Volumetric Classification: Unveiling the True Extent of Rotator Cuff Tears.

INTRODUCTION: Rotator cuff injury diagnosis involves comprehensive clinical, physical, and imaging assessments, with MRI being pivotal for detecting and classifying these injuries. However, the absence of a universally accepted classification system necessitates a more precise approach, advocating for the use of three-dimensional (3D) modeling to better understand and categorize rotator cuff tears. METHODOLOGY: This research was conducted as a prospective, single-institution study on 62 patients exhibiting full-thickness rotator cuff tears. Utilizing preoperative 1.5T MRI, the study aimed to create a more detailed classification system based on volumetric and surface area measurements. Advanced 3D modeling software was employed to transform MRI data into precise 3D representations, facilitating a more accurate analysis of the lesions. RESULTS: The study unveiled a novel classification system rooted in volumetric and surface area assessments, revealing significant discrepancies in the existing two-dimensional classifications. Approximately 45% of the cases demonstrated inconsistencies between traditional classifications and 3D measurements. Notably, medium-sized lesions were often overestimated, while small and large lesions were consistently underestimated in their severity. The volumetric and surface area-based classifications provided a more accurate depiction, highlighting the limitations of relying solely on coronal plane assessments in MRI. Comparative analysis confirmed the improved accuracy of the 3D method. CONCLUSION: The integration of 3D imaging and volumetric analysis offers novel advancement in diagnosing and classifying rotator cuff injuries. This study's findings challenge the conventional reliance on 2D MRI, proposing a more detailed and accurate classification system that enhances the precision of surgical planning and potentially improves patient outcomes. The incorporation of comprehensive 3D assessments into the diagnostic process represents a significant step forward in the orthopedic imaging field.

Decreasing false-positive detection of intracranial hemorrhage (ICH) using RAPID ICH 3.

INTRODUCTION: The prompt detection of intracranial hemorrhage (ICH) on a non-contrast head CT (NCCT) is critical for the appropriate triage of patients, particularly in high volume/high acuity settings. Several automated ICH detection tools have been introduced; however, at present, most suffer from suboptimal specificity leading to false-positive notifications. METHODS: NCCT scans from 4 large databases were evaluated for the presence of an ICH (IPH, IVH, SAH or SDH) of >0.4 ml using fully-automated RAPID ICH 3.0 as compared to consensus detection from at least two neuroradiology experts. Scans were excluded for (1) severe CT artifacts, (2) prior neurosurgical procedures, or (3) recent intravenous contrast. ICH detection accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and positive and negative likelihood ratios by were determined. RESULTS: A total of 881 studies were included. The automated software correctly identified 453/463 ICH-positive cases and 416/418 ICH-negative cases, resulting in a sensitivity of 97.84% and specificity 99.52%, positive predictive value 99.56%, and negative predictive value 97.65% for ICH detection. The positive and negative likelihood ratios for ICH detection were similarly favorable at 204.49 and 0.02 respectively. Mean processing time was <40 seconds. CONCLUSIONS: In this large data set of nearly 900 patients, the automated software demonstrated high sensitivity and specificity for ICH detection, with rare false-positives.

Intra-session test-retest reliability of functional connectivity in infants.

Resting functional MRI studies of the infant brain are increasingly becoming an important tool in developmental neuroscience. Whereas the test-retest reliability of functional connectivity (FC) measures derived from resting fMRI data have been characterized in the adult and child brain, similar assessments have not been conducted in infants. In this study, we examined the intra-session test-retest reliability of FC measures from 119 infant brain MRI scans from four neurodevelopmental studies. We investigated edge-level and subject-level reliability within one MRI session (between and within runs) measured by the Intraclass correlation coefficient (ICC). First, using an atlas-based approach, we examined whole-brain connectivity as well as connectivity within two common resting fMRI networks - the default mode network (DMN) and the sensorimotor network (SMN). Second, we examined the influence of run duration, study site, and scanning manufacturer (e.g., Philips and General Electric) on ICCs. Lastly, we tested spatial similarity using the Jaccard Index from networks derived from independent component analysis (ICA). Consistent with resting fMRI studies from adults, our findings indicated poor edge-level reliability (ICC = 0.14-0.18), but moderate-to-good subject-level intra-session reliability for whole-brain, DMN, and SMN connectivity (ICC = 0.40-0.78). We also found significant effects of run duration, site, and scanning manufacturer on reliability estimates. Some ICA-derived networks showed strong spatial reproducibility (e.g., DMN, SMN, and Visual Network), and were labelled based on their spatial similarity to analogous networks measured in adults. These networks were reproducibly found across different study sites. However, other ICA-networks (e.g. Executive Control Network) did not show strong spatial reproducibility, suggesting that the reliability and/or maturational course of functional connectivity may vary by network. In sum, our findings suggest that developmental scientists may be on safe ground examining the functional organization of some major neural networks (e.g. DMN and SMN), but judicious interpretation of functional connectivity is essential to its ongoing success.

