scholarly journals Deep Learning Methodology for Differentiating Glioma Recurrence From Radiation Necrosis Using Multimodal Magnetic Resonance Imaging: Algorithm Development and Validation (Preprint)

2020 ◽  
Author(s):  
Yang Gao ◽  
Xiong Xiao ◽  
Bangcheng Han ◽  
Guilin Li ◽  
Xiaolin Ning ◽  
...  
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Differential Diagnosis ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Tumor Recurrence ◽  
Radiation Necrosis ◽  
Resonance Imaging ◽  
Glioma Recurrence ◽  
Mri Scans

BACKGROUND The radiological differential diagnosis between tumor recurrence and radiation-induced necrosis (ie, pseudoprogression) is of paramount importance in the management of glioma patients. OBJECTIVE This research aims to develop a deep learning methodology for automated differentiation of tumor recurrence from radiation necrosis based on routine magnetic resonance imaging (MRI) scans. METHODS In this retrospective study, 146 patients who underwent radiation therapy after glioma resection and presented with suspected recurrent lesions at the follow-up MRI examination were selected for analysis. Routine MRI scans were acquired from each patient, including T1, T2, and gadolinium-contrast-enhanced T1 sequences. Of those cases, 96 (65.8%) were confirmed as glioma recurrence on postsurgical pathological examination, while 50 (34.2%) were diagnosed as necrosis. A light-weighted deep neural network (DNN) (ie, efficient radionecrosis neural network [ERN-Net]) was proposed to learn radiological features of gliomas and necrosis from MRI scans. Sensitivity, specificity, accuracy, and area under the curve (AUC) were used to evaluate performance of the model in both image-wise and subject-wise classifications. Preoperative diagnostic performance of the model was also compared to that of the state-of-the-art DNN models and five experienced neurosurgeons. RESULTS DNN models based on multimodal MRI outperformed single-modal models. ERN-Net achieved the highest AUC in both image-wise (0.915) and subject-wise (0.958) classification tasks. The evaluated DNN models achieved an average sensitivity of 0.947 (SD 0.033), specificity of 0.817 (SD 0.075), and accuracy of 0.903 (SD 0.026), which were significantly better than the tested neurosurgeons (<i>P</i>=.02 in sensitivity and <i>P</i>&lt;.001 in specificity and accuracy). CONCLUSIONS Deep learning offers a useful computational tool for the differential diagnosis between recurrent gliomas and necrosis. The proposed ERN-Net model, a simple and effective DNN model, achieved excellent performance on routine MRI scans and showed a high clinical applicability.

scholarly journals Deep Learning Methodology for Differentiating Glioma Recurrence From Radiation Necrosis Using Multimodal Magnetic Resonance Imaging: Algorithm Development and Validation

10.2196/19805 ◽  
2020 ◽  
Vol 8 (11) ◽  
pp. e19805
Author(s):  
Yang Gao ◽  
Xiong Xiao ◽  
Bangcheng Han ◽  
Guilin Li ◽  
Xiaolin Ning ◽  
...  
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Differential Diagnosis ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Tumor Recurrence ◽  
Radiation Necrosis ◽  
Resonance Imaging ◽  
Glioma Recurrence ◽  
Mri Scans

Background The radiological differential diagnosis between tumor recurrence and radiation-induced necrosis (ie, pseudoprogression) is of paramount importance in the management of glioma patients. Objective This research aims to develop a deep learning methodology for automated differentiation of tumor recurrence from radiation necrosis based on routine magnetic resonance imaging (MRI) scans. Methods In this retrospective study, 146 patients who underwent radiation therapy after glioma resection and presented with suspected recurrent lesions at the follow-up MRI examination were selected for analysis. Routine MRI scans were acquired from each patient, including T1, T2, and gadolinium-contrast-enhanced T1 sequences. Of those cases, 96 (65.8%) were confirmed as glioma recurrence on postsurgical pathological examination, while 50 (34.2%) were diagnosed as necrosis. A light-weighted deep neural network (DNN) (ie, efficient radionecrosis neural network [ERN-Net]) was proposed to learn radiological features of gliomas and necrosis from MRI scans. Sensitivity, specificity, accuracy, and area under the curve (AUC) were used to evaluate performance of the model in both image-wise and subject-wise classifications. Preoperative diagnostic performance of the model was also compared to that of the state-of-the-art DNN models and five experienced neurosurgeons. Results DNN models based on multimodal MRI outperformed single-modal models. ERN-Net achieved the highest AUC in both image-wise (0.915) and subject-wise (0.958) classification tasks. The evaluated DNN models achieved an average sensitivity of 0.947 (SD 0.033), specificity of 0.817 (SD 0.075), and accuracy of 0.903 (SD 0.026), which were significantly better than the tested neurosurgeons (P=.02 in sensitivity and P<.001 in specificity and accuracy). Conclusions Deep learning offers a useful computational tool for the differential diagnosis between recurrent gliomas and necrosis. The proposed ERN-Net model, a simple and effective DNN model, achieved excellent performance on routine MRI scans and showed a high clinical applicability.

