Evaluation of deep learning methods for parotid gland segmentation from CT images.

The segmentation of organs at risk is a crucial and time-consuming step in radiotherapy planning. Good automatic methods can significantly reduce the time clinicians have to spend on this task. Due to its variability in shape and low contrast to surrounding structures, segmenting the parotid gland is challenging. Motivated by the recent success of deep learning, we study the use of two-dimensional (2-D), 2-D ensemble, and three-dimensional (3-D) U-Nets for segmentation. The mean Dice similarity to ground truth is ∼ 0.83 for all three models. A patch-based approach for class balancing seems promising for false-positive reduction. The 2-D ensemble and 3-D U-Net are applied to the test data of the 2015 MICCAI challenge on head and neck autosegmentation. Both deep learning methods generalize well onto independent data (Dice 0.865 and 0.88) and are superior to a selection of model- and atlas-based methods with respect to the Dice coefficient. Since appropriate reference annotations are essential for training but often difficult and expensive to obtain, it is important to know how many samples are needed for training. We evaluate the performance after training with different-sized training sets and observe no significant increase in the Dice coefficient for more than 250 training cases.

Evaluation of segmentation methods on head and neck CT: Auto-segmentation challenge 2015.

PURPOSE: Automated delineation of structures and organs is a key step in medical imaging. However, due to the large number and diversity of structures and the large variety of segmentation algorithms, a consensus is lacking as to which automated segmentation method works best for certain applications. Segmentation challenges are a good approach for unbiased evaluation and comparison of segmentation algorithms. METHODS: In this work, we describe and present the results of the Head and Neck Auto-Segmentation Challenge 2015, a satellite event at the Medical Image Computing and Computer Assisted Interventions (MICCAI) 2015 conference. Six teams participated in a challenge to segment nine structures in the head and neck region of CT images: brainstem, mandible, chiasm, bilateral optic nerves, bilateral parotid glands, and bilateral submandibular glands. RESULTS: This paper presents the quantitative results of this challenge using multiple established error metrics and a well-defined ranking system. The strengths and weaknesses of the different auto-segmentation approaches are analyzed and discussed. CONCLUSIONS: The Head and Neck Auto-Segmentation Challenge 2015 was a good opportunity to assess the current state-of-the-art in segmentation of organs at risk for radiotherapy treatment. Participating teams had the possibility to compare their approaches to other methods under unbiased and standardized circumstances. The results demonstrate a clear tendency toward more general purpose and fewer structure-specific segmentation algorithms.

Computer algorithms for three-dimensional measurement of humeral anatomy: analysis of 140 paired humeri.

BACKGROUND: In the presence of severe osteoarthritis, osteonecrosis, or proximal humeral fracture, the contralateral humerus may serve as a template for the 3-dimensional (3D) preoperative planning of reconstructive surgery. The purpose of this study was to develop algorithms for performing 3D measurements of the humeral anatomy and further to assess side-to-side (bilateral) differences in humeral head retrotorsion, humeral head inclination, humeral length, and humeral head radius and height. METHODS: The 3D models of 140 paired humeri (70 cadavers) were extracted from computed tomographic data. Geometric characteristics quantifying the humeral anatomy in 3D were determined in a semiautomatic fashion using the developed computer algorithms. The results between the sides were compared for evaluating bilateral differences. RESULTS: The mean bilateral difference of the humeral retrotorsion angle was 6.7° (standard deviation [SD], 5.7°; range, -15.1° to 24.0°; P = .063); the mean side difference of the humeral head inclination angle was 2.3° (SD, 1.8°; range, -5.1° to 8.4°; P = .12). The side difference in humeral length (mean, 2.9 mm; SD, 2.5 mm; range, -8.7 mm to 10.1 mm; P = .04) was significant. The mean side difference in the head sphere radius was 0.5 mm (SD, 0.6 mm; range, -3.2 mm to 2.2 mm; P = .76), and the mean side difference in humeral head height was 0.8 mm (SD, 0.6 mm; range, -2.4 mm to 2.4 mm; P = .44). CONCLUSIONS: The contralateral anatomy may serve as a reliable reconstruction template for humeral length, humeral head radius, and humeral head height if it is analyzed with 3D algorithms. In contrast, determining humeral head retrotorsion and humeral head inclination from the contralateral anatomy may be more prone to error.