A Practical Approach to Diagnosis of Spinal Dysraphism.

Spinal dysraphisms (SDs) are congenital malformations of the spinal cord, determined by derangement in the complex cascade of embryologic events involved in spinal development. They represent a heterogeneous group ranging from mild clinical manifestations-going unnoticed or being discovered at clinical examination-to a causal factor of life quality impairment, especially when associated with musculoskeletal, gastrointestinal, genitourinary, or respiratory system malformations. Knowledge of the normal embryologic development of the spinal cord-which encompasses three main steps (gastrulation, primary neurulation, and secondary neurulation)-is crucial for understanding the pathogenesis, neuroradiologic scenarios, and clinical-radiologic classification of congenital malformations of the spinal cord. SDs can be divided with clinical examination or neuroradiologic study into two major groups: open SDs and closed SDs. Congenital malformations of the spinal cord include a wide range of abnormalities that vary considerably in imaging and clinical characteristics and complexity and therefore may represent a diagnostic challenge, even for the experienced radiologist. Online supplemental material is available for this article. ©RSNA, 2021.

The RSNA Pediatric Bone Age Machine Learning Challenge.

Purpose The Radiological Society of North America (RSNA) Pediatric Bone Age Machine Learning Challenge was created to show an application of machine learning (ML) and artificial intelligence (AI) in medical imaging, promote collaboration to catalyze AI model creation, and identify innovators in medical imaging. Materials and Methods The goal of this challenge was to solicit individuals and teams to create an algorithm or model using ML techniques that would accurately determine skeletal age in a curated data set of pediatric hand radiographs. The primary evaluation measure was the mean absolute distance (MAD) in months, which was calculated as the mean of the absolute values of the difference between the model estimates and those of the reference standard, bone age. Results A data set consisting of 14 236 hand radiographs (12 611 training set, 1425 validation set, 200 test set) was made available to registered challenge participants. A total of 260 individuals or teams registered on the Challenge website. A total of 105 submissions were uploaded from 48 unique users during the training, validation, and test phases. Almost all methods used deep neural network techniques based on one or more convolutional neural networks (CNNs). The best five results based on MAD were 4.2, 4.4, 4.4, 4.5, and 4.5 months, respectively. Conclusion The RSNA Pediatric Bone Age Machine Learning Challenge showed how a coordinated approach to solving a medical imaging problem can be successfully conducted. Future ML challenges will catalyze collaboration and development of ML tools and methods that can potentially improve diagnostic accuracy and patient care. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Siegel in this issue.

Ischemic stroke enhancement using a variational model and the expectation maximization method.

OBJECTIVES: In order to enable less experienced physicians to reliably detect early signs of stroke, A novel approach was proposed to enhance the visual perception of ischemic stroke in non-enhanced CT. METHODS: A set of 39 retrospective CT scans were used, divided into 23 cases of acute ischemic stroke and 16 normal patients. Stroke cases were obtained within 4.5 h of symptom onset and with a mean NIHSS of 12.9±7.4. After selection of adjunct slices from the CT exam, image averaging was performed to reduce the noise and redundant information. This was followed by a variational decomposition model to keep the relevant component of the image. The expectation maximization method was applied to generate enhanced images. RESULTS: We determined a test to evaluate the performance of observers in a clinical environment with and without the aid of enhanced images. The overall sensitivity of the observer's analysis was 64.5 % and increased to 89.6 % and specificity was 83.3 % and increased to 91.7 %. CONCLUSION: These results show the importance of a computational tool to assist neuroradiology decisions, especially in critical situations such as the diagnosis of ischemic stroke. KEY POINTS: • Diagnosing patients with stroke requires high efficiency to avoid irreversible cerebral damage. • A computational algorithm was proposed to enhance the visual perception of stroke. • Observers' performance was increased with the aid of enhanced images.

Performance of ChatGPT on the Brazilian Radiology and Diagnostic Imaging and Mammography Board Examinations.

