BI-RADS Category Assignments by GPT-3.5, GPT-4, and Google Bard: A Multilanguage Study.

Background The performance of publicly available large language models (LLMs) remains unclear for complex clinical tasks. Purpose To evaluate the agreement between human readers and LLMs for Breast Imaging Reporting and Data System (BI-RADS) categories assigned based on breast imaging reports written in three languages and to assess the impact of discordant category assignments on clinical management. Materials and Methods This retrospective study included reports for women who underwent MRI, mammography, and/or US for breast cancer screening or diagnostic purposes at three referral centers. Reports with findings categorized as BI-RADS 1-5 and written in Italian, English, or Dutch were collected between January 2000 and October 2023. Board-certified breast radiologists and the LLMs GPT-3.5 and GPT-4 (OpenAI) and Bard, now called Gemini (Google), assigned BI-RADS categories using only the findings described by the original radiologists. Agreement between human readers and LLMs for BI-RADS categories was assessed using the Gwet agreement coefficient (AC1 value). Frequencies were calculated for changes in BI-RADS category assignments that would affect clinical management (ie, BI-RADS 0 vs BI-RADS 1 or 2 vs BI-RADS 3 vs BI-RADS 4 or 5) and compared using the McNemar test. Results Across 2400 reports, agreement between the original and reviewing radiologists was almost perfect (AC1 = 0.91), while agreement between the original radiologists and GPT-4, GPT-3.5, and Bard was moderate (AC1 = 0.52, 0.48, and 0.42, respectively). Across human readers and LLMs, differences were observed in the frequency of BI-RADS category upgrades or downgrades that would result in changed clinical management (118 of 2400 [4.9%] for human readers, 611 of 2400 [25.5%] for Bard, 573 of 2400 [23.9%] for GPT-3.5, and 435 of 2400 [18.1%] for GPT-4; P < .001) and that would negatively impact clinical management (37 of 2400 [1.5%] for human readers, 435 of 2400 [18.1%] for Bard, 344 of 2400 [14.3%] for GPT-3.5, and 255 of 2400 [10.6%] for GPT-4; P < .001). Conclusion LLMs achieved moderate agreement with human reader-assigned BI-RADS categories across reports written in three languages but also yielded a high percentage of discordant BI-RADS categories that would negatively impact clinical management. © RSNA, 2024 Supplemental material is available for this article.

Current use and future perspectives of contrast-enhanced mammography (CEM): a survey by the European Society of Breast Imaging (EUSOBI).

OBJECTIVES: To perform a survey among members of the European Society of Breast Imaging (EUSOBI) regarding the use of contrast-enhanced mammography (CEM). METHODS: A panel of nine board-certified radiologists developed a 29-item online questionnaire, distributed to all EUSOBI members (inside and outside Europe) from January 25 to March 10, 2023. CEM implementation, examination protocols, reporting strategies, and current and future CEM indications were investigated. Replies were exploratively analyzed with descriptive and non-parametric statistics. RESULTS: Among 434 respondents (74.9% from Europe), 50% (217/434) declared to use CEM, 155/217 (71.4%) seeing less than 200 CEMs per year. CEM use was associated with academic settings and high breast imaging workload (p < 0.001). The lack of CEM adoption was most commonly due to the perceived absence of a clinical need (65.0%) and the lack of resources to acquire CEM-capable systems (37.3%). CEM protocols varied widely, but most respondents (61.3%) had already adopted the 2022 ACR CEM BI-RADS® lexicon. CEM use in patients with contraindications to MRI was the most common current indication (80.6%), followed by preoperative staging (68.7%). Patients with MRI contraindications also represented the most commonly foreseen CEM indication (88.0%), followed by the work-up of inconclusive findings at non-contrast examinations (61.5%) and supplemental imaging in dense breasts (53.0%). Respondents declaring CEM use and higher CEM experience gave significantly more current (p = 0.004) and future indications (p < 0.001). CONCLUSIONS: Despite a trend towards academic high-workload settings and its prevalent use in patients with MRI contraindications, CEM use and progressive experience were associated with increased confidence in the technique. CLINICAL RELEVANCE STATEMENT: In this first survey on contrast-enhanced mammography (CEM) use and perspectives among the European Society of Breast Imaging (EUSOBI) members, the perceived absence of a clinical need chiefly drove the 50% CEM adoption rate. CEM adoption and progressive experience were associated with more extended current and future indications. KEY POINTS: • Among the 434 members of the European Society of Breast Imaging who completed this survey, 50% declared to use contrast-enhanced mammography in clinical practice. • Due to the perceived absence of a clinical need, contrast-enhanced mammography (CEM) is still prevalently used as a replacement for MRI in patients with MRI contraindications. • The number of current and future CEM indications marked by respondents was associated with their degree of CEM experience.

