{"id":15414,"date":"2023-01-13T09:49:47","date_gmt":"2023-01-13T07:49:47","guid":{"rendered":"http:\/\/journals.khnu.km.ua\/vestnik\/?p=15414"},"modified":"2023-02-15T00:37:23","modified_gmt":"2023-02-14T22:37:23","slug":"oglyad-ta-analiz-osnovnyh-karkasnyh-merezh-vyyavlennya-oznak-dlya-klasyfikacziyi-zobrazhen-mrt-v-modelyah-glybynnogo-navchannya","status":"publish","type":"post","link":"https:\/\/journals.khnu.km.ua\/vestnik\/?p=15414","title":{"rendered":"\u041e\u0433\u043b\u044f\u0434 \u0442\u0430 \u0430\u043d\u0430\u043b\u0456\u0437 \u043e\u0441\u043d\u043e\u0432\u043d\u0438\u0445 \u043a\u0430\u0440\u043a\u0430\u0441\u043d\u0438\u0445 \u043c\u0435\u0440\u0435\u0436 \u0432\u0438\u044f\u0432\u043b\u0435\u043d\u043d\u044f \u043e\u0437\u043d\u0430\u043a \u0434\u043b\u044f \u043a\u043b\u0430\u0441\u0438\u0444\u0456\u043a\u0430\u0446\u0456\u0457 \u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u044c \u043c\u0440\u0442 \u0432 \u043c\u043e\u0434\u0435\u043b\u044f\u0445 \u0433\u043b\u0438\u0431\u0438\u043d\u043d\u043e\u0433\u043e \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f"},"content":{"rendered":"

<\/p>\n

\u041e\u0413\u041b\u042f\u0414 \u0422\u0410 \u0410\u041d\u0410\u041b\u0406\u0417 \u041e\u0421\u041d\u041e\u0412\u041d\u0418\u0425 \u041a\u0410\u0420\u041a\u0410\u0421\u041d\u0418\u0425 \u041c\u0415\u0420\u0415\u0416 \u0412\u0418\u042f\u0412\u041b\u0415\u041d\u041d\u042f \u041e\u0417\u041d\u0410\u041a \u0414\u041b\u042f \u041a\u041b\u0410\u0421\u0418\u0424\u0406\u041a\u0410\u0426\u0406\u0407 \u0417\u041e\u0411\u0420\u0410\u0416\u0415\u041d\u042c \u041c\u0420\u0422 \u0412 \u041c\u041e\u0414\u0415\u041b\u042f\u0425 \u0413\u041b\u0418\u0411\u0418\u041d\u041d\u041e\u0413\u041e \u041d\u0410\u0412\u0427\u0410\u041d\u041d\u042f<\/p>\n

REVIEW AND ANALYSIS OF BASIC FEATURE DETECTION NETWORKS FOR CLASSIFICATION OF MRI IMAGES IN DEEP LEARNING MODELS<\/p>\n

\u0421\u0442\u043e\u0440\u0456\u043d\u043a\u0438: 183-187. \u041d\u043e\u043c\u0435\u0440: \u21166, 2022 (315)\u00a0<\/strong> \"\"<\/a>
\n\u0410\u0432\u0442\u043e\u0440\u0438:<\/strong>
\n\u041f\u0423\u041a\u0410\u0427 \u041f\u0430\u0432\u043b\u043e
\n\u041d\u0430\u0446\u0456\u043e\u043d\u0430\u043b\u044c\u043d\u0438\u0439 \u0443\u043d\u0456\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442 \u00ab\u041b\u044c\u0432\u0456\u0432\u0441\u044c\u043a\u0430 \u043f\u043e\u043b\u0456\u0442\u0435\u0445\u043d\u0456\u043a\u0430\u00bb
\nORCID ID: 0000-0002-0488-6828<\/a>
\ne-mail: pavlopukach@gmail.com
\nPUKACH Pavlo
\nLviv Polytechnic National University
\nDOI:<\/strong> https:\/\/www.doi.org\/10.31891\/2307-5732-2022-315-6-183-187<\/a><\/p>\n

\u0410\u043d\u043e\u0442\u0430\u0446\u0456\u044f \u043c\u043e\u0432\u043e\u044e \u043e\u0440\u0438\u0433\u0456\u043d\u0430\u043b\u0443<\/strong><\/p>\n

