Deep-Learning Assessed Muscular Hypodensity Independently Predicts Mortality in DLBCL Patients Younger Than 60 Years

Maxime Jullien, Benoit Tessoulin, Hervé Ghesquières, Lucie Oberic, Franck Morschhauser, Hervé Tilly, Vincent Ribrag, Thierry Lamy, Catherine Thieblemont, Bruno Villemagne, Rémy Gressin, Kamal Bouabdallah, Corinne Haioun, Gandhi Damaj, Luc-Matthieu Fornecker, Jean-Marc Schiano De Colella, Pierre Feugier, Olivier Hermine, Guillaume Cartron, Christophe Bonnet, Marc André, Clément Bailly, René-Olivier Casasnovas, Steven Le Gouill, Maxime Jullien, Benoit Tessoulin, Hervé Ghesquières, Lucie Oberic, Franck Morschhauser, Hervé Tilly, Vincent Ribrag, Thierry Lamy, Catherine Thieblemont, Bruno Villemagne, Rémy Gressin, Kamal Bouabdallah, Corinne Haioun, Gandhi Damaj, Luc-Matthieu Fornecker, Jean-Marc Schiano De Colella, Pierre Feugier, Olivier Hermine, Guillaume Cartron, Christophe Bonnet, Marc André, Clément Bailly, René-Olivier Casasnovas, Steven Le Gouill

Abstract

Background: Muscle depletion (MD) assessed by computed tomography (CT) has been shown to be a predictive marker in solid tumors, but has not been assessed in non-Hodgkin's lymphomas. Despite software improvements, MD measurement remains highly time-consuming and cannot be used in clinical practice.

Methods: This study reports the development of a Deep-Learning automatic segmentation algorithm (DLASA) to measure MD, and investigate its predictive value in a cohort of 656 diffuse large B cell lymphoma (DLBCL) patients included in the GAINED phase III prospective trial (NCT01659099).

Results: After training on a series of 190 patients, the DLASA achieved a Dice coefficient of 0.97 ± 0.03. In the cohort, the median skeletal muscle index was 50.2 cm2/m2 and median muscle attenuation (MA) was 36.1 Hounsfield units (HU). No impact of sarcopenia was found on either progression free survival (PFS) or overall survival (OS). Muscular hypodensity, defined as MA below the tenth percentile according to sex, was associated with a lower OS and PFS, respectively (HR = 2.80 (95% CI 1.58-4.95), p < 0.001, and HR = 2.22 (95% CI 1.43-3.45), p < 0.001). Muscular hypodensity appears to be an independent risk factor for mortality in DLBCL and because of DLASA can be estimated in routine practice.

Keywords: U-NET; convolutional neural network; diffuse large B-cell lymphoma; muscle depletion; muscle hypodensity; sarcopenia.

Conflict of interest statement

HG reports grants, personal fees or non-financial support from Gilead Sciences, Janssen, Celgene, Roche, Takeda; LO, Advisory board: Roche, Takeda; honoraria: Celgene, Janssen, Roche; FM has received honoraria from Bristol-Myers Squibb and Janssen and served as a consultant or advisor to Celgene, Bayer, Abbvie, Verasteem, Gilead, Servier, Roche/Genentech, and Epizyme; HT, Consulting and advisory board: Roche, Janssen-Cilag, Karyopharm, Astra-Zeneca, Lectures: Roche, Bristol-Myers-Squibb, Servier; VR Infinity Pharmaceuticals, Bristol-Myers Squibb, PharmaMar, Gilead Sciences, AZD, Epizyme, Incyte, MSD, Servier, Roche, arGEN-X BVBA; CT Honoraria: Amgen, Celgene, Jazz Pharma, Kyte/Gilead, Novartis, Servier, Roche, Janssen; Research funding: Roche, Celgene, Aspira; CH Honoraria: Roche, Janssen-Cilag, Gilead, Takeda, Miltenyi and Servier; Travel grants: Amgen and Celgene; GD Board: Roche, takeda; Travel: Roche AbbVie Pfizer, Grants: takeda, roche; LF Honoraria: Roche, AstraZeneca, Servier, Takeda, Abbvie, Janssen; Advisory boards: Takeda, Roche, Gilead, AbbVie, Janssen-Cilag; Travel grants: La Roche, Gilead, Abbvie and Janssen-Cilag; PF Roche Genentech, celgene, Abbvie, Janssen and gilead; OH, Celgene research grant, Alexion research grant, Ab science co-founder research grant consulting, Inatherys co-founder research grants; GC has received honoraria from Janssen, Sanofi, Abbvie, Gilead, Roche, Celgene, Novartis, Takeda and served as a consultant or Celgene, Roche/Genentech; CB is board member for Roche; MA: Advisory Board: Takeda, Bristol-Myers-Squibb, Karyopharm, Gilead, Incyte, Research Grants: Roche, Johnson & Johnson, Takeda, Travel Grants: Roche, Bristol-Myers-Squib, Celgene, Gilead, Abbvie; ROC reports grants, personal fees and non-financial support from Roche Genentech, during the conduct of the study; reports personal fees from MSD, BMS, Abbvie, Amgen, Celgene, reports grants and personal fees from Takeda, GILEAD/kite, outside the submitted work; SLG reports grants, personal fees or non-financial support from Roche Genentech, during the conduct of the study; reports personal fees from Celgene, reports grants and personal fees from Janssen-Cilag; GILEAD/kite, Servier outside the submitted work. All other authors declare no competing interests (M.J., B.T., T.L., B.V., R.G., K.B., J.-M.S.D.C.).

