scholarly journals Towards Texture Accurate Slice Interpolation of Medical Images Using PixelMiner

2021 ◽  
Author(s):  
William Roger ◽  
Philippe Lambin ◽  
Simon Keek ◽  
Manon Beuque ◽  
Sergey Primakov ◽  
...  
Keyword(s):  
Mean Squared Error ◽  
Quantitative Imaging ◽  
Texture Features ◽  
Qualitative Assessment ◽  
Imaging Features ◽  
Edge Preservation ◽  
Human Trial ◽  
Analysis Models ◽  
Deep Learning Model ◽  
Lung Ct

Abstract Quantitative analysis models are used for various medical imaging tasks such as registration, classification, object detection, and segmentation which all benefit from high-quality imaging. We propose PixelMiner, a convolution-based deep-learning model which interpolates computed tomography (CT) imaging slices while better preserving quantitative imaging features than standard interpolation methods. PixelMiner was designed to produce texture-accurate slice interpolations by trading off pixel accuracy for texture accuracy using a novel architecture. PixelMiner was trained on a large dataset consisting of 7092 lung CT scans and validated using external lung CT datasets. We demonstrated the model's effectiveness by using edge preservation ratio (EPR), compared texture features commonly used in radiomics, and performed a qualitative assessment by human trial. PixelMiner had the highest EPR 82% (p<.01) of the time compared to the closest competing method. It had the lowest texture error, using a normalized root mean squared error (NRMSE) of 0.11 (p<.01), with the highest reproducibility of concordance correlation coefficient (CCC) ≥ 0.85 (p<.01). PixelMiner was chosen 72% of the time by human evaluation (p<.01). PixelMiner was not only demonstrated quantitatively to have improved structural and textural constructions but also shown to be preferable qualitatively.

scholarly journals Reproducibility of CT-based radiomic features against image resampling and perturbations for tumour and healthy kidney in renal cancer patients

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Margherita Mottola ◽  
Stephan Ursprung ◽  
Leonardo Rundo ◽  
Lorena Escudero Sanchez ◽  
Tobias Klatte ◽  
...  
Keyword(s):  
Quantitative Imaging ◽  
Texture Features ◽  
Voxel Size ◽  
Morphological Evaluation ◽  
Resampling Procedure ◽  
Automatic Methods ◽  
Visual Assessments ◽  
2D And 3D ◽  
Slice Spacing ◽  
Original Information

AbstractComputed Tomography (CT) is widely used in oncology for morphological evaluation and diagnosis, commonly through visual assessments, often exploiting semi-automatic tools as well. Well-established automatic methods for quantitative imaging offer the opportunity to enrich the radiologist interpretation with a large number of radiomic features, which need to be highly reproducible to be used reliably in clinical practice. This study investigates feature reproducibility against noise, varying resolutions and segmentations (achieved by perturbing the regions of interest), in a CT dataset with heterogeneous voxel size of 98 renal cell carcinomas (RCCs) and 93 contralateral normal kidneys (CK). In particular, first order (FO) and second order texture features based on both 2D and 3D grey level co-occurrence matrices (GLCMs) were considered. Moreover, this study carries out a comparative analysis of three of the most commonly used interpolation methods, which need to be selected before any resampling procedure. Results showed that the Lanczos interpolation is the most effective at preserving original information in resampling, where the median slice resolution coupled with the native slice spacing allows the best reproducibility, with 94.6% and 87.7% of features, in RCC and CK, respectively. GLCMs show their maximum reproducibility when used at short distances.

