RESUMEN
Applications of large language models (LLMs) in the healthcare field have shown promising results in processing and summarizing multidisciplinary information. This study evaluated the ability of three publicly available LLMs (GPT-3.5, GPT-4, and Google Gemini-then called Bard) to answer 60 multiple-choice questions (29 sourced from public databases, 31 newly formulated by experienced breast radiologists) about different aspects of breast cancer care: treatment and prognosis, diagnostic and interventional techniques, imaging interpretation, and pathology. Overall, the rate of correct answers significantly differed among LLMs (p = 0.010): the best performance was achieved by GPT-4 (95%, 57/60) followed by GPT-3.5 (90%, 54/60) and Google Gemini (80%, 48/60). Across all LLMs, no significant differences were observed in the rates of correct replies to questions sourced from public databases and newly formulated ones (p ≥ 0.593). These results highlight the potential benefits of LLMs in breast cancer care, which will need to be further refined through in-context training.
RESUMEN
PURPOSE: To evaluate if background parenchymal enhancement (BPE) on contrast-enhanced mammography (CEM), graded according to the 2022 CEM-dedicated Breast Imaging Reporting and Data System (BI-RADS) lexicon, is associated with breast density, menopausal status, and age. METHODS: This bicentric retrospective analysis included CEM examinations performed for the work-up of suspicious mammographic findings. Three readers independently and blindly evaluated BPE on recombined CEM images and breast density on low-energy CEM images. Inter-reader reliability was estimated using Fleiss κ. Multivariable binary logistic regression was performed, dichotomising breast density and BPE as low (a/b BI-RADS categories, minimal/mild BPE) and high (c/d BI-RADS categories, moderate/marked BPE). RESULTS: A total of 200 women (median age 56.8 years, interquartile range 50.5-65.6, 140/200 in menopause) were included. Breast density was classified as a in 27/200 patients (13.5%), as b in 110/200 (55.0%), as c in 52/200 (26.0%), and as d in 11/200 (5.5%), with moderate inter-reader reliability (κ = 0.536; 95% confidence interval [CI] 0.482-0.590). BPE was minimal in 95/200 patients (47.5%), mild in 64/200 (32.0%), moderate in 25/200 (12.5%), marked in 16/200 (8.0%), with substantial inter-reader reliability (κ = 0.634; 95% CI 0.581-0.686). At multivariable logistic regression, premenopausal status and breast density were significant positive predictors of high BPE, with adjusted odds ratios of 6.120 (95% CI 1.847-20.281, p = 0.003) and 2.416 (95% CI 1.095-5.332, p = 0.029) respectively. CONCLUSION: BPE on CEM is associated with well-established breast cancer risk factors, being higher in women with higher breast density and premenopausal status.
RESUMEN
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.
Asunto(s)
Neoplasias de la Mama , Adulto , Anciano , Femenino , Humanos , Persona de Mediana Edad , Mama/diagnóstico por imagen , Neoplasias de la Mama/diagnóstico por imagen , Lenguaje , Imagen por Resonancia Magnética/métodos , Mamografía/métodos , Sistemas de Información Radiológica/estadística & datos numéricos , Estudios Retrospectivos , Ultrasonografía Mamaria/métodosRESUMEN
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.
