Two-stage deep learning for accelerated 3D time-of-flight MRA without matched training data.

The biological nervous system possesses a powerful information processing capability, and only needs a partial signal stimulation to perceive the entire signal. Likewise, the hardware implementation of an information processing system with similar capabilities is of great significance, for reducing the dimensions of data from sensors and improving the processing efficiency. Here, it is reported that indium-gallium-zinc-oxide thin film phototransistors exhibit the optoelectronic switching and light-tunable synaptic characteristics for in-sensor compression and computing. Phototransistor arrays can compress the signal while sensing, to realize in-sensor compression. Additionally, a reservoir computing network can also be implemented via phototransistors for in-sensor computing. By integrating these two systems, a neuromorphic system for high-efficiency in-sensor compression and computing is demonstrated. The results reveal that even for cases where the signal is compressed by 50%, the recognition accuracy of reconstructed signal still reaches ≈96%. The work paves the way for efficient information processing of human-computer interactions and the Internet of Things.

Bio-Inspired In-Sensor Compression and Computing Based on Phototransistors.

OBJECTIVES The aim of this study was to compare the image quality of low-kV protocols with optimized automatic tube voltage selection (ATVS) settings to reduce either radiation dose or contrast medium (CM) with that of a reference protocol for computed tomography angiography (CTA) of the thoracoabdominal aorta. MATERIALS AND METHODS In this institutional review board-approved, single-center, prospective randomized controlled trial, 126 patients receiving CTA of the aorta were allocated to one of three computed tomography protocols: (A) reference protocol at 120 kVp and standard weight-adapted CM dose; (B) protocol at 90 kVp, reduced radiation and standard CM dose; and (C) protocol at 90 kVp, standard radiation and reduced CM dose. All three protocols were performed on a third-generation dual-source computed tomography scanner using the semimode of the ATVS system. The image-task-dependent optimization settings of the ATVS (slider level) were adjusted to level 11 (high-contrast task) for protocols A and B and level 3 (low-contrast task) for protocol C. Radiation dose parameters were assessed. The contrast-to-noise ratios (CNRs) of protocols B and C were tested for noninferiority compared with A. Subjective image quality was assessed using a 5-point Likert scale. RESULTS Size-specific dose estimate was 34.3% lower for protocol B compared with A (P < 0.0001). Contrast medium was 20.2% lower for protocol C compared with A (P < 0.0001). Mean CNR in B and C was noninferior to protocol A (CNR of 30.2 ± 7, 33.4 ± 6.7, and 30.5 ± 8.9 for protocols A, B, and C, respectively). There was no significant difference in overall subjective image quality among protocols (4.09 ± 0.21, 4.03 ± 0.19, and 4.08 ± 0.17 for protocols A, B, and C, respectively; P = 0.4). CONCLUSIONS The slider settings of an ATVS system can be adjusted to optimize either radiation dose or CM at noninferior image quality in low-kV CTA of the aorta. This optimization could be used to extend future ATVS algorithms to take clinical risk factors like kidney function of individual patients into account.

Computed Tomography Angiography of the Aorta-Optimization of Automatic Tube Voltage Selection Settings to Reduce Radiation Dose or Contrast Medium in a Prospective Randomized Trial

Deep learning (DL) is one of the most powerful data-driven machine-learning techniques in artificial intelligence (AI). It can automatically learn from raw data without manual feature selection. DL models have led to remarkable advances in data extraction and analysis for medical imaging. Magnetic resonance imaging (MRI) has proven useful in delineating the characteristics and extent of breast lesions and tumors. This review summarizes the current state-of-the-art applications of DL models in breast MRI. Many recent DL models were examined in this field, along with several advanced learning approaches and methods for data normalization and breast and lesion segmentation. For clinical applications, DL-based breast MRI models were proven useful in five aspects: diagnosis of breast cancer, classification of molecular types, classification of histopathological types, prediction of neoadjuvant chemotherapy response, and prediction of lymph node metastasis. For subsequent studies, further improvement in data acquisition and preprocessing is necessary, additional DL techniques in breast MRI should be investigated, and wider clinical applications need to be explored. 