\u0423 \u0446\u0456\u0439 \u0441\u0442\u0430\u0442\u0442\u0456 \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u043e \u043e\u0446\u0456\u043d\u043a\u0443 \u0441\u0443\u0447\u0430\u0441\u043d\u0438\u0445 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u0433\u043b\u0438\u0431\u043e\u043a\u043e\u0433\u043e \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f \u0434\u043b\u044f \u043a\u043b\u0430\u0441\u0438\u0444\u0456\u043a\u0430\u0446\u0456\u0457 \u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u044c \u041c\u0420\u0422 \u043a\u043e\u043b\u0456\u043d\u043d\u043e\u0433\u043e \u0441\u0443\u0433\u043b\u043e\u0431\u0430. \u0421\u0435\u0440\u0435\u0434 \u0443\u0441\u0456\u0445 \u0440\u043e\u0431\u0456\u0442, \u043f\u043e\u0432\u2019\u044f\u0437\u0430\u043d\u0438\u0445 \u0437 \u0446\u0438\u043c \u0434\u043e\u0441\u043b\u0456\u0434\u0436\u0435\u043d\u043d\u044f\u043c, \u0431\u0443\u043b\u043e \u043a\u0456\u043b\u044c\u043a\u0430 \u0441\u043f\u0440\u043e\u0431 \u043f\u0435\u0440\u0435\u043d\u0430\u0432\u0447\u0438\u0442\u0438 \u043e\u0440\u0438\u0433\u0456\u043d\u0430\u043b\u044c\u043d\u0443 \u043c\u043e\u0434\u0435\u043b\u044c MRNet \u043d\u0430 \u0431\u0456\u043b\u044c\u0448 \u0441\u0443\u0447\u0430\u0441\u043d\u0456 \u0430\u0440\u0445\u0456\u0442\u0435\u043a\u0442\u0443\u0440\u0438 \u043a\u043e\u043c\u043f\u2019\u044e\u0442\u0435\u0440\u043d\u043e\u0433\u043e \u0437\u043e\u0440\u0443. \u041a\u0440\u0456\u043c \u0442\u043e\u0433\u043e, \u0449\u0435 \u043d\u0435 \u043f\u043e\u0432\u0456\u0434\u043e\u043c\u043b\u044f\u043b\u043e\u0441\u044f \u043f\u0440\u043e \u0441\u043f\u0440\u043e\u0431\u0438 \u0437\u0430\u0434\u043e\u043a\u0443\u043c\u0435\u043d\u0442\u0443\u0432\u0430\u0442\u0438 \u043f\u043e\u0441\u0442\u0443\u043f\u043e\u0432\u0435 \u043f\u043e\u043a\u0440\u0430\u0449\u0435\u043d\u043d\u044f \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0456 \u043f\u0440\u043e\u0433\u043d\u043e\u0437\u0443\u0432\u0430\u043d\u043d\u044f MRNet \u0437\u0430 \u0434\u043e\u043f\u043e\u043c\u043e\u0433\u043e\u044e \u043d\u043e\u0432\u0438\u0445 \u0430\u0440\u0445\u0456\u0442\u0435\u043a\u0442\u0443\u0440 \u043a\u043e\u043c\u043f\u2019\u044e\u0442\u0435\u0440\u043d\u043e\u0433\u043e \u0431\u0430\u0447\u0435\u043d\u043d\u044f. \u0423 \u0434\u0430\u043d\u0456\u0439 \u0440\u043e\u0431\u043e\u0442\u0456 \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u043e \u043f\u043e\u0440\u0456\u0432\u043d\u044f\u043b\u044c\u043d\u0438\u0439 \u0430\u043d\u0430\u043b\u0456\u0437 \u0441\u0443\u0447\u0430\u0441\u043d\u0438\u0445 \u0430\u0440\u0445\u0456\u0442\u0435\u043a\u0442\u0443\u0440 \u043a\u043e\u043c\u043f\u2019\u044e\u0442\u0435\u0440\u043d\u043e\u0433\u043e \u0431\u0430\u0447\u0435\u043d\u043d\u044f \u0434\u043b\u044f \u0432\u0438\u043b\u0443\u0447\u0435\u043d\u043d\u044f \u043e\u0437\u043d\u0430\u043a \u0437 \u041c\u0420\u0422-\u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u044c \u043a\u043e\u043b\u0456\u043d\u043d\u043e\u0433\u043e \u0441\u0443\u0433\u043b\u043e\u0431\u0430 \u0432 \u0437\u0430\u0434\u0430\u0447\u0430\u0445 \u043a\u043b\u0430\u0441\u0438\u0444\u0456\u043a\u0430\u0446\u0456\u0457 \u0443\u0448\u043a\u043e\u0434\u0436\u0435\u043d\u044c \u0442\u0430 \u0430\u043d\u043e\u043c\u0430\u043b\u0456\u0439 \u043a\u043e\u043b\u0456\u043d\u043d\u043e\u0433\u043e \u0441\u0443\u0433\u043b\u043e\u0431\u0430. \u0422\u0430\u043a\u0438\u0439 \u0430\u043d\u0430\u043b\u0456\u0437 \u0454 \u043d\u0435\u043e\u0431\u0445\u0456\u0434\u043d\u0438\u043c \u044f\u043a \u0456\u043d\u0441\u0442\u0440\u0443\u043c\u0435\u043d\u0442 \u0434\u043b\u044f \u0441\u0442\u0432\u043e\u0440\u0435\u043d\u043d\u044f \u043f\u0440\u0438\u043a\u043b\u0430\u0434\u043d\u0438\u0445 \u0430\u0440\u0445\u0456\u0442\u0435\u043a\u0442\u0443\u0440 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f, \u0441\u043f\u0440\u044f\u043c\u043e\u0432\u0430\u043d\u0438\u0445 \u043d\u0430 \u0430\u0432\u0442\u043e\u043c\u0430\u0442\u0438\u0437\u043e\u0432\u0430\u043d\u0443 \u0434\u0456\u0430\u0433\u043d\u043e\u0441\u0442\u0438\u043a\u0443 \u0442\u0440\u0430\u0432\u043c \u043a\u043e\u043b\u0456\u043d\u0430 \u0432 \u043c\u0435\u0434\u0438\u0447\u043d\u0438\u0445 \u043f\u0440\u0438\u0441\u0442\u0440\u043e\u044f\u0445 \u0456 \u0441\u0438\u0441\u0442\u0435\u043c\u0430\u0445.
\n\u0410\u043b\u0433\u043e\u0440\u0438\u0442\u043c\u0438 \u0433\u043b\u0438\u0431\u0438\u043d\u043d\u043e\u0433\u043e \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f \u043c\u043e\u0436\u0443\u0442\u044c \u0431\u0443\u0442\u0438 \u0437\u0430\u0441\u0442\u043e\u0441\u043e\u0432\u0430\u043d\u0456 \u0431\u0435\u0437\u043f\u043e\u0441\u0435\u0440\u0435\u0434\u043d\u044c\u043e \u0434\u043e \u0431\u0430\u0433\u0430\u0442\u044c\u043e\u0445 \u0440\u0456\u0437\u043d\u043e\u043c\u0430\u043d\u0456\u0442\u043d\u0438\u0445 \u0437\u0430\u0432\u0434\u0430\u043d\u044c \u0440\u0435\u043d\u0442\u0433\u0435\u043d\u043e\u043b\u043e\u0433\u0456\u0457 \u043e\u043f\u043e\u0440\u043d\u043e-\u0440\u0443\u0445\u043e\u0432\u043e\u0433\u043e \u0430\u043f\u0430\u0440\u0430\u0442\u0443, \u0432\u043a\u043b\u044e\u0447\u0430\u044e\u0447\u0438 \u0440\u0435\u043a\u043e\u043d\u0441\u0442\u0440\u0443\u043a\u0446\u0456\u044e \u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u043d\u044f, \u0441\u0438\u043d\u0442\u0435\u0437 \u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u043d\u044f, \u0441\u0435\u0433\u043c\u0435\u043d\u0442\u0430\u0446\u0456\u044e \u0442\u043a\u0430\u043d\u0438\u043d, \u0430 \u0442\u0430\u043a\u043e\u0436 \u0434\u0456\u0430\u0433\u043d\u043e\u0441\u0442\u0438\u043a\u0443 \u0442\u0430 \u0432\u0438\u044f\u0432\u043b\u0435\u043d\u043d\u044f \u0445\u0430\u0440\u0430\u043a\u0442\u0435\u0440\u0438\u0441\u0442\u0438\u043a \u0437\u0430\u0445\u0432\u043e\u0440\u044e\u0432\u0430\u043d\u044c \u043e\u043f\u043e\u0440\u043d\u043e-\u0440\u0443\u0445\u043e\u0432\u043e\u0433\u043e \u0430\u043f\u0430\u0440\u0430\u0442\u0443 \u043d\u0430 \u0440\u0435\u043d\u0442\u0433\u0435\u043d\u043e\u0433\u0440\u0430\u043c\u0430\u0445, \u0443\u043b\u044c\u0442\u0440\u0430\u0437\u0432\u0443\u043a\u0443, \u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u043d\u044f\u0445 \u041a\u0422 \u0442\u0430 \u041c\u0420\u0422. \u0429\u043e\u0431 \u0441\u0444\u043e\u0440\u043c\u0443\u043b\u044e\u0432\u0430\u0442\u0438 \u0442\u0430\u043a\u0438\u0439 \u043f\u043e\u0440\u0456\u0432\u043d\u044f\u043b\u044c\u043d\u0438\u0439 \u0430\u043d\u0430\u043b\u0456\u0437, \u0443 \u0446\u0456\u0439 \u0441\u0442\u0430\u0442\u0442\u0456 \u043f\u043e\u0440\u0456\u0432\u043d\u044e\u0454\u0442\u044c\u0441\u044f \u043f\u0440\u043e\u0434\u0443\u043a\u0442\u0438\u0432\u043d\u0456\u0441\u0442\u044c \u0431\u0430\u0437\u043e\u0432\u043e\u0457 \u0430\u0440\u0445\u0456\u0442\u0435\u043a\u0442\u0443\u0440\u0438 MRNet \u0434\u043b\u044f \u0437\u0430\u0432\u0434\u0430\u043d\u043d\u044f \u043a\u043b\u0430\u0441\u0438\u0444\u0456\u043a\u0430\u0446\u0456\u0457 \u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u044c \u041c\u0420\u0422 \u043a\u043e\u043b\u0456\u043d\u043d\u043e\u0433\u043e \u0441\u0443\u0433\u043b\u043e\u0431\u0430, \u0432\u0438\u043a\u043e\u0440\u0438\u0441\u0442\u043e\u0432\u0443\u044e\u0447\u0438 \u0440\u0456\u0437\u043d\u0456 \u043d\u0430\u0439\u0441\u0443\u0447\u0430\u0441\u043d\u0456\u0448\u0456 \u0430\u0440\u0445\u0456\u0442\u0435\u043a\u0442\u0443\u0440\u0438 \u043a\u043e\u043c\u043f\u2019\u044e\u0442\u0435\u0440\u043d\u043e\u0433\u043e \u0431\u0430\u0447\u0435\u043d\u043d\u044f \u044f\u043a \u043a\u0430\u0440\u043a\u0430\u0441\u043d\u0456 \u043c\u0435\u0440\u0435\u0436\u0456 \u0434\u043b\u044f \u0432\u0438\u0434\u0456\u043b\u0435\u043d\u043d\u044f \u043e\u0437\u043d\u0430\u043a. \u0426\u0435 \u0442\u0430\u043a\u043e\u0436 \u0434\u0435\u043c\u043e\u043d\u0441\u0442\u0440\u0443\u0454 \u043f\u043e\u0441\u0442\u0443\u043f\u043e\u0432\u0435 \u043f\u0456\u0434\u0432\u0438\u0449\u0435\u043d\u043d\u044f \u0442\u043e\u0447\u043d\u043e\u0441\u0442\u0456 \u043f\u0440\u043e\u0433\u043d\u043e\u0437\u0443\u0432\u0430\u043d\u043d\u044f \u0446\u0438\u0445 \u043c\u043e\u0434\u0435\u043b\u0435\u0439 \u0432\u0456\u0434\u043f\u043e\u0432\u0456\u0434\u043d\u043e \u0434\u043e \u0435\u0432\u043e\u043b\u044e\u0446\u0456\u0457 \u0441\u0430\u043c\u0438\u0445 \u043a\u0430\u0440\u043a\u0430\u0441\u043d\u0438\u0445 \u043c\u043e\u0434\u0435\u043b\u0435\u0439. \u0414\u043e\u0441\u0438\u0442\u044c \u0432\u0430\u0436\u043b\u0438\u0432\u0438\u043c \u0430\u0441\u043f\u0435\u043a\u0442\u043e\u043c \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u043e\u0433\u043e \u0434\u043e\u0441\u043b\u0456\u0434\u0436\u0435\u043d\u043d\u044f \u0454 \u0442\u043e\u0439 \u0444\u0430\u043a\u0442, \u0449\u043e \u0432\u0441\u0456 \u043c\u043e\u0434\u0435\u043b\u0456 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f, \u0440\u043e\u0437\u0440\u043e\u0431\u043b\u0435\u043d\u0456 \u0442\u0430 \u043d\u0430\u0432\u0447\u0435\u043d\u0456 \u0432 \u0440\u043e\u0437\u0433\u043b\u044f\u043d\u0443\u0442\u043e\u043c\u0443 \u0435\u043a\u0441\u043f\u0435\u0440\u0438\u043c\u0435\u043d\u0442\u0456, \u043c\u0430\u044e\u0442\u044c \u0443\u043d\u0456\u0444\u0456\u043a\u043e\u0432\u0430\u043d\u0443 \u0430\u0440\u0445\u0456\u0442\u0435\u043a\u0442\u0443\u0440\u0443, \u0437\u0430 \u0432\u0438\u043d\u044f\u0442\u043a\u043e\u043c \u0448\u0430\u0440\u0443 \u0432\u0438\u0434\u0456\u043b\u0435\u043d\u043d\u044f \u043e\u0437\u043d\u0430\u043a, \u0456 \u0432\u0441\u0456 \u0432\u043e\u043d\u0438 \u0431\u0443\u043b\u0438 \u043d\u0430\u0432\u0447\u0435\u043d\u0456 \u0437 \u043d\u0443\u043b\u044f \u0437 \u0432\u0438\u043a\u043e\u0440\u0438\u0441\u0442\u0430\u043d\u043d\u044f\u043c \u043e\u0434\u043d\u0430\u043a\u043e\u0432\u0438\u0445 \u0433\u0456\u043f\u0435\u0440-\u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u0456\u0432 \u043c\u043e\u0434\u0435\u043b\u0456 \u0442\u0430 \u043f\u0430\u0440\u0430\u043c\u0435\u0442\u0440\u0456\u0432 \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f. \u0422\u0430\u043a\u043e\u0436, \u0434\u043b\u044f \u043f\u043e\u0440\u0456\u0432\u043d\u044f\u043d\u043d\u044f \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u0456\u0432 \u043a\u043b\u0430\u0441\u0438\u0444\u0456\u043a\u0430\u0446\u0456\u0457 \u0431\u0443\u043b\u043e \u0432\u0438\u043a\u043e\u0440\u0438\u0441\u0442\u0430\u043d\u043e \u0434\u043e\u0434\u0430\u0442\u043a\u043e\u0432\u0443 \u043c\u0435\u0442\u0440\u0438\u043a\u0443 \u2014 \u043f\u043e\u043a\u0430\u0437\u043d\u0438\u043a \u041a\u0430\u043f\u043f\u0430 \u041a\u043e\u0435\u043d\u0430, \u044f\u043a\u0438\u0439 \u0454 \u0437\u043d\u0430\u0447\u0443\u0449\u0438\u043c \u0447\u0435\u0440\u0435\u0437 \u043d\u0435\u0437\u0431\u0430\u043b\u0430\u043d\u0441\u043e\u0432\u0430\u043d\u0456\u0441\u0442\u044c \u0432\u0438\u043a\u043e\u0440\u0438\u0441\u0442\u0430\u043d\u043e\u0433\u043e \u043d\u0430\u0431\u043e\u0440\u0443 \u0434\u0430\u043d\u0438\u0445
\n\u041a\u043b\u044e\u0447\u043e\u0432\u0456 \u0441\u043b\u043e\u0432\u0430:<\/strong> \u041c\u0420\u0422, \u043a\u0430\u0440\u043a\u0430\u0441\u043d\u0430 \u043c\u0435\u0440\u0435\u0436\u0430, MRNet, \u0433\u043b\u0438\u0431\u0438\u043d\u043d\u0435 \u043d\u0430\u0432\u0447\u0430\u043d\u043d\u044f, \u043a\u043e\u043c\u043f\u2019\u044e\u0442\u0435\u0440\u043d\u0435 \u0431\u0430\u0447\u0435\u043d\u043d\u044f.<\/p>\n