Intra-scanner repeatability of quantitative imaging features in a 3D printed semi-anthropomorphic CT phantom

2021 ◽  
pp. 109818
Author(s):  
Hanna Muenzfeld ◽  
Claus Nowak ◽  
Stefanie Riedlberger ◽  
Alexander Hartenstein ◽  
Bernd Hamm ◽  
...  
Keyword(s):  
Quantitative Imaging ◽  
Imaging Features ◽  
3D Printed

scholarly journals Radiomics in radiation oncology—basics, methods, and limitations

2020 ◽  
Vol 196 (10) ◽  
pp. 848-855
Author(s):  
Philipp Lohmann ◽  
Khaled Bousabarah ◽  
Mauritius Hoevels ◽  
Harald Treuer
Keyword(s):  
Mathematical Models ◽  
Quantitative Imaging ◽  
Human Perception ◽  
Image Features ◽  
Radiotherapy Planning ◽  
Large Field ◽  
Imaging Features ◽  
Imaging Data ◽  
Complete Evaluation ◽  
Vast Number

Abstract Over the past years, the quantity and complexity of imaging data available for the clinical management of patients with solid tumors has increased substantially. Without the support of methods from the field of artificial intelligence (AI) and machine learning, a complete evaluation of the available image information is hardly feasible in clinical routine. Especially in radiotherapy planning, manual detection and segmentation of lesions is laborious, time consuming, and shows significant variability among observers. Here, AI already offers techniques to support radiation oncologists, whereby ultimately, the productivity and the quality are increased, potentially leading to an improved patient outcome. Besides detection and segmentation of lesions, AI allows the extraction of a vast number of quantitative imaging features from structural or functional imaging data that are typically not accessible by means of human perception. These features can be used alone or in combination with other clinical parameters to generate mathematical models that allow, for example, prediction of the response to radiotherapy. Within the large field of AI, radiomics is the subdiscipline that deals with the extraction of quantitative image features as well as the generation of predictive or prognostic mathematical models. This review gives an overview of the basics, methods, and limitations of radiomics, with a focus on patients with brain tumors treated by radiation therapy.

scholarly journals Saliency-based 3D convolutional neural network for categorising common focal liver lesions on multisequence MRI

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Shu-Hui Wang ◽  
Xin-Jun Han ◽  
Jing Du ◽  
Zhen-Chang Wang ◽  
Chunwang Yuan ◽  
...  
Keyword(s):  
Deep Learning ◽  
Characteristic Curve ◽  
Confusion Matrix ◽  
Diagnostic Errors ◽  
Learning Model ◽  
Focal Liver Lesions ◽  
Imaging Features ◽  
Liver Lesions ◽  
Saliency Maps ◽  
Deep Learning Model

Abstract Background The imaging features of focal liver lesions (FLLs) are diverse and complex. Diagnosing FLLs with imaging alone remains challenging. We developed and validated an interpretable deep learning model for the classification of seven categories of FLLs on multisequence MRI and compared the differential diagnosis between the proposed model and radiologists. Methods In all, 557 lesions examined by multisequence MRI were utilised in this retrospective study and divided into training–validation (n = 444) and test (n = 113) datasets. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate the performance of the model. The accuracy and confusion matrix of the model and individual radiologists were compared. Saliency maps were generated to highlight the activation region based on the model perspective. Results The AUC of the two- and seven-way classifications of the model were 0.969 (95% CI 0.944–0.994) and from 0.919 (95% CI 0.857–0.980) to 0.999 (95% CI 0.996–1.000), respectively. The model accuracy (79.6%) of the seven-way classification was higher than that of the radiology residents (66.4%, p = 0.035) and general radiologists (73.5%, p = 0.346) but lower than that of the academic radiologists (85.4%, p = 0.291). Confusion matrices showed the sources of diagnostic errors for the model and individual radiologists for each disease. Saliency maps detected the activation regions associated with each predicted class. Conclusion This interpretable deep learning model showed high diagnostic performance in the differentiation of FLLs on multisequence MRI. The analysis principle contributing to the predictions can be explained via saliency maps.

scholarly journals P1.01-041 Quantitative Imaging Features Predict Response of Immunotherapy in Non-Small Cell Lung Cancer Patients

2017 ◽  
Vol 12 (1) ◽  
pp. S474-S475 ◽  
Author(s):  
Ilke Tunali ◽  
Jhanelle Gray ◽  
Jin Qi ◽  
Mahmoud Abdullah ◽  
Yoganand Balagurunathan ◽  
...  
Keyword(s):  
Lung Cancer ◽  
Small Cell Lung Cancer ◽  
Cancer Patients ◽  
Cell Lung Cancer ◽  
Quantitative Imaging ◽  
Small Cell ◽  
Imaging Features ◽  
Small Cell Lung ◽  
Lung Cancer Patients

