Real-time system for biological cell tracking
Jazyk: | ruština |
---|---|
Rok vydání: | 2022 |
Předmět: |
в Ñежиме ÑеалÑного вÑемени
ÑегменÑаÑÐ¸Ñ ÑÑеек оÑÑлеживание ÑÑеек cell tracking classic cell segmentation algorithm клаÑÑиÑеÑкий алгоÑиÑм ÑегменÑаÑии ÑÑеек ÐбÑабоÑка изобÑажений real-time cell segmentation ÐзобÑÐ°Ð¶ÐµÐ½Ð¸Ñ |
DOI: | 10.18720/spbpu/3/2022/vr/vr22-4102 |
Popis: | Тема вÑпÑÑÐºÐ½Ð¾Ð¸Ì ÐºÐ²Ð°Ð»Ð¸ÑикаÑÐ¸Ð¾Ð½Ð½Ð¾Ð¸Ì ÑабоÑÑ: «СиÑÑема оÑÑÐ»ÐµÐ¶Ð¸Ð²Ð°Ð½Ð¸Ñ Ð±Ð¸Ð¾Ð»Ð¾Ð³Ð¸ÑеÑÐºÐ¸Ñ ÐºÐ»ÐµÑок в Ñежиме ÑеалÑного вÑемени». Ð Ð´Ð°Ð½Ð½Ð¾Ð¸Ì ÑабоÑе ÑаÑÑмаÑÑиваеÑÑÑ Ð¿ÑÐµÐ´Ð»Ð¾Ð¶ÐµÐ½Ð½Ð°Ñ ÑлÑÑÑеннаÑ U-ÑеÑÑ Ð¸ комбиниÑÑеÑÑÑ ÑегÑеÑÑÐ¸Ñ Ð¾Ð³ÑаниÑиÑелÑÐ½Ð¾Ð¸Ì Ñамки Ð´Ð»Ñ ÑеÑÐµÐ½Ð¸Ñ Ð·Ð°Ð´Ð°Ñи оÑÑÐ»ÐµÐ¶Ð¸Ð²Ð°Ð½Ð¸Ñ ÑÑеек. Ð¢ÐµÑ Ð½Ð¾Ð»Ð¾Ð³Ð¸Ñ Ð¾Ð±ÑабоÑки медиÑинÑÐºÐ¸Ñ Ð¸Ð·Ð¾Ð±ÑÐ°Ð¶ÐµÐ½Ð¸Ð¸Ì Ð¸ÑполÑзÑеÑÑÑ Ð´Ð»Ñ Ð°Ð½Ð°Ð»Ð¸Ð·Ð° и обÑабоÑки изобÑаженииÌ, опÑÐµÐ´ÐµÐ»ÐµÐ½Ð¸Ñ Ð¿Ð¾Ð»Ð¾Ð¶ÐµÐ½Ð¸Ñ, ÑегменÑаÑии и извлеÑÐµÐ½Ð¸Ñ Ð¼ÑÐ³ÐºÐ¸Ñ ÑÐºÐ°Ð½ÐµÐ¸Ì Ð¸ болÑного Ñела и доÑÑÐ¸Ð¶ÐµÐ½Ð¸Ñ Ð¾ÑноÑиÑелÑно Ñ Ð¾ÑоÑÐ¸Ñ ÑезÑлÑÑаÑов. ÐÑÑем ÑегменÑаÑии и оÑÑÐ»ÐµÐ¶Ð¸Ð²Ð°Ð½Ð¸Ñ Ð¸Ð·Ð¾Ð±ÑÐ°Ð¶ÐµÐ½Ð¸Ð¸Ì Ð¼ÐµÐ´Ð¸ÑинÑÐºÐ¸Ñ ÐºÐ»ÐµÑок можно ÑÑÑекÑивно ÑеÑиÑÑ Ð½ÐµÐºÐ¾ÑоÑÑе медиÑинÑкие пÑоблемÑ. ÐоÑÑÐ¾Ð¼Ñ Ð¼Ñ Ð¿Ñедлагаем ÑлÑÑÑеннÑÑ Ð¼Ð¾Ð´ÐµÐ»Ñ Ð½ÐµÐ¸ÌÑÐ¾Ð½Ð½Ð¾Ð¸Ì ÑеÑи, оÑнованнÑÑ Ð½Ð° ÑÑадиÑÐ¸Ð¾Ð½Ð½Ð¾Ð¸Ì ÑÑÑÑкÑÑÑе U-ÑеÑи в ÑоÑеÑании Ñ ÑегÑеÑÑÐ¸ÐµÐ¸Ì Ð¾Ð³ÑаниÑиваÑÑÐµÐ¸Ì Ñамки,Â Ð´Ð»Ñ Ð´Ð¾ÑÑÐ¸Ð¶ÐµÐ½Ð¸Ñ Ð¾ÑÑÐ»ÐµÐ¶Ð¸Ð²Ð°Ð½Ð¸Ñ ÑÑеек в ÑеалÑном вÑемени. ÐкÑпеÑименÑалÑнÑе ÑезÑлÑÑаÑÑ Ð¿Ð¾ÐºÐ°Ð·ÑваÑÑ, ÑÑо по ÑÑÐ°Ð²Ð½ÐµÐ½Ð¸Ñ Ñ ÑÑадиÑионнÑм алгоÑиÑмом ÑегменÑаÑии ÑÑеек алгоÑиÑм, пÑедложеннÑÐ¸Ì Ð² ÑÑа бÑмага Ð¸Ð¼ÐµÐµÑ Ð±Ð¾Ð»ÐµÐµ вÑÑокÑÑ ÑоÑноÑÑÑ Ð¸ менÑÑие поÑеÑи. ТоÑноÑÑÑ Ð¼Ð¾Ð´ÐµÐ»Ð¸, пÑÐµÐ´Ð»Ð¾Ð¶ÐµÐ½Ð½Ð¾Ð¸Ì Ð² ÑÑÐ¾Ð¸Ì ÑÑаÑÑе,Â Ð¼Ð¾Ð¶ÐµÑ Ð´Ð¾ÑÑигаÑÑ 98,46%, а поÑеÑи могÑÑ ÑоÑÑавлÑÑÑ Ð²Ñего 2,8%. РезÑлÑÑаÑÑ ÑÑÐ¾Ð¸Ì Ð´Ð¸ÑÑеÑÑаÑии могÑÑ Ð¿Ð¾Ð¼Ð¾ÑÑ Ð¿ÑоÑеÑÑиÑоваÑÑ Ð¼ÐµÐ»ÐºÐ¾Ð¼Ð°ÑÑÑабнÑе клеÑоÑнÑе модели. ÐбеÑпеÑиÑÑ Ð¾ÑÐ½Ð¾Ð²Ñ Ð¼ÐµÑода Ð´Ð»Ñ Ð¸Ð½ÑеллекÑÑалÑÐ½Ð¾Ð¸Ì ÑиÑÑÐµÐ¼Ñ Ð¼ÐµÐ´Ð¸ÑинÑÐºÐ¾Ð¸Ì Ð´Ð¸Ð°Ð³Ð½Ð¾ÑÑики на оÑнове по глÑÐ±Ð¾ÐºÐ¾Ð¼Ñ Ð¾Ð±ÑÑениÑ. The subject of the graduate qualification work is âreal-time system for biological cell trackingâ. The given work addresses the proposed an improved U-net and combinethe bounding box regression to achieve cell tracking task. Medical image processing technology is used to analyze and process images, realize the position detection, segmentation and extraction of soft tissue and diseased body, and achieve relatively good results. By segmenting and track- ing medical cell images, some medical problems can be effectively solved. Therefore, we propose an improved neural network model based on the traditional U-net structure, combined with bounding box regression, to achieve realtime cell tracking. The experimental results show that, compared with the traditional cell segmentation algorithm, the algorithm proposed in this paper has higher accuracy and lower loss. The accuracy of the model proposed in this paper can reach 98.46%, and the loss can be as low as 2.8%.The results of this thesis can help to test smallscale cellular models. Provide a method basis for intel- ligent medical diagnosis system based on deep learning. |
Databáze: | OpenAIRE |
Externí odkaz: |