•This review focuses different aspects of deep learning applications in radiology.•This paper covers evolution of deep learning, its potentials, risk and safety issues.•This review covers some deep ...learning techniques already applied.•It gives an overall view of impact of deep learning in the medical imaging industry.
The advent of Deep Learning (DL) is poised to dramatically change the delivery of healthcare in the near future. Not only has DL profoundly affected the healthcare industry it has also influenced global businesses. Within a span of very few years, advances such as self-driving cars, robots performing jobs that are hazardous to human, and chat bots talking with human operators have proved that DL has already made large impact on our lives. The open source nature of DL and decreasing prices of computer hardware will further propel such changes. In healthcare, the potential is immense due to the need to automate the processes and evolve error free paradigms. The sheer quantum of DL publications in healthcare has surpassed other domains growing at a very fast pace, particular in radiology. It is therefore imperative for the radiologists to learn about DL and how it differs from other approaches of Artificial Intelligence (AI). The next generation of radiology will see a significant role of DL and will likely serve as the base for augmented radiology (AR). Better clinical judgement by AR will help in improving the quality of life and help in life saving decisions, while lowering healthcare costs.
A comprehensive review of DL as well as its implications upon the healthcare is presented in this review. We had analysed 150 articles of DL in healthcare domain from PubMed, Google Scholar, and IEEE EXPLORE focused in medical imagery only. We have further examined the ethic, moral and legal issues surrounding the use of DL in medical imaging.
Cardiovascular diseases (CVDs) are the top ten leading causes of death worldwide. Atherosclerosis disease in the arteries is the main cause of the CVD, leading to myocardial infarction and stroke. ...The two primary image-based phenotypes used for monitoring the atherosclerosis burden is carotid intima-media thickness (cIMT) and plaque area (PA). Earlier segmentation and measurement methods were based on ad hoc conventional and semi-automated digital imaging solutions, which are unreliable, tedious, slow, and not robust. This study reviews the modern and automated methods such as artificial intelligence (AI)-based. Machine learning (ML) and deep learning (DL) can provide automated techniques in the detection and measurement of cIMT and PA from carotid vascular images. Both ML and DL techniques are examples of supervised learning, i.e., learn from “ground truth” images and transformation of test images that are not part of the training. This review summarizes (1) the evolution and impact of the fast-changing AI technology on cIMT/PA measurement, (2) the mathematical representations of ML/DL methods, and (3) segmentation approaches for cIMT/PA regions in carotid scans based for (a) region-of-interest detection and (b) lumen-intima and media-adventitia interface detection using ML/DL frameworks. AI-based methods for cIMT/PA segmentation have emerged for CVD/stroke risk monitoring and may expand to the recommended parameters for atherosclerosis assessment by carotid ultrasound.
Summary
Background
Multiple sclerosis is an inflammatory disorder of the central nervous system. Inflammation may create high susceptibility to subclinical atherosclerosis. The purpose of this study ...was to compare subclinical atherosclerosis and the role of inflammatory cytokines between the group of patients with relapsing-remitting multiple sclerosis (RRMS) and healthy controls matched for age and sex.
Methods
The study group consisted of 112 non-diabetic and non-hypertensive RRMS patients treated with disease modifying drugs (DMD) and the control group was composed of 51 healthy subjects. The common carotid artery (CCA) intima media thickness (IMT) was investigated. Serum levels of risk factors for atherosclerosis and inflammatory cytokines were also determined.
Results
The mean CCA IMT (0.572 ± 0.131 mm vs. 0.571 ± 0.114 mm) did not differ (
p
> 0.05) between patients and controls. The RRMS patients’ CCA IMT was significantly correlated with serum interleukin 6 (IL-6) (
p
= 0.027), high-sensitivity C-reactive protein (hs-CRP) (
p
= 0.027), cystatin C (
p
< 0.0005), glucose (
p
= 0.031), cholesterol (
p
= 0.008), LDL (
p
= 0.021), erythrocyte sedimentation rate (
p
= 0.001) and triglyceride (
p
= 0.018) level. We fitted generalized linear models in order to assess the relationship between CCA IMT and IL‑6 with adjustment for sex and age. The obtained results showed that adjusted for age (
p
< 0.001) and sex (
p
= 0.048) IL‑6 serum levels statistically significantly (
p
= 0.009) predict CCA IMT only in the RRMS group.