\u0420\u043e\u0437\u0448\u0438\u0440\u0435\u043d\u0430 \u0430\u043d\u043e\u0442\u0430\u0446\u0456\u044f \u0430\u043d\u0433\u043b\u0456\u0439\u0441\u044c\u043a\u043e\u044e \u00a0\u043c\u043e\u0432\u043e\u044e<\/strong><\/p>\n

This paper presents an evaluation of modern deep learning models for the classification of MRI images of the knee joint. Among all the work related to this research, there have been several attempts to retrain the original MRNet model on more modern computer vision architectures. Also, no attempt has yet been reported to document the incremental improvement in MRNet prediction accuracy using newer computer vision architectures. This paper presents a comparative analysis of modern deep architectures of computer vision for extracting features from MRI images of the knee joint in the tasks of classification of injuries and anomalies of the knee. Such an analysis is needed, at least as a guide to creating applied architectures of machine learning models aimed at automated diagnosis of knee injuries in medical devices and systems.
\nIn the field of artificial intelligence, deep learning (DL) algorithms can be applied directly to many different musculoskeletal radiology tasks, including image reconstruction, synthetic imaging, tissue segmentation, and diagnosis and detection of musculoskeletal disease characteristics on radiographs, ultrasound , CT and MRI images. Ideally, such systems should also help radiologists focus on rare diseases as well as very complex abnormalities. At the same time, the task of automating the process of diagnosing typical injuries and anomalies is set. The level of confidence in the result of prediction should be similar to the conclusions of commissions of expert radiologists. To frame such a benchmarking analysis, this paper compares the performance of the basic MRNet architecture for the knee MRI image classification task, using various state-of-the-art computer vision architectures as framework networks for feature extraction. It also demonstrates a gradual increase in the prediction accuracy of these models in accordance with the evolution of the framework models themselves. A rather important aspect of the presented research is the fact that all machine learning models developed and trained in the considered experiment have a unified architecture, except for the feature extraction framework, and they were all trained from scratch using the same model parameters and training parameters. In addition, the model estimation strategies in this work use an additional metric that has not yet been measured and compared in any related work, namely Cohen’s Kappa metric. This metric is significant because the MRNet dataset used in this paper is not balanced.
