TY  - JOUR
TI  - Automated Classification of Brain Tumors by Deep Learning- Based Models on Magnetic Resonance Images Using a DevelopedWeb-Based Interface
AB  - Objective: Primary central nervous system tumors (PCNSTs)compose nearly 3% of newlydiagnosed cancers worldwide and are more common in men. The incidence of brain tumors andPCNSTs-related deaths are gradually increasing all over the world. Recently, many studies havefocused on automated machine learning (AutoML) algorithms which are developed using deeplearning algorithms on medical imaging applications. The main purposes of this study are -todemonstrate the use of artificial intelligence-based techniques to predict medical images ofdifferent brain tumors (glioma, meningioma, pituitary adenoma) to provide techicalsupport toradiologists and -to develop a user-friendly and free web-based software to classify brain tumorsfor making quick and accurate clinical decisions.Methods: Open-sourced T1-weighted magnetic resonance brain tumor images were achieved fromNanfang Hospital, Guangzhou, China, and General Hospital, Tianjin Medical University,Toconstruct the proposed system which web-based interface and the deep learning-based models, theKeras/Auto-Keras library, which is employed in Python's programming language, is used.Accuracy, sensitivity, specificity, G-mean, F-score, and Matthews correlation coefficient metricswere used for performance evaluations.Results: While 80% (2599 instances) of the dataset was used in the training phase, 20% (465instances) was employed in the testing phase. All the performance metrics were higher than 98%for the classification of brain tumors on the training data set. Similarly, all the evaluation metricswere higher than 91% except for sensitivity and MCC for meningioma on the testing dataset.Conclusions: The results from the experiment reveal that the proposed software can be used todetect and diagnose three types of brain tumors. This developed web-based software can beaccessed freely in both English and Turkish at http://biostatapps.inonu.edu.tr/BTSY/.
AU  - YAŞAR, Şeyma
AU  - ÇOLAK, Cemil
AU  - TETİK, Bora
AU  - Ucuzal, Hasan
DO  - 10.18521/ktd.889777
PY  - 2021
JO  - KONURALP TIP DERGİSİ
VL  - 13
IS  - 2
SN  - 1309-3878
SP  - 192
EP  - 200
DB  - TRDizin
UR  - http://search/yayin/detay/466962
ER  -