Bone metastasis classification using whole body images from prostate cancer patients based on convolutional neural networks application
Date
2020Language
en
Keyword
Abstract
Bone metastasis is one of the most frequent diseases in prostate cancer; scintigraphy imaging is particularly important for the clinical diagnosis of bone metastasis. Up to date, minimal research has been conducted regarding the application of machine learning with emphasis on modern efficient convolutional neural networks (CNNs) algorithms, for the diagnosis of prostate cancer metastasis from bone scintigraphy images. The advantageous and outstanding capabilities of deep learning, machine learning's groundbreaking technological advancement, have not yet been fully investigated regarding their application in computer-aided diagnosis systems in the field of medical image analysis, such as the problem of bone metastasis classification in whole-body scans. In particular, CNNs are gaining great attention due to their ability to recognize complex visual patterns, in the same way as human perception operates. Considering all these new enhancements in the field of deep learning, a set of simpler, faster and more accurate CNN architectures, designed for classification of metastatic prostate cancer in bones, is explored. This research study has a two-fold goal: to create and also demonstrate a set of simple but robust CNN models for automatic classification of whole-body scans in two categories, malignant (bone metastasis) or healthy, using solely the scans at the input level. Through a meticulous exploration of CNN hyper-parameter selection and fine-tuning, the best architecture is selected with respect to classification accuracy. Thus a CNN model with improved classification capabilities for bone metastasis diagnosis is produced, using bone scans from prostate cancer patients. The achieved classification testing accuracy is 97.38%, whereas the average sensitivity is approximately 95.8%. Finally, the best-performing CNN method is compared to other popular and well-known CNN architectures used for medical imaging, like VGG16, ResNet50, GoogleNet and MobileNet. The classification results show that the proposed CNN-based approach outperforms the popular CNN methods in nuclear medicine for metastatic prostate cancer diagnosis in bones. © 2020 Papandrianos et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Collections
Related items
Showing items related by title, author, creator and subject.
-
Global, regional, and national age-sex specifc mortality for 264 causes of death, 1980-2016: A systematic analysis for the Global Burden of Disease Study 2016
Naghavi M., Abajobir A.A., Abbafati C., Abbas K.M., Abd-Allah F., Abera S.F., Aboyans V., Adetokunboh O., Ärnlöv J., Afshin A., Agrawal A., Kiadaliri A.A., Ahmadi A., Ahmed M.B., Aichour A.N., Aichour I., Aichour M.T.E., Aiyar S., Al-Eyadhy A., Alahdab F., Al-Aly Z., Alam K., Alam N., Alam T., Alene K.A., Ali S.D., Alizadeh-Navaei R., Alkaabi J.M., Alkerwi A., Alla F., Allebeck P., Allen C., Al-Raddadi R., Alsharif U., Altirkawi K.A., Alvis-Guzman N., Amare A.T., Amini E., Ammar W., Amoako Y.A., Anber N., Andersen H.H., Andrei C.L., Androudi S., Ansari H., Antonio C.A.T., Anwari P., Arora M., Artaman A., Aryal K.K., Asayesh H., Asgedom S.W., Atey T.M., Avila-Burgos L., Avokpaho E.F.G.A., Awasthi A., Quintanilla B.P.A., Béjot Y., Babalola T.K., Bacha U., Balakrishnan K., Barac A., Barboza M.A., Barker-Collo S.L., Barquera S., Barregard L., Barrero L.H., Baune B.T., Bedi N., Beghi E., Bekele B.B., Bell M.L., Bennett J.R., Bensenor I.M., Berhane A., Bernabé E., Betsu B.D., Beuran M., Bhatt S., Biadgilign S., Bienhof K., Bikbov B., Bisanzio D., Bourne