The effect of deep convolutional neural networks on radiologists' performance in the detection of hip fractures on digital pelvic radiographs.

PURPOSE: The purpose of our study is to develop deep convolutional neural network (DCNN) for detecting hip fractures using CT and MRI as a gold standard, and to evaluate the diagnostic performance of 7 readers with and without DCNN. METHODS: The study population consisted of 327 patients who underwent pelvic CT or MRI and were diagnosed with proximal femoral fractures. All radiographs were manually checked and annotated by radiologists referring to CT and MRI for selecting ROI. At first, a DCNN with the GoogLeNet model was trained by 302 cases. The remaining 25 cases and 25 control subjects were used for the observer performance study and for the testing of DCNN. Seven readers took part in this study. A continuous rating scale was used to record each observer's confidence level. Subsequently, each observer interpreted with the DCNN outputs and rated them again. The area under the curve (AUC) was used to compare the fracture detection. RESULTS: The average AUC of the 7 readers was 0.832. The AUC of DCNN alone was 0.905. The average AUC of the 7 readers with DCNN outputs was 0.876. The AUC of readers with DCNN output were higher than those without(p < 0.05). The AUC of the 2 experienced readers with DCNN output exceeded the AUC of DCNN alone. CONCLUSION: For detecting the hip fractures on radiographs, DCNN developed using CT and MRI as a gold standard by radiologists improved the diagnostic performance including the experienced readers.

Changes in patellar tracking after total knee arthroplasty: 10-year follow-up of Miller-Galante I knees.

Changes in patellar tilt angle and patellar displacement were evaluated in 18 knees with the Miller-Galante I knee arthroplasty system (Zimmer, Warsaw, Ind). Mean follow-up was 10 years. Patellar tilt angle at final follow-up (5.7 degrees) was significantly larger than at 1 year postoperatively (2.8 degrees). Patellar displacement at final follow-up (5.1 mm) was significantly larger than at 1 year postoperatively (3.4 mm). Preoperatively, patellar tilt angle showed a statistically significant correlation with the change in tilting angle during follow-up. These results suggest patellar tracking can worsen during the long-term postoperative period.

Lengthening the locking loop repair for zone 2 flexor tendon laceration and partial lateral release of the tendon sheath.

The authors present the clinical outcomes of nine zone 2 flexor tendon repairs using a locking loop technique (i.e. the Modified Pennington technique). The locking loops were located approximately 10 mm away from the lacerated tendon ends to "lengthen" the locking loop repair, as experimentally and clinically recommended. The partial lateral release of the tendon sheath, including the A2 and/or A4 pulley, was performed not only to locate the sutures but also to allow a full range of motion of the repair without catching on the tendon sheath, as clinically recommended. All the patients were followed up for six months or more except for one. All digits were evaluated as excellent or good at the final follow-up by the original Strickland criteria. No rupture occurred and no bowstring of the flexor tendon was observed. The clinical outcomes of the current study indicate that "lengthening" the locking loop repair is effective for zone 2 flexor tendon repair and that the partial lateral release of the tendon sheath, including the A2 and/or A4 pulley, does not result in the bowstring of the flexor tendon.