Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Cardiology Cardiology

Deep Learning Model for Coronary Angiography.

In Journal of cardiovascular translational research

The visual inspection of coronary artery stenosis is known to be significantly affected by variation, due to the presence of other tissues, camera movements, and uneven illumination. More accurate and intelligent coronary angiography diagnostic models are necessary for improving the above problems. In this study, 2980 medical images from 949 patients are collected and a novel deep learning-based coronary angiography (DLCAG) diagnose system is proposed. Firstly, we design a module of coronary classification. Then, we introduce RetinaNet to balance positive and negative samples and improve the recognition accuracy. Additionally, DLCAG adopts instance segmentation to segment the stenosis of vessels and depict the degree of the stenosis vessels. Our DLCAG is available at http://101.132.120.184:8077/ . When doctors use our system, all they need to do is login to the system, upload the coronary angiography videos. Then, a diagnose report is automatically generated.

Ling Hao, Chen Biqian, Guan Renchu, Xiao Yu, Yan Hui, Chen Qingyu, Bi Lianru, Chen Jingbo, Feng Xiaoyue, Pang Haoyu, Song Chunli

2023-Mar-16

Coronary artery stenosis, Deep learning, Diagnosis, Instance segmentation, Object detection

General General

Heterogeneous intercalated metal-organic framework active materials for fast-charging non-aqueous Li-ion capacitors.

In Nature communications ; h5-index 260.0

Intercalated metal-organic frameworks (iMOFs) based on aromatic dicarboxylate are appealing negative electrode active materials for Li-based electrochemical energy storage devices. They store Li ions at approximately 0.8 V vs. Li/Li+ and, thus, avoid Li metal plating during cell operation. However, their fast-charging capability is limited. Here, to circumvent this issue, we propose iMOFs with multi-aromatic units selected using machine learning and synthesized via solution spray drying. A naphthalene-based multivariate material with nanometric thickness allows the reversible storage of Li-ions in non-aqueous Li metal cell configuration reaching 85% capacity retention at 400 mA g-1 (i.e., 30 min for full charge) and 20 °C compared to cycling at 20 mA g-1 (i.e., 10 h for full charge). The same material, tested in combination with an activated carbon-based positive electrode, enables a discharge capacity retention of about 91% after 1000 cycles at 0.15 mA cm-2 (i.e., 2 h for full charge) and 20 °C. We elucidate the charge storage mechanism and demonstrate that during Li intercalation, the distorted crystal structure promotes electron delocalization by controlling the frame vibration. As a result, a phase transition suppresses phase separation, thus, benefitting the electrode's fast charging behavior.

Ogihara Nobuhiro, Hasegawa Masaki, Kumagai Hitoshi, Mikita Riho, Nagasako Naoyuki

2023-Mar-16

Radiology Radiology

Prognostic value of deep learning-based fibrosis quantification on chest CT in idiopathic pulmonary fibrosis.

In European radiology ; h5-index 62.0

OBJECTIVE : To investigate the prognostic value of deep learning (DL)-driven CT fibrosis quantification in idiopathic pulmonary fibrosis (IPF).

METHODS : Patients diagnosed with IPF who underwent nonenhanced chest CT and spirometry between 2005 and 2009 were retrospectively collected. Proportions of normal (CT-Norm%) and fibrotic lung volume (CT-Fib%) were calculated on CT using the DL software. The correlations of CT-Norm% and CT-Fib% with forced vital capacity (FVC) and diffusion capacity of carbon monoxide (DLCO) were evaluated. The multivariable-adjusted hazard ratios (HRs) of CT-Norm% and CT-Fib% for overall survival were calculated with clinical and physiologic variables as covariates using Cox regression. The feasibility of substituting CT-Norm% for DLCO in the GAP index was investigated using time-dependent areas under the receiver operating characteristic curve (TD-AUCs) at 3 years.

RESULTS : In total, 161 patients (median age [IQR], 68 [62-73] years; 104 men) were evaluated. CT-Norm% and CT-Fib% showed significant correlations with FVC (Pearson's r, 0.40 for CT-Norm% and - 0.37 for CT-Fib%; both p < 0.001) and DLCO (0.52 for CT-Norm% and - 0.46 for CT-Fib%; both p < 0.001). On multivariable Cox regression, both CT-Norm% and CT-Fib% were independent prognostic factors when adjusted to age, sex, smoking status, comorbid chronic diseases, FVC, and DLCO (HRs, 0.98 [95% CI 0.97-0.99; p < 0.001] for CT-Norm% at 3 years and 1.03 [1.01-1.05; p = 0.01] for CT-Fib%). Substituting CT-Norm% for DLCO showed comparable discrimination to the original GAP index (TD-AUC, 0.82 [0.78-0.85] vs. 0.82 [0.79-0.86]; p = 0.75).

