A Review on Brain Tumor Diagnosis from MRI Images : Practical Implications, Key Achievements, and Lessons Learned

Deep Learning (DL) algorithms enabled computational models consist of multiple processing layers that represent data with multiple levels of abstraction. In recent years, usage of deep learning is rapidly proliferating in almost every domain, especially in medical image processing, medical image analysis, and bioinformatics. Consequently, deep learning has dramatically changed and improved the means of recognition, prediction, and diagnosis effectively in numerous areas of healthcare such as pathology, brain tumor, lung cancer, abdomen, cardiac, and retina. Considering the wide range of applications of deep learning, the objective of this article is to review major deep learning concepts pertinent to brain tumor analysis (e.g., segmentation, classification, prediction, evaluation.). A review conducted by summarizing a large number of scientific contributions to the field (i.e., deep learning in brain tumor analysis) is presented in this study. A coherent taxonomy of research landscape from the literature has also been mapped, and the major aspects of this emerging field have been discussed and analyzed. A critical discussion section to show the limitations of deep learning techniques has been included at the end to elaborate open research challenges and directions for future work in this emergent area.

Brain Tumor Analysis Empowered with Deep Learning: A Review, Taxonomy, and Future Challenges.

Automated detection of brain tumor is a more challenging work due to the variability and complexity of shape, size, texture and location of lesions. The non-invasive MRI methods appear as a front line brain tumor detection tools (without ionization radiation). In this manuscript, an unsupervised clustering approach for tumor segmentation is proposed. Moreover, a fused feature vector is used which is a mixture of Gabor wavelet features (GWF), histograms of oriented gradient (HOG), local binary pattern (LBP) and segmentation based fractal texture analysis (SFTA) features. Random forest (RF) classifier is applied for classification between three sub tumoral regions such as complete, enhancing and non-enhancing tumor. To avoid over fitting problem, fivefold and 0.5 holdout cross-validation approaches are used. The promising detection efficiency depicts the dominance of proposed approach.

Detection of Brain Tumor based on Features Fusion and Machine Learning

Purpose. In this study, we proposed an automated deep learning (DL) method for head and neck cancer (HNC) gross tumor volume (GTV) contouring on positron emission tomography-computed tomography (PET-CT) images. Materials and Methods. PET-CT images were collected from 22 newly diagnosed HNC patients, of whom 17 (Database 1) and 5 (Database 2) were from two centers, respectively. An oncologist and a radiologist decided the gold standard of GTV manually by consensus. We developed a deep convolutional neural network (DCNN) and trained the network based on the two-dimensional PET-CT images and the gold standard of GTV in the training dataset. We did two experiments: Experiment 1, with Database 1 only, and Experiment 2, with both Databases 1 and 2. In both Experiment 1 and Experiment 2, we evaluated the proposed method using a leave-one-out cross-validation strategy. We compared the median results in Experiment 2 (GTVa) with the performance of other methods in the literature and with the gold standard (GTVm). Results. A tumor segmentation task for a patient on coregistered PET-CT images took less than one minute. The dice similarity coefficient (DSC) of the proposed method in Experiment 1 and Experiment 2 was 0.481∼0.872 and 0.482∼0.868, respectively. The DSC of GTVa was better than that in previous studies. A high correlation was found between GTVa and GTVm (R = 0.99, ). The median volume difference (%) between GTVm and GTVa was 10.9%. The median values of DSC, sensitivity, and precision of GTVa were 0.785, 0.764, and 0.789, respectively. Conclusion. A fully automatic GTV contouring method for HNC based on DCNN and PET-CT from dual centers has been successfully proposed with high accuracy and efficiency. Our proposed method is of help to the clinicians in HNC management.

/pdf/fully-automated-delineation-of-gross-tumor-volume-for-head-32jusi1yal.pdf

Fully Automated Delineation of Gross Tumor Volume for Head and Neck Cancer on PET-CT Using Deep Learning: A Dual-Center Study

Automatic modulation classification of digital modulation signals with stacked autoencoders

Accurate tumor segmentation is an essential and crucial step for computer-aided brain tumor diagnosis and surgical planning. Subjective segmentations are widely adopted in clinical diagnosis and treating, but they are neither accurate nor reliable. An automatical and objective system for brain tumor segmentation is strongly expected. But they are still facing some challenges such as lower segmentation accuracy, demanding a priori knowledge or requiring the human intervention. In this paper, a novel and new coarse-to-fine method is proposed to segment the brain tumor. This hierarchical framework consists of preprocessing, deep learning network based classification and post-processing. The preprocessing is used to extract image patches for each MR image and obtains the gray level sequences of image patches as the input of the deep learning network. The deep learning network based classification is implemented by a stacked auto-encoder network to extract the high level abstract feature from the input, and utilizes the extracted feature to classify image patches. After mapping the classification result to a binary image, the post-processing is implemented by a morphological filter to get the final segmentation result. In order to evaluate the proposed method, the experiment was applied to segment the brain tumor for the real patient dataset. The final performance shows that the proposed brain tumor segmentation method is more accurate and efficient.

A deep learning-based segmentation method for brain tumor in MR images

Accurate tumor segmentation has the ability to provide doctors with a basis for surgical planning. Moreover, brain tumor segmentation needs to extract different tumor tissues (Edema, tumor, tumor enhancement, and necrosis) from normal tissues which is a big challenge because tumor structures vary considerably across patients in terms of size, extension, and localization. In this article, we evaluate a fully automated method for segmenting brain tumor images from multi‐modal magnetic resonance imaging volumes based on stacked de‐noising auto‐encoders (SDAEs). Specially, we adopted multi‐modality information from T1, T1c, T2, and Flair images, respectively. We extracted gray level patches from different modalities as the input of the SDAE. After trained by the SDAE, the raw network parameters will be obtained, which are adopted as a parameter of the feed forward neural network for classification. A simple post‐processing is implemented by threshold segmentation method to generate a mask to get the final segmentation result. By evaluating the proposed method on the BRATS 2015, it can be proven that our method obtains the better performance than other state‐of‐the‐art counterpart methods. And a preliminary dice score of 0.86 for whole tumor segmentation has been achieved.

Multi-modal brain tumor image segmentation based on SDAE

In the invention, through an improved threshold segmentation algorithm, segmentation of a grey matter and a white matter of a brain image is realized, which is good for auxiliary diagnosis of brain atrophy of a patient. The method is characterized by firstly, using an adaptive filter to process an original image, reducing a noise of the original image and enhancing a contrast ratio of the image; then, for the processed image, using a region growing algorithm to carry out brain decollement on the image, rejecting a non-parenchymal portion; and then using an iterative threshold method to calculate a threshold and using a near weighted value algorithm to carry out binarization segmentation on the image so that an obtained result is a segmentation result of a brain white matter; finally, based on a result of the previous step, carrying out segmentation so that the obtained result is a segmentation result of a brain grey matter.

RongFeng Dong

Papers

A deep learning-based segmentation method for brain tumor in MR images

Multi-modal brain tumor image segmentation based on SDAE

Brain parenchyma segmentation realization based on improved threshold segmentation algorithm

A deep learning-based segmentation method for brain tumor in MR images