Automating cardiothoracic ratio measurements in chest X-rays

Lethal skeletal dysplasia is estimated to occur in 0.95 per 10,000 deliveries. Thanatophoric dysplasia affects about 1in 25000 to 50000 births. The term thanatophoric is Greek word for “death bearing”. Children with this condition are usually stillborn or die shortly after birth from respiratory failure. We report a case of LSD (Thanatophoric dysplasia), in an unbooked patient where previous two children and couple were absolutely normal. Our patient, 31 years old, unbooked case presented with history of amenorrhea 8 months and unable to perceive fetal movements. Her husband’s age was 33 years. This was her third pregnancy. She had previous 2 deliveries by LSCS. Ultrasonography revealed single intrauterine live fetus in breech presentation with multiple fetal anomalies. There was shortening and deformity of all four limbs (micromelia) with poor mineralization of all bones. Thorax was pear shaped with short horizontal ribs and abnormal cardiothoracic ratio. LSCS was done in emergency for impending rupture of previous LSCS scar. Post-delivery examination and X-ray of the fetus revealed decreased skull mineralization, frontal bossing, hypoplastic nasal bone, midface hypoplasia, mandibular hypoplasia, pear shaped chest, protuberant abdomen, micromelia, dumbbell shaped appearance of all long bones. TD is caused due to mutation of the fibroblast growth factor receptor 3 gene (FGFR3), which is located on the short arm of chromosome 4. Type I TD is characterized by marked underdeveloped skeleton and short-curved long bones. Conventional radiographic examination remains the most useful means of studying the dysplastic skeleton. Bony evaluation is best done on X-rays or ultrasonography. The diagnosis of TD can be established with ultrasound and molecular confirmation in the second trimester can help in genetic counselling and termination of such lethal pregnancies. LSD’s are rare event. If our patient had undergone anomaly scan in second trimester of pregnancy, this defect could have been detected earlier. The outcome of fetus is lethal but maternal morbidity can be reduced if diagnosed early.

Download Full-text

Cardiothoracic Ratio Measurement Using Artificial Intelligence: Observer and Method Validation Studies

10.21203/rs.3.rs-300251/v1 ◽

2021 ◽

Author(s):

Pairash Saiviroonporn ◽

Kanchanaporn Rodbangyang ◽

Trongtum Tongdee ◽

Warasinee Chaisangmongkon ◽

Pakorn Yodprom ◽

...

Keyword(s):

Artificial Intelligence ◽

Operation Time ◽

Coefficient Of Determination ◽

X Rays ◽

Large Dataset ◽

Ratio Measurement ◽

Manual Operation ◽

Cardiothoracic Ratio ◽

Manual Methods ◽

Classification Test

Abstract Background Artificial Intelligence (AI) technique for cardiothoracic ratio (CTR) measurement is a promising tool that has been technically validated but not clinically evaluated on a large dataset. This study observes and validates AI and manual methods for CTR measurement on a large dataset and investigates the clinical utility of the AI method. Results Five thousand normal chest x-rays and 2,517 images with cardiomegaly and CTR values, were analyzed using manual, AI-assisted, and AI only methods. AI methods obtained CTR values from a VGG-16 U-Net model. An in-house software was used to aid the study and to record measurement time. Intra and inter-observer experiments were performed on manual and AI-assisted methods and the average of each method was employed in a method variation study. AI outcomes were graded in the AI-assisted method as excellent (accepted by both users independently), good (required adjustment), and poor (failed outcome). Bland-Altman plot with coefficient of variation (CV), and coefficient of determination (R-squared) were employed to evaluate agreement and correlation between measurements. Finally, the performance of a cardiomegaly classification test was evaluated using a CTR cutoff at the standard (0.5), optimum, and maximum sensitivity. Manual CTR measurements on cardiomegaly data were comparable to the previous radiologist reports (CV of 2.13% vs 2.04%). The observer and method variations from the AI method were about three times higher than from the manual method (CV of 5.78% vs 2.13%). AI assistance resulted in 40% excellent, 56% good, and 4% poor grading. AI assistance significantly improved agreement on inter-observer measurement compared to manual methods (CV; bias: 1.72%; -0.61% vs 2.13%; -1.62%) and was faster to perform (2.2 ± 2.4 secs vs 10.6 ± 1.5 secs). R-squared and classification-test were not reliable indicators to verify that the AI method could replace manual operation. Conclusion AI alone is not suitable to replace manual operation due to its high variation, but it is useful to assist the radiologist because it can reduce observer variation and operation time. Agreement of measurement should be used to compare AI and manual methods, rather than R-square or classification performance tests.

