scholarly journals Fine-Tuning Approach for Segmentation of Gliomas in Brain Magnetic Resonance Images with a Machine Learning Method to Normalize Image Differences among Facilities

Cancers ◽  
2021 ◽  
Vol 13 (6) ◽  
pp. 1415 ◽  
Author(s):  
Satoshi Takahashi ◽  
Masamichi Takahashi ◽  
Manabu Kinoshita ◽  
Mototaka Miyake ◽  
Risa Kawaguchi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Image Segmentation ◽  
Magnetic Resonance ◽  
Magnetic Resonance Images ◽  
Fine Tuning ◽  
Tumor Segmentation ◽  
Dice Coefficient ◽  
Test Portion ◽  
Japanese Cohort ◽  
Significant Difference

Machine learning models for automated magnetic resonance image segmentation may be useful in aiding glioma detection. However, the image differences among facilities cause performance degradation and impede detection. This study proposes a method to solve this issue. We used the data from the Multimodal Brain Tumor Image Segmentation Benchmark (BraTS) and the Japanese cohort (JC) datasets. Three models for tumor segmentation are developed. In our methodology, the BraTS and JC models are trained on the BraTS and JC datasets, respectively, whereas the fine-tuning models are developed from the BraTS model and fine-tuned using the JC dataset. Our results show that the Dice coefficient score of the JC model for the test portion of the JC dataset was 0.779 ± 0.137, whereas that of the BraTS model was lower (0.717 ± 0.207). The mean Dice coefficient score of the fine-tuning model was 0.769 ± 0.138. There was a significant difference between the BraTS and JC models (p < 0.0001) and the BraTS and fine-tuning models (p = 0.002); however, no significant difference between the JC and fine-tuning models (p = 0.673). As our fine-tuning method requires fewer than 20 cases, this method is useful even in a facility where the number of glioma cases is small.

scholarly journals NIMG-29. DEVELOPING AUTOMATIC SEGMENTATION METHOD FOR BRAIN TUMOR MR IMAGES THAT CAN BE USED AT MULTIPLE FACILITIES

2020 ◽  
Vol 22 (Supplement_2) ◽  
pp. ii153-ii154
Author(s):  
Satoshi Takahashi ◽  
Masamichi Takahashi ◽  
Manabu Kinoshita ◽  
Mototaka Miyake ◽  
Risa Kawaguchi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Image Segmentation ◽  
Brain Tumor ◽  
Automatic Segmentation ◽  
Fine Tuning ◽  
Tumor Segmentation ◽  
Mr Images ◽  
Japanese Cohort ◽  
Significant Difference ◽  
Jc Model

Abstract BACKGROUND Manual segmentation of brain tumor images from a large volume of MR images generated in clinical routines is difficult and time-consuming. Hence, it is imperative to develop a machine learning model for automated segmentation of brain tumor images. PURPOSE Machine learning models for automated MR image segmentation of gliomas may be useful. However, the image differences among facilities cause performance degradation and impede successful automatic segmentation. In this study, we proposed a method to solve this issue. METHODS We used the data from the Multimodal Brain Tumor Image Segmentation Benchmark (BraTS) and the Japanese cohort (JC) datasets collected from 10 facilities. Three models for tumor segmentation were developed. The BraTS model was trained on the BraTS dataset, and the JC model was trained on the JC dataset; whereas, the Fine-tuning model was a fine-tuned BraTS model using the JC dataset. RESULTS MR images of 544 patients were obtained for the JC dataset. Half of the JC dataset was used for independent testing. The Dice coefficient score of the JC model for the JC dataset was 0.779± 0.137, whereas that of the BraTS model was remarkably lower (0.717 ± 0.207). The mean of the Fine-tuning models for the JC dataset was 0.769 ± 0.138. There was a significant difference between the BraTS and JC models (P &lt; 0.0001) and the BraTS and Fine-tuning models (P = 0.002); however, no significant difference was observed between the JC and Fine-tuning models (P = 0.673). CONCLUSIONS Application of the BraTS model to heterogeneous datasets can significantly reduce its performance; however, fine-tuning can solve this issue. Since our fine-tuning method only requires less than 20 cases, this methodology is particularly useful for a facility where there are a few glioma cases.

scholarly journals An image segmentation framework for extracting tumors from breast magnetic resonance images

2018 ◽  
Vol 11 (04) ◽  
pp. 1850014 ◽  
Author(s):  
Le Sun ◽  
Jinyuan He ◽  
Xiaoxia Yin ◽  
Yanchun Zhang ◽  
Jeon-Hor Chen ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Magnetic Resonance ◽  
Breast Cancer Diagnosis ◽  
Vital Role ◽  
Magnetic Resonance Images ◽  
Tumor Segmentation ◽  
Breast Magnetic Resonance ◽  
Magnetic Resonance Imaging Mri ◽  
Tumor Extraction ◽  
Disease Analysis

Magnetic resonance imaging (MRI) has been a prevalence technique for breast cancer diagnosis. Computer-aided detection and segmentation of lesions from MRIs plays a vital role for the MRI-based disease analysis. There are two main issues of the existing breast lesion segmentation techniques: requiring manual delineation of Regions of Interests (ROIs) as a step of initialization; and requiring a large amount of labeled images for model construction or parameter learning, while in real clinical or experimental settings, it is highly challenging to get sufficient labeled MRIs. To resolve these issues, this work proposes a semi-supervised method for breast tumor segmentation based on super voxel strategies. After image segmentation with advanced cluster techniques, we take a supervised learning step to classify the tumor and nontumor patches in order to automatically locate the tumor regions in an MRI. To obtain the optimal performance of tumor extraction, we take extensive experiments to learn parameters for tumor segmentation and classification, and design 225 classifiers corresponding to different parameter settings. We call the proposed method as Semi-supervised Tumor Segmentation (SSTS), and apply it to both mass and nonmass lesions. Experimental results show better performance of SSTS compared with five state-of-the-art methods.

