bone age
Recently Published Documents


TOTAL DOCUMENTS

1240
(FIVE YEARS 383)

H-INDEX

50
(FIVE YEARS 6)

2022 ◽  
Vol 93 ◽  
pp. 222-228
Author(s):  
Anne Berg Breen ◽  
Harald Steen ◽  
Are Pripp ◽  
Ragnhild Gunderson ◽  
Hilde Kristine Sandberg Mentzoni ◽  
...  

Background and purpose — Skeletal maturity is a crucial parameter when calculating remaining growth in children. We compared 3 different methods, 2 manual and 1 automated, in the radiological assessment of bone age with respect to precision and systematic difference. Material and methods — 66 simultaneous examinations of the left hand and left elbow from children treated for leg-length discrepancies were randomly selected for skeletal age assessment. The radiographs were anonymized and assessed twice with at least 3 weeks’ interval according to the Greulich and Pyle (GP) and Sauvegrain (SG) methods by 5 radiologists with different levels of experience. The hand radiographs were also assessed for GP bone age by use of the automated BoneXpert (BX) method for comparison. Results — The inter-observer intraclass correlation coefficient (ICC) was 0.96 for the GP and 0.98 for the SG method. The inter- and intra-observer standard error of the measurement (SEm) was 0.41 and 0.32 years for the GP method and 0.27 and 0.21 years for the SG method with a significant difference (p < 0.001) between the methods and between the experienced and the less experienced radiologists for both methods (p = 0.003 and p < 0.001). In 25% of the assessments the discrepancy between the GP and the SG methodwas > 1 year. There was no systematic difference comparing either manual method with the automatic BX method. Interpretation — With respect to the precision of skeletal age determination, we recommend using the SG method or preferably the automated BX method based on GP assessments in the calculation of remaining growth.


2022 ◽  
Author(s):  
Sarah Lebovitz ◽  
Hila Lifshitz-Assaf ◽  
Natalia Levina

Artificial intelligence (AI) technologies promise to transform how professionals conduct knowledge work by augmenting their capabilities for making professional judgments. We know little, however, about how human-AI augmentation takes place in practice. Yet, gaining this understanding is particularly important when professionals use AI tools to form judgments on critical decisions. We conducted an in-depth field study in a major U.S. hospital where AI tools were used in three departments by diagnostic radiologists making breast cancer, lung cancer, and bone age determinations. The study illustrates the hindering effects of opacity that professionals experienced when using AI tools and explores how these professionals grappled with it in practice. In all three departments, this opacity resulted in professionals experiencing increased uncertainty because AI tool results often diverged from their initial judgment without providing underlying reasoning. Only in one department (of the three) did professionals consistently incorporate AI results into their final judgments, achieving what we call engaged augmentation. These professionals invested in AI interrogation practices—practices enacted by human experts to relate their own knowledge claims to AI knowledge claims. Professionals in the other two departments did not enact such practices and did not incorporate AI inputs into their final decisions, which we call unengaged “augmentation.” Our study unpacks the challenges involved in augmenting professional judgment with powerful, yet opaque, technologies and contributes to literature on AI adoption in knowledge work.


Author(s):  
Douglas Villalta ◽  
Jose Bernardo Quintos

Abstract Gonadotropin releasing hormone analogs (GnRHas) are an effective treatment to address the compromise in height potential seen in patients with central precocious puberty. There is no evidence in the literature of a single GnRHa used for longer than 2 years before being removed or replaced. We describe a patient who was on continuous gonadotropin suppression for 7 years and despite this, achieved a height potential within one standard deviation of mid-parental height. A boy aged 10 years and 3 months presented to endocrine clinic with signs of precocious puberty and advanced bone age. Initial labs showed random LH 9.4 mIU/mL, FSH 16.3 mIU/mL, DHEAS 127 mcg/dl, and testosterone 628 ng/dL. He was initially started on Lupron injections before transitioning to a Histrelin implant. Follow-up laboratory results 5 months post-suppression showed pre-pubertal random LH 0.2 mIU/mL, FSH 0.1 mIU/mL, and testosterone 5 ng/dL. The patient was lost to follow-up and returned 5 years later presenting with gynecomastia and delayed bone age. He had continuous gonadotropin suppression with random LH 0.10 mIU/mL, FSH 0.16 mIU/mL, and testosterone 8 ng/dL. The Histrelin implant was removed and 4 months after removal labs showed random pubertal hormone levels with LH 5.6 mIU/mL, FSH 4.3 mIU/mL, and testosterone 506 ng/dl. The patient’s mid-parental height was 175.3 cm and the patient’s near final height was 170.6 cm which is within one standard deviation of his genetic potential. Further studies are needed to explore continuous gonadotropin hormone suppression with a single Histrelin implant beyond 2 years.


Medicine ◽  
2022 ◽  
Vol 101 (1) ◽  
pp. e28516
Author(s):  
Woo Young Jang ◽  
Kyung-Sik Ahn ◽  
Saelin Oh ◽  
Ji Eun Lee ◽  
Jimi Choi ◽  
...  
Keyword(s):  

2022 ◽  
Vol 6 (1) ◽  
pp. 9-13
Author(s):  
Esra ÖZGÜL ◽  
Aylin YÜCEL ◽  
Furkan KAYA ◽  
Serkan Bilge KOCA ◽  
Ayşe ERTEKİN
Keyword(s):  
Bone Age ◽  

2021 ◽  
Vol 15 (1) ◽  
pp. 141-148
Author(s):  
Suprava Patnaik ◽  
Sourodip Ghosh ◽  
Richik Ghosh ◽  
Shreya Sahay

Skeletal maturity estimation is routinely evaluated by pediatrics and radiologists to assess growth and hormonal disorders. Methods integrated with regression techniques are incompatible with low-resolution digital samples and generate bias, when the evaluation protocols are implemented for feature assessment on coarse X-Ray hand images. This paper proposes a comparative analysis between two deep neural network architectures, with the base models such as Inception-ResNet-V2 and Xception-pre-trained networks. Based on 12,611 hand X-Ray images of RSNA Bone Age database, Inception-ResNet-V2 and Xception models have achieved R-Squared value of 0.935 and 0.942 respectively. Further, in the same order, the MAE accomplished by the two models are 12.583 and 13.299 respectively, when subjected to very few training instances with negligible chances of overfitting.


2021 ◽  
Vol 38 (6) ◽  
pp. 1565-1574
Author(s):  
Cüneyt Ozdemir ◽  
Mehmet Ali Gedik ◽  
Yılmaz Kaya

Bone age is estimated in pediatric medicine for medical and legal purposes. In pediatric medicine, it aids in the growth and development assessment of various diseases affecting children. In forensic medicine, it is required to determine criminal liability by age, refugee age estimation, and child-adult discrimination. In such cases, radiologists or forensic medicine specialists conduct bone age estimation from left hand-wrist radiographs using atlas methods that require time and effort. This study aims to develop a computer-based decision support system using a new modified deep learning approach to accelerate radiologists' workflow for pediatric bone age estimation from wrist radiographs. The KCRD dataset created by us was used to test the proposed method. The performance of the proposed modified IncepitonV3 model compared to IncepitonV3, MobileNetV2, EfficientNetB7 models. Acceptably high results (MAE=4.3, RMSE=5.76, and R2=0.99) were observed with the modified IncepitonV3 transfer deep learning method.


Sign in / Sign up

Export Citation Format

Share Document