Deep learning‐based body part recognition algorithm for three‐dimensional medical images

Abstract

Background The automatic recognition of human body parts in three‐dimensional medical images is important in many clinical applications. However, methods presented in prior studies have mainly classified each two‐dimensional (2D) slice independently rather than recognizing a batch of consecutive slices as a specific body part. Purpose In this study, we aim to develop a deep learning‐based method designed to automatically divide computed tomography (CT) and magnetic resonance imaging (MRI) scans into five consecutive body parts: head, neck, chest, abdomen, and pelvis. Methods A deep learning framework was developed to recognize body parts in two stages. In the first preclassification stage, a convolutional neural network (CNN) using the GoogLeNet Inception v3 architecture and a long short‐term memory (LSTM) network were combined to classify each 2D slice; the CNN extracted information from a single slice, whereas the LSTM employed rich contextual information among consecutive slices. In the second postprocessing stage, the input scan was further partitioned into consecutive body parts by identifying the optimal boundaries between them based on the slice classification results of the first stage. To evaluate the performance of the proposed method, 662 CT and 1434 MRI scans were used. Results Our method achieved a very good performance in 2D slice classification compared with state‐of‐the‐art methods, with overall classification accuracies of 97.3% and 98.2% for CT and MRI scans, respectively. Moreover, our method further divided whole scans into consecutive body parts with mean boundary errors of 8.9 and 3.5 mm for CT and MRI data, respectively. Conclusions The proposed method significantly improved the slice classification accuracy compared with state‐of‐the‐art methods, and further accurately divided CT and MRI scans into consecutive body parts based on the results of slice classification. The developed method can be employed as an important step in various computer‐aided diagnosis and medical image analysis schemes.

Feasibility of a deep-learning based anatomical region labeling tool for Cone-Beam Computed Tomography scans in radiotherapy

“…Bold texts represent the better result between the two models. literature (94.1% and 97.3%, respectively) [12,14], our ARL resulted in a better performance with an overall accuracy of 99.2%. However, a direct comparison between those methods is not the primary aim of this study as different imaging modalities, number of classes, and imaging planes have been used in each method.…”

“…Several algorithms have recently been proposed for the classification of anatomical regions in CT and MRI scans [11][12][13][14]. Among those, Ouyang et al [14] achieved the highest classification accuracy of 97.3% on their test dataset composed of 663 CT scans. These previous studies showcase the potential of deep learning techniques on such region labeling problem.…”

“…Hence, classifying CBCT images may become a challenge as fewer useful features and more artifacts may be present on the CBCT scan for accurate region labeling. CBCT scans also have a small field-of-view (FOV), which is usually restricted to the treatment region only, making a consecutive body part recognition algorithm as in [14] more complicated.…”

Machine Learning Classification of Body Part, Imaging Axis, and Intravenous Contrast Enhancement on CT Imaging

“…Several ML models for classifying body parts and contrast enhancement have been developed but these handled a limited number of body parts and phases of postcontrast imaging. [4][5][6][7][8] The aim of this study was the development and evaluation of ML models that automatically classify CT series by the body part(s) imaged, axis of imaging, and IV contrast enhancement.…”