизация, накопление, хранение, уточнение (обновление, изменение), извлечение, использование, передача (доступ, предоставление), блокирование, удаление, уничтожение персональных данных.

6. Срок обработки и хранения: до получения от Субъекта персональных данных требования о прекращении обработки/отзыва согласия.

7. Способ отзыва: заявление об отзыве в письменном виде путём его направления на адрес электронной почты Оператора: info@rcsi.science или путем письменного обращения по юридическому адресу: 119991, г. Москва, Ленинский просп., д.32А

8. Субъект персональных данных вправе запретить своему оборудованию прием этих данных или ограничить прием этих данных. При отказе от получения таких данных или при ограничении приема данных некоторые функции Сайта могут работать некорректно. Субъект персональных данных обязуется сам настроить свое оборудование таким способом, чтобы оно обеспечивало адекватный его желаниям режим работы и уровень защиты данных файлов «cookie», Оператор не предоставляет технологических и правовых консультаций на темы подобного характера.

9. Порядок уничтожения персональных данных при достижении цели их обработки или при наступлении иных законных оснований определяется Оператором в соответствии с законодательством Российской Федерации.

10. Я согласен/согласна квалифицировать в качестве своей простой электронной подписи под настоящим Согласием и под Политикой обработки персональных данных выполнение мною следующего действия на сайте: https://journals.rcsi.science/ нажатие мною на интерфейсе с текстом: «Сайт использует сервис «Яндекс.Метрика» (который использует файлы «cookie») на элемент с текстом «Принять и продолжить».