Clinical applications of deep learning in breast MRI.

BACKGROUND AND PURPOSE: The clinical practice of three-dimensional TOF-MRA, despite its capability in brain artery assessment, has been hampered by the relatively long scan time, while recent developments in fast imaging techniques with random undersampling has shed light on an improved balance between image quality and imaging speed. Our aim was to evaluate the effectiveness of TOF-MRA accelerated by compressed sensitivity encoding and to identify the optimal acceleration factors for routine clinical use. MATERIALS AND METHODS: One hundred subjects, enrolled at 5 centers, underwent 8 brain TOF-MRA sequences: 5 sequences using compressed sensitivity encoding with acceleration factors of 2, 4, 6, 8, and 10 (CS2, CS4, CS6, CS8, and CS10), 2 using sensitivity encoding with factors of 2 and 4 (SF2 and SF4), and 1 without acceleration as a reference sequence (RS). Five large arteries, 6 medium arteries, and 6 small arteries were evaluated quantitatively (reconstructed signal intensity, structural similarity, contrast ratio) and qualitatively (scores on arteries, artifacts, overall image quality, and diagnostic confidence for aneurysm and stenosis). Comparisons were performed among the 8 sequences. RESULTS: The quantitative measurements showed that the reconstructed signal intensities of the assessed arteries and the structural similarity consistently decreased as the compressed sensitivity encoding acceleration factor increased, and no significant difference was found for the contrast ratios in pair-wise comparisons among SF2, CS2, and CS4. Qualitative evaluations showed no significant difference in pair-wise comparisons among RS, SF2, and CS2 (P > .05). The visualization of all the assessed arteries was acceptable for CS2 and CS4, while 2 small arteries in images of CS6 were not reliably displayed, and the visualization of large arteries was acceptable in images of CS8 and CS10. CONCLUSIONS: CS4 is recommended for routine brain TOF-MRA with balanced image quality and acquisition time; CS6, for examinations when small arteries are not evaluated; and CS10, for fast visualization of large arteries.

http://www.ajnr.org/content/ajnr/42/7/1208.full.pdf

Acceleration of Brain TOF-MRA with Compressed Sensitivity Encoding: A Multicenter Clinical Study

BACKGROUND Compressed sensing (CS) has been widely used to improve the speed of MRI, but the feasibility of application in 3D intracranial MR angiography (MRA) needs to be evaluated in clinical practice. PURPOSE To evaluate the clinical feasibility of CS-MRA in comparison with conventional 3D-MRA (Con-MRA). STUDY TYPE Retrospective. SUBJECTS Forty-nine consecutive patients with suspected intracranial arterial disease. FIELD STRENGTH/SEQUENCE 3T MRI. 3D time-of-flight (TOF) MRA using a CS algorithm and conventional 3D TOF MRA scan. ASSESSMENT Three radiologists (4, 11, and 12 years of experience in neuroradiology) independently assessed the image quality, vascular lesions, and variations of intracranial arteries of both CS-MRA and Con-MRA, respectively. STATISTICAL TESTS The Kendall W test was performed to assess the interobserver agreement of image quality and intracranial arterial stenosis. A nonparametric test (Wilcoxon test) was used for comparison of the image quality and definition of the external carotid artery (ECA). Weighted kappa analysis was performed for the interstudy agreement of intracranial arterial stenosis. The aneurysm, decreased branches, congenital hypoplasia, absence, and variant branching of intracranial arteries were observed and evaluated for interobserver agreement and interstudy agreement by kappa analysis. Paired-t-tests for signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were conducted. RESULTS Image quality is better for CS-MRA compared with Con-MRA with significance (Z = -3.710 to -2.673, with P < 0.01). The interstudy agreement of lesion and variation of intracranial arteries assessment for each observer was excellent. The SNR and CNR were significantly higher in CS-MRA compared with Con-MRA (P < 0.001). The definition of ECA of CS-MRA was significantly better (Z = -4.9, P < 0.001). DATA CONCLUSION CS-MRA showed significantly higher image quality with less blur, comparable image diagnostic performance of intracranial arteries, and better display of ECA than Con-MRA. LEVEL OF EVIDENCE 3 Technical Efficacy Stage: 2 J. Magn. Reson. Imaging 2019;50:1843-1851.