Download Full-text

Diagnosing heart failure from chest X-ray images using deep learning

European Heart Journal ◽

10.1093/ehjci/ehaa946.1201 ◽

2020 ◽

Vol 41 (Supplement_2) ◽

Author(s):

T Matsumoto ◽

S Kodera ◽

H Shinohara ◽

A Kiyosue ◽

Y Higashikuni ◽

...

Keyword(s):

Heart Failure ◽

Deep Learning ◽

Data Augmentation ◽

Learning Algorithm ◽

Funding Source ◽

X Rays ◽

X Ray ◽

Cardiothoracic Ratio ◽

Prediction Probability ◽

Chest X Ray

Abstract The development of deep learning technology has enabled machines to achieve high-level accuracy in interpreting medical images. While many previous studies have examined the detection of pulmonary nodules and cardiomegaly in chest X-rays using deep learning, the application of this technology to heart failure remains rare. In this study, we investigated the performance of a deep learning algorithm in terms of diagnosing heart failure using images obtained from chest X-rays. We used 952 chest X-ray images from a labeled database published by the National Institutes of Health. Two cardiologists respectively verified and relabeled these images, for a total of 260 “normal” and 378 “heart failure” images, and the remainder were discarded because they had been incorrectly labeled. In this study “heart failure” was defined as “cardiomegaly or congestion”, in a chest X-ray with cardiothoracic ratio (CTR) over 50% or radiographic presence of pulmonary edema. To enable the machine to extract a sufficient number of features from the images, we used the general machine learning approach called data augmentation and transfer learning. Owing mostly to this technique and the adequate relabeling process, we established a model to detect heart failure in chest X-ray by applying deep learning, and obtained an accuracy of 82%. Sensitivity and specificity to heart failure were 75% and 94.4%, respectively. Furthermore, heatmap imaging allowed us to visualize decisions made by the machine. The figure shows randomly selected examples of the prediction probabilities and heatmaps of the chest X-rays from the dataset. The original image is on the left and its heatmap is on the right, with its prediction probability written below. The red areas on the heatmaps show important regions, according to which the machine determined the classification. While some images with ambiguous radiolucency such as (e) and (f) were prone to be misdiagnosed by this model, most of the images like (a)–(d) were diagnosed correctly. Deep learning can thus help support the diagnosis of heart failure using chest X-ray images. Heatmaps and probabilities of prediction Funding Acknowledgement Type of funding source: Public grant(s) – National budget only. Main funding source(s): JSPS KAKENHI

Download Full-text

Prognostic Implication of Longitudinal Changes in Cardiothoracic Ratio and Aortic Arch Calcification in Hemodialysis Patients

Journal of Personalized Medicine ◽

10.3390/jpm11080788 ◽

2021 ◽

Vol 11 (8) ◽

pp. 788

Author(s):

Tung-Ling Chung ◽

Yi-Hsueh Liu ◽

Jiun-Chi Huang ◽

Pei-Yu Wu ◽

Hung-Pin Tu ◽

...

Keyword(s):