Inter-reader agreement of breast magnetic resonance imaging and contrast-enhanced mammography in breast cancer diagnosis: a multi-reader retrospective study.

OBJECTIVE: Breast magnetic resonance imaging (MRI) and contrast-enhanced mammography (CEM) are nowadays used in breast imaging but studies about their inter-reader agreement are lacking. Therefore, we compared the inter-reader agreement of CEM and MRI in breast cancer diagnosis in the same patients. METHODS: Breast MRI and CEM exams performed in a single center (09/2020-09/2021) for an IRB-approved study were retrospectively and independently evaluated by four radiologists of two different centers with different levels of experience who were blinded to the clinical and other imaging data. The reference standard was the histological diagnosis or at least 1-year negative imaging follow-up. Inter-reader agreement was examined using Cohen's and Fleiss' kappa (κ) statistics and compared with the Wald test. RESULTS: Of the 750 patients, 395 met inclusion criteria (44.5 ± 14 years old), with 752 breasts available for CEM and MRI. Overall agreement was moderate (κ = 0.60) for MRI and substantial (κ = 0.74) for CEM. For expert readers, the agreement was substantial (κ = 0.77) for MRI and almost perfect (κ = 0.82) for CEM; for non-expert readers was fair (κ = 0.39); and for MRI and moderate (κ = 0.57) for CEM. Pairwise agreement between expert readers and non-expert readers was moderate (κ = 0.50) for breast MRI and substantial (κ = 0.74) for CEM and it showed a statistically superior agreement of the expert over the non-expert readers only for MRI (p = 0.011) and not for CEM (p = 0.062). CONCLUSIONS: The agreement of CEM was superior to that of MRI (p = 0.012), including for both expert (p = 0.031) and non-expert readers (p = 0.005).

MRI-Conditional Breast Tissue Expander: First In-Human Multi-Case Assessment of MRI-Related Complications and Image Quality.

This study aims to assess potential complications and effects on the magnetic resonance imaging (MRI) image quality of a new MRI-conditional breast tissue expander (Motiva Flora®) in its first in-human multi-case application. Twenty-four patients with 36 expanders underwent non-contrast breast MRI with T1-weighted, T2-weighted, and diffusion-weighted imaging (DWI) sequences on a 3 T unit before breast tissue expander exchange surgery, being monitored during and after MRI for potential complications. Three board-certified breast radiologists blindly and independently reviewed image quality using a four-level scale ("poor", "sufficient", "good", and "excellent"), with inter-reader reliability being assessed with Kendall's τb. The maximum diameters of RFID-related artifacts on T1-weighted and DWI sequences were compared with the Wilcoxon signed-rank test. All 24 examinations were completed without patient-related or device-related complications. The T1-weighted and T2-weighted sequences of all the examinations had "excellent" image quality and a median 11 mm (IQR 9-12 mm) RFID artifact maximum diameter, significantly lower (p < 0.001) than on the DWI images (median 32.5 mm, IQR 28.5-34.5 mm). DWI quality was rated at least "good" in 63% of the examinations, with strong inter-reader reliability (Kendall's τb 0.837, 95% CI 0.687-0.952). This first in-human study confirms the MRI-conditional profile of this new expander, which does not affect the image quality of T1-weighted and T2-weighted sequences and moderately affects DWI quality.

European Society of Breast Imaging (EUSOBI) guidelines on the management of axillary lymphadenopathy after COVID-19 vaccination: 2023 revision.

