研究生: |
羅仕昌 SHIH-CHANG LO |
---|---|
論文名稱: |
Deep Learning for Prediction of Treatment effectiveness on Ovarian Cancer from histopathology images Deep Learning for Prediction of Treatment effectiveness on Ovarian Cancer from histopathology images |
指導教授: |
王靖維
Ching-Wei Wang |
口試委員: |
趙載光
Tai-Kuang Chao 白孟宜 Meng-Yi Bai 許維君 Wei-Chun Hsu |
學位類別: |
碩士 Master |
系所名稱: |
應用科技學院 - 醫學工程研究所 Graduate Institute of Biomedical Engineering |
論文出版年: | 2020 |
畢業學年度: | 108 |
語文別: | 英文 |
論文頁數: | 49 |
中文關鍵詞: | Epithelial ovarian cancer 、Treatment effectiveness prediction 、Hybrid deep learning classification framework 、Cascaded deep learning based segmentation framework 、Bevacizumab 、Whole-slide image analysis |
外文關鍵詞: | Epithelial ovarian cancer, Treatment effectiveness prediction, Hybrid deep learning classification framework, Cascaded deep learning based segmentation framework, Bevacizumab, Whole-slide image analysis |
相關次數: | 點閱:190 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
Despite the progress made during the last two decades in the surgery and chemotherapy of ovarian cancer, more than 70% of advanced patients are with recurrent cancer and decease. Surgical debulking of tumors following chemotherapy is the conventional treatment for advanced carcinoma, but patients with such treatment remain at great risk for recurrence and developing drug resistance, and only about 30% of the women affected will be cured. New therapies with molecular-targeted agents have become available. Bevacizumab is a humanized monoclonal antibody targeting VEGF that promotes tumor growth and angiogenesis and has been recently approved by the FDA as a monotherapy for advanced ovarian cancer in combination with chemotherapy. Prediction of treatment effectiveness and individualized therapeutic strategies are critical for therapeutic proteins, but to the authors’ best knowledge, there is no effective biomarker for prediction of patient response to bevacizumab. Here we have built three deep learning based approaches to accurately predict therapeutic effect for bevacizumab of ovarian cancer patients from histopathological whole slide images, without any pathologist¬provided locally annotated regions. Quantitative evaluation shows that the second and third models achieve the area under curve (AUC) and recall (0.988, 0.958) and (0.958, 1), respectively. This findings suggest that deep learning models could assist treatment planning for personalized medicines and potentially be used in drug development.
Despite the progress made during the last two decades in the surgery and chemotherapy of ovarian cancer, more than 70% of advanced patients are with recurrent cancer and decease. Surgical debulking of tumors following chemotherapy is the conventional treatment for advanced carcinoma, but patients with such treatment remain at great risk for recurrence and developing drug resistance, and only about 30% of the women affected will be cured. New therapies with molecular-targeted agents have become available. Bevacizumab is a humanized monoclonal antibody targeting VEGF that promotes tumor growth and angiogenesis and has been recently approved by the FDA as a monotherapy for advanced ovarian cancer in combination with chemotherapy. Prediction of treatment effectiveness and individualized therapeutic strategies are critical for therapeutic proteins, but to the authors’ best knowledge, there is no effective biomarker for prediction of patient response to bevacizumab. Here we have built three deep learning based approaches to accurately predict therapeutic effect for bevacizumab of ovarian cancer patients from histopathological whole slide images, without any pathologist¬provided locally annotated regions. Quantitative evaluation shows that the second and third models achieve the area under curve (AUC) and recall (0.988, 0.958) and (0.958, 1), respectively. This findings suggest that deep learning models could assist treatment planning for personalized medicines and potentially be used in drug development.
[1]S. Lheureux, M. Braunstein, and A. M. Oza, “Epithelial ovarian cancer: Evolution ofmanagement in the era of precision medicine,”CA:ACancerJournalforClinicians,May 2019.
[2]A. Jemal, R. Siegel, E. Ward, Y. Hao, J. Xu, T. Murray, and M. J. Thun, “CancerStatistics, 2008,”CA:ACancerJournalforClinicians, vol. 58, pp. 71–96, Jan. 2008.