scholarly journals Diagnosa Tumor Otak Berdasarkan Citra MRI (Magnetic Resonance Imaging)

2019 ◽  
Vol 18 (2) ◽  
Author(s):  
Ida Bagus Leo Mahadya Suta ◽  
Rukmi Sari Hartati ◽  
Yoga Divayana
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Convolutional Neural Network ◽  
Resonance Imaging ◽  
Magnetic Resonance Imaging Mri

Tumor otak menjadi salah satu penyakit yang paling mematikan, salah satu jenis yang paling banyak ditemukan adalah glioma sekitar 6 dari 100.000 pasien adalah penderita glioma. Citra digital melalui Magnetic Resonance Imaging (MRI) merupakan salah satu metode untuk membantu dokter dalam menganalisa dan mengklasifikasikan jenis tumor otak. Namun, klasifikasi secara manual membutuhkan waktu yang lama dan memiliki resiko kesalahan yang tinggi, untuk itu dibutuhkan suatu cara otomatis dan akurat dalam melakukan klasifikasi citra MRI. Convolutional Neural Network (CNN) menjadi salah satu solusi dalam melakukan klasifikasi otomatis dalam citra MRI. CNN merupakan algoritma deep learning yang memiliki kemampuan untuk belajar sendiri dari kasus kasus sebelumnya. Dan dari penelitian yang telah dilakukan, diperoleh hasil bahwa CNN mampu dalam menyelesaikan klasifikasi tumor otak dengan akurasi yang tinggi. Peningkatan akurasi diperoleh dengan mengembangkan algoritma CNN baik melalui menentukan nilai kernel dan/atau fungsi aktivasi.

scholarly journals Back Propagation Neural Network-Based Magnetic Resonance Imaging Image Features in Treating Intestinal Obstruction in Digestive Tract Diseases with Chengqi Decoction

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Yongfeng Li ◽  
Kaina Wang ◽  
Li Gao ◽  
Xiaojun Lu
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Intestinal Obstruction ◽  
Back Propagation ◽  
Block Size ◽  
Back Propagation Neural Network ◽  
Image Features ◽  
Resonance Imaging ◽  
Mri Scans

This study was to explore the adoption effect of magnetic resonance imaging (MRI) image features based on back propagation neural network (BPNN) in evaluating the curative effect of Chengqi Decoction (CD) for intestinal obstruction (ileus), so as to evaluate the clinical adoption value of this algorithm. Ninety patients with ileus were recruited, and the patients were treated with CD and underwent MRI scans of the lower abdomen. A BPNN model was fabricated and applied to segment the MRI images of patients and identify the lesion. As a result, when the overlap step was 16 and the block size was 32 × 32, the running time of the BPNN algorithm was the shortest. The segmentation accuracy was the highest if there were two hidden layer (HL) nodes, reaching 97.3%. The recognition rates of small intestinal stromal tumor (SIST), colon cancer, adhesive ileus, and volvulus of MRI images segmented by the algorithm were 91.5%, 88.33%, 90.3%, and 88.9%, respectively, which were greatly superior to those of manual interpretation ( P < 0.05 ). After the intervention of CD, the percentages of patients with ileus that were cured, markedly effective, effective, and ineffective were 65.38%, 23.16%, 5.38%, and 6.08%, respectively. The cure rate after intervention of CD (65.38%) was much higher in contrast to that before intervention (13.25%) ( P < 0.05 ). In short, CD showed a good therapeutic effect on ileus and can effectively improve the prognosis of patients. In addition, MRI images based on BPNN showed a good diagnostic effect on ileus, and it was worth applying to clinical diagnosis.