Axillary lymphadenopathy is a common side effect of COVID-19 vaccination, leading to increased imaging-detected asymptomatic and symptomatic unilateral axillary lymphadenopathy. This has threatened to negatively impact the workflow of breast imaging services, leading to the release of ten recommendations by the European Society of Breast Imaging (EUSOBI) in August 2021. Considering the rapidly changing scenario and data scarcity, these initial recommendations kept a highly conservative approach. As of 2023, according to newly acquired evidence, EUSOBI proposes the following updates, in order to reduce unnecessary examinations and avoid delaying necessary examinations. First, recommendation n. 3 has been revised to state that breast examinations should not be delayed or rescheduled because of COVID-19 vaccination, as evidence from the first pandemic waves highlights how delayed or missed screening tests have a negative effect on breast cancer morbidity and mortality, and that there is a near-zero risk of subsequent malignant findings in asymptomatic patients who have unilateral lymphadenopathy and no suspicious breast findings. Second, recommendation n. 7 has been revised to simplify follow-up strategies: in patients without breast cancer history and no imaging findings suspicious for cancer, symptomatic and asymptomatic imaging-detected unilateral lymphadenopathy on the same side of recent COVID-19 vaccination (within 12 weeks) should be classified as a benign finding (BI-RADS 2) and no further work-up should be pursued. All other recommendations issued by EUSOBI in 2021 remain valid.

Artificial intelligence (AI) in biomedical research: discussion on authors' declaration of AI in their articles title.

Artificial intelligence (AI) and its different approaches, from machine learning to deep learning, are not new. We discuss here about the declaration of AI in the title of those articles dealing with AI. From 1990 to 2021, while AI articles in the PubMed increased from 300 to 59,596, the percentage declaring AI in the title describes a U-like-shaped curve: about 30% in early 1990s, less than 13% in 2005-2014, again 30% in 2020-2021. A similar trend was observed for AI in medical imaging. While the initial decline could be due to the establishment of AI methods, the recent increase could be related to the capacity of AI to outperform humans, especially in image recognition, fuelled by the adoption of graphic processing units for general purpose computing. The recent increase may also be due to the relevance of open issues about AI, including the standardisation of methods, explainability of results, and concerns about AI-induced epoch-making transformations: to say "We are using AI" in the title may also reflect these concerns.

Contrast-enhanced mammography-guided biopsy: why, when, and where we need it.

KEY POINTS: • The use of CEM-guided biopsy is spreading after initial experiences in a few pilot centers.• CEM-guided biopsy has the potential to ensure fast, low-cost, and effective tissue sampling of MRI-detected and CEM-detected lesions that do not have a corresponding finding at morphological imaging.• The need and utility of CEM-guided biopsy are warranted by the impending expansion of morpho-functional imaging towards breast cancer screening for women with extremely dense breasts.

Artificial intelligence for digital breast tomosynthesis: Impact on diagnostic performance, reading times, and workload in the era of personalized screening.

The ultimate goals of the application of artificial intelligence (AI) to digital breast tomosynthesis (DBT) are the reduction of reading times, the increase of diagnostic performance, and the reduction of interval cancer rates. In this review, after outlining the journey from computer-aided detection/diagnosis systems to AI applied to digital mammography (DM), we summarize the results of studies where AI was applied to DBT, noting that long-term advantages of DBT screening and its crucial ability to decrease the interval cancer rate are still under scrutiny. AI has shown the capability to overcome some shortcomings of DBT in the screening setting by improving diagnostic performance and by reducing recall rates (from -2 % to -27 %) and reading times (up to -53 %, with an average 20 % reduction), but the ability of AI to reduce interval cancer rates has not yet been clearly investigated. Prospective validation is needed to assess the cost-effectiveness and real-world impact of AI models assisting DBT interpretation, especially in large-scale studies with low breast cancer prevalence. Finally, we focus on the incoming era of personalized and risk-stratified screening that will first see the application of contrast-enhanced breast imaging to screen women with extremely dense breasts. As the diagnostic advantage of DBT over DM was concentrated in this category, we try to understand if the application of AI to DM in the remaining cohorts of women with heterogeneously dense or non-dense breast could close the gap in diagnostic performance between DM and DBT, thus neutralizing the usefulness of AI application to DBT.

Ultrasonography as first line imaging for the diagnosis of positional plagiocephaly.

BACKGROUND: In the last years, numerous studies evaluated different tools for the diagnosis of positional plagiocephaly (PP). The purpose of this study was to evaluate ultrasonography (US) as a first line screening test of lambdoid sutural patency in child with PP and to compare our results with the literature. METHODS: All consecutive patients who referred to our Institute from January 2016 to October 2017 with the suspicion of PP, were included in the study and performed US examination of the lambdoid sutures. A 3-6-month clinical follow-up was performed by a pediatric neurosurgeon or a pediatrician to confirm the diagnosis of PP. RESULTS: Thirty-five children performed US examination and in all cases the diagnosis of PP was confirmed. No cases of anticipated suture fusion were examined during this period. The concordance between US findings and clinical exam follow-up was 100%. CONCLUSIONS: Ultrasonography of the lambdoid sutures represents an ideal first-line screening test and reliable alternative to other diagnostic techniques for lambdoid sutural patency in child with PP, being radiation free, fast and cheap.