[3]C. M. Phelan, , K. B. Kuchenbaecker, J. P. Tyrer, S. P. Kar, K. Lawrenson, S. J.Winham, J. Dennis, A. Pirie, M. J. Riggan, G. Chornokur, M. A. Earp, P. C. Lyra,J. M. Lee, S. Coetzee, J. Beesley, L. McGuffog, P. Soucy, E. Dicks, A. Lee, D. Barrowdale, J. Lecarpentier, G. Leslie, C. M. Aalfs, K. K. H. Aben, M. Adams, J. Adlard, I. L. Andrulis, H. AntonCulver, N. Antonenkova, G. Aravantinos, N. Arnold,B. K. Arun, B. Arver, J. Azzollini, J. Balmaña, S. N. Banerjee, L. Barjhoux, R. B.Barkardottir, Y. Bean, M. W. Beckmann, A. BeeghlyFadiel, J. Benitez, M. Bermisheva, M. Q. Bernardini, M. J. Birrer, L. Bjorge, A. Black, K. Blankstein, M. J.Blok, C. Bodelon, N. Bogdanova, A. Bojesen, B. Bonanni, Å. Borg, A. R. Bradbury,J. D. Brenton, C. Brewer, L. Brinton, P. Broberg, A. BrooksWilson, F. Bruinsma,J. Brunet, B. Buecher, R. Butzow, S. S. Buys, T. Caldes, M. A. Caligo, I. Campbell,R. Cannioto, M. E. Carney, T. Cescon, S. B. Chan, J. ChangClaude, S. Chanock,X. Q. Chen, Y.E. Chiew, J. Chiquette, W. K. Chung, K. B. M. Claes, T. Conner,L. S. Cook, J. Cook, D. W. Cramer, J. M. Cunningham, A. A. D'Aloisio, M. B.Daly, F. Damiola, S. D. Damirovna, A. DansonkaMieszkowska, F. Dao, R. Davidson, A. DeFazio, C. Delnatte, K. F. Doheny, O. Diez, Y. C. Ding, J. A. Doherty,S. M. Domchek, C. M. Dorfling, T. Dörk, L. Dossus, M. Duran, M. Dürst, B. Dworniczak, D. Eccles, T. Edwards, R. Eeles, U. Eilber, B. Ejlertsen, A. B. Ekici, S. Ellis,M. Elvira, K. H. Eng, C. Engel, D. G. Evans, P. A. Fasching, S. Ferguson, S. F.Ferrer, J. M. Flanagan, Z. C. Fogarty, R. T. Fortner, F. Fostira, W. D. Foulkes,G. Fountzilas, B. L. Fridley, T. M. Friebel, E. Friedman, D. Frost, P. A. Ganz,J. Garber, M. J. García, V. GarciaBarberan, A. Gehrig, A. GentryMaharaj, A.M. Gerdes, G. G. Giles, R. Glasspool, G. Glendon, A. K. Godwin, D. E. Goldgar,T. Goranova, M. Gore, M. H. Greene, J. Gronwald, S. Gruber, E. Hahnen, C. A.Haiman, N. Håkansson, U. Hamann, T. V. O. Hansen, P. A. Harrington, H. R. Harris, J. Hauke, A. Hein, A. Henderson, M. A. T. Hildebrandt, P. Hillemanns, S. Hodgson,C. K. Høgdall, E. Høgdall, F. B. L. Hogervorst, H. Holland, M. J. Hooning, K. Hosking, R.Y. Huang, P. J. Hulick, J. Hung, D. J. Hunter, D. G. Huntsman, T. Huzarski,E. N. Imyanitov, C. Isaacs, E. S. Iversen, L. Izatt, A. Izquierdo, A. Jakubowska,P. James, R. Janavicius, M. Jernetz, A. Jensen, U. B. Jensen, E. M. John, S. Johnatty,M. E. Jones, P. Kannisto, B. Y. Karlan, A. Karnezis, K. Kast, C. J. Kennedy, E. Khusnutdinova, L. A. Kiemeney, J. I. Kiiski, S.W. Kim, S. K. Kjaer, M. Köbel, R. K.Kopperud, T. A. Kruse, J. Kupryjanczyk, A. Kwong, Y. Laitman, D. Lambrechts,N. Larrañaga, M. C. Larson, C. Lazaro, N. D. Le, L. L. Marchand, J. W. Lee,S. B. Lele, A. Leminen, D. Leroux, J. Lester, F. Lesueur, D. A. Levine, D. Liang,C. Liebrich, J. Lilyquist, L. Lipworth, J. Lissowska, K