Brain tumor classification using deep CNN features via transfer learning

By S. Deepak, P. M. Ameer. Comput. Biol. Medicine, 2019

1,106 citations recorded by the source corpus.

Brain tumor classification is an important problem in computer-aided diagnosis (CAD) for medical applications. This paper focuses on a 3-class classification problem to differentiate among glioma, meningioma and pituitary tumors, which form three prominent types of brain tumor. The proposed classification system adopts the concept of deep transfer learning and uses a pre-trained GoogLeNet to extract features from brain MRI images. Proven classifier models are integrated to classify the extracted features. The experiment follows a patient-level five-fold cross-validation process, on MRI dataset from figshare. The proposed system records a mean classification accuracy of 98%, outperforming all state-of-the-art methods. Other performance measures used in the study are the area under the curve (AUC), precision, recall, F-score and specificity. In addition, the paper addresses a practical aspect by evaluating the system with fewer training samples. The observations of the study imply that transfer learning is a useful technique when the availability of medical images is limited. The paper provides an analytical discussion on misclassifications also.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Neurology

View Paper: https://www.semanticscholar.org/paper/ec5673aef99a6d5c31a757846af4eef5e8d7766f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Neurology

Citations in the corpus

MRI-Based Brain Tumor Classification Using Ensemble of Deep Features and Machine Learning Classifiers (2021, methodology): “In recent years, several studies proposed deep-learning-based feature extraction methods for MRI-based brain tumor classification using pre-trained deep CNN models: ResNet-50 [69,70], ResNet-101 [71], DenseNet-121 [70,72], VGG-16 [69,70], VGG-19 [70,73], AlexNet [74], Inception V1 (GoogLeNet) [29], ”
A Review of Deep Transfer Learning and Recent Advancements (2022, methodology): “[21, 22, 23, 24, 25] are successful examples of using this method.”
Deep Transfer Learning Approaches in Performance Analysis of Brain Tumor Classification Using MRI Images (2022, background): “During image data acquisition, a variety of scanners would be used for scanning the images at different timeperiod, which may result in large variations in pixel intensity [25, 26].”
A Deep Learning Model Based on Concatenation Approach for the Diagnosis of Brain Tumor (2020, methodology): “, [6] also adopted the concept of deep transfer for classification of images and employed the same data source discussed in [5].”
Brain tumor detection and classification using machine learning: a comprehensive survey (2021, background): “[249] 2019 GoogLeNet 233 MRI patient’s data 98% ACC”
A scoping review of transfer learning research on medical image analysis using ImageNet (2020, neutral): “M o d el C a te g o ry Inception [27,39–46] [47–51] [52,53] [54–59] [60,61] [62–65] [66] [67] VGGNet [68–73] [74–76] [77–81] [82–84] [85–87] [88] [89– 91] [92– 94] ResNet [95–97] [98– 101] [102– 105] [106] [107–109] [110,111] [112] [113]”
Multimodal Brain Tumor Classification Using Deep Learning and Robust Feature Selection: A Machine Learning Application for Radiologists (2020, methodology): “A brain tumor is an abnormal growth of brain cells in an uncontrollable way [1,2].”