R.R.A., Breitborde N.J.K., Bulto L.N.B., Bumgarner B.R., Butt Z.A., Cárdenas R., Cahuana-Hurtado L., Cameron E., Campuzano J.C., Car J., Carrero J.J., Carter A., Casey D.C., Castañeda-Orjuela C.A., Catalá-López F., Charlson F.J., Chibueze C.E., Chimed-Ochir O., Chisumpa V.H., Chitheer A.A., Christopher D.J., Ciobanu L.G., Cirillo M., Cohen A.J., Colombara D., Cooper C., Cowie B.C., Criqui M.H., Dandona L., Dandona R., Dargan P.I., Das Neves J., Davitoiu D.V., Davletov K., De Courten B., Degenhardt L., Deiparine S., Deribe K., Deribew A., Dey S., Dicker D., Ding E.L., Djalalinia S., Do H.P., Doku D.T., Douwes-Schultz D., Driscoll T.R., Dubey M., Duncan B.B., Echko M., El-Khatib Z.Z., Ellingsen C.L., Enayati A., Erskine H.E., Eskandarieh S., Esteghamati A., Ermakov S.P., Estep K., Sa Farinha C.S., Faro A., Farzadfar F., Feigin V.L., Fereshtehnejad S.-M., Fernandes J.C., Ferrari A.J., Feyissa T.R., Filip I., Finegold S., Fischer F., Fitzmaurice C., Flaxman A.D., Foigt N., Frank T., Fraser M., Fullman N., Fürst T., Furtado J.M., Gakidou E., Garcia-Basteiro A.L., Gebre T., Gebregergs G.B., Gebrehiwot T.T., Gebremichael D.Y., Geleijnse J.M., Genova-Maleras R., Gesesew H.A., Gething P.W., Gillum R.F., Ginawi I.A.M., Giref A.Z., Giroud M., Giussani G., Godwin W.W., Gold A.L., Goldberg E.M., Gona P.N., Gopalani S.V., Gouda H.N., Goulart A.C., Griswold M., Gupta P.C., Gupta R., Gupta T., Gupta V., Haagsma J.A., Hafezi-Nejad N., Hailu A.D., Hailu G.B., Hamadeh R.R., Hambisa M.T., Hamidi S., Hammami M., Hancock J., Handal A.J., Hankey G.J., Hao Y., Harb H.L., Hareri H.A., Hassanvand M.S., Havmoeller R., Hay S.I., He F., Hedayati M.T., Henry N.J., Heredia-Pi I.B., Herteliu C., Hoek H.W., Horino M., Horita N., Hosgood H.D., Hostiuc S., Hotez P.J., Hoy D.G., Huynh C., Iburg K.M., Ikeda C., Ileanu B.V., Irenso A.A., Irvine C.M.S., Jürisson M., Jacobsen K.H., Jahanmehr N., Jakovljevic M.B., Javanbakht M., Jayaraman S.P., Jeemon P., Jha V., John D., Johnson C.O., Johnson S.C., Jonas J.B., Kabir Z., Kadel R., Kahsay A., Kamal R., Karch A., Karimi S.M., Karimkhani C., Kasaeian A., Kassaw N.A., Kassebaum N.J., Katikireddi S.V., Kawakami N., Keiyoro P.N., Kemmer L., Kesavachandran C.N., Khader Y.S., Khan E.A., Khang Y.-H., Khoja A.T.A., Khosravi A., Khosravi M.H., Khubchandani J., Kieling C., Kievlan D., Kim D., Kim Y.J., Kimokoti R.W., Kinfu Y., Kissoon N., Kivimaki M., Knudsen A.K., Kopec J.A., Kosen S., Koul P.A., Koyanagi A., Defo B.K., Kulikof X.R., Kumar G.A., Kumar P., Kutz M., Kyu H.H., Lal D.K., Lalloo R., Lambert T.L.N., Lan Q., Lansingh V.C., Larsson A., Lee P.H., Leigh J., Leung J., Levi M., Li Y., Kappe D.L., Liang X., Liben M.L., Lim S.S., Liu A., Liu P.Y., Liu Y., Lodha R., Logroscino G., Lorkowski S., Lotufo P.A., Lozano R., Lucas T.C.D., Ma S., Macarayan E.R.K., Maddison E.R., Abd El Razek M.M., Majdan M., Majdzadeh R., Majeed A., Malekzadeh R., Malhotra R., Malta D.C., Manguerra H., Manyazewal T., Mapoma C.C., Marczak L.B., Markos D., Martinez-Raga J., Martins-Melo F.R., Martopullo I., McAlinden C., McGaughey M., McGrath J.J., Mehata S., Meier T., Meles K.G., Memiah P., Memish Z.A., Mengesha M.M., Mengistu D.T., Menota B.G., Mensah G.A., Meretoja A., Meretoja T.J., Millear A., Miller T.R., Minnig S., Mirarefn M., Mirrakhimov E.M., Misganaw A., Mishra S.R., Mohammad K.A., Mohammadi A., Mohammed S., Mokdad A.H., Mola G.L.D., Mollenkopf S.K., Molokhia M., Monasta L., Hernandez J.C.M., Montico M., Mooney M.D., Moradi-Lakeh M., Moraga P., Morawska L., Morrison S.D., Morozof C., Mountjoy-Venning C., Mruts K.B., Muller K., Murthy G.V.S., Musa K.I., Nachega J.B., Naheed A., Naldi L., Nangia V., Nascimento B.R., Nasher J.T., Natarajan G., Negoi I., Ngunjiri J.W., Nguyen C.T., Nguyen G., Nguyen M., Nguyen Q.L., Nguyen T.H., Nichols E., Ningrum D.N.A., Nong V.M., Noubiap J.J.N., Ogbo F.A., Oh I.