Computation of contrast-enhanced perfusion using only two CT scan phases: a proof-of-concept study on abdominal organs.

BACKGROUND: Computed tomography perfusion imaging (CTPI) by repeated scanning has clinical relevance but implies relatively high radiation exposure. We present a method to measure perfusion from two CT scan phases only, considering tissue enhancement, feeding vessel (aortic) peak enhancement, and bolus shape. METHODS: CTPI scans (each with 40 frames acquired every 1.5 s) of 11 patients with advanced hepatocellular carcinoma (HCC) enrolled between 2012 and 2016 were retrospectively analysed (aged 69 ± 9 years, 8/11 males). Perfusion was defined as the maximal slope of the time-enhancement curve divided by the peak enhancement of the feeding vessel (aorta). Perfusion was computed two times, first using the maximum slope derived from all data points and then using the peak tissue enhancement and the bolus shape obtained from the aortic curve. RESULTS: Perfusion values from the two methods were linearly related (r2 = 0.92, p < 0.001; Bland-Altman analysis bias -0.12). The mathematical model showed that the perfusion ratio of two ROIs with the same feeding vessel (aorta) corresponds to their peak enhancement ratio (r2 = 0.55, p < 0.001; Bland-Altman analysis bias -0.68). The relationship between perfusion and tissue enhancement is predicted to be linear in the clinical range of interest, being only function of perfusion, peak feeding vessel enhancement, and bolus shape. CONCLUSIONS: This proof-of-concept study showed that perfusion values of HCC, kidney, and pancreas could be computed using enhancement measured only with two CT scan phases, if aortic peak enhancement and bolus shape are known.

Contrast-enhanced mammography for the assessment of screening recalls: a two-centre study.

OBJECTIVES: To evaluate the potential of contrast-enhanced mammography (CEM) for reducing the biopsy rate of screening recalls. METHODS: Recalled women were prospectively enrolled to undergo CEM alongside standard assessment (SA) through additional views, tomosynthesis, and/or ultrasound. Exclusion criteria were symptoms, implants, allergy to contrast agents, renal failure, and pregnancy. SA and CEM were independently evaluated by one of six radiologists, who recommended biopsy or 2-year follow-up. Biopsy rates according to SA or recombined CEM (rCEM) were compared with the McNemar's test. Diagnostic performance was calculated considering lesions with available final histopathology. RESULTS: Between January 2019 and July 2021, 220 women were enrolled, 207 of them (median age 56.6 years) with 225 suspicious findings analysed. Three of 207 patients (1.4%) developed mild self-limiting adverse reactions to iodinated contrast agent. Overall, 135/225 findings were referred for biopsy, 90/225 by both SA and rCEM, 41/225 by SA alone and 4/225 by rCEM alone (2/4 being one DCIS and one invasive carcinoma). The rCEM biopsy rate (94/225, 41.8%, 95% CI 35.5-48.3%) was 16.4% lower (p < 0.001) than the SA biopsy rate (131/225, 58.2%, 95% CI 51.7-64.5%). Considering the 124/135 biopsies with final histopathology (44 benign, 80 malignant), rCEM showed a 93.8% sensitivity (95% CI 86.2-97.3%) and a 65.9% specificity (95% CI 51.1-78.1%), all 5 false negatives being ductal carcinoma in situ detectable as suspicious calcifications on low-energy images. CONCLUSIONS: Compared to SA, the rCEM-based work-up would have avoided biopsy for 37/225 (16.4%) suspicious findings. Including low-energy images in interpretation provided optimal overall CEM sensitivity. KEY POINTS: • The work-up of suspicious findings detected at mammographic breast cancer screening still leads to a high rate of unnecessary biopsies, involving between 2 and 6% of screened women. • In 207 recalled women with 225 suspicious findings, recombined images of contrast-enhanced mammography (CEM) showed a 93.8% sensitivity and a 65.9% specificity, all 5 false negatives being ductal carcinoma in situ detectable on low-energy images as suspicious calcifications. • CEM could represent an easily available one-stop shop option for the morphofunctional assessment of screening recalls, potentially reducing the biopsy rate by 16.4%.

