RESUMO
Background and purpose:
The aim of the study was to investigate the question: Can MRI radiomics analysis of the periaqueductal gray region elucidate the pathophysiological mechanisms underlying various migraine subtypes, and can a machine learning model using these radiomics features accurately differentiate between migraine patients and healthy individuals, as well as between migraine subtypes, including atypical cases with overlapping symptoms?
. Methods:The study analyzed initial MRI images of individuals taken after their first migraine diagnosis, and additional MRI scans were acquired from healthy subjects. Radiomics modeling was applied to analyze all the MRI images in the periaqueductal gray region. The dataset was randomized, and oversampling was used if there was class imbalance between groups. The optimal algorithm-based feature selection method was employed to select the most important 5-10 features to differentiate between the two groups. The classification performance of AI algorithms was evaluated using receiver operating characteristic analysis to calculate the area under the curve, classification accuracy, sensitivity, and specificity values. Participants were required to have a confirmed diagnosis of either episodic migraine, probable migraine, or chronic migraine. Patients with aura, those who used migraine-preventive medication within the past six months, or had chronic illnesses, psychiatric disorders, cerebrovascular conditions, neoplastic diseases, or other headache types were excluded from the study. Additionally, 102 healthy subjects who met the inclusion and exclusion criteria were included.
. Results:The algorithm-based information gain method for feature reduction had the best performance among all methods, with the first-order, gray-level size zone matrix, and gray-level co-occurrence matrix classes being the dominant feature classes. The machine learning model correctly classified 82.4% of migraine patients from healthy subjects. Within the migraine group, 74.1% of the episodic migraine-probable migraine patients and 90.5% of the chronic migraine patients were accurately classified. No significant difference was found between probable migraine and episodic migraine patients in terms of the periaqueductal gray region radiomics features. The kNN algorithm showed the best performance for classifying episodic migraine-probable migraine subtypes, while the Random Forest algorithm demonstrated the best performance for classifying the migraine group and chronic migraine subtype.
. Conclusion:A radiomics-based machine learning model, utilizing standard MR images obtained during the diagnosis and follow-up of migraine patients, shows promise not only in aiding migraine diagnosis and classification for clinical approach, but also in understanding the neurological mechanisms underlying migraines.
.Assuntos
Transtornos de Enxaqueca , Substância Cinzenta Periaquedutal , Humanos , Radiômica , Imageamento por Ressonância Magnética/métodos , Transtornos de Enxaqueca/diagnóstico , Aprendizado de Máquina , Estudos RetrospectivosRESUMO
SUMMARY: Although acute and chronic pathologies of the glenohumeral and acromioclavicular joints are frequently encountered in the population, the anatomy and morphometry are not fully known. The aim of this study is to determine the measurements of morphometric parameters according to age groups and sex in a large series of Turkish population. Nine hundred and forty-one shoulders computed tomography (CT) images were screened and those of subjects with healthy anatomical structure were included. Humeral head diameter (HDD) was measured on CT images. Measurements were made using 3D-CT images of: width (GW) and height (GH) of the glenoid cavity; width (CW) and height (CH) of the distal clavicular joint surface; and width (AW) and height (AH) of the acromial joint surface. Data were compared, stratified by age and sex. Images of 223 patients (118 men, 105 women) were analyzed. The following mean measurements were determined: HDD, 41.77±3.77 mm; GH, 34.66±3.26 mm; GW, 25.50±2.90 mm; CW, 14.85±3.51 mm; CH, 8.49±2.27 mm; AW, 12.97±2.94 mm; AH, 7.01±1.77 mm. When startified by sex, HDD (p<0.001), GH (p<0.001), GW (p<0.001), CW (p<0.001), CH (p=0.002), AW (p<0.001) and AH (p<0.001) measurements were significantly different and mean values were greater in men. Similarly for age, significant differences were found for GH (p=0.028), CW (p<0.001), AW (p<0.001), AH (p<0.001). The parametric values we have obtained in the Turkish population we measure differ from the measurements made in different populations according to age groups and sex. Knowing these features will contribute to treatment planning, implant and prosthesis applications.
Aunque las patologías agudas y crónicas de las articulaciones glenohumeral y acromioclavicular son frecuentes en la población, la anatomía y morfometría no se conocen por completo. El objetivo de este estudio fue determinar las medidas de los parámetros morfométricos según grupos de edad y sexo en una serie de individuos de población turca. Se examinaron 941 imágenes de tomografía computarizada (TC) de hombro y se incluyeron las de sujetos con una estructura anatómica sana. El diámetro de la cabeza humeral (HDD) se midió en imágenes de TC. Las mediciones se realizaron utilizando imágenes 3D-CT de: ancho (GW) y altura (GH) de la cavidad glenoidea; anchura (CW) y altura (CH) de la superficie articular clavicular; y anchura (AW) y altura (AH) de la superficie articular acromial. Los datos fueron comparados, estratificados por edad y sexo. Se analizaron imágenes de 223 pacientes (118 hombres, 105 mujeres). Se determinaron las siguientes medidas medias: HDD, 41,77±3,77 mm; GH, 34,66 ± 3,26 mm; GW, 25,50±2,90 mm; CW, 14,85±3,51 mm; CH, 8,49±2,27 mm; AW, 12,97±2,94 mm; AH, 7,01±1,77 mm. Cuando se inicia por sexo, HDD (p<0,001), GH (p<0,001), GW (p<0,001), CW (p<0,001), CH (p=0,002), AW (p<0,001) y AH (p <0,001) las mediciones fueron significativamente diferentes y los valores medios fueron mayores en los hombres. De igual forma para la edad se encontraron diferencias significativas para GH (p=0,028), CW (p<0,001), AW (p<0,001), AH (p<0,001). Los valores paramétricos que hemos obtenido en la población turca difieren de las medidas realizadas en diferentes poblaciones según grupos de edad y sexo. El conocimiento de estas características contribuirá a la planificación del tratamiento, aplicaciones de implantes y prótesis.