. H. Lu, J. Lubinński, C. Luccarini, L. Lundvall, P. L. Mai, G. MendozaFandiño, S. Manoukian, L. F. A. G. Massuger, T. May, S. Mazoyer, J. N. McAlpine, V. McGuire, J. R. McLaughlin, I. McNeish, H. MeijersHeijboer, A. Meindl, U. Menon, A. R. Mensenkamp, M. A. Merritt, R. L. Milne, G. Mitchell, F. Modugno, J. MoesSosnowska, M. Moffitt, M. Montagna, K. B. Moysich, A. M. Mulligan, J. Musinsky, K. L. Nathanson, L. Nedergaard, R. B. Ness, S. L. Neuhausen, H. Nevanlinna, D. Niederacher, R. L. Nussbaum, K. Odunsi, E. Olah, O. I. Olopade, H. Olsson, C. Olswold, D. M. O'Malley,K. ren Ong, N. C. OnlandMoret, N. Orr, S. Orsulic, A. Osorio, D. Palli, L. Papi,T.W. ParkSimon, J. Paul, C. L. Pearce, I. S. Pedersen, P. H. M. Peeters, B. Peissel, A. Peixoto, T. Pejovic, L. M. Pelttari, J. B. Permuth, P. Peterlongo, L. Pezzani,G. Pfeiler, K.A. Phillips, M. Piedmonte, M. C. Pike, A. M. Piskorz, S. R. Poblete,T. Pocza, E. M. Poole, B. Poppe, M. E. Porteous, F. Prieur, D. Prokofyeva, E. Pugh,M. A. Pujana, P. Pujol, P. Radice, J. Rantala, C. RappaportFuerhauser, G. Rennert, K. Rhiem, P. Rice, A. Richardson, M. Robson, G. C. Rodriguez, C. RodríguezAntona, J. Romm, M. A. Rookus, M. A. Rossing, J. H. Rothstein, A. Rudolph, I. B.Runnebaum, H. B. Salvesen, D. P. Sandler, M. J. Schoemaker, L. Senter, V. W. Setiawan, G. Severi, P. Sharma, T. Shelford, N. Siddiqui, L. E. Side, W. Sieh, C. F.Singer, H. Sobol, H. Song, M. C. Southey, A. B. Spurdle, Z. Stadler, D. Steinemann,D. StoppaLyonnet, L. E. SuchestonCampbell, G. Sukiennicki, R. Sutphen, C. Sutter, A. J. Swerdlow, C. I. Szabo, L. Szafron, Y. Y. Tan, J. A. Taylor, M.K. Tea,M. R. Teixeira, S.H. Teo, K. L. Terry, P. J. Thompson, L. C. V. Thomsen, D. L.Thull, L. Tihomirova, A. V. Tinker, M. Tischkowitz, S. Tognazzo, A. E. Toland,A. Tone, B. Trabert, R. C. Travis, A. Trichopoulou, N. Tung, S. S. Tworoger, A. M. van Altena, D. V. D. Berg, A. H. van der Hout, R. B. van der Luijt, M. V. Heetvelde,E. V. Nieuwenhuysen, E. J. van Rensburg, A. Vanderstichele, R. VaronMateeva,A. Vega, D. V. Edwards, I. Vergote, R. A. Vierkant, J. Vijai, A. Vratimos, L. Walker,C. Walsh, D. Wand, S. WangGohrke, B. Wappenschmidt, P. M. Webb, C. R. Weinberg, J. N. Weitzel, N. Wentzensen, A. S. Whittemore, J. T. Wijnen, L. R. Wilkens,A. Wolk, M. Woo, X. Wu, A. H. Wu, H. Yang, D. Yannoukakos, A. Ziogas, K. K.Zorn, S. A. Narod, D. F. Easton, C. I. Amos, J. M. Schildkraut, S. J. Ramus, L. Ottini,M. T. Goodman, S. K. Park, L. E. Kelemen, H. A. Risch, M. Thomassen, K. Offit,J. Simard, R. K. Schmutzler, D. Hazelett, A. N. Monteiro, F. J. Couch, A. Berchuck,G. ChenevixTrench, E. L. Goode, T. A. Sellers, S. A. Gayther, A. C. Antoniou,P. D. P. Pharoah, , , , and and, “Identification of 12 new susceptibility loci for different histotypes of epithelial ovarian cancer,”Nature Genetics, vol. 49, pp. 680–691,Mar. 2017.