Magnetic Resonance-Guided Laser Ablation Improves Local Control for Postradiosurgery Recurrence and/or Radiation Necrosis

Neurosurgery ◽  
2014 ◽  
Vol 74 (6) ◽  
pp. 658-667 ◽  
Author(s):  
Malay S. Rao ◽  
Eric L. Hargreaves ◽  
Atif J. Khan ◽  
Bruce G. Haffty ◽  
Shabbar F. Danish
Keyword(s):  
Magnetic Resonance Imaging ◽  
Magnetic Resonance ◽  
Stereotactic Radiosurgery ◽  
Local Control ◽  
Tumor Recurrence ◽  
Radiation Necrosis ◽  
Karnofsky Performance Status ◽  
Target Range ◽  
Resonance Imaging

ABSTRACT BACKGROUND: Enhancing lesions that progress after stereotactic radiosurgery are often tumor recurrence or radiation necrosis. Magnetic resonance-guided laser-induced thermal therapy (LITT) is currently being explored for minimally invasive treatment of intracranial neoplasms. OBJECTIVE: To report the largest series to date of local control with LITT for the treatment of recurrent enhancing lesions after stereotactic radiosurgery for brain metastases. METHODS: Patients with recurrent metastatic intracranial tumors or radiation necrosis who had previously undergone radiosurgery and had a Karnofsky performance status of &gt;70 were eligible for LITT. Sixteen patients underwent a total of 17 procedures. The primary end point was local control using magnetic resonance imaging scans at intervals of &gt;4 weeks. Radiographic outcomes were followed up prospectively until death or local recurrence (defined as &gt;25% increase in volume compared with the 24-hour postprocedural scan). RESULTS: Fifteen patients (age, 46-82 years) were available for follow-up. Primary tumor histology was non–small-cell lung cancer (n = 12) and adenocarcinoma (n = 3). On average, the lesion size measured 3.66 cm3 (range, 0.46-25.45 cm3); there were 3.3 ablations per treatment (range, 2-6), with 7.73-cm depth to target (range, 5.5-14.1 cm), ablation dose of 9.85 W (range, 8.2-12.0 W), and total ablation time of 7.43 minutes (range, 2-15 minutes). At a median follow-up of 24 weeks (range, 4-84 weeks), local control was 75.8% (13 of 15 lesions), median progression-free survival was 37 weeks, and overall survival was 57% (8 of 14 patients). Two patients experience recurrence at 6 and 18 weeks after the procedure. Five patients died of extracranial disease progression; 1 patient died of neurological progression elsewhere in the brain. CONCLUSION: Magnetic resonance imaging-guided LITT is a well-tolerated procedure and may be effective in treating tumor recurrence/radiation necrosis.

scholarly journals Brain Tumor Classification using Deep Learning Algorithms

2021 ◽  
Vol 9 (12) ◽  
pp. 417-426
Author(s):  
Ankita Kadam
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Neural Networks ◽  
Deep Learning ◽  
Brain Tumor ◽  
Magnetic Resonance ◽  
Brain Tumors ◽  
Tumor Classification ◽  
Resonance Imaging ◽  
Magnetic Resonance Imaging Mri

Abstract: A Brain tumor is one aggressive disease. An estimated more than 84,000 people will receive a primary brain tumor diagnosis in 2021 and an estimated 18,600 people will die from a malignant brain tumor (brain cancer) in 2021.[8] The best technique to detect brain tumors is by using Magnetic Resonance Imaging (MRI). More than any other cancer, brain tumors can have lasting and life-altering physical, cognitive, and psychological impacts on a patient’s life and hence faster diagnosis and best treatment plan should be devised to improve the life expectancy and well-being of these patients. Neural networks have shown colossal accuracy in image classification and segmentation problems. In this paper, we propose comparative studies of various deep learning models based on different types of Neural Networks(ANN, CNN, TL) to firstly identify brain tumors and then classify them into Benign Tumor, Malignant Tumor or Pituitary Tumor. The data set used holds 3190 images on T1-weighted contrast-enhanced images which were cleaned and augmented. The best ANN model concluded with an accuracy of 78% and the best CNN model consisting of 3 convolution layers had an accuracy of 90%. The VGG16(retrained on the dataset) model surpasses other ANN, CNN, TL models for multi-class tumor classification. This proposed network achieves significantly better performance with a validation accuracy of 94% and an F1-Score of 91. Keywords: Artificial Neural Network(ANN), Convolution Neural Network (CNN), Transfer Learning(TL), Magnetic Resonance Imaging(MRI.)

