Journal Article

DKFZ-2026-01681

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Automated Thoracolumbar Stump Rib Detection and Analysis in a Large CT Cohort

Möller, H. ; Dima, A. ; Keinert-Weth, B. ; Graf, R. ; Atad, M. ; Paetzold, J. ; Jungmann, F. ; Braren, R.DKFZ* ; Kofler, F. ; Menze, B. ; Rueckert, D. ; Kirschke, J. S. ; Schön, H.

2026
MDPI Basel

Abstract: Thoracolumbar stump ribs are one of the essential indicators of thoracolumbar transitionalvertebrae or enumeration anomalies. While some studies manually assess these anomaliesand describe the ribs qualitatively, this study aims to automate thoracolumbar stump rib detection and analyze their morphology quantitatively. To this end, we train a high-resolutiondeep learning model for rib segmentation using nnUNet and achieve significant improvements over existing models (Dice score 0.997 vs. 0.779, p-value < 0.01). In addition, weemploy a novel iterative algorithm and piecewise linear interpolation to estimate rib length,achieving a success rate of 98.2%. When analyzing morphological features, we show thatstump ribs articulate more posteriorly at the vertebrae (−19.2 ± 3.8 vs. −13.8 ± 2.5 mm,p-value < 0.01), are thinner (260.6 ± 103.4 vs. 563.6 ± 127.1 mm2, p-value < 0.01), andare oriented more downwards and sideways within the first centimeters in contrast tofull-length ribs. We show that with partially visible ribs, these features can achieve anF1-score of 0.84 and an AUC of 0.98 in differentiating stump ribs from regular ones. Wepublish the model weights and masks for public use.

Note: #DKTKZFB9#

---

Contributing Institute(s):

1. DKTK Koordinierungsstelle München (MU01)

Research Program(s):

1. 899 - ohne Topic (POF4-899) (POF4-899)

Appears in the scientific report 2026

---

Database coverage:
; ; ; Article Processing Charges ; Clarivate Analytics Master Journal List ; DOAJ Seal ; Ebsco Academic Search ; Emerging Sources Citation Index ; Fees ; SCOPUS ; Web of Science Core Collection

---