CONCLUSION : CT-Norm% and CT-Fib% calculated using chest CT-based deep learning software were independent prognostic factors for overall survival in IPF.

KEY POINTS : • Normal and fibrotic lung volume proportions were automatically calculated using commercial deep learning software from chest CT taken from 161 patients diagnosed with idiopathic pulmonary fibrosis. • CT-quantified volumetric parameters from commercial deep learning software were correlated with forced vital capacity (Pearson's r, 0.40 for normal and - 0.37 for fibrotic lung volume proportions) and diffusion capacity of carbon monoxide (Pearson's r, 0.52 and - 0.46, respectively). • Normal and fibrotic lung volume proportions (hazard ratios, 0.98 and 1.04; both p < 0.001) independently predicted overall survival when adjusted for clinical and physiologic variables.

Nam Ju Gang, Choi Yunhee, Lee Sang-Min, Yoon Soon Ho, Goo Jin Mo, Kim Hyungjin

2023-Mar-16

Deep learning, Idiopathic pulmonary fibrosis, Multidetector computed tomography, Prognosis

General General

Ultrafast MRI using deep learning echoplanar imaging for a comprehensive assessment of acute ischemic stroke.

In European radiology ; h5-index 62.0

OBJECTIVES : Acute ischemic stroke (AIS) is an emergency requiring both fast and informative MR sequences. We aimed to assess the performance of an artificial intelligence-enhanced ultrafast (UF) protocol, compared to the reference protocol, in the AIS management.

METHODS : We included patients admitted in the emergency department for suspected AIS. Each patient underwent a 3-T MR protocol, including reference acquisitions of T2-FLAIR, DWI, and SWI (duration: 7 min 54 s) and their accelerated multishot EPI counterparts for T2-FLAIR and T2*, complemented by a single-shot EPI DWI (duration: 1 min 54 s). Two blinded neuroradiologists reviewed each dataset, assessing DWI (detection, location, number of acute lesions), FLAIR (vascular hyperintensities, visibility of acute lesions), and SWI/T2* (hemorrhagic transformation, thrombus). We compared the agreement between the diagnoses obtained with both protocols using kappa coefficients.

RESULTS : A total of 173 patients were included consecutively, of whom 80 with an AIS in DWI. We found an almost perfect agreement between the UF and reference protocols regarding the detection, distribution, number of AIS in DWI (κ = 0.98, 0.98, and 0.87 respectively), the presence of vascular hyperintensities, and the presence of a parenchymal hyperintensity in the AIS region in FLAIR (κ = 0.93 and 0.89 respectively). Agreement was substantial in T2*/SWI for thrombus detection, and fair for hemorrhagic transformation detection (κ = 0.64 and 0.38 respectively). Differential diagnoses were similarly detected by both protocols (κ = 1).

CONCLUSIONS : Our AI-enhanced ultrafast MRI protocol allowed an effective detection and characterization of both AIS and differential diagnoses in less than 2 min.

KEY POINTS : • The AI-enhanced ultrafast MRI protocol allowed an effective detection of acute stroke. • Characterization of stroke features with the UF protocol was equivalent to the reference sequences. • Differential diagnoses were detected similarly by the UF and reference protocols.

Verclytte Sebastien, Gnanih Robin, Verdun Stephane, Feiweier Thorsten, Clifford Bryan, Ambarki Khalid, Pasquini Marta, Ding Juliette

2023-Mar-16

Artificial intelligence, Ischemic stroke, Magnetic resonance imaging

Radiology Radiology

Synthetic T2-weighted fat sat based on a generative adversarial network shows potential for scan time reduction in spine imaging in a multicenter test dataset.

In European radiology ; h5-index 62.0

OBJECTIVES : T2-weighted (w) fat sat (fs) sequences, which are important in spine MRI, require a significant amount of scan time. Generative adversarial networks (GANs) can generate synthetic T2-w fs images. We evaluated the potential of synthetic T2-w fs images by comparing them to their true counterpart regarding image and fat saturation quality, and diagnostic agreement in a heterogenous, multicenter dataset.