Asunto(s)
Neoplasias de la Mama , Medios de Contraste , Mamografía , Sociedades Médicas , Humanos , Mamografía/métodos , Europa (Continente) , Femenino , Neoplasias de la Mama/diagnóstico por imagen , Encuestas y Cuestionarios , Pautas de la Práctica en Medicina/estadística & datos numéricosRESUMEN
OBJECTIVES: To investigate the influence of preoperative breast MRI on mastectomy and reoperation rates in patients with pure ductal carcinoma in situ (DCIS). METHODS: The MIPA observational study database (7245 patients) was searched for patients aged 18-80 years with pure unilateral DCIS diagnosed at core needle or vacuum-assisted biopsy (CNB/VAB) and planned for primary surgery. Patients who underwent preoperative MRI (MRI group) were matched (1:1) to those who did not receive MRI (noMRI group) according to 8 confounding covariates that drive referral to MRI (age; hormonal status; familial risk; posterior-to-nipple diameter; BI-RADS category; lesion diameter; lesion presentation; surgical planning at conventional imaging). Surgical outcomes were compared between the matched groups with nonparametric statistics after calculating odds ratios (ORs). RESULTS: Of 1005 women with pure unilateral DCIS at CNB/VAB (507 MRI group, 498 noMRI group), 309 remained in each group after matching. First-line mastectomy rate in the MRI group was 20.1% (62/309 patients, OR 2.03) compared to 11.0% in the noMRI group (34/309 patients, p = 0.003). The reoperation rate was 10.0% in the MRI group (31/309, OR for reoperation 0.40) and 22.0% in the noMRI group (68/309, p < 0.001), with a 2.53 OR of avoiding reoperation in the MRI group. The overall mastectomy rate was 23.3% in the MRI group (72/309, OR 1.40) and 17.8% in the noMRI group (55/309, p = 0.111). CONCLUSIONS: Compared to those going directly to surgery, patients with pure DCIS at CNB/VAB who underwent preoperative MRI had a higher OR for first-line mastectomy but a substantially lower OR for reoperation. CLINICAL RELEVANCE STATEMENT: When confounding factors behind MRI referral are accounted for in the comparison of patients with CNB/VAB-diagnosed pure unilateral DCIS, preoperative MRI yields a reduction of reoperations that is more than twice as high as the increase in overall mastectomies. KEY POINTS: ⢠Confounding factors cause imbalance when investigating the influence of preoperative MRI on surgical outcomes of pure DCIS. ⢠When patient matching is applied to women with pure unilateral DCIS, reoperation rates are significantly reduced in women who underwent preoperative MRI. ⢠The reduction of reoperations brought about by preoperative MRI is more than double the increase in overall mastectomies.
RESUMEN
PURPOSE: Primary purpose was to assess changes of bone mineral density (BMD) in diffuse large B cell lymphoma (DLBCL) patients treated with rituximab, cyclophosphamide, doxorubicin, vincristine, and prednisone R-CHOP (like) chemotherapy regimen. Secondary purposes were to assess other body composition features changes and to assess the association of pre-therapy values and their changes over time with survival. MATERIAL AND METHODS: Patients selected underwent R-CHOP(like) regimen for DLBCL, and underwent PET-CT before and after treatment. Main clinical data collected included body mass index, date of last follow-up, date of progression, and date of death. From the low-dose CT images, BMD was assessed at the L1 level; the other body composition values, including muscle and fat distribution, were assessed at the L3 level by using a dedicated software. Descriptive statistics were reported as median and interquartile range, or frequencies and percentages. Statistical comparisons of body composition variables between pre- and post-treatment assessments were performed using the Wilcoxon matched pairs signed rank test. Non-normal distribution of variables was tested with the Shapiro-Wilk test. For qualitative variables, the Fisher exact test was used. Log rank test was used to compare survival between different subgroups of the study population defined by specific body composition cutoffs. The significance level was set at p < 0.05. RESULTS: Eighty-two patients were included. The mean follow-up was 37.5 ± 21.4 months. A significant difference was found in mean BMD before and after R-CHOP(like) treatment (p < 0.0001). The same trend was observed for mean skeletal muscle area (SMA) (p = 0.004) and mean skeletal muscle index (SMI) (p = 0.006). No significant association was demonstrated between body composition variables, PFS and OS. CONCLUSION: R-CHOP(like) treatment in DLBCL patients was associated with significant reduction of BMD, SMA and SMI.
Asunto(s)
Linfoma de Células B Grandes Difuso , Tomografía Computarizada por Tomografía de Emisión de Positrones , Humanos , Anticuerpos Monoclonales de Origen Murino/efectos adversos , Supervivencia sin Enfermedad , Protocolos de Quimioterapia Combinada Antineoplásica/uso terapéutico , Rituximab/uso terapéutico , Linfoma de Células B Grandes Difuso/diagnóstico por imagen , Linfoma de Células B Grandes Difuso/tratamiento farmacológico , Vincristina/uso terapéutico , Vincristina/efectos adversos , Doxorrubicina/uso terapéutico , Resultado del TratamientoRESUMEN
This exploratory retrospective study aims to quantitatively compare the image quality of unenhanced brain computed tomography (CT) reconstructed with an iterative (AIDR-3D) and a deep learning-based (AiCE) reconstruction algorithm. After a preliminary phantom study, AIDR-3D and AiCE reconstructions (0.5 mm thickness) of 100 consecutive brain CTs acquired in the emergency setting on the same 320-detector row CT scanner were retrospectively analyzed, calculating image noise reduction attributable to the AiCE algorithm, artifact indexes in the posterior cranial fossa, and contrast-to-noise ratios (CNRs) at the cortical and thalamic levels. In the phantom study, the spatial resolution of the two datasets proved to be comparable; conversely, AIDR-3D reconstructions showed a broader noise pattern. In the human study, median image noise was lower with AiCE compared to AIDR-3D (4.7 vs. 5.3, p < 0.001, median 19.6% noise reduction), whereas AIDR-3D yielded a lower artifact index than AiCE (7.5 vs. 8.4, p < 0.001). AiCE also showed higher median CNRs at the cortical (2.5 vs. 1.8, p < 0.001) and thalamic levels (2.8 vs. 1.7, p < 0.001). These results highlight how image quality improvements granted by deep learning-based (AiCE) and iterative (AIDR-3D) image reconstruction algorithms vary according to different brain areas.