[4]CANCER REGISTRY ANNUAL REPORT, 2017,TAIWAN. HEALTH PROMOTIONADMINISTRATION, MINISTRY OF HEALTH AND WELFARE, TAIWAN, 2019.Online; accessed 15July2020.
[5]R. L. Coleman, B. J. Monk, A. K. Sood, and T. J. Herzog, “Latest research and treatment of advancedstage epithelial ovarian cancer,”Nature Reviews Clinical Oncology, vol. 10, pp. 211–224, Feb. 2013.
[6]W. Graybill, A. K. Sood, B. J. Monk, and R. L. Coleman, “State of the science:Emerging therapeutic strategies for targeting angiogenesis in ovarian cancer,”Gynecologic Oncology, vol. 138, pp. 223–226, Aug. 2015.
[7]R. A. Burger, M. F. Brady, M. A. Bookman, G. F. Fleming, B. J. Monk, H. Huang,R. S. Mannel, H. D. Homesley, J. Fowler, B. E. Greer, M. Boente, M. J. Birrer, andS. X. Liang, “Incorporation of Bevacizumab in the Primary Treatment of OvarianCancer,”New England Journal of Medicine, vol. 365, pp. 2473–2483, Dec. 2011.
[8]G. Long and C. Llop,The Biopharmaceutical Pipeline: Innovative Therapies inClinical Development. Boston, MA: The Analysis Group, July 2017. Online; accessed 15July2020.
[9]J. Vamathevan, D. Clark, P. Czodrowski, I. Dunham, E. Ferran, G. Lee, B. Li,A. Madabhushi, P. Shah, M. Spitzer, and S. Zhao, “Applications of machine learning in drug discovery and development.,”Nature reviews. Drug discovery, vol. 18,pp. 463–477, June 2019.
[10]Z. Zhang, P. Chen, M. McGough, F. Xing, C. Wang, M. Bui, Y. Xie, M. Sapkota,L. Cui, J. Dhillon, N. Ahmad, F. K. Khalil, S. I. Dickinson, X. Shi, F. Liu, H. Su,J. Cai, and L. Yang, “Pathologistlevel interpretable wholeslide cancer diagnosiswith deep learning,”Nature Machine Intelligence, vol. 1, pp. 236–245, May 2019.
[11]A. CruzRoa, H. Gilmore, A. Basavanhally, M. Feldman, S. Ganesan, N. N. Shih,J. Tomaszewski, F. A. González, and A. Madabhushi, “Accurate and reproducibleinvasive breast cancer detection in wholeslide images: A Deep Learning approachfor quantifying tumor extent,”Scientific Reports, vol. 7, Apr. 2017.
[12]K. Sirinukunwattana, S. E. A. Raza, Y.W. Tsang, D. R. J. Snead, I. A. Cree, andN.M. Rajpoot, “Locality SensitiveDeep Learning forDetection andClassification ofNuclei in Routine Colon Cancer Histology Images,”IEEE Transactions on MedicalImaging, vol. 35, pp. 1196–1206, May 2016.
[13]G. Campanella, M. G. Hanna, L. Geneslaw, A. Miraflor, V. W. K. Silva, K. J. Busam,E. Brogi, V. E. Reuter, D. S. Klimstra, and T. J. Fuchs, “Clinicalgrade computationalpathology using weakly supervised deep learning on whole slide images,”NatureMedicine, vol. 25, pp. 1301–1309, July 2019.
[14]W. Bulten, P. Bándi, J. Hoven, R. van de Loo, J. Lotz, N. Weiss, J. van der Laak,B. van Ginneken, C. H. van de Kaa, and G. Litjens, “Epithelium segmentation using deep learning in H&Estained prostate specimens with immunohistochemistryas reference standard,”Scientific Reports, vol. 9, Jan. 2019.