Conclusion
The findings of the present study suggest that when treated with DMD RRMS might not be an independent risk factor for early atherosclerosis presenting with arterial wall thickening; however, the results suggest a significant association of IL‑6 serum levels with CCA IMT only in the RRMS group.
The carotid intima-media thickness (cIMT) is an important biomarker for cardiovascular diseases and stroke monitoring. This study presents an intelligence-based, novel, robust, and clinically-strong ...strategy that uses a combination of deep-learning (DL) and machine-learning (ML) paradigms.
A two-stage DL-based system (a class of AtheroEdge™ systems) was proposed for cIMT measurements. Stage I consisted of a convolution layer-based encoder for feature extraction and a fully convolutional network-based decoder for image segmentation. This stage generated the raw inner lumen borders and raw outer interadventitial borders. To smooth these borders, the DL system used a cascaded stage II that consisted of ML-based regression. The final outputs were the far wall lumen-intima (LI) and media-adventitia (MA) borders which were used for cIMT measurements. There were two sets of gold standards during the DL design, therefore two sets of DL systems (DL1 and DL2) were derived.
A total of 396 B-mode ultrasound images of the right and left common carotid artery were used from 203 patients (Institutional Review Board approved, Toho University, Japan). For the test set, the cIMT error for the DL1 and DL2 systems with respect to the gold standard was 0.126 ± 0.134 and 0.124 ± 0.100 mm, respectively. The corresponding LI error for the DL1 and DL2 systems was 0.077 ± 0.057 and 0.077 ± 0.049 mm, respectively, while the corresponding MA error for DL1 and DL2 was 0.113 ± 0.105 and 0.109 ± 0.088 mm, respectively. The results showed up to 20% improvement in cIMT readings for the DL system compared to the sonographer's readings. Four statistical tests were conducted to evaluate reliability, stability, and statistical significance.
The results showed that the performance of the DL-based approach was superior to the nonintelligence-based conventional methods that use spatial intensities alone. The DL system can be used for stroke risk assessment during routine or clinical trial modes.
This study examines the association between six types of carotid artery disease image-based phenotypes and HbA1c in diabetes patients. Six phenotypes (intima-media thickness measurements (cIMT ...(ave.), cIMT (max.), cIMT (min.)), bidirectional wall variability (cIMTV), morphology-based total plaque area (mTPA), and composite risk score (CRS)) were measured in an automated setting using AtheroEdge™ (AtheroPoint, CA, USA).
Consecutive 199 patients (157 M, age: 68.96 ± 10.98 years), L/R common carotid artery (CCA; 398 US scans) who underwent a carotid ultrasound (L/R) were retrospectively analyzed using AtheroEdge™ system. Two operators (novice and experienced) manually calibrated all the US scans using AtheroEdge™. Logistic regression (LR) and Odds ratio (OR) was computed and phenotypes were ranked.
The baseline results showed 150 low-risk patients (HbA1c < 6.50 mg/dl) and 49 high-risk patients (HbA1c ≥ 6.50 mg/dl). The fasting blood sugar (FBS) was highly associated with HbA1c (P < 0.001). Except for cIMTV, all phenotypes showed an OR > 1.0 (P < 0.001) for left common carotid artery (LCCA), right carotid artery (RCCA), and mean of left and right common carotid artery (MCCA). After adjusting the FBS, the OR for mTPA showed a higher risk for LCCA, RCCA, and MCCA. The coefficient of correlation (CC) between phenotypes and HbA1c were strong and inter-CC between cIMT and mTPA/CRS was above 0.9 (P < 0.001). The statistical tests showed that phenotypes were significantly associated with diabetes (P-value<0.0001).
All phenotypes using AtheroEdge™, except cIMTV, showed a strong association with HbA1c. mTPA and CRS were equally strong phenotypes as cIMT. The CRS phenotype showed the strongest relationship to HbA1c.
•Association between carotid artery disease risk biomarkers and HbA1c.•Odds ratio (OR) was computed using logistic regression.•Statistical tests showed that biomarkers were significantly associated with diabetes.
