Deep Learning for Automated Measurement of Patellofemoral Anatomic Landmarks.

BACKGROUND: Patellofemoral anatomy has not been well characterized. Applying deep learning to automatically measure knee anatomy can provide a better understanding of anatomy, which can be a key factor in improving outcomes. METHODS: 483 total patients with knee CT imaging (April 2017-May 2022) from 6 centers were selected from a cohort scheduled for knee arthroplasty and a cohort with healthy knee anatomy. A total of 7 patellofemoral landmarks were annotated on 14,652 images and approved by a senior musculoskeletal radiologist. A two-stage deep learning model was trained to predict landmark coordinates using a modified ResNet50 architecture initialized with self-supervised learning pretrained weights on RadImageNet. Landmark predictions were evaluated with mean absolute error, and derived patellofemoral measurements were analyzed with Bland-Altman plots. Statistical significance of measurements was assessed by paired t-tests. RESULTS: Mean absolute error between predicted and ground truth landmark coordinates was 0.20/0.26 cm in the healthy/arthroplasty cohort. Four knee parameters were calculated, including transepicondylar axis length, transepicondylar-posterior femur axis angle, trochlear medial asymmetry, and sulcus angle. There were no statistically significant parameter differences (p > 0.05) between predicted and ground truth measurements in both cohorts, except for the healthy cohort sulcus angle. CONCLUSION: Our model accurately identifies key trochlear landmarks with ~0.20-0.26 cm accuracy and produces human-comparable measurements on both healthy and pathological knees. This work represents the first deep learning regression model for automated patellofemoral annotation trained on both physiologic and pathologic CT imaging at this scale. This novel model can enhance our ability to analyze the anatomy of the patellofemoral compartment at scale.

Postoperative imaging of thoracic aortic repairs.

Imaging plays a crucial role in the postoperative monitoring of thoracic aortic repairs. With the development of multiple surgical techniques to repair the ascending aorta and aortic arch, it can be a daunting challenge for the radiologist to diagnose potential pathologies in this sea of various techniques, each with their own normal postoperative appearance and potential complications. In this paper, we will provide a comprehensive review of the postoperative imaging in the setting of thoracic aortic repairs, including the role of imaging, components of thoracic aortic repairs, the normal postoperative appearance, and potential complications.

A Membrane-Bound Transcription Factor is Proteolytically Regulated by the AAA+ Protease FtsH in Staphylococcus aureus.

In bacteria, chromosomal DNA resides in the cytoplasm, and most transcription factors are also found in the cytoplasm. However, some transcription factors, called membrane-bound transcription factors (MTFs), reside in the cytoplasmic membrane. Here, we report the identification of a new MTF in the Gram-positive pathogen Staphylococcus aureus and its regulation by the protease FtsH. The MTF, named MbtS (membrane-bound transcription factor of Staphylococcus aureus), is encoded by SAUSA300_2640 and predicted to have an N-terminal DNA binding domain and three transmembrane helices. The MbtS protein was degraded by membrane vesicles containing FtsH or by the purified FtsH. MbtS bound to an inverted repeat sequence in its promoter region, and the DNA binding was essential for its transcription. Transcriptional comparison between the ftsH deletion mutant and the ftsH mbtS double mutant showed that MbtS could alter the transcription of over 200 genes. Although the MbtS protein was not detected in wild-type (WT) cells grown in a liquid medium, the protein was detected in some isolated colonies on an agar plate. In a murine model of a skin infection, the disruption of mbtS increased the lesion size. Based on these results, we concluded that MbtS is a new S. aureus MTF whose activity is proteolytically regulated by FtsH.IMPORTANCEStaphylococcus aureus is an important pathogenic bacterium causing various diseases in humans. In the bacterium, transcription is typically regulated by the transcription factors located in the cytoplasm. In this study, we report an atypical transcription factor identified in S. aureus Unlike most other transcription factors, the newly identified transcription factor is located in the cytoplasmic membrane, and its activity is proteolytically controlled by the membrane-bound AAA+ protease FtsH. The newly identified MTF, named MbtS, has the potential to regulate the transcription of over 200 genes. This study provides a molecular mechanism by which a protease affects bacterial transcription and illustrates the diversity of the bacterial transcriptional regulation.