METHODS : A GAN was used to synthesize T2-w fs from T1- and non-fs T2-w. The training dataset comprised scans of 73 patients from two scanners, and the test dataset, scans of 101 patients from 38 multicenter scanners. Apparent signal- and contrast-to-noise ratios (aSNR/aCNR) were measured in true and synthetic T2-w fs. Two neuroradiologists graded image (5-point scale) and fat saturation quality (3-point scale). To evaluate whether the T2-w fs images are indistinguishable, a Turing test was performed by eleven neuroradiologists. Six pathologies were graded on the synthetic protocol (with synthetic T2-w fs) and the original protocol (with true T2-w fs) by the two neuroradiologists.

RESULTS : aSNR and aCNR were not significantly different between the synthetic and true T2-w fs images. Subjective image quality was graded higher for synthetic T2-w fs (p = 0.023). In the Turing test, synthetic and true T2-w fs could not be distinguished from each other. The intermethod agreement between synthetic and original protocol ranged from substantial to almost perfect agreement for the evaluated pathologies.

DISCUSSION : The synthetic T2-w fs might replace a physical T2-w fs. Our approach validated on a challenging, multicenter dataset is highly generalizable and allows for shorter scan protocols.

KEY POINTS : • Generative adversarial networks can be used to generate synthetic T2-weighted fat sat images from T1- and non-fat sat T2-weighted images of the spine. • The synthetic T2-weighted fat sat images might replace a physically acquired T2-weighted fat sat showing a better image quality and excellent diagnostic agreement with the true T2-weighted fat images. • The present approach validated on a challenging, multicenter dataset is highly generalizable and allows for significantly shorter scan protocols.

Schlaeger Sarah, Drummer Katharina, El Husseini Malek, Kofler Florian, Sollmann Nico, Schramm Severin, Zimmer Claus, Wiestler Benedikt, Kirschke Jan S

2023-Mar-16

Artificial intelligence, Magnetic resonance imaging, Spine

General General

Distribution of [11C]-JNJ-42491293 in the marmoset brain: a positron emission tomography study.

In Naunyn-Schmiedeberg's archives of pharmacology

JNJ-42491293 is a metabotropic glutamate 2 (mGlu2) positive allosteric modulator (PAM) that was radiolabelled with [11C]- to serve as a positron emission tomography (PET) ligand. Indeed, in vitro, the molecule displays high selectivity at mGlu2 receptors. However, PET experiments performed in rats, macaques and humans, have suggested that [11C]-JNJ-42491293 could interact with an unidentified, non-mGlu2 receptor binding site. The brain distribution of [11C]-JNJ-42491293 has not been determined in the brain of the common marmoset, a small non-human primate increasingly used in neuroscience research. Here, we investigated the distribution of [11C]-JNJ-42491293 in the marmoset brain. Three marmosets underwent brain magnetic resonance imaging (MRI) and 90-min dynamic PET scans with [11C]-JNJ-42491293 in combination with vehicle or the mGlu2 PAM AZD8529 (0.1, 1 and 10 mg/kg). In the scans in which [11C]-JNJ-42491293 was co-administered with vehicle, the brain areas with the highest standardised uptake values (SUVs) were the midbrain, cerebellum and thalamus, while the lowest SUVs were found in the pons. The addition of AZD8529 (0.1, 1 and 10 mg/kg) to [11C]-JNJ-42491293 did not modify the SUVs obtained with [11C]-JNJ-42491293 alone, and ex vivo blocking autoradiography with PAM AZD8529 (10, 100, 300 µM) on marmoset brain sections showed increased signals in the blocking conditions compared to vehicle, suggesting that no competition occurred between the 2 ligands. The results we obtained here do not suggest that [11C]-JNJ-42491293 interacts selectively, or even at all, with mGlu2 receptors in the marmoset, in agreement with findings previously reported in macaque and human.

Kang Min Su, Hamadjida Adjia, Bédard Dominique, Nuara Stephen G, Gourdon Jim C, Frey Stephen, Aliaga Arturo, Ross Karen, Hopewell Robert, Bdair Hussein, Mathieu Axel, Tardif Christine Lucas, Soucy Jean-Paul, Massarweh Gassan, Rosa-Neto Pedro, Huot Philippe

2023-Mar-16

AZD8529, Marmoset, PET, Positive allosteric modulator, [11C]-JNJ-42491293, mGlu2 receptor