Figures

Figure 1
Figure 1
(A) Correlation between manual segmentation and DLASA segmentation. (B) Visual rendering of manual (ground truth) and automated (DLASA) segmentation. DLASA: Deep Learning automated segmentation algorithm. SAT: subcutaneous adipose tissue (blue). VAT: visceral adipose tissue (yellow). Muscle region of interest (red).
Figure 2
Figure 2
OS and PFS according to muscle hypodensity (A) and obesity (B). OS: overall survival. PFS: progression-free survival.

References

    1. Tisdale M.J. Cachexia in cancer patients. Nat. Rev. Cancer. 2002;2:862–871. doi: 10.1038/nrc927.
    1. Dewys W.D., Begg C., Lavin P.T., Band P.R., Bennett J.M., Bertino J.R., Cohen M.H., Douglass H.O., Engstrom P.F., Ezdinli E.Z., et al. Prognostic effect of weight loss prior to chemotherapy in cancer patients. Eastern Cooperative Oncology Group. Am. J. Med. 1980;69:491–497. doi: 10.1016/S0149-2918(05)80001-3.
    1. Fearon K., Strasser F., Anker S.D., Bosaeus I., Bruera E., Fainsinger R.L., Jatoi A., Loprinzi C., MacDonald N., Mantovani G., et al. Definition and classification of cancer cachexia: An international consensus. Lancet Oncol. 2011;12:489–495. doi: 10.1016/S1470-2045(10)70218-7.
    1. Prado C.M.M., Birdsell L.A., Baracos V.E. The emerging role of computerized tomography in assessing cancer cachexia. Curr. Opin. Support. Palliat. Care. 2009;3:269–275. doi: 10.1097/SPC.0b013e328331124a.
    1. Mourtzakis M., Prado C.M.M., Lieffers J.R., Reiman T., McCargar L.J., Baracos V.E. A practical and precise approach to quantification of body composition in cancer patients using computed tomography images acquired during routine care. Appl. Physiol. Nutr. Metab. 2008;33:997–1006. doi: 10.1139/H08-075.
    1. Aubrey J., Esfandiari N., Baracos V.E., Buteau F.A., Frenette J., Putman C.T., Mazurak V.C. Measurement of skeletal muscle radiation attenuation and basis of its biological variation. Acta Physiol. Oxf. Engl. 2014;210:489–497. doi: 10.1111/apha.12224.
    1. van Vugt J.L.A., Levolger S., Gharbharan A., Koek M., Niessen W.J., Burger J.W.A., Willemsen S.P., de Bruin R.W.F., IJzermans J.N.M. A comparative study of software programmes for cross-sectional skeletal muscle and adipose tissue measurements on abdominal computed tomography scans of rectal cancer patients. J. Cachexia Sarcopenia Muscle. 2017;8:285–297. doi: 10.1002/jcsm.12158.
    1. LeCun Y., Bengio Y., Hinton G. Deep learning. Nature. 2015;521:436–444. doi: 10.1038/nature14539.
    1. Ronneberger O., Fischer P., Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Lect. Notes Comput. Sci. 2015;9351:234–241.
    1. Guo Z., Guo N., Gong K., Zhong S., Li Q. Gross tumor volume segmentation for head and neck cancer radiotherapy using deep dense multi-modality network. Phys. Med. Biol. 2019;64:205015. doi: 10.1088/1361-6560/ab440d.
    1. Li J., Sarma K.V., Ho K.C., Gertych A., Knudsen B.S., Arnold C.W. A Multi-scale U-Net for Semantic Segmentation of Histological Images from Radical Prostatectomies. AMIA Annu. Symp. Proc. 2017;2017:1140–1148.
