RESUMEN
Biomedical information retrieval for diagnosis, treatment and prognosis has been studied for a long time. In particular, image recognition using deep learning has been shown to be very effective for cancers and diseases. In these fields, scaphoid fracture recognition is a hot topic because the appearance of scaphoid fractures is not easy to detect. Although there have been a number of recent studies on this topic, no studies focused their attention on surgical treatment recommendations and nonsurgical prognosis status classification. Indeed, a successful treatment recommendation will assist the doctor in selecting an effective treatment, and the prognosis status classification will help a radiologist recognize the image more efficiently. For these purposes, in this paper, we propose potential solutions through a comprehensive empirical study assessing the effectiveness of recent deep learning techniques on surgical treatment recommendation and nonsurgical prognosis status classification. In the proposed system, the scaphoid is firstly segmented from an unknown X-ray image. Next, for surgical treatment recommendation, the fractures are further filtered and recognized. According to the recognition result, the surgical treatment recommendation is generated. Finally, even without sufficient fracture information, the doctor can still make an effective decision to opt for surgery or not. Moreover, for nonsurgical patients, the current prognosis status of avascular necrosis, non-union and union can be classified. The related experimental results made using a real dataset reveal that the surgical treatment recommendation reached 80% and 86% in accuracy and AUC (Area Under the Curve), respectively, while the nonsurgical prognosis status classification reached 91% and 96%, respectively. Further, the methods using transfer learning and data augmentation can bring out obvious improvements, which, on average, reached 21.9%, 28.9% and 5.6%, 7.8% for surgical treatment recommendations and nonsurgical prognosis image classification, respectively. Based on the experimental results, the recommended methods in this paper are DenseNet169 and ResNet50 for surgical treatment recommendation and nonsurgical prognosis status classification, respectively. We believe that this paper can provide an important reference for future research on surgical treatment recommendation and nonsurgical prognosis classification for scaphoid fractures.
RESUMEN
PURPOSE: The relationship between the psoas muscle index (PMI) and the appendicular skeletal muscle index (ASMI) in patients with compensated advanced chronic liver disease (cACLD) is not yet understood. Our goal is to determine which level of the lumbar spine best represents the appendicular skeletal muscle. METHODS AND MATERIALS: This retrospective study involved patients with cACLD between January 2020 and December 2021. We documented the patients' body weight, height, gait speed, handgrip strength, appendicular skeletal muscle measured by DXA, and psoas muscle area segmented on computed tomography or magnetic resonance imaging. Low muscle mass, as defined by the Asian working group for sarcopenia, is less than 7.0 kg/m2 in males and less than 5.4 kg/m2 in females. We analyzed the correlation between PMI and ASMI. RESULTS: A total of 134 patients were enrolled in the study, with 74 being male and 60 being female. The mean age was 63.9 ± 7.7 years old. Significant associations (p < 0.001) were found between PMI of all levels and ASMI. In the analysis of Pearson's correlation coefficients, it was noted that the r value increased gradually in both males (r = 0.3197 at L2, 0.4006 at L3, 0.5769 at L4) and females (r = 0.3771 at L2, 0.4557 at L3, 0.5251 at L4). Similarly, the area under the curve (AUC) values predicting low muscle mass were as follows: for males, AUC=0.582 at L2, 0.619 at L3, 0.728 at L4; for females, AUC=0.685 at L2, 0.733 at L3, 0.744 at L4. The cut-off point for PMI in males was 4.12 at L2, 6.25 at L3, and 8.48 at L4, while in females was 2.61 at L2, 4.47 at L3, 6.07 at L4. CONCLUSION: The Psoas muscle index can be used to assess the muscle mass status in patients with cACLD. Among the various levels that can be used, we recommend using the fourth inferior endplate of the lumbar spine, as it shows the highest correlation. Additionally, we suggest using a PMI cut-off point of 8.48 cm2/m2 for males and 6.07 cm2/m2 for females as a predictor of low muscle mass in Asian.