>Izhodišča in namen raziskaveMultipla skleroza (MS) je kronična in vnetna bolezen osrednjega živčevja. Vnetje je prisotno v vseh stopnjah multiple skleroze in lahko povzroči dovzetnost za razvoj ...subklinične ateroskleroze. Ateroskleroza je zapleten proces z etiologijo, ki zajema več dejavnikov in vključuje vnetne, fibroproliferativne in angiogene odzive. Gre za kronični vnetni proces arterijske (žilne) stene in debelina karotidne intimne medije (IMT) velja za njen zgodnji označevalec. Namen te študije je bil primerjati subklinično aterosklerozo, vlogo vnetnih citokinov in pomen genetskih polimorfizmov med skupino bolnikov z recidivno-remitentno multiplo sklerozo (RR MS) in skupino zdravih posameznikov, ki so primerljivi po starosti in spolu.Bolniki in metodeV študijsko skupino smo vključili 112 bolnikov z RR MS, zdravljenih z zdravili, ki vplivajo na dolgoročni potek bolezni (angl. disease modifying drugs, DMD). V kontrolno skupino pa je bilo vključenih 51 zdravih oseb. Raziskali smo IMT skupne karotidne arterije (CCA). Nihče izmed bolnikov ali kontrolne skupine se ni zdravil zaradi sladkorne bolezni ali arterijske hipertenzije. Analizirali smo skupno karotidno arterijo (CCA) in območje bifurkacije (BIF) IMT. Analizirali smo tri digitalizirane ultrazvočne slike z istega odseka arterije in izračunali povprečno vrednost. Določili smo serumske vrednosti tradicionalnih dejavnikov tveganja za aterosklerozo, Creaktivnega proteina z visoko občutljivostjo (hs-CRP), cistatina C in vnetnih citokinov. Bolnike smo ovrednotili tudi z uporabo lestvic za oceno funkcionalne prizadetosti (angl. Multiple Sclerosis Functional Composite, MSFC) in razširjeno lestvico stopnje prizadetosti (ang. Expanded Disability Status Scale, EDSS). V genetsko analizo smo prav tako vključili bolnike z RR MS in kontrolno skupino. Za asociacijsko študijo smo izbrali kandidatne polimorfizme,za katere je bila predhodno v znanstveni literaturi opisana povezava s subklinično aterosklerozo in multiplo sklerozo. DNA smo ekstrahirali iz mononuklearnih celic izoliranih iz periferne venske krvi. Genotipizacijo polimorfizmov SNP smo izvedli z mikromrežo Infinium Global Screening Array-24 v1.0 BeadChip (GSA). RezultatiPovprečna vrednost CCA IMT (0,572 ± 0,131 v primerjavi z 0,571 ± 0,114 mm) se med bolniki in kontrolno skupino ni razlikovala (p > 0,05). CCA IMT bolnikov z RRMS je statistično pomembno korelirala s serumskim nivojem interlevkina 6 (IL-6) (p = 0,027), hs-CRP (p = 0,027), cistatina C (p <0,0005), glukoze (p = 0,031), holesterola (p = 0,008), LDL holesterola (p = 0,021), hitrostjo sedimentacije eritrocitov (p = 0,001) in trigliceridov (p = 0,018). Ugotovili smo tudi pomembno korelacijo med vrednostmi CCA IMT pri RR MS bolnikih in EDSS oceno (p = 0,019), časom pri časovnem testu hoje 25 čevljev (angl. Timed 25-Foot Walk, T25FW) (p = 0,001), eno od treh komponent MSFC in časom dominantne roke pri testu devetih zatičev (angl. 9 Hole Peg Test, 9HPT) (p = 0,019), še drugi izmed komponent MSFC. Uporabili smo posplošene linearne modele, da bi ocenili razmerje med CCA IMT in IL-6 s prilagoditvijo na spol in starost. Pridobljeni rezultati kažejo, da serumske ravni IL-6, prilagojene starosti (p <0,001) in spolu (p = 0,048), statistično značilno (p = 0,009), napovedujejo CCA IMT samo v skupini z RR MS. Pri genetski analizi smo ugotovili, da je frekvenca alela T pri polimorfizmu rs7412, ki se nahaja v genu APOE statistično značilno višja pri bolnikih (26 %) v primerjavi s kontrolno skupino (6 %) (p = 0,005; OR: 5,53).
The role of erectile dysfunction (ED) has recently shown an association with the risk of stroke and coronary heart disease (CHD) via the atherosclerotic pathway. Cardiovascular disease (CVD)/stroke ...risk has been widely understood with the help of carotid artery disease (CTAD), a surrogate biomarker for CHD. The proposed study emphasizes artificial intelligence-based frameworks such as machine learning (ML) and deep learning (DL) that can accurately predict the severity of CVD/stroke risk using carotid wall arterial imaging in ED patients.