[15]R. Mishra, O. Daescu, P. Leavey, D. Rakheja, and A. Sengupta, “Histopathological Diagnosis for Viable and Nonviable Tumor Prediction for Osteosarcoma Using Convolutional Neural Network,” inBioinformatics Research and Applications,pp. 12–23, Springer International Publishing, May 2017.
[16]K. Bera, K. A. Schalper, D. L. Rimm, V. Velcheti, and A. Madabhushi, “Artificialintelligence in digital pathology new tools for diagnosis and precision oncology.,”Nature reviews. Clinical oncology, vol. 16, pp. 703–715, Nov. 2019.
[17]N. Coudray, P. S. Ocampo, T. Sakellaropoulos, N. Narula, M. Snuderl, D. Fenyö,A. L. Moreira, N. Razavian, and A. Tsirigos, “Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning,”NatureMedicine, vol. 24, pp. 1559–1567, Sept. 2018.
[18]B. Monk, L. Minion, and R. Coleman, “Antiangiogenic agents in ovarian cancer:past, present, and future,”Annals of Oncology, vol. 27, pp. i33–i39, Apr. 2016.
[19]S. Mabuchi, Y. Terai, K. Morishige, A. TanabeKimura, H. Sasaki, M. Kanemura,S. Tsunetoh, Y. Tanaka, M. Sakata, R. A. Burger, T. Kimura, and M. Ohmichi,“Maintenance Treatment with Bevacizumab Prolongs Survival in an In vivo OvarianCancer Model,”Clinical Cancer Research, vol. 14, pp. 7781–7789, Dec. 2008.
[20]B. J. Monk, H. Dalton, J. H. Farley, D. M. Chase, and I. Benjamin, “Antiangiogenicagents as a maintenance strategy for advanced epithelial ovarian cancer,”CriticalReviews in Oncology/Hematology, vol. 86, pp. 161–175, May 2013.
[21]A. M. Oza, A. D. Cook, J. Pfisterer, A. Embleton, J. A. Ledermann, E. PujadeLauraine, G. Kristensen, M. S. Carey, P. Beale, A. Cervantes, T.W. ParkSimon,G. Rustin, F. Joly, M. R. Mirza, M. Plante, M. Quinn, A. Poveda, G. C. Jayson,D. Stark, A. M. Swart, L. Farrelly, R. Kaplan, M. K. B. Parmar, and T. J. Perren,“Standard chemotherapy with or without bevacizumab for women with newly diagnosed ovarian cancer (ICON7): overall survival results of a phase 3 randomisedtrial,”The Lancet Oncology, vol. 16, pp. 928–936, Aug. 2015.
[22]C. Aghajanian, S. V. Blank, B. A. Goff, P. L. Judson, M. G. Teneriello, A. Husain, M. A. Sovak, J. Yi, and L. R. Nycum, “OCEANS: A Randomized, DoubleBlind, PlaceboControlled Phase III Trial of Chemotherapy With or WithoutBevacizumab in Patients With PlatinumSensitive Recurrent Epithelial Ovarian,Primary Peritoneal, or Fallopian Tube Cancer,”Journal of Clinical Oncology,vol. 30, pp. 2039–2045, June 2012.
[23]Z. Han, B. Wei, Y. Zheng, Y. Yin, K. Li, and S. Li, “Breast cancer multiclassificationfrom histopathological images with structured deep learning model,”Scientific Reports, vol. 7, June 2017.
[24]J. Chang, J. Yu, T. Han, H. jae Chang, and E. Park, “A method for classifying medicalimages using transfer learning: A pilot study on histopathology of breast cancer,” in2017IEEE19thInternationalConferenceoneHealthNetworking,ApplicationsandServices (Healthcom), IEEE, Oct. 2017.
[25]F. A. Spanhol, L. S. Oliveira, C. Petitjean, and L. Heutte, “Breast cancer histopathological image classification using convolutional neural networks,” in2016 International Joint Conference on Neural Networks (IJCNN), IEEE, July 2016.
[26]A. M. Rossetto and W. Zhou, “Deep learning for categorization of lung cancer CTimages,” in2017 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE), IEEE, July 2017.
[27]J. T. Kwak and S. M. Hewitt, “Nuclear architecture analysis of prostate cancer viaconvolutional neural networks,”IEEE Access, vol. 5, pp. 18526–18533, 2017.