Pituitary volume in children with growth hormone deficiency, idiopathic short stature and controls

2016 ◽  
Vol 29 (10) ◽  
Author(s):  
Marion Kessler ◽  
Michael Tenner ◽  
Michael Frey ◽  
Richard Noto
Keyword(s):  
Growth Hormone ◽  
Magnetic Resonance ◽  
Growth Hormone Deficiency ◽  
Short Stature ◽  
Hormone Secretion ◽  
Growth Hormone Secretion ◽  
Magnetic Resonance Images ◽  
Idiopathic Short Stature ◽  
Hormone Deficiency ◽  
Significant Difference

AbstractBackground:The objective of the study was to describe the pituitary volume (PV) in pediatric patients with isolated growth hormone deficiency (IGHD), idiopathic short stature (ISS) and normal controls.Methods:Sixty-nine patients (57 male, 12 female), with a mean age of 11.9 (±2.0), were determined to have IGHD. ISS was identified in 29 patients (20 male, 9 female), with a mean age of 12.7 (±3.7). Sixty-six controls (28 female, 38 male), mean age 9.8 (±4.7) were also included. Three-dimensional (3D) magnetic resonance images with contrast were obtained to accurately measure PV.Results:There was a significant difference in the mean PV among the three groups. The IGHD patients had a mean PV 230.8 (±89.6), for ISS patients it was 286.8 (±108.2) and for controls it was 343.7 (±145.9) (p<0.001). There was a normal increase in PV with age in the ISS patients and controls, but a minimal increase in the IGHD patients.Conclusions:Those patients with isolated GHD have the greatest reduction in PV compared to controls and the patients with ISS fall in between. We speculate that a possible cause for the slowed growth in some ISS patients might be related to diminished chronic secretion of growth hormone over time, albeit having adequate pituitary reserves to respond acutely to GH stimulation. Thus, what was called neurosecretory GHD in the past, might, in some patients, be relative pituitary hypoplasia and resultant diminished growth hormone secretion. Thus, PV determinations by magnetic resonance imaging (MRI) could assist in the diagnostic evaluation of the slowly growing child.

scholarly journals Imaging Surrogates of Infiltration Obtained Via Multiparametric Imaging Pattern Analysis Predict Subsequent Location of Recurrence of Glioblastoma

Neurosurgery ◽  
2016 ◽  
Vol 78 (4) ◽  
pp. 572-580 ◽  
Author(s):  
Hamed Akbari ◽  
Luke Macyszyn ◽  
Xiao Da ◽  
Michel Bilello ◽  
Ronald L. Wolf ◽  
...  
Keyword(s):  
Machine Learning ◽  
Magnetic Resonance ◽  
Tumor Recurrence ◽  
Pattern Analysis ◽  
Early Recurrence ◽  
Magnetic Resonance Images ◽  
Tumor Infiltration ◽  
Multiparametric Imaging ◽  
Peritumoral Tissue ◽  
Spatial Maps

Abstract BACKGROUND: Glioblastoma is an aggressive and highly infiltrative brain cancer. Standard surgical resection is guided by enhancement on postcontrast T1-weighted (T1) magnetic resonance imaging, which is insufficient for delineating surrounding infiltrating tumor. OBJECTIVE: To develop imaging biomarkers that delineate areas of tumor infiltration and predict early recurrence in peritumoral tissue. Such markers would enable intensive, yet targeted, surgery and radiotherapy, thereby potentially delaying recurrence and prolonging survival. METHODS: Preoperative multiparametric magnetic resonance images (T1, T1-gadolinium, T2-weighted, T2-weighted fluid-attenuated inversion recovery, diffusion tensor imaging, and dynamic susceptibility contrast-enhanced magnetic resonance images) from 31 patients were combined using machine learning methods, thereby creating predictive spatial maps of infiltrated peritumoral tissue. Cross-validation was used in the retrospective cohort to achieve generalizable biomarkers. Subsequently, the imaging signatures learned from the retrospective study were used in a replication cohort of 34 new patients. Spatial maps representing the likelihood of tumor infiltration and future early recurrence were compared with regions of recurrence on postresection follow-up studies with pathology confirmation. RESULTS: This technique produced predictions of early recurrence with a mean area under the curve of 0.84, sensitivity of 91%, specificity of 93%, and odds ratio estimates of 9.29 (99% confidence interval: 8.95-9.65) for tissue predicted to be heavily infiltrated in the replication study. Regions of tumor recurrence were found to have subtle, yet fairly distinctive multiparametric imaging signatures when analyzed quantitatively by pattern analysis and machine learning. CONCLUSION: Visually imperceptible imaging patterns discovered via multiparametric pattern analysis methods were found to estimate the extent of infiltration and location of future tumor recurrence, paving the way for improved targeted treatment.

Sign in / Sign up

Export Citation Format

Share Document