Parotis bezi tümörlerinin ayırıcı tanısında multiparametrik manyetik rezonans görüntüleme kullanılarak geliştirilen derin öğrenme modeli
Küçük Resim Yok
Tarih
2021
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
İnönü Üniversitesi
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Amaç: Sık görülen parotis tümörlerinin ayırıcı tanısında, multiparametrik MRG kullanılarak geliştirilen derin öğrenme modeliyle yapay zeka bazlı yeni bir yaklaşım oluşturmak. Gereç ve Yöntem: Parotis bezinde tümör bulunan 123 hasta ile tümör bulunmayan 50 hastanın MRG görüntüleri retrospektif olarak incelendi. Bu görüntülerle eğitilen InceptionResNetV2 derin öğrenme modeli ve majority voting yaklaşımıyla parotis tümörleri sınıflandırıldı. Modelin ayırıcı tanı performansı SVM, KNN ve LD sınıflandırıcıları kullanılarak değerlendirildi. Derin öğrenme modelinde giriş verisi olarak; post-kontrast T1A, T2A konvansiyonel MRG sekansları ve b0, b1000 ve ADC difüzyon ağırlıklı sekanslar kullanıldı. Çalışma üç evrede gerçekleştirildi. I. evrede kontrol grubu (KG), pleomorfik adenom (PMA), Warthin tümörü (WT), malign tümör (MT) ayırıcı tanısı yapıldı ve MRG sekanslarının giriş verisinde kombine ve non-kombine olarak verildiği iki yaklaşım oluşturuldu. II. evrede benign tümör (PMA ve WT), MT ve KG'nin ayırıcı tanısı yapıldı. III. evrede ise, parotis bezinde tümör bulunan ve bulunmayan hastaların ayırıcı tanısının yapılması amaçlandı. Bulgular: Evre I'de non-kombine yaklaşımda doğruluk, sensivite ve spesifitenin sırasıyla %86,43, %83,24 ve %95,35; kombine yaklaşımdaysa sırasıyla %92,86, %90,34 ve %97,51 olduğu saptandı. Evre I'de sınıflandırıcılar arasında en iyi sonuca %93,57 doğrulukla SVM sınıflandırıcısı sahipti. Evre II'de doğruluk %92,14, sensivite %83,33 ve spesifite %93,99 olarak saptandı. Evre III'deyse doğruluk %99,29, sensivite %100 ve spesifite %99.02 olarak hesaplandı. Derin öğrenme modelinin PMA ayırıcı tanısı için doğruluğu %97,62, WT için %92,31 ve MT için %71,43 olarak saptandı. Sonuç ve Öneriler: Bu çalışmada son yıllarda popüler hale gelen derin öğrenme modelleriyle parotis tümörlerini otomatik ve yüksek doğrulukla sınıflandıran yeni bir yaklaşım sunulmuş ve istatistiksel olarak başarılı sonuçlar elde edilmiştir. Bu model hekimlere, parotis kitlelerinin MRG görüntülerini değerlendirmelerinde kolaylık sağlayacaktır. Anahtar Kelimeler: Yapay Zeka, Derin Öğrenme, Parotis Tümörleri, Bilgisayar Destekli Tanı
Aim: To create a new artificial intelligence-based approach by developing a deep learning model using multiparametric MRI in the differential diagnosis of common parotid tumors. Material and Methods: MRI images of 123 patients diagnosed with parotid tumors and 50 patients without parotid tumors were analyzed retrospectively. With these images, parotid tumors were classified using the InceptionResNetV2 deep learning (DL) model and majority voting approach. The differential diagnostic performance of the model was evaluated using SVM, KNN, and LD classifiers. As input data in the DL model, post-contrast T1A, T2A conventional MRI sequences, and b0, b1000, and ADC diffusion-weighted sequences were used. The study was conducted in three stages. In Stage I, the differential diagnosis of control group (CG), pleomorphic adenoma (PMA), Warthin tumor (WT), malignant tumor (MT) was examined and there were two approaches in which MRI sequences were given as combined and non-combined in the input data. In Stage II; differential diagnosis of the benign tumor (PMA and WT), MT, and CG was made. In Stage III, it was aimed to make the differential diagnosis of patients with a tumor in the parotid gland and healthy parotid gland tissue. Results: In Stage I, the accuracy, sensitivity, and specificity in the non-combined approach were 86,43%, 83,24%, and 95,35%; in the combined approach, it was found to be 92,86%, 90,34%, and 97,51%, respectively. In Stage I, the SVM classifier had the best result among the classifiers with an accuracy of 93,57%. In Stage II, the accuracy was 92,14%, the sensitivity was 83,33% and the specificity was 93,99%. In Stage III, the accuracy was 99,29%, the sensitivity was 100%, and the specificity was 99,02%. The accuracy of the DL model for differential diagnosis of PMA was calculated 97,62%, WT 92,31%, and MT 71,43%. Conclusions: In this study, a new approach is presented that classifies common parotid tumors automatically and with high accuracy using DL models that have become popular in recent years, and statistically successful results have been obtained. This model will provide convenience for physicians in evaluating MRI images of parotid masses. Keywords: Artificial Intelligence, Deep Learning, Parotid Tumors, Computer Aided Diagnosis
Aim: To create a new artificial intelligence-based approach by developing a deep learning model using multiparametric MRI in the differential diagnosis of common parotid tumors. Material and Methods: MRI images of 123 patients diagnosed with parotid tumors and 50 patients without parotid tumors were analyzed retrospectively. With these images, parotid tumors were classified using the InceptionResNetV2 deep learning (DL) model and majority voting approach. The differential diagnostic performance of the model was evaluated using SVM, KNN, and LD classifiers. As input data in the DL model, post-contrast T1A, T2A conventional MRI sequences, and b0, b1000, and ADC diffusion-weighted sequences were used. The study was conducted in three stages. In Stage I, the differential diagnosis of control group (CG), pleomorphic adenoma (PMA), Warthin tumor (WT), malignant tumor (MT) was examined and there were two approaches in which MRI sequences were given as combined and non-combined in the input data. In Stage II; differential diagnosis of the benign tumor (PMA and WT), MT, and CG was made. In Stage III, it was aimed to make the differential diagnosis of patients with a tumor in the parotid gland and healthy parotid gland tissue. Results: In Stage I, the accuracy, sensitivity, and specificity in the non-combined approach were 86,43%, 83,24%, and 95,35%; in the combined approach, it was found to be 92,86%, 90,34%, and 97,51%, respectively. In Stage I, the SVM classifier had the best result among the classifiers with an accuracy of 93,57%. In Stage II, the accuracy was 92,14%, the sensitivity was 83,33% and the specificity was 93,99%. In Stage III, the accuracy was 99,29%, the sensitivity was 100%, and the specificity was 99,02%. The accuracy of the DL model for differential diagnosis of PMA was calculated 97,62%, WT 92,31%, and MT 71,43%. Conclusions: In this study, a new approach is presented that classifies common parotid tumors automatically and with high accuracy using DL models that have become popular in recent years, and statistically successful results have been obtained. This model will provide convenience for physicians in evaluating MRI images of parotid masses. Keywords: Artificial Intelligence, Deep Learning, Parotid Tumors, Computer Aided Diagnosis
Açıklama
Anahtar Kelimeler
Kulak Burun ve Boğaz, Otorhinolaryngology (Ear-Nose-Throat)