This prospective exploratory study conducted from January 2023 through May 2023 evaluated the ability of ChatGPT to answer questions from Brazilian radiology board examinations, exploring how different prompt strategies can influence performance using GPT-3.5 and GPT-4. Three multiple-choice board examinations that did not include image-based questions were evaluated: (a) radiology and diagnostic imaging, (b) mammography, and (c) neuroradiology. Five different styles of zero-shot prompting were tested: (a) raw question, (b) brief instruction, (c) long instruction, (d) chain-of-thought, and (e) question-specific automatic prompt generation (QAPG). The QAPG and brief instruction prompt strategies performed best for all examinations (P < .05), obtaining passing scores (≥60%) on the radiology and diagnostic imaging examination when testing both versions of ChatGPT. The QAPG style achieved a score of 60% for the mammography examination using GPT-3.5 and 76% using GPT-4. GPT-4 achieved a score up to 65% in the neuroradiology examination. The long instruction style consistently underperformed, implying that excessive detail might harm performance. GPT-4's scores were less sensitive to prompt style changes. The QAPG prompt style showed a high volume of the "A" option but no statistical difference, suggesting bias was found. GPT-4 passed all three radiology board examinations, and GPT-3.5 passed two of three examinations when using an optimal prompt style. Keywords: ChatGPT, Artificial Intelligence, Board Examinations, Radiology and Diagnostic Imaging, Mammography, Neuroradiology © RSNA, 2023 See also the commentary by Trivedi and Gichoya in this issue.

Can three-dimensional models enhance understanding and knowledge of rotator cuff tears?

OBJECTIVES: Magnetic resonance imaging (MRI) is currently the standard diagnostic tool for rotator cuff tears. However, its two-dimensional (2D) output, displayed on a monitor, can complicate the interpretation of anatomy. Three-dimensional (3D) imaging may offer a solution to this issue. This study aimed to demonstrate the diagnostic and interpretive value of a 3D model in assessing lesion anatomy. The hypothesis was that 3D models, compared to 2D MRI, can enhance the comprehension and knowledge of rotator cuff injuries, improve the application of classifications for total tears, and provide a more precise definition of the size and type of tear. METHODS: A prospective single-centre study was conducted. 3D models for rotator cuff tears were created and analysed in conjunction with preoperative MRI for each patient up to 2 months before surgery. The 3D models were based on the preoperative MRI. Collected data included 2D plane measurements by MRI in coronal and sagittal planes, descriptions of 3D lesion geometry (new shapes), 3D measurements in coronal and sagittal planes, arthroscopic classifications of rotator cuff injuries, and arthroscopic measurements in coronal and sagittal planes. RESULTS: After examining 25 cases, 3D imaging demonstrated similar arthroscopic values post-bursectomy in the sagittal plane (16.70 â€‹mm for 3D and 18.28 â€‹mm for post-bursectomy, p-value â€‹= â€‹0.189), although these measurements did not align with those of MRI (which underestimated measurements, p-value â€‹= â€‹0.010). Both MRI measurement and 3D imaging showed similar measurement accuracy in the coronal plane when compared to arthroscopic measurements taken before and after bursectomy. The creation of 3D objects enabled the analysis of new geometries, including the length, width, and depth of each lesion. These geometries included the rectangle, rectangular trapezoid, scalene trapezoid, irregular pentagon, and irregular hexagon. CONCLUSIONS: 3D models can enhance the understanding and knowledge of rotator cuff injuries. They can be a promising tool for diagnosing and interpreting the anatomy of the injury, particularly in the sagittal plane. The new 3D understanding of the pathological process has led to the description of new geometric features not visible in conventional 2D MRI. LEVEL OF EVIDENCE: II - Development of diagnostic criteria on consecutive patients (all compared to "gold" standard).

Validation of a deep learning algorithm for bone age estimation among patients in the city of São Paulo, Brazil.

Objective: To validate a deep learning (DL) model for bone age estimation in individuals in the city of São Paulo, comparing it with the Greulich and Pyle method. Materials and Methods: This was a cross-sectional study of hand and wrist radiographs obtained for the determination of bone age. The manual analysis was performed by an experienced radiologist. The model used was based on a convolutional neural network that placed third in the 2017 Radiological Society of North America challenge. The mean absolute error (MAE) and the root-mean-square error (RMSE) were calculated for the model versus the radiologist, with comparisons by sex, race, and age. Results: The sample comprised 714 examinations. There was a correlation between the two methods, with a coefficient of determination of 0.94. The MAE of the predictions was 7.68 months, and the RMSE was 10.27 months. There were no statistically significant differences between sexes or among races (p > 0.05). The algorithm overestimated bone age in younger individuals (p = 0.001). Conclusion: Our DL algorithm demonstrated potential for estimating bone age in individuals in the city of São Paulo, regardless of sex and race. However, improvements are needed, particularly in relation to its use in younger patients.