-H., Okoro A., Olagunju A.T., Olsen H.E., Olusanya B.O., Olusanya J.O., Ong K., Opio J.N., Oren E., Ortiz A., Osman M., Ota E., Mahesh P.A., Pacella R.E., Pakhale S., Pana A., Panda B.K., Jonas S., Papachristou C., Park E.-K., Patten S.B., Patton G.C., Paudel D., Paulson K., Pereira D.M., Perez-Ruiz F., Perico N., Pervaiz A., Petzold M., Phillips M.R., Pigott D.M., Pinho C., Plass D., Pletcher M.A., Polinder S., Postma M.J., Pourmalek F., Purcell C., Qorbani M., Radfar A., Rafay A., Rahimi-Movaghar V., Rahman M., Ur Rahman M.H., Rai R.K., Ranabhat C.L., Rankin Z., Rao P.C., Rath G.K., Rawaf S., Ray S.E., Rehm J., Reiner R.C., Reitsma M.B., Remuzzi G., Rezaei S., Rezai M.S., Rokni M.B., Ronfani L., Roshandel G., Roth G.A., Rothenbacher D., Ruhago G.M., Rizwan S.A., Saadat S., Sachdev P.S., Sadat N., Safdarian M., Saf S., Safiri S., Sagar R., Sahathevan R., Salama J., Salamati P., Salomon J.A., Samy A.M., Sanabria J.R., Sanchez-Niño M.D., Santomauro D., Santos I.S., Milicevic M.M.S., Sartorius B., Satpathy M., Shahraz S., Schmidt M.I., Schneider I.J.C., Schulhofer-Wohl S., Schutte A.E., Schwebel D.C., Schwendicke F., Sepanlou S.G., Servan-Mori E.E., Shackelford K.A., Shaikh M.A., Shamsipour M., Shamsizadeh M., Islam S.M.S., Sharma J., Sharma R., She J., Sheikhbahaei S., Shey M., Shi P., Shields C., Shigematsu M., Shiri R., Shirude S., Shiue I., Shoman H., Shrime M.G., Sigfusdottir I.D., Silpakit N., Silva J.P., Singh A., Singh J.A., Skiadaresi E., Sligar A., Smith A., Smith D.L., Smith M., Sobaih B.H.A., Soneji S., Sorensen R.J.D., Soriano J.B., Sreeramareddy C.T., Srinivasan V., Stanaway J.D., Stathopoulou V., Steel N., Stein D.J., Steiner C., Steinke S., Stokes M.A., Strong M., Strub B., Subart M., Sufyan M.B., Sunguya B.F., Sur P.J., Swaminathan S., Sykes B.L., Tabarés-Seisdedos R., Tadakamadla S.K., Takahashi K., Takala J.S., Talongwa R.T., Tarawneh M.R., Tavakkoli M., Taveira N., Tegegne T.K., Tehrani-Banihashemi A., Temsah M.-H., Terkawi A.S., Thakur J.S., Thamsuwan O., Thankappan K.R., Thomas K.E., Thompson A.H., Thomson A.J., Thrift A.G., Tobe-Gai R., Topor-Madry R., Torre A., Tortajada M., Towbin J.A., Tran B.X., Troeger C., Truelsen T., Tsoi D., Tuzcu E.M., Tyrovolas S., Ukwaja K.N., Undurraga E.A., Updike R., Uthman O.A., Uzochukwu B.S.C., Van Boven J.F.M., Vasankari T., Venketasubramanian N., Violante F.S., Vlassov V.V., Vollset S.E., Vos T., Wakayo T., Wallin M.T., Wang Y.-P., Weiderpass E., Weintraub R.G., Weiss D.J., Werdecker A., Westerman R., Whetter B., Whiteford H.A., Wijeratne T., Wiysonge C.S., Woldeyes B.G., Wolfe C.D.A., Woodbrook R., Workicho A., Xavier D., Xiao Q., Xu G., Yaghoubi M., Yakob B., Yano Y., Yaseri M., Yimam H.H., Yonemoto N., Yoon S.-J., Yotebieng M., Younis M.Z., Zaidi Z., El Sayed Zaki M., Zegeye E.A., Zenebe Z.M., Zerfu T.A., Zhang A.L., Zhang X., Zipkin B., Zodpey S., Lopez A.D., Murray C.J.L., GBD 2016 Causes of Death Collaborators (2017)Background: Monitoring levels and trends in premature mortality is crucial to understanding how societies can address prominent sources of early death. The Global Burden of Disease 2016 Study (GBD 2016) provides a comprehensive ... -
Alterations of microRNAs in solid cancers and their prognostic value
Chira, P.; Vareli, K.; Sainis, I.; Papandreou, C.; Briasoulis, E. (2010)MicroRNAs (miRNAs) are evolutionarily conserved, naturally abundant, small, regulatory non-coding RNAs that inhibit gene expression at the post-transcriptional level in a sequence-specific manner. Each miRNA represses the ... -
Treatment of lung cancer
Rapti, A.; Kerenidi, T.; Zarogoulidis, K. (2012)