scholarly journals Tumor Segmentation in Contrast-Enhanced Magnetic Resonance Imaging for Nasopharyngeal Carcinoma: Deep Learning with Convolutional Neural Network

2018 ◽  
Vol 2018 ◽  
pp. 1-7 ◽  
Author(s):  
Qiaoliang Li ◽  
Yuzhen Xu ◽  
Zhewei Chen ◽  
Dexiang Liu ◽  
Shi-Ting Feng ◽  
...  
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Nasopharyngeal Carcinoma ◽  
Convolutional Neural Network ◽  
Tumor Segmentation ◽  
Dice Similarity Coefficient ◽  
Resonance Imaging ◽  
Contrast Enhanced

Objectives. To evaluate the application of a deep learning architecture, based on the convolutional neural network (CNN) technique, to perform automatic tumor segmentation of magnetic resonance imaging (MRI) for nasopharyngeal carcinoma (NPC). Materials and Methods. In this prospective study, 87 MRI containing tumor regions were acquired from newly diagnosed NPC patients. These 87 MRI were augmented to >60,000 images. The proposed CNN network is composed of two phases: feature representation and scores map reconstruction. We designed a stepwise scheme to train our CNN network. To evaluate the performance of our method, we used case-by-case leave-one-out cross-validation (LOOCV). The ground truth of tumor contouring was acquired by the consensus of two experienced radiologists. Results. The mean values of dice similarity coefficient, percent match, and their corresponding ratio with our method were 0.89±0.05, 0.90±0.04, and 0.84±0.06, respectively, all of which were better than reported values in the similar studies. Conclusions. We successfully established a segmentation method for NPC based on deep learning in contrast-enhanced magnetic resonance imaging. Further clinical trials with dedicated algorithms are warranted.

scholarly journals Identification of Alzheimer's disease using a convolutional neural network model based on T1-weighted magnetic resonance imaging

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Jong Bin Bae ◽  
Subin Lee ◽  
Wonmo Jung ◽  
Sejin Park ◽  
Weonjin Kim ◽  
...  
Keyword(s):  
Neural Network ◽  
Magnetic Resonance Imaging ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Magnetic Resonance ◽  
Convolutional Neural Network ◽  
Medial Temporal Lobe ◽  
Processing Time ◽  
Resonance Imaging ◽  
Mri Scans

AbstractThe classification of Alzheimer’s disease (AD) using deep learning methods has shown promising results, but successful application in clinical settings requires a combination of high accuracy, short processing time, and generalizability to various populations. In this study, we developed a convolutional neural network (CNN)-based AD classification algorithm using magnetic resonance imaging (MRI) scans from AD patients and age/gender-matched cognitively normal controls from two populations that differ in ethnicity and education level. These populations come from the Seoul National University Bundang Hospital (SNUBH) and Alzheimer’s Disease Neuroimaging Initiative (ADNI). For each population, we trained CNNs on five subsets using coronal slices of T1-weighted images that cover the medial temporal lobe. We evaluated the models on validation subsets from both the same population (within-dataset validation) and other population (between-dataset validation). Our models achieved average areas under the curves of 0.91–0.94 for within-dataset validation and 0.88–0.89 for between-dataset validation. The mean processing time per person was 23–24 s. The within-dataset and between-dataset performances were comparable between the ADNI-derived and SNUBH-derived models. These results demonstrate the generalizability of our models to different patients with different ethnicities and education levels, as well as their potential for deployment as fast and accurate diagnostic support tools for AD.

Sign in / Sign up

Export Citation Format

Share Document