Asunto(s)
Aprendizaje Profundo , Humanos , Estudios Retrospectivos , Tomografía Computarizada por Rayos X , Encéfalo/diagnóstico por imagen , Procesamiento de Imagen Asistido por ComputadorRESUMEN
PURPOSE: To evaluate the technical success and efficacy rates of US-guided percutaneous vacuum-assisted excision (VAE) of breast fibroadenomas, also assessing procedural complications and long-term patient satisfaction rates. MATERIALS AND METHODS: The institutional database of a tertiary breast cancer referral centre was retrospectively reviewed to retrieve all women with fibroadenomas who underwent US-guided VAE between May 2011 and September 2019. We subsequently included in this study all fibroadenomas with a maximum diameter of 3 cm at US and an available histological confirmation obtained by core-needle biopsy before VAE. Immediately after VAE, technical success (defined as the correct VAE execution) and the occurrence of procedural complications were evaluated. Imaging follow-up (US ± mammography) after 6, 12, 24 and 36 months was performed to evaluate technical efficacy (defined as the absence of fibroadenoma recurrence at 6-month follow-up). Long-term patient satisfaction was evaluated with telephonic interviews in October 2022. RESULTS: We retrospectively included 108 women (median age 46 years) with 110 fibroadenomas diagnosed at core-needle biopsy with a median lesion size at US of 12 mm. Technical success was obtained in 110/110 VAEs (100%). Minor procedural complications (haematomas) occurred in 7/110 VAEs (6%), whereas 8/110 patients had a fibroadenoma recurrence at 6-month follow-up, resulting in a 93% technical efficacy (102/110 VAEs). All patients available for telephonic follow-up (104/104, 100%) reported high satisfaction with VAE results. CONCLUSION: US-guided VAE is a safe and effective procedure for the excision of fibroadenomas, representing a viable alternative to surgery, with a low complication rate and high patient satisfaction.
Asunto(s)
Neoplasias de la Mama , Fibroadenoma , Femenino , Humanos , Persona de Mediana Edad , Fibroadenoma/diagnóstico por imagen , Fibroadenoma/cirugía , Fibroadenoma/patología , Estudios Retrospectivos , Ultrasonografía Intervencional/métodos , Neoplasias de la Mama/diagnóstico por imagen , Neoplasias de la Mama/cirugía , Neoplasias de la Mama/patología , MamografíaRESUMEN
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.
RESUMEN
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.
RESUMEN
The potential enviromental impact of iodinated (ICAs) and gadolinium-based contrast agents (GBCAs) have recently come under scrutiny, considering the current nonselective wastewater treatment. However, their rapid excretion after intravenous administration could allow their potential recovery by targeting hospital sewage. The GREENWATER study aims to appraise the effective quantities of ICAs and GBCAs retrievable from patients' urine collected after computed tomography (CT) and magnetic resonance imaging (MRI) exams, selecting ICA/GBCA per-patient urinary excretion and patients' acceptance rate as study endpoints. Within a prospective, observational, single-centre, 1-year framework, we will enrol outpatients aged ≥ 18 years, scheduled to perform contrast-enhanced CT or MRI, willing to collect post-examination urine in dedicated canisters by prolonging their hospital stay to 1 h after injection. Collected urine will be processed and partially stored in the institutional biobank. Patient-based analysis will be performed for the first 100 CT and 100 MRI patients, and then, all analyses will be conducted on the pooled urinary sample. Quantification of urinary iodine and gadolinium will be performed with spectroscopy after oxidative digestion. The evaluation of the acceptance rate will assess the "environmental awareness" of patients and will aid to model how procedures to reduce ICA/GBCA enviromental impact could be adapted in different settings. Key points ⢠Enviromental impact of iodinated and gadolinium-based contrast agents represents a growing point of attention.⢠Current wastewater treatment is unable to retrieve and recycle contrast agents.⢠Prolonging hospital stay may allow contrast agents retrieval from patients' urine.⢠The GREENWATER study will assess the effectively retrievable contrast agents' quantities.⢠The enrolment acceptance rate will allow to evaluate patients' "green sensitivity".