Aortic Arch ◽

Chest Radiography ◽

Antiplatelet Agents ◽

Older Age ◽

X Rays ◽

Cardiothoracic Ratio ◽

Follow Up Study ◽

Significant Difference ◽

Aortic Arch Calcification

Patients with end-stage renal disease have a high prevalence of cardiovascular disease. Chest radiography can be used to assess cardiothoracic ratio (CTR) and aortic arch calcification (AoAC). The aims of this longitudinal follow-up study were to investigate factors associated with changes in CTR and AoAC and understand whether these changes are associated with overall and cardiovascular mortality in hemodialysis (HD) patients. We enrolled 260 patients undergoing HD who had at least two available chest X-rays from 2008 to 2015. CTR and AoAC were assessed in each patient using measurements from baseline and annual chest X-rays. The CTR increased from 49.05% to 51.86% and the AoAC score increased from 3.84 to 9.73 over 7 years. The estimated slopes were 0.24 (p < 0.0001) for CTR and 0.08 (p = 0.0441) for AoAC. Increased AoAC, older age, female sex, coronary artery disease, and decreased albumin were associated with an increase in CTR, and older age, cerebrovascular disease, decreased albumin, increased Kt/V, and the use of antiplatelet agents were associated with an increase in AoAC. During follow-up, 136 of the 260 (52.3%) patients died, of whom 72 died due to cardiovascular causes. The change in CTR was greater in those who died (p = 0.0125) than in those who survived. The AoAC score was also higher in those who died than in those who survived, although there was no significant difference in the change in AoAC between the two groups (p = 0.8035). CTR and AoAC increased significantly over time in the HD patients in this longitudinal follow-up study, and the change in CTR was greater in those who died than in those who survived. Chest radiography is a simple and useful tool to assess the progression of CTR and AoAC as a prognostic marker.

Download Full-text

Cardiothoracic ratio measurement using artificial intelligence: observer and method validation studies

BMC Medical Imaging ◽

10.1186/s12880-021-00625-0 ◽

2021 ◽

Vol 21 (1) ◽

Author(s):

Pairash Saiviroonporn ◽

Kanchanaporn Rodbangyang ◽

Trongtum Tongdee ◽

Warasinee Chaisangmongkon ◽

Pakorn Yodprom ◽

...

Keyword(s):

Artificial Intelligence ◽

Operating Time ◽

Operation Time ◽

Coefficient Of Determination ◽

X Rays ◽

Large Dataset ◽

Ratio Measurement ◽

Cardiothoracic Ratio ◽

Manual Methods ◽

Classification Test

Abstract Background Artificial Intelligence (AI) is a promising tool for cardiothoracic ratio (CTR) measurement that has been technically validated but not clinically evaluated on a large dataset. We observed and validated AI and manual methods for CTR measurement using a large dataset and investigated the clinical utility of the AI method. Methods Five thousand normal chest x-rays and 2,517 images with cardiomegaly and CTR values, were analyzed using manual, AI-assisted, and AI-only methods. AI-only methods obtained CTR values from a VGG-16 U-Net model. An in-house software was used to aid the manual and AI-assisted measurements and to record operating time. Intra and inter-observer experiments were performed on manual and AI-assisted methods and the averages were used in a method variation study. AI outcomes were graded in the AI-assisted method as excellent (accepted by both users independently), good (required adjustment), and poor (failed outcome). Bland–Altman plot with coefficient of variation (CV), and coefficient of determination (R-squared) were used to evaluate agreement and correlation between measurements. Finally, the performance of a cardiomegaly classification test was evaluated using a CTR cutoff at the standard (0.5), optimum, and maximum sensitivity. Results Manual CTR measurements on cardiomegaly data were comparable to previous radiologist reports (CV of 2.13% vs 2.04%). The observer and method variations from the AI-only method were about three times higher than from the manual method (CV of 5.78% vs 2.13%). AI assistance resulted in 40% excellent, 56% good, and 4% poor grading. AI assistance significantly improved agreement on inter-observer measurement compared to manual methods (CV; bias: 1.72%; − 0.61% vs 2.13%; − 1.62%) and was faster to perform (2.2 ± 2.4 secs vs 10.6 ± 1.5 secs). The R-squared and classification-test were not reliable indicators to verify that the AI-only method could replace manual operation. Conclusions AI alone is not yet suitable to replace manual operations due to its high variation, but it is useful to assist the radiologist because it can reduce observer variation and operation time. Agreement of measurement should be used to compare AI and manual methods, rather than R-square or classification performance tests.

Download Full-text

Heritability of Cardiothoracic Ratio and Aortic Arch Calcification in Twins

Medicina ◽

10.3390/medicina57050421 ◽

2021 ◽

Vol 57 (5) ◽

pp. 421

Author(s):

Zsofia Jokkel ◽

Bianka Forgo ◽

Christopher Hani-Gaius Ghattas ◽

Marton Piroska ◽

Helga Szabó ◽

...