Primary clinical study of radiomics for diagnosing simple bone cyst of the jaw

2021 ◽  
pp. 20200384
Author(s):  
Zhe-Yi Jiang ◽  
Tian-Jun Lan ◽  
Wei-Xin Cai ◽  
Qian Tao
Keyword(s):  
Bone Cyst ◽  
Maxillofacial Surgery ◽  
Correlation Coefficients ◽  
Texture Features ◽  
Image Features ◽  
Control Group ◽  
Imaging Features ◽  
Bone Cysts ◽  
Difference Matrix ◽  
Occurrence Matrix

Objective: To screen the radiomic features of simple bone cysts of the jaws and explore the potential application of radiomics in pre-operative diagnosis of jaw simple bone cysts. Methods: The investigators designed and implemented a case–control study. 19 patients with simple bone cysts who were admitted to the Department of Maxillofacial Surgery, Sun Yat-sen University Affiliated Stomatology Hospital from 2013 to 2019 were included in this study. Their clinical data and cone-beam computed tomography (CBCT) images were examined. The control group consisted of patients with odontogenic keratocyst. CBCT imaging features were analyzed and compared between the patient and control groups. Results: Overall, 10,323 image features were extracted through feature analysis. A subset of 25 radiomic features obtained after feature selection were analyzed further. These 25 features were significantly different between the 2 groups (p < 0.05). The absolute value of correlation coefficient was 0.487–0.775. Gray-level co-occurrence matrix (GLCM) contrast, neighborhood gray tone difference matrix (NGTDM) contrast, and GLCM variance were the features with the highest correlation coefficients. Conclusions: Pre-operative radiomics analysis showed the differences between simple bone cysts and odontogenic keratocysts, can help to diagnose simple bone cysts. Three specific texture features—GLCM contrast, NGTDM contrast, and GLCM variance—may be the characteristic imaging features of simple bone cysts of the jaw.

scholarly journals Real-time diameter of the fetal aorta from ultrasound

2019 ◽  
Vol 32 (11) ◽  
pp. 6735-6744
Author(s):  
Nicoló Savioli ◽  
Enrico Grisan ◽  
Silvia Visentin ◽  
Erich Cosmi ◽  
Giovanni Montana ◽  
...  
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Network Architecture ◽  
Mean Squared Error ◽  
Ultrasound Images ◽  
Imaging Features ◽  
Execution Speed ◽  
The Mean ◽  
Temporal Redundancy ◽  
Gated Recurrent Unit

AbstractThe automatic analysis of ultrasound sequences can substantially improve the efficiency of clinical diagnosis. This article presents an attempt to automate the challenging task of measuring the vascular diameter of the fetal abdominal aorta from ultrasound images. We propose a neural network architecture consisting of three blocks: a convolutional neural network (CNN) for the extraction of imaging features, a convolution gated recurrent unit (C-GRU) for exploiting the temporal redundancy of the signal, and a regularized loss function, called CyclicLoss, to impose our prior knowledge about the periodicity of the observed signal. The solution is investigated with a cohort of 25 ultrasound sequences acquired during the third-trimester pregnancy check, and with 1000 synthetic sequences. In the extraction of features, it is shown that a shallow CNN outperforms two other deep CNNs with both the real and synthetic cohorts, suggesting that echocardiographic features are optimally captured by a reduced number of CNN layers. The proposed architecture, working with the shallow CNN, reaches an accuracy substantially superior to previously reported methods, providing an average reduction of the mean squared error from 0.31 (state-of-the-art) to 0.09 $$\mathrm{mm}^2$$mm2, and a relative error reduction from 8.1 to 5.3%. The mean execution speed of the proposed approach of 289 frames per second makes it suitable for real-time clinical use.

Sign in / Sign up

Export Citation Format

Share Document