Deep Learning Based Rib Centerline Extraction and Labeling

Lenga, Matthias; Klinder, Tobias; Bürger, Christian; Berg, Jens von; Franz, Astrid; Lorenz, Cristian

doi:10.1007/978-3-030-11166-3_9

Cited by 9 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our algorithm follows a data-driven approach: it relies on the human annotations of rib fractures and learns to directly predict the voxel-level segmentation of fractures. Notably, the proposed FracNet does not rely on the extraction of rib centerlines in typical rib analysis algorithms [27]. As illustrated in Fig.…”

Section: Dataset Pretreatmentmentioning

confidence: 99%

Deep-learning-assisted detection and segmentation of rib fractures from CT scans: Development and validation of FracNet

Jin

Yang

Kuang³

et al. 2020

eBioMedicine

112

View full text Add to dashboard Cite

Section: Dataset Pretreatmentmentioning

confidence: 99%

Deep-learning-assisted detection and segmentation of rib fractures from CT scans: Development and validation of FracNet

Jin

Yang

Kuang³

et al. 2020

eBioMedicine

112

View full text Add to dashboard Cite

“…Result points having a corresponding GTP within δ were counted as true positive (TP), all other as false positive (FP). From the TP, FP, and FN values we calculated sensitivity, precision and Dice using Equation (1). Table 3 summarizes our results from the 4-fold cross-validation.…”

Section: Rib Centerlinesmentioning

confidence: 99%

Computational Methods and Clinical Applications in Musculoskeletal Imaging

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Automated extraction and labeling of rib centerlines is a typically needed prerequisite for more advanced assisted reading tools that help the radiologist to efficiently inspect all 24 ribs in a CT volume. In this paper, we combine a deep learning-based rib detection with a dedicated centerline extraction algorithm applied to the detection result for the purpose of fast, robust and accurate rib centerline extraction and labeling from CT volumes. More specifically, we first apply a fully convolutional neural network (FCNN) to generate a probability map for detecting the first rib pair, the twelfth rib pair, and the collection of all intermediate ribs. In a second stage, a newly designed centerline extraction algorithm is applied to this multi-label probability map. Finally, the distinct detection of first and twelfth rib separately, allows to derive individual rib labels by simple sorting and counting the detected centerlines. We applied our method to CT volumes from 116 patients which included a variety of different challenges and achieved a centerline accuracy of 0.787 mm with respect to manual centerline annotations.

show abstract

“…e second type is fracture recognition models based on deep learning [7]. e following are characteristics that exist in the current rib fracture diagnosis using deep learning: (1) the CT image-based rib fracture dataset has samples with doubtful annotation [8], and different doctors have different annotations for the same case [9]. e doubtful annotation is a great challenge for deep learning models.…”

Section: Introductionmentioning

confidence: 99%

An Algorithm for Automatic Rib Fracture Recognition Combined with nnU-Net and DenseNet

Zhang

Yan³

et al. 2022

Evidence-Based Complementary and Alternative Medicine

View full text Add to dashboard Cite

Rib fracture is the most common thoracic clinical trauma. Most patients have multiple different types of rib fracture regions, so accurate and rapid identification of all trauma regions is crucial for the treatment of rib fracture patients. In this study, a two-stage rib fracture recognition model based on nnU-Net is proposed. First, a deep learning segmentation model is trained to generate candidate rib fracture regions, and then, a deep learning classification model is trained in the second stage to classify the segmented local fracture regions according to the candidate fracture regions generated in the first stage to determine whether they are fractures or not. The results show that the two-stage deep learning model proposed in this study improves the accuracy of rib fracture recognition and reduces the false-positive and false-negative rates of rib fracture detection, which can better assist doctors in fracture region recognition.

show abstract

Deep Learning Based Rib Centerline Extraction and Labeling

Cited by 9 publications

References 7 publications

Deep-learning-assisted detection and segmentation of rib fractures from CT scans: Development and validation of FracNet

Deep-learning-assisted detection and segmentation of rib fractures from CT scans: Development and validation of FracNet

Computational Methods and Clinical Applications in Musculoskeletal Imaging

An Algorithm for Automatic Rib Fracture Recognition Combined with nnU-Net and DenseNet

Contact Info

Product

Resources

About