Keyword(s):

Environmental Factors ◽

Aortic Arch ◽

Structural Equation ◽

Cardiovascular Complications ◽

X Rays ◽

Cardiothoracic Ratio ◽

South Korean ◽

High Heritability ◽

Genetic And Environmental Factors ◽

Aortic Arch Calcification

Background and Objectives: Aortic arch calcification (AoAC) is associated with a variety of cardiovascular complications. The measurement and grading of AoAC using posteroanterior (PA) chest X-rays are well established. The cardiothoracic ratio (CTR) can be simultaneously measured with PA chest X-rays and used as an index of cardiomegaly. The genetic and environmental contributions to the degree of the AoAC and CTR are not well understood. The purpose of this study was to investigate the effect of genetics and environmental factors on the AoAC and CTR. Materials and Methods: A total of 684 twins from the South Korean twin registry (261 monozygotic, MZ and 81 dizygotic, DZ pairs; mean age 38.6 ± 7.9 years, male/female = 264/420) underwent PA chest X-rays. Cardiovascular risk factors and anthropometric data were also collected. The AoAC and CTR were measured and graded using a standardized method. A structural equation method was used to calculate the proportion of variance explained by genetic and environmental factors behind AoAC and CTR. Results: The within-pair differences were low regarding the grade of AoAC, with only a few twin pairs showing large intra-pair differences. We found that the thoracic width showed high heritability (0.67, 95% CI: 0.59–0.73, p = 1). Moderate heritability was detected regarding cardiac width (0.54, 95% CI: 0.45–0.62, p = 0.572) and CTR (0.54, 95% CI: 0.44–0.62, p = 0.701). Conclusions: The heritable component was significant regarding thoracic width, cardiac width, and the CTR.

Download Full-text

White-Light Coronal Structures: Streamers and CMEs

International Astronomical Union Colloquium ◽

10.1017/s0252921100025045 ◽

1994 ◽

Vol 144 ◽

pp. 82

Author(s):

E. Hildner

Keyword(s):

Emission Line ◽

Electron Density ◽

White Light ◽

Coronal Mass Ejections ◽

X Rays ◽

Solar Cycles ◽

Temperature Function ◽

X Ray ◽

Eclipse Observations ◽

Coronal Structures

AbstractOver the last twenty years, orbiting coronagraphs have vastly increased the amount of observational material for the whitelight corona. Spanning almost two solar cycles, and augmented by ground-based K-coronameter, emission-line, and eclipse observations, these data allow us to assess,inter alia: the typical and atypical behavior of the corona; how the corona evolves on time scales from minutes to a decade; and (in some respects) the relation between photospheric, coronal, and interplanetary features. This talk will review recent results on these three topics. A remark or two will attempt to relate the whitelight corona between 1.5 and 6 R⊙to the corona seen at lower altitudes in soft X-rays (e.g., with Yohkoh). The whitelight emission depends only on integrated electron density independent of temperature, whereas the soft X-ray emission depends upon the integral of electron density squared times a temperature function. The properties of coronal mass ejections (CMEs) will be reviewed briefly and their relationships to other solar and interplanetary phenomena will be noted.

Download Full-text

Emergence of Twisted Magnetic Flux Related Sigmoidal Brightening

International Astronomical Union Colloquium ◽

10.1017/s0252921100064630 ◽

2000 ◽

Vol 179 ◽

pp. 263-264

Author(s):

K. Sundara Raman ◽

K. B. Ramesh ◽

R. Selvendran ◽

P. S. M. Aleem ◽

K. M. Hiremath

Keyword(s):