Objetivo: Validar em indivíduos paulistas um modelo de aprendizado profundo (deep learning - DL) para estimativa da idade óssea, comparando-o com o método de Greulich e Pyle. Materiais e Métodos: Estudo transversal com radiografias de mão e punho para idade óssea. A análise manual foi feita por um radiologista experiente. Foi usado um modelo baseado em uma rede neural convolucional que ficou em terceiro lugar no desafio de 2017 da Radiological Society of North America. Calcularam-se o erro médio absoluto (mean absolute error - MAE) e a raiz do erro médio quadrado (root mean-square error - RMSE) do modelo contra o radiologista, com comparações entre sexo, etnia e idade. Resultados: A amostra compreendia 714 exames. Houve correlação entre ambos os métodos com coeficiente de determinação de 0,94. O MAE das predições foi 7,68 meses e a RMSE foi 10,27 meses. Não houve diferenças estatisticamente significantes entre sexos ou raças (p > 0,05). O algoritmo superestimou a idade óssea nos mais jovens (p = 0,001). Conclusão: O nosso algoritmo de DL demonstrou potencial para estimar a idade óssea em indivíduos paulistas, independentemente do sexo e da raça. Entretanto, há necessidade de aprimoramentos, particularmente em pacientes mais jovens.

Stand-alone lateral interbody fusion for the treatment of low-grade degenerative spondylolisthesis.

The purpose of this paper was to investigate the stand-alone lateral interbody fusion as a minimally invasive option for the treatment of low-grade degenerative spondylolisthesis with a minimum 24-month followup. Prospective nonrandomized observational single-center study. 52 consecutive patients (67.6 ± 10 y/o; 73.1% female; 27.4 ± 3.4 BMI) with single-level grade I/II single-level degenerative spondylolisthesis without significant spine instability were included. Fusion procedures were performed as retroperitoneal lateral transpsoas interbody fusions without screw supplementation. The procedures were performed in average 73.2 minutes and with less than 50cc blood loss. VAS and Oswestry scores showed lasting improvements in clinical outcomes (60% and 54.5% change, resp.). The vertebral slippage was reduced in 90.4% of cases from mean values of 15.1% preoperatively to 7.4% at 6-week followup (P < 0.001) and was maintained through 24 months (7.1%, P < 0.001). Segmental lordosis (P < 0.001) and disc height (P < 0.001) were improved in postop evaluations. Cage subsidence occurred in 9/52 cases (17%) and 7/52 cases (13%) spine levels needed revision surgery. At the 24-month evaluation, solid fusion was observed in 86.5% of the levels treated. The minimally invasive lateral approach has been shown to be a safe and reproducible technique to treat low-grade degenerative spondylolisthesis.

New trends in diffusion-weighted magnetic resonance imaging as a tool in differentiation of serous cystadenoma and mucinous cystic tumor: a prospective study.

BACKGROUND/AIMS: Pancreatic cystic lesions are increasingly being recognized. Magnetic resonance imaging (MRI) is the method that brings the greatest amount of information about the morphologic features of pancreatic cystic lesions. To establish if diffusion-weighted MRI (DW-MRI) can be used as a tool to differentiate mucinous from nonmucinous lesions. METHODS: Fifty-six patients with pancreatic cystic lesions (benign, n = 46; malignant, n = 10) were prospectively evaluated with DW-MRI in order to differentiate mucinous from nonmucinous lesions. Final diagnosis was obtained by follow-up (n = 31), surgery (n = 16) or endoscopic ultrasound-guided fine needle aspiration (n = 9). Serous cystadenoma was identified in 32 (57%) patients. RESULTS: The threshold value established for the differentiation of mucinous from nonmucinous lesions was 2,230.06 s/mm(2) for ADC of 700. DWI-MRI behavior between mucinous and nonmucinous groups revealed sensitivity, specificity, positive predictive value, negative predictive value and accuracy to be 80, 98, 92, 93 and 93%, respectively (p < 0.01, power of sample = 1.0). In the comparison of the diffusion behavior between mucinous (n = 13) and serous (n = 32) lesions, the sensitivity, specificity, positive predictive value, negative predictive value and accuracy were 100, 97, 92, 100 and 98%, respectively (p < 0.01, power of sample = 1.0). The results of endoscopic ultrasound-guided fine needle aspiration were similar to those of DW-MRI. CONCLUSIONS: DW-MRI can be included as part of the array of tools to differentiate mucinous from nonmucinous lesions and can help in the management of pancreatic cystic lesions. and IAP.