Asunto(s)
Medios de Contraste , Aguas Residuales , Humanos , Gadolinio/orina , Hospitales , Estudios Prospectivos , Sustancias Reductoras , Estudios Observacionales como AsuntoRESUMEN
OBJECTIVES: To report mastectomy and reoperation rates in women who had breast MRI for screening (S-MRI subgroup) or diagnostic (D-MRI subgroup) purposes, using multivariable analysis for investigating the role of MRI referral/nonreferral and other covariates in driving surgical outcomes. METHODS: The MIPA observational study enrolled women aged 18-80 years with newly diagnosed breast cancer destined to have surgery as the primary treatment, in 27 centres worldwide. Mastectomy and reoperation rates were compared using non-parametric tests and multivariable analysis. RESULTS: A total of 5828 patients entered analysis, 2763 (47.4%) did not undergo MRI (noMRI subgroup) and 3065 underwent MRI (52.6%); of the latter, 2441/3065 (79.7%) underwent MRI with preoperative intent (P-MRI subgroup), 510/3065 (16.6%) D-MRI, and 114/3065 S-MRI (3.7%). The reoperation rate was 10.5% for S-MRI, 8.2% for D-MRI, and 8.5% for P-MRI, while it was 11.7% for noMRI (p ≤ 0.023 for comparisons with D-MRI and P-MRI). The overall mastectomy rate (first-line mastectomy plus conversions from conserving surgery to mastectomy) was 39.5% for S-MRI, 36.2% for P-MRI, 24.1% for D-MRI, and 18.0% for noMRI. At multivariable analysis, using noMRI as reference, the odds ratios for overall mastectomy were 2.4 (p < 0.001) for S-MRI, 1.0 (p = 0.957) for D-MRI, and 1.9 (p < 0.001) for P-MRI. CONCLUSIONS: Patients from the D-MRI subgroup had the lowest overall mastectomy rate (24.1%) among MRI subgroups and the lowest reoperation rate (8.2%) together with P-MRI (8.5%). This analysis offers an insight into how the initial indication for MRI affects the subsequent surgical treatment of breast cancer. KEY POINTS: ⢠Of 3065 breast MRI examinations, 79.7% were performed with preoperative intent (P-MRI), 16.6% were diagnostic (D-MRI), and 3.7% were screening (S-MRI) examinations. ⢠The D-MRI subgroup had the lowest mastectomy rate (24.1%) among MRI subgroups and the lowest reoperation rate (8.2%) together with P-MRI (8.5%). ⢠The S-MRI subgroup had the highest mastectomy rate (39.5%) which aligns with higher-than-average risk in this subgroup, with a reoperation rate (10.5%) not significantly different to that of all other subgroups.
Asunto(s)
Neoplasias de la Mama , Femenino , Humanos , Neoplasias de la Mama/diagnóstico por imagen , Neoplasias de la Mama/cirugía , Mastectomía , Mastectomía Segmentaria , Mama , Imagen por Resonancia Magnética , Cuidados PreoperatoriosRESUMEN
OBJECTIVE: Breast arterial calcifications (BAC) are a sex-specific cardiovascular disease biomarker that might improve cardiovascular risk stratification in women. We implemented a deep convolutional neural network for automatic BAC detection and quantification. METHODS: In this retrospective study, four readers labelled four-view mammograms as BAC positive (BAC+) or BAC negative (BAC-) at image level. Starting from a pretrained VGG16 model, we trained a convolutional neural network to discriminate BAC+ and BAC- mammograms. Accuracy, F1 score, and area under the receiver operating characteristic curve (AUC-ROC) were used to assess the diagnostic performance. Predictions of calcified areas were generated using the generalized gradient-weighted class activation mapping (Grad-CAM++) method, and their correlation with manual measurement of BAC length in a subset of cases was assessed using Spearman ρ. RESULTS: A total 1493 women (198 BAC+) with a median age of 59 years (interquartile range 52-68) were included and partitioned in a training set of 410 cases (1640 views, 398 BAC+), validation set of 222 cases (888 views, 89 BAC+), and test set of 229 cases (916 views, 94 BAC+). The accuracy, F1 score, and AUC-ROC were 0.94, 0.86, and 0.98 in the training set; 0.96, 0.74, and 0.96 in the validation set; and 0.97, 0.80, and 0.95 in the test set, respectively. In 112 analyzed views, the Grad-CAM++ predictions displayed a strong correlation with BAC measured length (ρ = 0.88, p < 0.001). CONCLUSION: Our model showed promising performances in BAC detection and in quantification of BAC burden, showing a strong correlation with manual measurements. CLINICAL RELEVANCE STATEMENT: Integrating our model to clinical practice could improve BAC reporting without increasing clinical workload, facilitating large-scale studies on the impact of BAC as a biomarker of cardiovascular risk, raising awareness on women's cardiovascular health, and leveraging mammographic screening. KEY POINTS: ⢠We implemented a deep convolutional neural network (CNN) for BAC detection and quantification. ⢠Our CNN had an area under the receiving operator curve of 0.95 for BAC detection in the test set composed of 916 views, 94 of which were BAC+ . ⢠Furthermore, our CNN showed a strong correlation with manual BAC measurements (ρ = 0.88) in a set of 112 views.