Using the PRISMA model, 231 of the best studies were selected. The proposed study mainly consists of two components: (i) the pathophysiology of ED and its link with coronary artery disease (COAD) and CHD in the ED framework and (ii) the ultrasonic-image morphological changes in the carotid arterial walls by quantifying the wall parameters and the characterization of the wall tissue by adapting the ML/DL-based methods, both for the prediction of the severity of CVD risk. The proposed study analyzes the hypothesis that ML/DL can lead to an accurate and early diagnosis of the CVD/stroke risk in ED patients. Our finding suggests that the routine ED patient practice can be amended for ML/DL-based CVD/stroke risk assessment using carotid wall arterial imaging leading to fast, reliable, and accurate CVD/stroke risk stratification.
We conclude that ML and DL methods are very powerful tools for the characterization of CVD/stroke in patients with varying ED conditions. We anticipate a rapid growth of these tools for early and better CVD/stroke risk management in ED patients.
AtheroEdge Composite Risk Score (AECRS1.010yr) is an integrated stroke/cardiovascular risk calculator that was recently developed and computes the 10-year risk of carotid image phenotypes by ...integrating conventional cardiovascular risk factors (CCVRFs). It is therefore important to understand how closely AECRS1.010yr is associated with the ten other currently available conventional cardiovascular risk calculators (CCVRCs).
The Institutional Review Board of Toho University approved the examination of the left/right common carotid arteries of 202 Japanese patients. Step 1 consists of measurement of AECRS1.010yr, given current image phenotypes and CCVRFs. Step 2 consists of computing the risk score using ten different CCVRCs given CCVR factors: QRISK3, Framingham Risk Score (FRS), United Kingdom Prospective Diabetes Study (UKPDS) 56, UKPDS60, Reynolds Risk Score (RRS), Pooled cohort Risk Score (PCRS or ASCVD), Systematic Coronary Risk Evaluation (SCORE), Prospective Cardiovascular Munster Study (PROCAM) calculator, NIPPON, and World Health Organization (WHO) risk. Step 3 consists of computing the closeness factor between AECRS1.010yr and ten CCVRCs using cumulative ranking index derived using eight different statistically derived metrics.
AECRS1.010yr reported the highest area-under-the-curve (0.927;P < 0.001) among all the risk calculators. The top three CCVRCs closest to AECRS1.010yr were QRISK3, FRS, and UKPDS60 with cumulative ranking scores of 2.1, 3.0, and 3.8, respectively.
AECRS1.010yr produced the largest AUC due to the integration of image-based phenotypes with CCVR factors, and ranked at first place with the highest AUC. Cumulative ranking of ten CCVRCs demonstrated that QRISK3 was the closest calculator to AECRS1.010yr, which is also consistent with the industry trend.
Conventional cardiovascular risk factors (CCVRFs) and carotid ultrasound image-based phenotypes (CUSIP) are independently associated with long-term risk of cardiovascular (CV) disease. In this study, ...26 cardiovascular risk (CVR) factors which consisted of a combination of CCVRFs and CUSIP together were ranked. Further, an optimal risk calculator using AtheroEdge composite risk score (AECRS1.0) was designed and benchmarked against seven conventional CV risk (CVR) calculators.
Two types of ranking were performed: (i) ranking of 26 CVR factors and (ii) ranking of eight types of 10-year risk calculators. In the first case, multivariate logistic regression was used to compute the odds ratio (OR) and in the second, receiver operating characteristic curves were used to evaluate the performance of eight types of CVR calculators using SPSS23.0 and MEDCALC12.0 with validation against STATA15.0.
The left and right common carotid arteries (CCA) of 202 Japanese patients were examined to obtain 404 ultrasound scans. CUSIP ranked in the top 50% of the 26 covariates. Intima-media thickness variability (IMTV) and IMTV10yr were the most influential carotid phenotypes for left CCA (OR = 250, P < 0.0001 and OR = 207, P < 0.0001 respectively) and right CCA (OR = 1614, P < 0.0001 and OR = 626, P < 0.0001 respectively). However, for the mean CCA, AECRS1.0 and AECRS1.010yr reported the most highly significant OR among all the CVR factors (OR = 1.073, P < 0.0001 and OR = 1.104, P < 0.0001). AECRS1.010yr also reported highest area-under-the-curve (AUC = 0.904, P < 0.0001) compared to seven types of conventional calculators. Age and glycated haemoglobin reported highest OR (1.96, P < 0.0001 and 1.05, P = 0.012) among all other CCVRFs.
AECRS1.010yr demonstrated the best performance due to presence of CUSIP and ranked at the first place with highest AUC.