Proceedings ArticleDOI
Unboxing the blackbox - Visualizing the model on hand radiographs in skeletal bone age assessment
Reads0
Chats0
TLDR
In this article, an end-to-end approach which uses inception trained from scratch, achieves 80% accuracy in predicting age within 1 year from the ground truth, using attention maps to explain what regions of the image, the model is focusing on while assessing the bone age and the heat maps thus generated match the features used by the radiologists while predicting manually.Abstract:
Skeletal Bone age assessment is one of the routine radiological procedures performed by paediatricians and endocrinologists for investigating genetic disorders, developmental abnormalities and metabolic complications In this process skeletal age is compared against child's chronological age to uncover discrepancies if any Hand radiographs being the cheapest, reliable and widely used modality, are used to predict the bone age in children from 1-18 years of age Conventional methods make use of atlases to predict the age which are time consuming, tedious and have problems of inter-observer variability We propose an end to end approach which uses inception trained from scratch, achieves 80% accuracy in predicting age within 1 year from the ground truth Further, attention maps are generated to explain what regions of the image, the model is focusing on while assessing the bone age and the heat maps thus generated match the features used by the radiologists while predicting manuallyread more
Citations
More filters
Proceedings ArticleDOI
BoneAgeAI: A Novel Age Prediction Tool using Deep Convolutional Neural Networks
TL;DR: A novel Bone Age prediction system using pre-trained Deep convolutional neural networks is developed and achieved a Mean Absolute Difference of 6.9 months and Root Mean Square Deviation of 12.12 months.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Journal ArticleDOI
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
Geoffrey E. Hinton,Li Deng,Dong Yu,George E. Dahl,Abdelrahman Mohamed,Navdeep Jaitly,Andrew W. Senior,Vincent Vanhoucke,Patrick Nguyen,Tara N. Sainath,Brian Kingsbury +10 more
TL;DR: This article provides an overview of progress and represents the shared views of four research groups that have had recent successes in using DNNs for acoustic modeling in speech recognition.
Posted Content
Learning Deep Features for Discriminative Localization
TL;DR: In this article, the authors revisited the global average pooling layer and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels.
Book
Radiographic Atlas of Skeletal Development of the Hand and Wrist
TL;DR: This Atlas is principally based on the Brush Foundation Study of Human Growth and Development, conceived in 1929 by Professor T. Wingate Todd and obtained in the six years subsequent to Todd's publication of his Atlas of Skeletal Maturation of the Hand.
Journal ArticleDOI
Bone age assessment of children using a digital hand atlas.
Arkadiusz Gertych,Aifeng Zhang,James W. Sayre,James W. Sayre,Sylwia Pospiech-Kurkowska,H. K. Huang +5 more
TL;DR: An automated method to assess bone age of children using a digital hand atlas and is being integrated with a PACS for validation of clinical use.