Asunto(s)
Enfermedades de la Mama , Enfermedades Cardiovasculares , Aprendizaje Profundo , Femenino , Humanos , Persona de Mediana Edad , Estudios Retrospectivos , Mamografía/métodos , Enfermedades de la Mama/diagnóstico por imagenRESUMEN
PURPOSE: Introduce DWI and quantitative ADC evaluation in O-RADS MRI system and observe how diagnostic performance changes. Assess its validity and reproducibility between readers with different experience in female pelvic imaging. Finally, evaluate any correlation between ADC value and histotype in malignant lesions. MATERIALS AND METHODS: In total, 173 patients with 213 indeterminate adnexal masses (AMs) on ultrasound were subjected to MRI examination, from which 140 patients with 172 AMs were included in the final analysis. Standardised MRI sequences were used, including DWI and DCE sequences. Two readers, blinded to histopathological data, retrospectively classified AMs according to the O-RADS MRI scoring system. A quantitative analysis method was applied by placing a ROI on the ADC maps obtained from single-exponential DWI sequences. AMs considered benign (O-RADS MRI score 2) were excluded from the ADC analysis. RESULTS: Excellent inter-reader agreement was found in the classification of lesions according to the O-RADS MRI score (K = 0.936; 95% CI). Two ROC curves were created to determine the optimal cut-off value for the ADC variable between O-RADS MRI categories 3-4 and 4-5, respectively, 1.411 × 10-3 mm2/sec and 0.849 × 10-3 mm2/sec. Based on these ADC values, 3/45 and 22/62 AMs were upgraded, respectively, to score 4 and 5, while 4/62 AMs were downgraded to score 3. ADC values correlated significantly with the ovarian carcinoma histotype (p value < 0.001). CONCLUSION: Our study demonstrates the prognostic potential of DWI and ADC values in the O-RADS MRI classification for better radiological standardisation and characterisation of AMs.
Asunto(s)
Imagen de Difusión por Resonancia Magnética , Imagen por Resonancia Magnética , Humanos , Femenino , Estudios Retrospectivos , Reproducibilidad de los Resultados , Sensibilidad y Especificidad , Imagen por Resonancia Magnética/métodos , Curva ROC , Imagen de Difusión por Resonancia Magnética/métodosRESUMEN
OBJECTIVES: To compare the radiological findings of immune checkpoint inhibitor-related pneumonitis (IRP) and COVID-19 pneumonia, evaluating the potential of the CO-RADS score to differentiate between them. METHODS: Two readers blindly reviewed chest CTs from age- and sex-matched groups of 33 patients with IRP and 33 patients with COVID-19 pneumonia. Each examiner evaluated the presence of 13 CT features, semiquantitatively scored lung involvement, and assigned a CO-RADS score. Inter-reader reliability in the assessment of CT features and CO-RADS categories was evaluated with Cohen's κ. Distribution differences between groups were evaluated with the χ2, Fisher's, and Mann-Whitney U tests. RESULTS: Substantial or higher inter-reader reliability was found in CO-RADS assignments (κ = 0.664) and in the evaluation of CT features (κ ≥ 0.638), among which the sole feature found to significantly differentiate IRP from COVID-19 pneumonia was unilateral presentation (p < 0.001). Lung involvement semiquantitative scores and CO-RADS scores were significantly higher (p < 0.001) in COVID patients (median involvement score 4, IQR 4-6; median CO-RADS score 5, IQR 4-5) than in IRP patients (median involvement score 2.5, IQR 2-4; median CO-RADS score 3, IQR 3-4) but exploratory analysis of CO-RADS specificity revealed comparatively low values, ranging between 51.5% (Reader 1) and 54.6% (Reader 2). CONCLUSIONS: CT features of IRP and COVID-19 pneumonia frequently overlap, save for the extent of lung involvement and bilaterality. In the current SARS-CoV-2 pandemic, the low specificity of the CO-RADS score for the differential diagnosis of COVID-19 pneumonia and IRP may prompt to reconsider the role of imaging in IRP work-up.