Clinical Artificial Intelligence Applications in Radiology: Neuro.

Radiologists have been at the forefront of the digitization process in medicine. Artificial intelligence (AI) is a promising area of innovation, particularly in medical imaging. The number of applications of AI in neuroradiology has also grown. This article illustrates some of these applications. This article reviews machine learning challenges related to neuroradiology. The first approval of reimbursement for an AI algorithm by the Centers for Medicare and Medicaid Services, covering a stroke software for early detection of large vessel occlusion, is also discussed.

Arthroscopic Superior Capsule Reconstruction Using Three-Dimensional Preoperative Planning: Technique Description.

We describe a technique using a fascia lata autograft with 3-dimensional (3D) printing to reconstruct the rotator cuff. Prototyping constitutes the construction of physical prototypes with high complexity after virtual studies. Such models increase the knowledge of the characteristics and size of rotator cuff injuries, thus improving the accuracy of determining the correct size of the graft to be used in superior capsule reconstruction. We present a case of superior capsule reconstruction using 3D printing for enhancing the accuracy of fascia lata allograft size and tension determination; 3D reconstruction has never been described in the literature for rotator cuff injuries.

Deep COVID DeteCT: an international experience on COVID-19 lung detection and prognosis using chest CT.

The Coronavirus disease 2019 (COVID-19) presents open questions in how we clinically diagnose and assess disease course. Recently, chest computed tomography (CT) has shown utility for COVID-19 diagnosis. In this study, we developed Deep COVID DeteCT (DCD), a deep learning convolutional neural network (CNN) that uses the entire chest CT volume to automatically predict COVID-19 (COVID+) from non-COVID-19 (COVID-) pneumonia and normal controls. We discuss training strategies and differences in performance across 13 international institutions and 8 countries. The inclusion of non-China sites in training significantly improved classification performance with area under the curve (AUCs) and accuracies above 0.8 on most test sites. Furthermore, using available follow-up scans, we investigate methods to track patient disease course and predict prognosis.

Follow-up of endovascular treatment of direct carotid-cavernous fistulas.

INTRODUCTION: Direct carotid-cavernous fistula (CCF) is a direct communication between the internal carotid artery (ICA) and the cavernous sinus. Some patients treated with detachable balloons develop pseudoaneurysms or present with a true aneurysm recanalization in the cavernous ICA with poorly known long-term radiological and clinical progression. The objective of the present study was to evaluate the long-term clinical and radiological progression of patients treated with detachable balloons. METHODS: The present study evaluated 13 patients previously treated for direct CCF by an endovascular approach. RESULTS: The follow-up period ranged between 19 and 128 months. Ophthalmological evaluation demonstrated alterations in eight patients (61.5%). All of these alterations were already present from the moment of the treatment and displayed no signs of progression. Cranial magnetic resonance imaging (MRI) and magnetic resonance angiography (MRA) were performed in all patients, and 11 pseudoaneurysms were demonstrated in ten of the 11 patients in whom ICA patency had been preserved. Five patients were submitted for cerebral digital subtraction angiography (DSA) to characterize the pseudoaneurysms previously observed on MRA studies, with no significant differences in morphology, size, aneurismal neck, and number of lesions. CONCLUSION: Endovascular treatment of direct CCF with detachable balloons has been shown to be a long-term effective and stable therapeutic method. The authors found asymptomatic pseudoaneurysms in 91% of cases where the ICA patency was preserved. MRI and MRA demonstrated an accuracy similar to that of DSA in the diagnosis of pseudoaneurysms of cavernous ICA.

Neuromyelitis optica: brain abnormalities in a Brazilian cohort.

Neuromyelitis optica (NMO) is a demyelinating disease consisting of relapsing-remitting optic neuritis and myelitis with a more severe course than Multiple Sclerosis. Recently, it has been shown that almost 50% of patients with NMO can have brain magnetic resonance imaging (MRI) abnormalities. We report on six Brazilian patients with NMO, fulfilling the 1999 Wingerchuck criteria for this disease, with abnormal brain MRI and discuss their clinical and radiological features.