Development and Validation of an AI-driven Mammographic Breast Density Classification Tool Based on Radiologist Consensus.

Mammographic breast density (BD) is commonly visually assessed using the Breast Imaging Reporting and Data System (BI-RADS) four-category scale. To overcome inter- and intraobserver variability of visual assessment, the authors retrospectively developed and externally validated a software for BD classification based on convolutional neural networks from mammograms obtained between 2017 and 2020. The tool was trained using the majority BD category determined by seven board-certified radiologists who independently visually assessed 760 mediolateral oblique (MLO) images in 380 women (mean age, 57 years ± 6 [SD]) from center 1; this process mimicked training from a consensus of several human readers. External validation of the model was performed by the three radiologists whose BD assessment was closest to the majority (consensus) of the initial seven on a dataset of 384 MLO images in 197 women (mean age, 56 years ± 13) obtained from center 2. The model achieved an accuracy of 89.3% in distinguishing BI-RADS a or b (nondense breasts) versus c or d (dense breasts) categories, with an agreement of 90.4% (178 of 197 mammograms) and a reliability of 0.807 (Cohen κ) compared with the mode of the three readers. This study demonstrates accuracy and reliability of a fully automated software for BD classification. Keywords: Mammography, Breast, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms Supplemental material is available for this article. © RSNA, 2022.

Radiation Dose of Contrast-Enhanced Mammography: A Two-Center Prospective Comparison.

The radiation dose associated with contrast-enhanced mammography (CEM) has been investigated only by single-center studies. In this retrospective study, we aimed to compare the radiation dose between two centers performing CEM within two prospective studies, using the same type of equipment. The CEM mean glandular dose (MGD) was computed for low energy (LE) and high energy (HE) images and their sum was calculated for each view. MGD and related parameters (entrance dose, breast thickness, compression, and density) were compared between the two centers using the Mann−Whitney test. Finally, per-patient MGD was calculated by pooling the two datasets and determining the contribution of LE and HE images. A total of 348 CEM examinations were analyzed (228 from Center 1 and 120 from Center 2). The median total MGD per view was 2.33 mGy (interquartile range 2.19−2.51 mGy) at Center 1 and 2.46 mGy (interquartile range 2.32−2.70 mGy) at Center 2, with a 0.15 mGy median difference (p < 0.001) equal to 6.2%. LE-images contributed between 64% and 77% to the total patient dose in CEM, with the remaining 23−36% being associated with HE images. The mean radiation dose for a two-view bilateral CEM exam was 4.90 mGy, about 30% higher than for digital mammography.

A Machine Learning Ensemble Based on Radiomics to Predict BI-RADS Category and Reduce the Biopsy Rate of Ultrasound-Detected Suspicious Breast Masses.

We developed a machine learning model based on radiomics to predict the BI-RADS category of ultrasound-detected suspicious breast lesions and support medical decision-making towards short-interval follow-up versus tissue sampling. From a retrospective 2015-2019 series of ultrasound-guided core needle biopsies performed by four board-certified breast radiologists using six ultrasound systems from three vendors, we collected 821 images of 834 suspicious breast masses from 819 patients, 404 malignant and 430 benign according to histopathology. A balanced image set of biopsy-proven benign (n = 299) and malignant (n = 299) lesions was used for training and cross-validation of ensembles of machine learning algorithms supervised during learning by histopathological diagnosis as a reference standard. Based on a majority vote (over 80% of the votes to have a valid prediction of benign lesion), an ensemble of support vector machines showed an ability to reduce the biopsy rate of benign lesions by 15% to 18%, always keeping a sensitivity over 94%, when externally tested on 236 images from two image sets: (1) 123 lesions (51 malignant and 72 benign) obtained from two ultrasound systems used for training and from a different one, resulting in a positive predictive value (PPV) of 45.9% (95% confidence interval 36.3-55.7%) versus a radiologists' PPV of 41.5% (p < 0.005), combined with a 98.0% sensitivity (89.6-99.9%); (2) 113 lesions (54 malignant and 59 benign) obtained from two ultrasound systems from vendors different from those used for training, resulting into a 50.5% PPV (40.4-60.6%) versus a radiologists' PPV of 47.8% (p < 0.005), combined with a 94.4% sensitivity (84.6-98.8%). Errors in BI-RADS 3 category (i.e., assigned by the model as BI-RADS 4) were 0.8% and 2.7% in the Testing set I and II, respectively. The board-certified breast radiologist accepted the BI-RADS classes assigned by the model in 114 masses (92.7%) and modified the BI-RADS classes of 9 breast masses (7.3%). In six of nine cases, the model performed better than the radiologist did, since it assigned a BI-RADS 3 classification to histopathology-confirmed benign masses that were classified as BI-RADS 4 by the radiologist.

