Versatile Framework for Medical Image Processing and Analysis with Application to Automatic Bone Age Assessment

Abstract

Deep learning technique has made a tremendous impact on medical image processing and analysis. Typically, the procedure of medical image processing and analysis via deep learning technique includes image segmentation, image enhancement, and classification or regression. A challenge for supervised deep learning frequently mentioned is the lack of annotated training data. In this paper, we aim to address the problems of training transferred deep neural networks with limited amount of annotated data. We proposed a versatile framework for medical image processing and analysis via deep active learning technique. The framework includes (1) applying deep active learning approach to segment specific regions of interest (RoIs) from raw medical image by using annotated data as few as possible; (2) generative adversarial Network is employed to enhance contrast, sharpness, and brightness of segmented RoIs; (3) Paced Transfer Learning (PTL) strategy which means fine-tuning layers in deep neural networks from top to bottom step by step to perform medical image classification or regression tasks. In addition, in order to understand the necessity of deep-learning-based medical image processing tasks and provide clues for clinical usage, class active map (CAM) is employed in our framework to visualize the feature maps. To illustrate the effectiveness of the proposed framework, we apply our framework to the bone age assessment (BAA) task using RSNA dataset and achieve the state-of-the-art performance. Experimental results indicate that the proposed framework can be effectively applied to medical image analysis task.

Age Assessment of Youth and Young Adults Using Magnetic Resonance Imaging of the Knee: A Deep Learning Approach

“…This challenge aimed to encourage participants to develop algorithms that could most-accurately determine the bone age of subjects from 0 to 19 years of age, providing a database of around 12,000 radiograph images of the hand and wrist, labeled as to their bone age [53]. The participants proposed CNN models, like the ones by Iglovikov et al [54], Zhao et al [55], and Ren et al [22], which achieved MAEs of 7.52, 7.66, and 5.2 months. However good the obtained results were, they were not comparable to our results, since our aim was to predict the chronological age of a subject, and the RSNA project’s goal was to predict the bone age.…”

Automatic quantification of superficial foveal avascular zone in optical coherence tomography angiography implemented with deep learning

“…Currently, deep learning for the automatic classification and segmentation of OCT images in ophthalmology affords excellent results [15,16]. Furthermore, deep learning is applicable to image B/C adjustments [17,18]. Therefore, we herein propose a method based on deep learning for the segmentation and quantification of the sFAZ in OCTA images.…”

Segmentation of Medical X-ray Bone Image Using Different Image Processing Techniques

“…Mathematical morphology, distance transform, marker-controlled technique, and watershed transform was also used in their approach, result proved the efficiency of image segmentation in enhancing the procedures and the workflow of the radiological examination. Zhao et al [10] developed a versatile framework for medical image processing using deep learning approach. The study employed RSNA dataset generative adversarial network (GAN) and class active map was used for image processing.…”