Magnetic Field ◽

Magnetic Fields ◽

Magnetic Flux ◽

Ultra Violet ◽

Active Regions ◽

Morphological Properties ◽

Energy Storage And Conversion ◽

The Sun ◽

X Rays ◽

The Magnetic Field

Extended AbstractWe have examined the morphological properties of a sigmoid associated with an SXR (soft X-ray) flare. The sigmoid is cospatial with the EUV (extreme ultra violet) images and in the optical part lies along an S-shaped Hαfilament. The photoheliogram shows flux emergence within an existingδtype sunspot which has caused the rotation of the umbrae giving rise to the sigmoidal brightening.It is now widely accepted that flares derive their energy from the magnetic fields of the active regions and coronal levels are considered to be the flare sites. But still a satisfactory understanding of the flare processes has not been achieved because of the difficulties encountered to predict and estimate the probability of flare eruptions. The convection flows and vortices below the photosphere transport and concentrate magnetic field, which subsequently appear as active regions in the photosphere (Rust & Kumar 1994 and the references therein). Successive emergence of magnetic flux, twist the field, creating flare productive magnetic shear and has been studied by many authors (Sundara Ramanet al.1998 and the references therein). Hence, it is considered that the flare is powered by the energy stored in the twisted magnetic flux tubes (Kurokawa 1996 and the references therein). Rust & Kumar (1996) named the S-shaped bright coronal loops that appear in soft X-rays as ‘Sigmoids’ and concluded that this S-shaped distortion is due to the twist developed in the magnetic field lines. These transient sigmoidal features tell a great deal about unstable coronal magnetic fields, as these regions are more likely to be eruptive (Canfieldet al.1999). As the magnetic fields of the active regions are deep rooted in the Sun, the twist developed in the subphotospheric flux tube penetrates the photosphere and extends in to the corona. Thus, it is essentially favourable for the subphotospheric twist to unwind the twist and transmit it through the photosphere to the corona. Therefore, it becomes essential to make complete observational descriptions of a flare from the magnetic field changes that are taking place in different atmospheric levels of the Sun, to pin down the energy storage and conversion process that trigger the flare phenomena.

Download Full-text

The Clinical, Roentgenological and Morphological Effects of an Acute Exposure of Phosgene on the Lungs of Dogs

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100065237 ◽

1971 ◽

Vol 29 ◽

pp. 236-237

Author(s):

R. F. Bils ◽

W. F. Diller ◽

F. Huth

Keyword(s):

Latent Period ◽

Chemical Industry ◽

Toxic Substance ◽

Lung Edema ◽

X Rays ◽

Beagle Dogs ◽

Male And Female ◽

Morphological Alterations ◽

Before And After ◽

Electron Microscopes

Phosgene still plays an important role as a toxic substance in the chemical industry. Thiess (1968) recently reported observations on numerous cases of phosgene poisoning. A serious difficulty in the clinical handling of phosgene poisoning cases is a relatively long latent period, up to 12 hours, with no obvious signs of severity. At about 12 hours heavy lung edema appears suddenly, however changes can be seen in routine X-rays taken after only a few hours' exposure (Diller et al., 1969). This study was undertaken to correlate these early changes seen by the roengenologist with morphological alterations in the lungs seen in the'light and electron microscopes.Forty-two adult male and female Beagle dogs were selected for these exposure experiments. Treated animals were exposed to 94.5-107-5 ppm phosgene for 10 min. in a 15 m3 chamber. Roentgenograms were made of the thorax of each animal before and after exposure, up to 24 hrs.

Download Full-text

Chemical Species Identification in an SEM by Changes in Emitted X-Ray Energies

Proceedings, annual meeting, Electron Microscopy Society of America ◽

10.1017/s0424820100052869 ◽

1974 ◽

Vol 32 ◽

pp. 570-571

Author(s):

R. H. Duff

Keyword(s):

Species Identification ◽

Valence Electron ◽

Chemical Species ◽

X Rays ◽

Chemical Bonds ◽

Small Shift ◽

X Ray ◽

Electron Transitions ◽

Peak Energy ◽

Chemical Combination

A material irradiated with electrons emits x-rays having energies characteristic of the elements present. Chemical combination between elements results in a small shift of the peak energies of these characteristic x-rays because chemical bonds between different elements have different energies. The energy differences of the characteristic x-rays resulting from valence electron transitions can be used to identify the chemical species present and to obtain information about the chemical bond itself. Although these peak-energy shifts have been well known for a number of years, their use for chemical-species identification in small volumes of material was not realized until the development of the electron microprobe.

Download Full-text