[28]N. M. Balasooriya and R. D. Nawarathna, “A sophisticated convolutional neural network model for brain tumor classification,” in2017 IEEE International Conferenceon Industrial and Information Systems (ICIIS), IEEE, Dec. 2017.
[29]A. M. Godkhindi and R. M. Gowda, “Automated detection of polyps in CT colonography images using deep learning algorithms in colon cancer diagnosis,” in2017 International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS), IEEE, Aug. 2017.
[30]M. F. Jamaluddin, M. F. A. Fauzi, and F. S. Abas, “Tumor detection and whole slideclassification of h&e lymph node images using convolutional neural network,” in2017 IEEE International Conference on Signal and Image Processing Applications(ICSIPA), IEEE, Sept. 2017.
[31]A. Esteva, B. Kuprel, R. A. Novoa, J. Ko, S. M. Swetter, H. M. Blau, and S. Thrun,“Dermatologistlevel classification of skin cancer with deep neural networks,”Nature, vol. 542, pp. 115–118, Jan. 2017.
[32]E. Shelhamer, J. Long, and T. Darrell, “Fully Convolutional Networks for SemanticSegmentation,”IEEE Transactions on Pattern Analysis and Machine Intelligence,vol. 39, pp. 640–651, Apr. 2017.
[33]R. Luo, F. J. Sedlazeck, T.W. Lam, and M. C. Schatz, “A multitask convolutionaldeep neural network for variant calling in single molecule sequencing,”NatureCommunications, vol. 10, Mar. 2019.
[34]C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, and Z. Wojna, “Rethinking the inception architecture for computer vision,” inProceedings of the IEEE conference oncomputer vision and pattern recognition, pp. 2818–2826, 2016.
[35]A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deepconvolutional neural networks,” inAdvances in neural information processing systems, pp. 1097–1105, 2012.
[36]M. Veta, J. P. W. Pluim, P. J. van Diest, and M. A. Viergever, “Breast CancerHistopathology Image Analysis: A Review,”IEEE Transactions on Biomedical Engineering, vol. 61, pp. 1400–1411, May 2014.
[37]M. Signaevsky, M. Prastawa, K. Farrell, N. Tabish, E. Baldwin, N. Han, M. A. Iida,J. Koll, C. Bryce, D. Purohit, V. Haroutunian, A. C. McKee, T. D. Stein, C. L.White, J. Walker, T. E. Richardson, R. Hanson, M. J. Donovan, C. CordonCardo,J. Zeineh, G. Fernandez, and J. F. Crary, “Artificial intelligence in neuropathology:deep learningbased assessment of tauopathy,”Laboratory Investigation, vol. 99,pp. 1019–1029, Feb. 2019.
[38]P. Naylor, M. Lae, F. Reyal, and T. Walter, “Segmentation of Nuclei in Histopathology Images by Deep Regression of the Distance Map,”IEEE Transactions on Medical Imaging, vol. 38, pp. 448–459, Feb. 2019.
[39]J. Choi, K. Lee, W.K. Jeong, S. Y. Chun, and P. Park, “Pathology AI PlatformChallenge: Liver Cancer Segmentation,” Pathology AI Platform, 2019.
[40]R. Siegel, D. Naishadham, and A. Jemal, “Cancer statistics, 2013.,”CA: a cancerjournal for clinicians, vol. 63, pp. 11–30, Jan. 2013.
[41]A. Varga, S. PihaPaul, P. A. Ott, J. M. Mehnert, D. BertonRigaud, A. Morosky,P. Yang, J. Ruman, and D. Matei, “Pembrolizumab in patients with programmeddeath ligand 1–positive advanced ovarian cancer: Analysis of KEYNOTE028,”Gynecologic Oncology, vol. 152, pp. 243–250, Feb. 2019.
[42]J. Seoane and L. De MattosArruda, “The challenge of intratumour heterogeneity inprecision medicine.,”Journal of internal medicine, vol. 276, pp. 41–51, July 2014.
[43]D. Wu, D. C. Wang, Y. Cheng, M. Qian, M. Zhang, Q. Shen, and X. Wang, “Rolesof tumor heterogeneity in the development of drug resistance: A call for precisiontherapy.,”Seminars in cancer biology, vol. 42, pp. 13–19, Feb. 2017.