    1. Norman B., Pedoia V., Majumdar S. Use of 2D U-Net Convolutional Neural Networks for Automated Cartilage and Meniscus Segmentation of Knee MR Imaging Data to Determine Relaxometry and Morphometry. Radiology. 2018;288:177–185. doi: 10.1148/radiol.2018172322.
    1. Blanc-Durand P., Jégou S., Kanoun S., Berriolo-Riedinger A., Bodet-Milin C., Kraeber-Bodéré F., Carlier T., Le Gouill S., Casasnovas R.-O., Meignan M., et al. Fully automatic segmentation of diffuse large B cell lymphoma lesions on 3D FDG-PET/CT for total metabolic tumour volume prediction using a convolutional neural network. Eur. J. Nucl. Med. Mol. Imaging. 2020;48:1362–1370. doi: 10.1007/s00259-020-05080-7.
    1. Burns J.E., Yao J., Chalhoub D., Chen J.J., Summers R.M. A Machine Learning Algorithm to Estimate Sarcopenia on Abdominal CT. Acad. Radiol. 2020;27:311–320. doi: 10.1016/j.acra.2019.03.011.
    1. Dabiri S., Popuri K., Cespedes Feliciano E.M., Caan B.J., Baracos V.E., Beg M.F. Muscle segmentation in axial computed tomography (CT) images at the lumbar (L3) and thoracic (T4) levels for body composition analysis. Comput. Med. Imaging Graph. 2019;75:47–55. doi: 10.1016/j.compmedimag.2019.04.007.
    1. Edwards K., Chhabra A., Dormer J., Jones P., Boutin R.D., Lenchik L., Fei B. Abdominal muscle segmentation from CT using a convolutional neural network. Proc. SPIE Int. Soc. Opt. Eng. 2020;11317:113170L.
    1. Lee H., Troschel F.M., Tajmir S., Fuchs G., Mario J., Fintelmann F.J., Do S. Pixel-Level Deep Segmentation: Artificial Intelligence Quantifies Muscle on Computed Tomography for Body Morphometric Analysis. J. Digit. Imaging. 2017;30:487–498. doi: 10.1007/s10278-017-9988-z.
    1. Lee J.S., Kim Y.S., Kim E.Y., Jin W. Prognostic significance of CT-determined sarcopenia in patients with advanced gastric cancer. PLoS ONE. 2018;13:e0202700. doi: 10.1371/journal.pone.0202700.
    1. Cho Y., Kim J.W., Keum K.C., Lee C.G., Jeung H.C., Lee I.J. Prognostic Significance of Sarcopenia With Inflammation in Patients With Head and Neck Cancer Who Underwent Definitive Chemoradiotherapy. Front. Oncol. 2018;8:457. doi: 10.3389/fonc.2018.00457.
    1. Kim E.Y., Lee H.Y., Kim Y.S., Park I., Ahn H.K., Cho E.K., Jeong Y.M., Kim J.H. Prognostic significance of cachexia score assessed by CT in male patients with small cell lung cancer. Eur. J. Cancer Care. 2018;27:e12695. doi: 10.1111/ecc.12695.
    1. Daly L.E., Power D.G., O’Reilly Á., Donnellan P., Cushen S.J., O’Sullivan K., Twomey M., Woodlock D.P., Redmond H.P., Ryan A.M. The impact of body composition parameters on ipilimumab toxicity and survival in patients with metastatic melanoma. Br. J. Cancer. 2017;116:310–317. doi: 10.1038/bjc.2016.431.
    1. Martin L., Birdsell L., Macdonald N., Reiman T., Clandinin M.T., McCargar L.J., Murphy R., Ghosh S., Sawyer M.B., Baracos V.E. Cancer cachexia in the age of obesity: Skeletal muscle depletion is a powerful prognostic factor, independent of body mass index. J. Clin. Oncol. 2013;31:1539–1547. doi: 10.1200/JCO.2012.45.2722.
    1. Lanic H., Kraut-Tauzia J., Modzelewski R., Clatot F., Mareschal S., Picquenot J.M., Stamatoullas A., Leprêtre S., Tilly H., Jardin F. Sarcopenia is an independent prognostic factor in elderly patients with diffuse large B-cell lymphoma treated with immunochemotherapy. Leuk. Lymphoma. 2014;55:817–823. doi: 10.3109/10428194.2013.816421.
