ﺑﺎزﯾﺎﺑﯽ ﺗﺼﺎوﯾﺮ ﭘﺰﺷﮑﯽ رﯾﻪ ﺑﺎ اﺳﺘﻔﺎده از درﻫﻢ ﺳﺎزی ﺑﺎ ﻧﺎﻇﺮ، اﻧﺘﺨﺎب وﯾﮋﮔﯽ mrmr و ﺷﺒﮑﻪﻫﺎی ﻋﺼﺒﯽ ﮐﺎﻧﻮﻟﻮﺷﻨﯽ ﻋﻤﯿﻖ

ﺗﻮﺳﻌﻪ ﭘﺰﺷﮑﯽ ﻧﻮﯾﻦ از ﯾﮏ ﻃﺮف اﻣﮑﺎن ذﺧﯿﺮهﺳﺎزی ﺗﺼﺎوﯾﺮ ﭘﺰﺷﮑﯽ را ﻓﺮاﻫﻢ ﮐﺮده اﺳﺖ و از ﻃﺮف دﯾﮕﺮ ﺑﺪﻟﯿﻞ اﻓﺰاﯾﺶ روزاﻧﻪ ذﺧﯿﺮهﺳﺎزی اﯾﻦ ﻗﺒﯿﻞ داده، ﻣﺪﯾﺮﯾﺖ و ﺑﺎزﯾﺎﺑﯽ آنﻫﺎ را ﻧﯿﺰ ﺑﺎ ﻣﺸﮑﻞ ﻣﻮاﺟﻪ ﺳﺎﺧﺘﻪ اﺳﺖ. ﺑﺎ ﺗﻮﺟﻪ ﺑﻪ آﻧﮑﻪ ﺗﺼﺎوﯾﺮ ﭘﺰﺷﮑﯽ ﺑﻪ ﻋﻨﻮان اﺑﺰاری ﻗﺪرﺗﻤﻨﺪ در ﺗﺸﺨﯿﺺ زودرس اﻏﻠﺐ ﺑﯿﻤﺎریﻫﺎ ﻣﻮرد اﺳﺘﻔﺎده ﻫﺴﺘﻨﺪ، اراﺋﻪ ﺳﯿﺴﺘﻤﯽ ﺗﻮاﻧﻤﻨﺪ ﮐﻪ ﺑﺘﻮاﻧﺪ از ﺣﺠﻢ رو ﺑﻪ رﺷﺪ ﺗﺼﺎوﯾﺮ ﭘﺰﺷﮑﯽ، ﺗﺼﺎوﯾﺮی ﺑﺎ ﻣﺤﺘﻮای ﻣﺸﺎﺑﻪ را ﺑﺎزﯾﺎﺑﯽ ﻧﻤﺎﯾﺪ، در ﮐﻨﺘﺮل و درﻣﺎن ﺑﺴﯿﺎر ﻣﻮﺛﺮ اﺳﺖ. در اﯾﻦ ﻣﻘﺎﻟﻪ ﯾﮏ ﺳﯿﺴﺘﻢ ﺑﺎزﯾﺎﺑﯽ ﺗﺼﺎوﯾﺮ ﭘﺰﺷﮑﯽ ﻣﺒﺘﻨﯽ ﺑﺮ ﺷﺒﮑﻪ ﻋﺼﺒﯽ ﺳﯿﺎﻣﯽ ﻣﺘﺸﮑﻞ از دو زﯾﺮ ﺷﺒﮑﻪ ﮐﺎﻧﻮﻟﻮﺷﻦ ﺑﺎ 13 ﻻﯾﻪ اراﺋﻪ ﺷﺪه اﺳﺖ. ﺑﺮای رﺳﯿﺪن ﺑﻪ زﯾﺮ ﻣﺠﻤﻮﻋﻪ ﺑﻬﯿﻨﻪ از وﯾﮋﮔﯽﻫﺎی ﻋﻤﯿﻖ اﺳﺘﺨﺮاج ﺷﺪه ﺗﻮﺳﻂ ﺳﯿﺎﻣﯽ، از ﺗﮑﻨﯿﮏ ﺣﺪاﻗﻞ اﻓﺰوﻧﮕﯽ- ﺣﺪاﮐﺜﺮ ﻫﻤﺒﺴﺘﮕﯽ mrmr اﺳﺘﻔﺎده ﺷﺪه اﺳﺖ و ﭘﺲ از درﻫﻢﺳﺎزی ﺑﺎﯾﻨﺮی وﯾﮋﮔﯽﻫﺎ، ﺑﺎزﯾﺎﺑﯽ ﺗﺼﺎوﯾﺮ ﻣﺸﺎﺑﻪ ﺑﺎ اﺳﺘﻔﺎده از ﻓﺎﺻﻠﻪ hamming اﻧﺠﺎم ﻣﯽﺷﻮد. اﮔﺮ ﭼﻪ ﻣﺪل ﻣﻄﺮح ﻗﺎﺑﻠﯿﺖ ﺑﺎزﯾﺎﺑﯽ اﻧﻮاع ﺗﺼﺎوﯾﺮ ﭘﺰﺷﮑﯽ ﺳﻄﺢ ﺧﺎﮐﺴﺘﺮی را دارد، اﻣﺎ ﺑﺮای ارزﯾﺎﺑﯽ آن، از دو ﻧﻮع ﺗﺼﺎوﯾﺮ رﯾﻪ، ﺷﺎﻣﻞ ﺗﺼﺎوﯾﺮ ﺳﯽﺗﯽ اﺳﮑﻦ ﺑﯿﻤﺎران ﮐﻮوﯾﺪ-19 در ﭘﺎﯾﮕﺎه داده ct-cov و ﺗﺼﺎوﯾﺮ اﺷﻌﻪ x ﺑﯿﻤﺎران ذاتاﻟﺮﯾﻪ در ﭘﺎﯾﮕﺎه pneumonia اﺳﺘﻔﺎده ﺷﺪه اﺳﺖ. ﻧﺘﺎﯾﺞ ﺣﺎﮐﯽ از آن اﺳﺖ ﮐﻪ روش ﭘﯿﺸﻨﻬﺎد ﺷﺪه در ﭘﺎﯾﮕﺎه ﮐﻮوﯾﺪ ﺑﻪ ﺗﺮﺗﯿﺐ در 5 و 10 ﺗﺼﻮﯾﺮ ﺑﺎزﯾﺎﺑﯽ ﺗﻮاﻧﺴﺘﻪ اﺳﺖ ﺑﻪ ﻣﯿﺎﻧﮕﯿﻦ دﻗﺖ 93.83% و 92.73% و در ﭘﺎﯾﮕﺎه داده ذاتاﻟﺮﯾﻪ ﺑﻪ ﻣﯿﺎﻧﮕﯿﻦ دﻗﺖ 100% دﺳﺖ ﯾﺎﺑﺪ ﮐﻪ در ﻣﻘﺎﯾﺴﻪ ﺑﺎ روشﻫﺎی ﭘﯿﺸﯿﻦ ﺗﻮاﻧﺴﺘﻪ اﺳﺖ ﺑﺎزﯾﺎﺑﯽ ﺗﺼﺎوﯾﺮ رﯾﻪ را ﺑﻬﺒﻮد ﺑﺒﺨﺸﺪ.

lung image retrieval based on supervised hashing, mrmr feature selection and deep convolutional neural network

on the one hand, the development of modern medicine has made it possible to store medical images, and on the other hand, due to the daily increase in the storage of such data, it has also made their management and recovery difficult. considering that medical images are used as a powerful tool in the early diagnosis of most diseases, providing a powerful system that can retrieve images with similar content from the growing volume of medical images is very effective in control and treatment. in this article, a medical image retrieval system based on siamese neural network consisting of two convolutional sub-networks with 13 layers is presented. to reach the optimal subset of deep features extracted by siamese, the minimum redundancy-maximum relevant mrmr technique has been used, and after binary hashing of the features, similar images are retrieved using hamming distance. although the proposed model is capable of retrieving a variety of gray scale medical images, two types of lung images have been used to evaluate it, including ct scan images of covid-19 patients in the ct-cov database and x-ray images of pneumonia patients in the pneumonia database. the results indicate that the proposed method in the covid database has been able to achieve an average precision of 93.83% and 92.73% in 5 and 10 retrieved images respectively, and an average precision of 100% in the pneumonia database, which is compared to previous methods have been able to improve the retrieval of lung images.