Automatic quadriceps and patellae segmentation of MRI with cascaded U²‐Net and SASSNet deep learning model

Abstract

Purpose Automatic muscle segmentation is critical for advancing our understanding of human physiology, biomechanics, and musculoskeletal pathologies, as it allows for timely exploration of large multi‐dimensional image sets. Segmentation models are rarely developed/validated for the pediatric model. As such, autosegmentation is not available to explore how muscle architectural changes during development and how disease/pathology affects the developing musculoskeletal system. Thus, we aimed to develop and validate an end‐to‐end, fully automated, deep learning model for accurate segmentation of the rectus femoris and vastus lateral, medialis, and intermedialis using a pediatric database. Methods We developed a two‐stage cascaded deep learning model in a coarse‐to‐fine manner. In the first stage, the U2‐Net roughly detects the muscle subcompartment region. Then, in the second stage, the shape‐aware 3D semantic segmentation method SASSNet refines the cropped target regions to generate the more finer and accurate segmentation masks. We utilized multifeature image maps in both stages to stabilize performance and validated their use with an ablation study. The second‐stage SASSNet was independently run and evaluated with three different cropped region resolutions: the original image resolution, and images downsampled 2× and 4× (high, mid, and low). The relationship between image resolution and segmentation accuracy was explored. In addition, the patella was included as a comparator to past work. We evaluated segmentation accuracy using leave‐one‐out testing on a database of 3D MR images (0.43 × 0.43 × 2 mm) from 40 pediatric participants (age 15.3 ± 1.9 years, 55.8 ± 11.8 kg, 164.2 ± 7.9 cm, 38F/2 M). Results The mid‐resolution second stage produced the best results for the vastus medialis, rectus femoris, and patella (Dice similarity coefficient = 95.0%, 95.1%, 93.7%), whereas the low‐resolution second stage produced the best results for the vastus lateralis and vastus intermedialis (DSC = 94.5% and 93.7%). In comparing the low‐ to mid‐resolution cases, the vasti intermedialis, vastus medialis, rectus femoris, and patella produced significant differences (p = 0.0015, p = 0.0101, p < 0.0001, p = 0.0003) and the vasti lateralis did not (p = 0.2177). The high‐resolution stage 2 had significantly lower accuracy (1.0 to 4.4 dice percentage points) compared to both the mid‐ and low‐resolution routines (p value ranged from < 0.001 to 0.04). The one exception was the rectus femoris, where there was no difference between the low‐ and high‐resolution cases. The ablation study demonstrated that the multifeature is more reliable than the single feature. Conclusions Our successful implementation of this two‐stage segmentation pipeline provides a critical tool for expanding pediatric muscle physiology and clinical research. With a relatively small and variable dataset, our fully automatic segmentation technique produces accuracies that matched or exceeded the current state of the art. The two‐stage segmentation avoids memor...

Automated segmentation of the healed anterior cruciate ligament from T2* relaxometry MRI scans

“…These results fit in with the increasing application of deep learning for MR image segmentation of the knee, where it has been found that deep learning has been able to achieve consistent, accurate segmentation of structures of interest. 12,13,[27][28][29][30][31][32] However, most automated segmentation algorithms developed for the knee have focused on the cartilage, meniscus, and bones. [27][28][29][30][31][32] This may be due, in part, to some of the unique challenges associated with ACL segmentation.…”

“…12,13,[27][28][29][30][31][32] However, most automated segmentation algorithms developed for the knee have focused on the cartilage, meniscus, and bones. [27][28][29][30][31][32] This may be due, in part, to some of the unique challenges associated with ACL segmentation. For example, previous semi-automated segmentation approaches faced difficulties segmenting the origin and insertion of the ACL.…”

The segmentation and intelligent recognition of structural surfaces in borehole images based on the U2-Net network

“…U 2 -Net [ 21 – 24 ] is an image semantic segmentation network that combines multi-scale feature extraction and a two-level nested residual network structure. It ensures the output of high-resolution feature maps while controlling memory usage and computational costs at a lower level.…”

Deep Learning-Based Medical Images Segmentation of Musculoskeletal Anatomical Structures: A Survey of Bottlenecks and Strategies

“…U-Net MRI [5,7,11,19,25,27,[31][32][33][34][35][36][37][38][39][40][41][42]44,46,55,57,64,65,89,107] US [49,100,101] CT [4,9,13,15,16,59,69,[71][72][73][76][77][78][79][80][81]83,90,91,[93][94][95]99,[103]…”