Automatic detection of midfacial fractures in facial bone CT images using deep learning-based object detection models.

BACKGROUND: Midfacial fractures are among the most frequent facial fractures. Surgery is recommended within 2 weeks of injury, but this time frame is often extended because the fracture is missed on diagnostic imaging in the busy emergency medicine setting. Using deep learning technology, which has progressed markedly in various fields, we attempted to develop a system for the automatic detection of midfacial fractures. The purpose of this study was to use this system to diagnose fractures accurately and rapidly, with the intention of benefiting both patients and emergency room physicians. METHODS: One hundred computed tomography images that included midfacial fractures (e.g., maxillary, zygomatic, nasal, and orbital fractures) were prepared. In each axial image, the fracture area was surrounded by a rectangular region to create the annotation data. Eighty images were randomly classified as the training dataset (3736 slices) and 20 as the validation dataset (883 slices). Training and validation were performed using Single Shot MultiBox Detector (SSD) and version 8 of You Only Look Once (YOLOv8), which are object detection algorithms. RESULTS: The performance indicators for SSD and YOLOv8 were respectively: precision, 0.872 and 0.871; recall, 0.823 and 0.775; F1 score, 0.846 and 0.82; average precision, 0.899 and 0.769. CONCLUSIONS: The use of deep learning techniques allowed the automatic detection of midfacial fractures with good accuracy and high speed. The system developed in this study is promising for automated detection of midfacial fractures and may provide a quick and accurate solution for emergency medical care and other settings.

Automatic orbital segmentation using deep learning-based 2D U-net and accuracy evaluation: A retrospective study.

The purpose of this study was to verify whether the accuracy of automatic segmentation (AS) of computed tomography (CT) images of fractured orbits using deep learning (DL) is sufficient for clinical application. In the surgery of orbital fractures, many methods have been reported to create a 3D anatomical model for use as a reference. However, because the orbit bone is thin and complex, creating a segmentation model for 3D printing is complicated and time-consuming. Here, the training of DL was performed using U-Net as the DL model, and the AS output was validated with Dice coefficients and average symmetry surface distance (ASSD). In addition, the AS output was 3D printed and evaluated for accuracy by four surgeons, each with over 15 years of clinical experience. One hundred twenty-five CT images were prepared, and manual orbital segmentation was performed in all cases. Ten orbital fracture cases were randomly selected as validation data, and the remaining 115 were set as training data. AS was successful in all cases, with good accuracy: Dice, 0.860 ± 0.033 (mean ± SD); ASSD, 0.713 ± 0.212 mm. In evaluating AS accuracy, the expert surgeons generally considered that it could be used for surgical support without further modification. The orbital AS algorithm developed using DL in this study is extremely accurate and can create 3D models rapidly at low cost, potentially enabling safer and more accurate surgeries.

The HDAC inhibitor OBP-801 suppresses the growth of myxofibrosarcoma cells.

PURPOSE: Myxofibrosarcoma is characterized by a high rate of recurrence after surgery. Since myxofibrosarcoma is refractory to conventional cytotoxic chemotherapy, the established radical treatment is primary wide resection. The effects of histone deacetylase (HDAC) inhibitors on myxofibrosarcoma have not yet been investigated. Therefore, the main purpose of the present study was to examine the effects of a HDAC inhibitor on myxofibrosarcoma. METHODS: The effects of the HDAC inhibitor OBP-801 on human myxofibrosarcoma cells were examined using cell viability assay, flow cytometric analysis of the cell cycle and apoptosis, and Western blotting. The effects of combinations of OBP-801 with pazopanib or Akt-mTOR inhibitors were also investigated using cell viability assay. RESULTS: OBP-801 inhibited the growth of myxofibrosarcoma NMFH-1 and NMFH-2 cells. It also induced cell cycle arrest at the G2 phase and apoptosis in both cell lines. The inhibitory effects of pazopanib and Akt-mTOR inhibitors on the growth of myxofibrosarcoma cells were enhanced by the combination with OBP-801. CONCLUSIONS: The present results demonstrated that OBP-801 exerted therapeutic effects in myxofibrosarcoma in both single and concomitant administrations. Therefore, OBP-801 has potential as a novel treatment for myxofibrosarcoma.

Sulforaphane suppresses cell growth and collagen expression of keloid fibroblasts.

Keloids are fibroproliferative diseases characterized by the accumulation of an extracellular matrix including collagen. Various growth factors, or cytokines, and their receptors are overexpressed in keloids, and they are expected to be therapy targets. Sulforaphane, a dietary isothiocyanate, has recently shown anti-tumor, anti-inflammatory, and anti-fibrotic properties. In this study, we found that sulforaphane inhibited cell growth and reduced collagen at the mRNA and protein levels in keloid fibroblasts. Moreover, sulforaphane markedly suppressed the expression of IL-6 and α-SMA and inhibited Stat3 and Smad3 signaling pathways in keloid fibroblast KF112 cells. Sulforaphane induced G2/M cell-cycle arrest with the induction of p21 in KF112 cells. In addition, sulforaphane inhibited cell growth and suppressed the expression of collagen in keloid fibroblasts under a coculture with peripheral blood mononuclear cells. Furthermore, sulforaphane suppressed IL-6, Stat3, and Smad3 signaling in the coculture system. This study suggests that sulforaphane may be a novel keloid treatment.

Preventive effects on seroma formation with use of the harmonic focus shears after breast reconstruction with the latissimus dorsi flap.

BACKGROUND: Postoperative seroma is the most common complication of latissimus dorsi (LD) flap surgery for breast reconstruction. The use of EC for elevation of the flap might cause additional risk for seroma formation by injuring surrounding lymph vessels due to heat dispersion. There is a possibility that seroma formation can be prevented by using alternative devices such as harmonic focus (HF) shears that can dissect the tissue simultaneously with sealing the lymph vessels. METHODS: Forty-eight patients who underwent breast reconstruction with LD flaps since August 2011 up to April 2015 were enrolled. They were retrospectively split into two groups: 24 in group HF, 24 in group EC (conventional electrocautery). The primary outcome measures were rate of seroma formation and total volume of drain discharge and indwelling period of drainage at the anterior chest and donor site. Secondary outcome measures were length of hospital stay and duration of surgery. RESULTS: The incidence of seroma was 45.8% in the EC group and 20.8% in the HF group. The total volumes of the drain discharge and indwelling period of drainage in the back (donor site) were significantly decreased in the HF group. The length of the hospital stay and surgical time was significantly shorter for the HF group. CONCLUSIONS: The use of HF shears on the LD flap donor site is helpful for reducing seroma formation, the length of the drainage period, the surgical time, and the length of the hospital stay.