\nKeywords:<\/strong> MRI, framework network, MRNet, deep learning, computer vision.<\/p>\n

References<\/strong><\/p>\n

    \n
  1. Nacey N.C. Magnetic resonance imaging of the knee: An overview and update of conventional and state of the art imaging \/ N.C. Nacey, M.G. Geeslin, G.W. Miller, J. L. Pierce \/\/ J. Magn. Reson. Imaging. \u2013 2017. \u2013 \u2116 45. \u2013 P.\u00a0 1257\u20131275.<\/li>\n
  2. IHS Markit Ltd (Prepared for the AAMC). The Complexities of Physician Supply and Demand: Projections from 2019 to 2034 AAMC, Washington, DC, USA, June 2021. https:\/\/www.aamc.org\/media\/54681\/download.<\/li>\n
  3. Gore J.C. Artificial intelligence in medical imaging \/ J.C. Gore \/\/ J. Magn. Reson. Imaging. \u2013 2020. \u2013 \u2116 68. \u2013 P.\u00a0A1-A4.<\/li>\n
  4. He K. Deep Residual Learning for Image Recognition \/ K. He, X. Zhang, S. Ren, J. Sun. \/\/ arXiv. \u2013 2015. \u2013 arXiv:1512.03385.<\/li>\n
  5. Tsai C. Knee Injury Detection using MRI with Efficiently-Layered Network (ELNet) \/ C. Tsai, N. Kiryati, E. Konen, I. Eshed, A. Mayer \/\/ Proceedings of the Third Conference on Medical Imaging with Deep Learning, Montreal, QC, Canada, 6\u20138 July 2020, Volume 121, p. 784\u2013794.<\/li>\n
  6. Krizhevsky A. ImageNet Classification with Deep Convolutional Neural Networks \/ A. Krizhevsky, I. Sutskever, E.G. Hinton \/\/ Proceedings of the Advances in Neural Information Processing Systems 25 (NIPS 2012), Lake Tahoe, NV, USA, 3\u20138 December 2012. https:\/\/papers.nips.cc\/paper\/2012\/hash\/c399862d3b9d6b76c8436e924a68c45b-Abstract.html<\/li>\n
  7. Azcona D. A Comparative Study of Existing and New Deep Learning Methods for Detecting Knee Injuries using the MRNet Dataset \/ D. Azcona, K. McGuinness, A.F. Smeaton \/\/ Proceedings of the 2020 International Conference on Intelligent Data Science Technologies and Applications (IDSTA), Valencia, Spain, 19\u201322 October 2020, p. 88\u201394.<\/li>\n
  8. Simonyan K. Very Deep Convolutional Networks for Large-Scale Image Recognition \/ K. Simonyan, A. Zisserman \/\/ arXiv. \u2013 2015. \u2013 arXiv:1409.1556.<\/li>\n
  9. Tan M. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks \/ M. Tan, Q.V. Le \/\/ arXiv. \u2013 2019. \u2013 arXiv:1905.11946.<\/li>\n
  10. \u0160tajduhar I. Semi-automated detection of anterior cruciate ligament injury from MRI \/ I. \u0160tajduhar, M. Mamula, D. Mileti\u00b4c, G. \/\/ Unal Comput. Methods Programs Biomed. \u2013 2017. \u2013 140. \u2013 P. 151\u2013164.<\/li>\n
  11. Bien N. Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet \/ N. Bien, P. Rajpurkar, R.L. Ball, J. Irvin, A. Park, E. Jones, M. Bereket, B.N. Patel, K.W. Yeom, K. Shpanskaya \/\/ LoS Med. \u2013 2018. \u2013 15. \u2013 e1002699.<\/li>\n
  12. Shorten C. A survey on Image Data Augmentation for Deep Learning \/ C. Shorten, T.M. Khoshgoftaar \/\/ J. Big Data. \u2013 2019. \u2013 6. \u2013 P. 1\u201348.<\/li>\n
  13. Wang J. The Effectiveness of Data Augmentation in Image Classification using Deep Learning \/ J. Wang, L. Perez \/\/ arXiv. \u2013 2017. \u2013 arXiv:1712.04621.<\/li>\n<\/ol>\n

     <\/p>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[1,74],"tags":[],"_links":{"self":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/15414"}],"collection":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=15414"}],"version-history":[{"count":4,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/15414\/revisions"}],"predecessor-version":[{"id":15982,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/15414\/revisions\/15982"}],"wp:attachment":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=15414"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=15414"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=15414"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}