Assuntos
Humanos , Masculino , Feminino , Adulto , Pessoa de Meia-Idade , Idoso , Adulto Jovem , Articulação do Ombro/diagnóstico por imagem , Articulação Acromioclavicular/diagnóstico por imagem , Articulação do Ombro/anatomia & histologia , Turquia , Articulação Acromioclavicular/anatomia & histologia , Acrômio , Tomografia Computadorizada por Raios X , Fatores Sexuais , Análise de Variância , Fatores Etários , Distribuição por Idade e Sexo , Cavidade GlenoideRESUMO
SUMMARY: Intramedullary headless screw fixation has come to the fore in the treatment of metacarpal fractures in recent years with its advantages. Our aim was to evaluate the metacarpal morphometry for retrograde intramedullary entrance and to determine the optimal entry point. Computed tomography images of 105 patients including 64 men and 41 women, were examined. Distal and proximal metacarpal widths, medullary cavity width, cortex thickness and the measurements of the optimal entry site in volar-dorsal and radio-ulnar directions were measured in both coronal and sagittal planes. In the sagittal plane, the second metacarpal had the widest proximal width (16.29 mm), distal width was greatest in the third metacarpal (14.34 mm) which was significantly different between the sexes (p<0.001). Third metacarpal had the widest medullary cavity width in the sagittal plane (4.12 mm). In the coronal plane, it was the second metarcarpal with the widest proximal (16.14 mm) and distal width (13.92 mm) and was also the longest (66.32 mm). Unlike the sagittal plane, the medullary cavity width in the coronal plane was at the widest (4.06 mm) in fifth metacarpal. The points determined for optimal entry were respectively (4.60 mm; 4.97 mm; 4.55 mm; 4.36 mm) in the dorsal-volar plane, close to the dorsal side. There was no significant difference between the sexes for optimal insertion point in the sagittal planes in all the measured metacarpals. Considering its three dimensional structure, metacarpal bones have irregular morphometric properties and these features differ in sagittal and coronal planes. The optimal entry site is located in the midline in the coronal plane, while it is located in the sagittal plane close to the dorsal part. Knowing these properties can reduce the complication rate by reducing entry attempts and help select the correct material.
RESUMEN: En los últimos años, debido a sus ventajas la fijación intramedular con tornillos sin cabeza ha pasado a primer plano en el tratamiento de las fracturas de los huesos metacarpianos. Nuestro objetivo fue evaluar la morfometría del hueso metacarpiano para la entrada intramedular retrógrada y determinar el punto de entrada óptimo. Se examinaron imágenes de tomografía computarizada de 105 pacientes, incluidos 64 hombres y 41 mujeres. Los anchos de los huesos metacarpianos distal y proximal, el ancho de la cavidad medular, el grosor de la cortical y las medidas del sitio de entrada óptimo en las direcciones palmar-dorsal y radioulnar se midieron en los planos coronal y sagital. En el plano sagital, el segundo hueso metacarpiano presentó el mayor ancho proximal (16,29 mm), el ancho distal fue mayor en el tercer hueso metacarpiano (14,34 mm), lo que fue significativamente diferente entre individuos de ambos sexos (p<0,001). El tercer metacarpiano tenía la cavidad medular más ancha en el plano sagital (4,12 mm). En el plano coronal, era el segundo hueso metarcarpiano con mayor ancho proximal (16,14 mm) y distal (13,92 mm) y también era el más largo (66,32 mm). A diferencia del plano sagital, el ancho de la cavidad medular en el plano coronal era más ancho (4,06 mm) en el quinto hueso metacarpiano. Los puntos determinados para la entrada óptima fueron respectivamente (4,60 mm; 4,97 mm; 4,55 mm; 4,36 mm) en el plano dorsal-volar, próximo del lado dorsal. No hubo diferencia significativa entre ambos sexos para el punto de inserción óptimo en los planos sagitales en todos los huesos metacarpianos medidos. Teniendo en consideración su estructura tridimensional, los huesos metacarpianos tienen propiedades morfométricas irregulares, y estas características difieren en los planos sagital y coronal. El sitio de entrada óptimo se encuentra en la línea mediana en el plano coronal, mientras que se ubica en el plano sagital cerca de la parte dorsal. Conocer estas propiedades puede reducir la tasa de complicaciones al disminuir los intentos de entrada y ayudar a seleccionar el material correcto.