    1. Jabbour J., Manana B., Zahreddine A., Saade C., Charafeddine M., Bazarbachi A., Blaise D., El-Cheikh J. Sarcopenic obesity derived from PET/CT predicts mortality in lymphoma patients undergoing hematopoietic stem cell transplantation. Curr. Res. Transl. Med. 2019;67:93–99. doi: 10.1016/j.retram.2018.12.001.
    1. Chu M.P., Lieffers J., Ghosh S., Belch A., Chua N.S., Fontaine A., Sangha R., Turner R.A., Baracos V.E., Sawyer M.B. Skeletal muscle density is an independent predictor of diffuse large B-cell lymphoma outcomes treated with rituximab-based chemoimmunotherapy. J. Cachexia Sarcopenia Muscle. 2017;8:298–304. doi: 10.1002/jcsm.12161.
    1. Le Gouill S., Ghesquieres H., Obéric L., Morschhauser F., Tilly H., Ribrag V., Lamy T., Thieblemont C., Maisonneuve H., Gressin R., et al. Obinutuzumab versus Rituximab in young patients with advanced DLBCL, a PET-guided and randomized phase 3 study by LYSA. Blood. 2020;137:2307–2320. doi: 10.1182/blood.2020008750.
    1. Le Gouill S., Thieblemont C., Oberic L., Moreau A., Bouabdallah K., Dartigeas C., Damaj G., Gastinne T., Ribrag V., Feugier P., et al. Rituximab after Autologous Stem-Cell Transplantation in Mantle-Cell Lymphoma. N. Engl. J. Med. 2017;377:1250–1260. doi: 10.1056/NEJMoa1701769.
    1. Dice L.R. Measures of the Amount of Ecologic Association Between Species. Ecology. 1945;26:297–302. doi: 10.2307/1932409.
    1. Cheson B.D., Pfistner B., Juweid M.E., Gascoyne R.D., Specht L., Horning S.J., Coiffier B., Fisher R.I., Hagenbeek A., Zucca E., et al. Revised response criteria for malignant lymphoma. J. Clin. Oncol. 2007;25:579–586. doi: 10.1200/JCO.2006.09.2403.
    1. Belharbi S., Chatelain C., Hérault R., Adam S., Thureau S., Chastan M., Modzelewski R. Spotting L3 slice in CT scans using deep convolutional network and transfer learning. Comput. Biol. Med. 2017;87:95–103. doi: 10.1016/j.compbiomed.2017.05.018.
    1. Morsbach F., Zhang Y.-H., Martin L., Lindqvist C., Brismar T. Body composition evaluation with computed tomography: Contrast media and slice thickness cause methodological errors. Nutrition. 2019;59:50–55. doi: 10.1016/j.nut.2018.08.001.
    1. Fuchs G., Chretien Y.R., Mario J., Do S., Eikermann M., Liu B., Yang K., Fintelmann F.J. Quantifying the effect of slice thickness, intravenous contrast and tube current on muscle segmentation: Implications for body composition analysis. Eur. Radiol. 2018;28:2455–2463. doi: 10.1007/s00330-017-5191-3.
    1. Sabel M.S., Lee J., Cai S., Englesbe M.J., Holcombe S., Wang S. Sarcopenia as a prognostic factor among patients with stage III melanoma. Ann. Surg. Oncol. 2011;18:3579–3585. doi: 10.1245/s10434-011-1976-9.
    1. Antoun S., Lanoy E., Iacovelli R., Albiges-Sauvin L., Loriot Y., Merad-Taoufik M., Fizazi K., di Palma M., Baracos V.E., Escudier B. Skeletal muscle density predicts prognosis in patients with metastatic renal cell carcinoma treated with targeted therapies. Cancer. 2013;119:3377–3384. doi: 10.1002/cncr.28218.

Source: PubMed

Patrocinadores e Colaboradores

Condições médicas

Intervenções de drogas

3
Se inscrever