Mammography self-evaluation online test for screening readers: an Italian Society of Medical Radiology (SIRM) initiative.

OBJECTIVES: To report and analyse the characteristics and performance of the first cohort of Italian radiologists completing the national mammography self-evaluation online test established by the Italian Society of Medical Radiology (SIRM). METHODS: A specifically-built dataset of 132 mammograms (24 with screen-detected cancers and 108 negative cases) was preliminarily tested on 48 radiologists to define pass thresholds (62% sensitivity and 86% specificity) and subsequently made available online to SIRM members during a 13-month timeframe between 2018 and 2019. Associations between participants' characteristics, pass rates, and diagnostic accuracy were then investigated with descriptive statistics and univariate and multivariable regression analyses. RESULTS: A total of 342 radiologists completed the test, 151/342 (44.2%) with success. All individual variables, except gender, showed a significant correlation with pass rates and diagnostic sensitivity, confirmed by univariate logistic regression, while only involvement in organised screening programs and number of mammograms read per year showed a positive association with specificity at univariate logistic regression. In the multivariable regression analysis, fewer variables remained significant: > 3000 mammograms read per year for success rate; female gender, public practice setting, and higher experience self-judgement for sensitivity; no variables were significantly associated with specificity. CONCLUSIONS: This national self-evaluation test effectively differentiated multiple aspects of mammographic reading experience, but specific breast imaging experience was shown not to strictly guarantee good diagnostic accuracy. Due to its easy use and the validity of obtained results, this test could be extended to all Italian breast radiologists, regardless of their experience, also as a Breast Unit accreditation criterion. KEY POINTS: • This self-evaluation test was found to be able to differentiate various degrees of mammographic interpretation experience. • Breast cancer screening readers should undergo a self-assessment test, since experience parameters alone do not guarantee diagnostic ability.

Abdominal obesity phenotype is associated with COVID-19 chest X-ray severity score better than BMI-based obesity.

PURPOSE: Chest X-ray (CXR) severity score and BMI-based obesity are predictive risk factors for COVID-19 hospital admission. However, the relationship between abdominal obesity and CXR severity score has not yet been fully explored. METHODS: This retrospective cohort study analyzed the association of different adiposity indexes, including waist circumference and body mass index (BMI), with CXR severity score in 215 hospitalized patients with COVID-19. RESULTS: Patients with abdominal obesity showed significantly higher CXR severity scores and had higher rates of CXR severity scores ≥ 8 compared to those without abdominal obesity (P < 0.001; P = 0.001, respectively). By contrast, patients with normal weight, with overweight and those with BMI-based obesity showed no significant differences in either CXR severity scores or in the rates of CXR severity scores ≥ 8 (P = 0.104; P = 0.271, respectively). Waist circumference and waist-to-height ratio (WHtR) correlated more closely with CXR severity scores than BMI (r = 0.43, P < 0.001; r = 0.41, P < 0.001; r = 0.17, P = 0.012, respectively). The area under the curves (AUCs) for waist circumference and WHtR were significantly higher than that for BMI in identifying a high CXR severity score (≥ 8) (0.68 [0.60-0.75] and 0.67 [0.60-0.74] vs 0.58 [0.51-0.66], P = 0.001). A multivariate analysis indicated abdominal obesity (risk ratio: 1.75, 95% CI: 1.25-2.45, P < 0.001), bronchial asthma (risk ratio: 1.73, 95% CI: 1.07-2.81, P = 0.026) and oxygen saturation at admission (risk ratio: 0.96, 95% CI: 0.94-0.97, P < 0.001) as the only independent factors associated with high CXR severity scores. CONCLUSION: Abdominal obesity phenotype is associated with a high CXR severity score better than BMI-based obesity in hospitalized patients with COVID-19. Therefore, when visiting the patient in a hospital setting, waist circumference should be measured, and patients with abdominal obesity should be monitored closely. Level of evidence Cross-sectional descriptive study, Level V.