Clinical feasibility study of 3D intracranial magnetic resonance angiography using compressed sensing.

Purpose. To investigate whether quantitative radiomics features extracted from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) could be used to differentiate triple-negative breast cancer (TNBC) and nontriple-negative breast cancer (non-TNBC). Materials and Methods. This retrospective study included DCE-MRI images of 81 breast cancer patients (44 TNBC and 37 non-TNBC) from August 2018 to October 2019. The MR scans were achieved at a 1.5 T MR scanner. For each patient, the largest tumor mass was selected to analyze. Three-dimensional (3D) images of the regions of interest (ROIs) were automatically segmented on the third DCE phase by a deep learning segmentation model; then, the ROIs were checked and revised by 2 radiologists. DCE-MRI radiomics features were extracted from the 3D tumor volume. The patients were randomly divided into training ( ) and test ( ) cohorts. The machine learning classifier was built in the training dataset, and 5-fold cross-validation was performed on the training cohort to train and validate. The data of the test cohort were used to investigate the predictive power of the radiomics model in predicting TNBC and non-TNBC. The performance of the model was evaluated by the area under receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. Results. The radiomics model based on 15 features got the best performance. The AUC achieved 0.741 for the cross-validation, and 0.867 for the independent testing cohort. Conclusion. The radiomics model based on automatic image segmentation of DCE-MRI can be used to distinguish TNBC and non-TNBC.

/pdf/radiomics-analysis-based-on-automatic-image-segmentation-of-19sun1wly1.pdf

Radiomics Analysis Based on Automatic Image Segmentation of DCE-MRI for Predicting Triple-Negative and Nontriple-Negative Breast Cancer.

OBJECTIVE To compare conventional method and compressed-sensing (CS) accelerated 3D balanced fast field echo imaging (bFFE) of inner ear. METHODS Twenty patients with suspected inner ear disease underwent CS accelerated 3D-bFFE (CS-bFFE) and conventional 3D-bFFE (Con-bFFE) by a 3T MRI. The overall image quality, motion artifacts, and image quality of specific structures of inner ear were assessed on ordinal scales by three radiologists who were blinded to the scan protocols. Kendall W test was used to evaluate interobserver agreement and Wilcoxon test was performed to compare the image quality and motion artifacts between CS-bFFE and Con-bFFE. RESULTS The acquisition duration of CS-bFFE (1 min 53 s) was 49% faster than Con-bFFE. Three radiologists had good inter-observer agreement of image quality (Kendall W value of 0.829 for CS-bFFE and 0.815 for Con-bFFE) and motion artifacts evaluation (Kendall W value of 0861 for CS-bFFE and 0.707 for Con-bFFE). The better overall image quality of CS-bFFE was assessed (4.93 ± 0.23 for CS-bFFE, 4.53 ± 0.70 for Con-bFFE, Z = -2.254, p = 0.024). The image quality score of facial and cochlear nerve gained higher in CS-bFFE (4.93 ± 0.23 for CS-bFFE, 4.58 ± 0.64 for Con-bFFE, Z = -2.094, p = 0.036). No significant difference of motion artifacts (p = 0.050) between CS-bFFE and Con-bFFE. CONCLUSIONS The CS-bFFE improves image quality and reduces acquisition time significantly, and it is a feasible MRI protocol for inner ear imaging.

Compressed-sensing accelerated magnetic resonance imaging of inner ear.

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Yuan Jiang

Author Tools

Chat about Author

Papers

Clinical feasibility study of 3D intracranial magnetic resonance angiography using compressed sensing.

Radiomics Analysis Based on Automatic Image Segmentation of DCE-MRI for Predicting Triple-Negative and Nontriple-Negative Breast Cancer.

Compressed-sensing accelerated magnetic resonance imaging of inner ear.