Asunto(s)
COVID-19 , Neumonía , Humanos , Inhibidores de Puntos de Control Inmunológico , SARS-CoV-2 , Reproducibilidad de los Resultados , Tomografía Computarizada por Rayos X/métodos , Estudios RetrospectivosRESUMEN
Background US-indeterminate adnexal lesions remain an important indication for gynecologic surgery. MRI can serve as a problem-solving tool through the use of the Ovarian-Adnexal Imaging Reporting and Data System (O-RADS) MRI lexicon, which is based on the ADNEX MR scoring system. Purpose To perform a systematic review and meta-analysis of the diagnostic performance of pelvic MRI interpreted using the ADNEX or O-RADS MRI stratification systems to characterize US-indeterminate adnexal lesions and of the category-wise malignancy rates. Materials and Methods A systematic literature search from May 2013 (publication of the ADNEX MR score) to September 2022 was performed. Studies reporting the use of pelvic MRI interpreted with the ADNEX or O-RADS MRI systems to characterize US-indeterminate adnexal lesions, with pathologic examination and/or follow-up as the reference standard, were included. Summary estimates of diagnostic performance were obtained with the bivariate random-effects model, while category-wise summary malignancy rates of O-RADS MRI 2, 3, 4, and 5 lesions were obtained with a random-effects model. Effects of covariates on heterogeneity and diagnostic performance were investigated through meta-regression. Results Thirteen study parts from 12 studies (3731 women, 4520 adnexal lesions) met the inclusion criteria. Diagnostic performance meta-analysis for 4012 lesions found a 92% summary sensitivity (95% CI: 88, 95) and a 91% summary specificity (95% CI: 89, 93). The meta-analysis of malignancy rates for 3641 lesions showed summary malignancy rates of 0.1% (95% CI: 0, 1) among O-RADS MRI 2 lesions, 6% (95% CI: 3, 9) among O-RADS MRI 3 lesions, 60% (95% CI: 52, 67) among O-RADS MRI 4 lesions, and 96% (95% CI: 92, 99) among O-RADS MRI 5 lesions. Conclusion Pelvic MRI interpreted with the Ovarian-Adnexal Reporting and Data System (O-RADS) MRI lexicon had high diagnostic performance for the characterization of US-indeterminate adnexal lesions. Summary estimates of malignancy rates in the O-RADS MRI 4 and O-RADS MRI 5 categories were higher than predicted ones. © RSNA, 2022 Supplemental material is available for this article. See also the editorial by Lee and Kang in this issue.
Asunto(s)
Enfermedades de los Anexos , Neoplasias Ováricas , Femenino , Humanos , Enfermedades de los Anexos/patología , Anexos Uterinos/diagnóstico por imagen , Neoplasias Ováricas/patología , Imagen por Resonancia Magnética/métodos , Ultrasonografía/métodos , Sensibilidad y Especificidad , Estudios RetrospectivosRESUMEN
Accumulating evidence shows that contrast-enhanced mammography (CEM) has higher diagnostic performance than digital mammography and ultrasound and comparable diagnostic performance to MRI for various indications. CEM also offers certain practical advantages for patients. Nevertheless, the clinical implementation of CEM has been limited because of a range of factors. This AJR Expert Panel Narrative Review explores such factors hindering CEM implementation. These factors include the following: the risks of iodinated contrast media, increased radiation exposure, indications for which CEM is not the preferred test or for which further evidence is needed, workflow adjustments needed when performing CEM examinations, incomplete availability of CEM-guided biopsy systems, and reimbursement challenges. Considerations that currently mitigate or are expected to mitigate these factors are also highlighted.
Asunto(s)
Neoplasias de la Mama , Mamografía , Humanos , Femenino , Medios de Contraste , Examen Físico , Imagen por Resonancia Magnética , Neoplasias de la Mama/diagnóstico por imagenRESUMEN
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.