[44]S. Masoumi Moghaddam, A. Amini, D. L. Morris, and M. H. Pourgholami, “Significance of vascular endothelial growth factor in growth and peritoneal disseminationof ovarian cancer.,”Cancer metastasis reviews, vol. 31, pp. 143–162, June 2012.
[45]D. M. Chase, D. J. Chaplin, and B. J. Monk, “The development and use of vasculartargeted therapy in ovarian cancer,”Gynecologic Oncology, vol. 145, pp. 393–406,May 2017.
[46]C. Bais, B. Mueller, M. F. Brady, R. S. Mannel, R. A. Burger, W. Wei, K. M. Marien,M. M. Kockx, A. Husain, and M. J. B. and, “Tumor microvessel density as a potentialpredictive marker for bevacizumab benefit: GOG0218 biomarker analyses,”JNCI:Journal of the National Cancer Institute, vol. 109, May 2017.
[47]D. Lambrechts, H.J. Lenz, S. de Haas, P. Carmeliet, and S. J. Scherer, “Markers ofresponse for the antiangiogenic agent bevacizumab.,”Journal of clinical oncology: official journal of the American Society of Clinical Oncology, vol. 31, pp. 1219–1230, Mar. 2013.
[48]K. D. Steffensen, C. V. Madsen, R. F. Andersen, M. Waldstrøm, P. Adimi, andA. Jakobsen, “Prognostic importance of cellfree DNA in chemotherapy resistantovarian cancer treated with bevacizumab.,”European journal of cancer (Oxford,England : 1990), vol. 50, pp. 2611–2618, Oct. 2014.
[49]R. N. Gacche and Y. G. Assaraf, “Redundant angiogenic signaling and tumor drugresistance,”Drug Resistance Updates, vol. 36, pp. 47–76, Jan. 2018.
[50]C. Gourley, A. McCavigan, T. Perren, J. Paul, C. O. Michie, M. Churchman,A. Williams, W. G. McCluggage, M. Parmar, R. S. Kaplan, L. A. Hill, I. A. Halfpenny, E. J. O'Brien, O. Raji, S. Deharo, T. Davison, P. Johnston, K. E. Keating,D. P. Harkin, and R. D. Kennedy, “Molecular subgroup of highgrade serous ovarian cancer (HGSOC) as a predictor of outcome following bevacizumab.,”Journal ofClinical Oncology, vol. 32, pp. 5502–5502, May 2014.
[51]S. Kommoss, B. Winterhoff, A. L. Oberg, G. E. Konecny, C. Wang, S. M. Riska,J.B. Fan, M. J. Maurer, C. April, V. Shridhar, F. Kommoss, A. du Bois, F. Hilpert, S. Mahner, K. Baumann, W. Schroeder, A. Burges, U. Canzler, J. Chien, A. C.Embleton, M. Parmar, R. Kaplan, T. Perren, L. C. Hartmann, E. L. Goode, S. C.Dowdy, and J. Pfisterer, “Bevacizumab May Differentially Improve Ovarian Cancer Outcome in Patients with Proliferative and Mesenchymal Molecular Subtypes,”Clinical Cancer Research, vol. 23, pp. 3794–3801, Feb. 2017.
[52]R. Maggi, A. M. Cariboni, M. M. Marelli, R. M. Moretti, V. Andrè, M. Marzagalli,and P. Limonta, “GnRH and GnRH receptors in the pathophysiology of the humanfemale reproductive system,”Human Reproduction Update, vol. 22, pp. 358–381,Dec. 2015.
[53]D. M. Chase, M. W. Sill, B. J. Monk, M. D. Chambers, K. M. Darcy, E. S. Han,B. J. Buening, J. I. Sorosky, J. P. Fruehauf, and R. A. Burger, “Changes in tumorblood flow as measured by Dynamic ContrastEnhanced Magnetic Resonance Imaging (DCEMRI) may predict activity of single agent bevacizumab in recurrent epithelial ovarian (EOC) and primary peritoneal cancer (PPC) patients: an exploratoryanalysis of a Gynecologic Oncology Group Phase II study.,”Gynecologic oncology,vol. 126, pp. 375–380, Sept. 2012.