Safety of Onyx Transarterial Embolization of Skull Base Dural Arteriovenous Fistulas from Meningeal Branches of the External Carotids also Fed by Meningeal Branches of Internal Carotid or Vertebral Arteries.

PURPOSE: To analyze the angiographic and clinical results of transarterial embolization with Onyx (Medtronic-Covidien, Irvine, CA) in dural arteriovenous fistulas (DAVFs) partially fed by arteries arising from the carotid siphon or the vertebral arteries. METHODS: We isolated 40 DAVFs supplied by either the tentorial artery of the internal carotid artery (ICA) or the posterior meningeal artery of the vertebral artery. These DAVFs were embolized with Onyx through the middle meningeal artery or the occipital artery. We reviewed the occurrence of reflux into the arteries of carotid or vertebral origin. RESULTS: In all the cases, reflux occurred into the first millimeters of the DAVF arterial feeders arising from carotid or vertebral arteries but slowly enough to be controlled by interruption of Onyx injection. Reflux was always minimal and Onyx never reached the ostium of the arteries. No cerebral ischemic complications occurred in our series. CONCLUSION: The behavior of Onyx is clearly different from that of cyanoacrylate glue, resulting in superior control during injection. Reflux into arteries arising from the ICA or vertebral artery during DAVF treatment always carries a risk of unintentional non-target embolization of normal cerebral vasculature but Onyx appears to be safe in this situation.

Validation of a deep learning algorithm for bone age estimation among patients in the city of São Paulo, Brazil / Validação de algoritmo de aprendizado profundo para detecção da idade óssea em pacientes de São Paulo, Brasil

Abstract Objective: To validate a deep learning (DL) model for bone age estimation in individuals in the city of São Paulo, comparing it with the Greulich and Pyle method. Materials and Methods: This was a cross-sectional study of hand and wrist radiographs obtained for the determination of bone age. The manual analysis was performed by an experienced radiologist. The model used was based on a convolutional neural network that placed third in the 2017 Radiological Society of North America challenge. The mean absolute error (MAE) and the root-mean-square error (RMSE) were calculated for the model versus the radiologist, with comparisons by sex, race, and age. Results: The sample comprised 714 examinations. There was a correlation between the two methods, with a coefficient of determination of 0.94. The MAE of the predictions was 7.68 months, and the RMSE was 10.27 months. There were no statistically significant differences between sexes or among races (p > 0.05). The algorithm overestimated bone age in younger individuals (p = 0.001). Conclusion: Our DL algorithm demonstrated potential for estimating bone age in individuals in the city of São Paulo, regardless of sex and race. However, improvements are needed, particularly in relation to its use in younger patients.

Resumo Objetivo: Validar em indivíduos paulistas um modelo de aprendizado profundo (deep learning - DL) para estimativa da idade óssea, comparando-o com o método de Greulich e Pyle. Materiais e Métodos: Estudo transversal com radiografias de mão e punho para idade óssea. A análise manual foi feita por um radiologista experiente. Foi usado um modelo baseado em uma rede neural convolucional que ficou em terceiro lugar no desafio de 2017 da Radiological Society of North America. Calcularam-se o erro médio absoluto (mean absolute error - MAE) e a raiz do erro médio quadrado (root mean-square error - RMSE) do modelo contra o radiologista, com comparações entre sexo, etnia e idade. Resultados: A amostra compreendia 714 exames. Houve correlação entre ambos os métodos com coeficiente de determinação de 0,94. O MAE das predições foi 7,68 meses e a RMSE foi 10,27 meses. Não houve diferenças estatisticamente significantes entre sexos ou raças (p > 0,05). O algoritmo superestimou a idade óssea nos mais jovens (p = 0,001). Conclusão: O nosso algoritmo de DL demonstrou potencial para estimar a idade óssea em indivíduos paulistas, independentemente do sexo e da raça. Entretanto, há necessidade de aprimoramentos, particularmente em pacientes mais jovens.

Basal encephalocele associated with morning glory syndrome: case report.

The basal encephaloceles refer to rare entities and they correspond to herniation of brain tissue through defects of skull along the cribiform plate or the sphenoid bone. A rare morning glory syndrome, with characteristic retinal defect has been reported in association with basal encephaloceles. Hypophysis hormonal deficiencies may occur. We accounted for a pituitary dwarfism with delayed diagnosed transsphenoidal encephalocele associated with morning glory syndrome, showing the alterations found in retinography, computed tomography and magnetic resonance imaging.