Distal radius fractures (DRFs) are one of the most common types of fracture and one which is often treated surgically. Standard X-rays are obtained for DRFs, and in most cases that have an intra-articular component, a routine CT is also performed. However, it is estimated that CT is only required in 20% of cases and therefore routine CT's results in the overutilisation of resources burdening radiology and emergency departments. In this study, we explore the feasibility of using deep learning to differentiate intra- and extra-articular DRFs automatically and help streamline which fractures require a CT.

Retrospectively x-ray images were retrieved from 615 DRF patients who were treated with an ORIF at the Royal Brisbane and Women's Hospital. The images were classified into AO Type A, B or C fractures by three training registrars supervised by a consultant. Deep learning was utilised in a two-stage process: 1) localise and focus the region of interest around the wrist using the YOLOv5 object detection network and 2) classify the fracture using a EfficientNet-B3 network to differentiate intra- and extra-articular fractures.

The distal radius region of interest (ROI) detection stage using the ensemble model of YOLO networks detected all ROIs on the test set with no false positives. The average intersection over union between the YOLO detections and the ROI ground truth was Error! Digit expected.. The DRF classification stage using the EfficientNet-B3 ensemble achieved an area under the receiver operating characteristic curve of 0.82 for differentiating intra-articular fractures.

The proposed DRF classification framework using ensemble models of YOLO and EfficientNet achieved satisfactory performance in intra- and extra-articular fracture classification. This work demonstrates the potential in automatic fracture characterization using deep learning and can serve to streamline decision making for axial imaging helping to reduce unnecessary CT scans.

Summary

Timing for the application and use of fentanyl patches for pre-emptive analgesia and sedation is crucial to obtain good clinical outcomes. Placement and timing is important to maximise clinical effect and apparent levels of analgesia.

In major lower limb amputation, preservation of the knee joint significantly improves outcome. In the severely compromised limb, to preserve the knee joint, high tibial transection may be necessary creating a less than optimal stump. This study reviews the outcome in below knee amputees with stumps 10cm or shorter.

All 209 below knee (BK) amputees attending the New Zealand Artificial Limb Board’s Dunedin Centre were reviewed. The centre is the sole provider of prosthetic services in the southern region. Forty-four amputees (21% of total) had stumps of 10cm or less in length as measured by caliper rule. After a minimum twelve month follow-up these amputees were placed in two groups.

Group 1: Short Stump (10cm to 8cm)

Wood-Stanmore Grades were given for walking ability (Hanspal and Fisher 1991). Rehabilitation was further assessed using a modified Houghton Questionnaire (Houghton et al 1992).

Mean stump length for all 209 BK amputees was 12.5 centimeters (range 5 to 25 centimeters).

Group 1. Short Stump (ten to eight centimeters 0 – 37 amputees

Nineteen amputees – Good to Excellent (Wood – Stanmore Grade V and V1) i.e. walking indoors and outdoors without aids and with near normal gait. (10 trauma, four dysvascular, four tumour, one infection).

Group 2. Ultra Short Stump (7.5cm to 5cm) – seven amputees

Six amputees – Good to Excellent (Grade V or V1) – (all trauma)

Group one mostly had a posterior myocutaneous flap amputation with retention of the proximal fibula. In Group two, all had resection of the proximal fibula with varied flaps often with skin grafting. The patellar tendon was intact but two patients had lost the hamstring insertion with hyperextension of the knee, one requiring prosthesis with side steels and thigh corset. In group two the best results followed high resection of the common peroneal nerve and careful shaping of the tibial remnant. Cortical bone formed at the transection level allowing total contact prosthetic fitting with some end bearing.

BK amputation is described as optimally 12.5 centimeters to 17.5 centimeters below the knee joint (10 to 12.5 centimeters in vascular disease). Saving the knee should always be considered and with combined surgical and prosthetic skill a stump as short as five centimeters may be fitted satisfactorily particularly in the young and following trauma.

Over the 10-year period 1969 to 1978, 271 consecutive cases of congenital dislocation of the hip were diagnosed at birth. Standard anteroposterior radiographs of the pelvis were obtained routinely and were analysed retrospectively. The medial gap, a measure of the separation between the proximal femur and the pelvic wall, was found to be significantly increased in cases with unilateral or bilateral dislocation when compared to normal. A medial greater than five millimetres is indicative of femoral head displacement and is of value where the clinical diagnosis is uncertain. The rate of missed dislocation at birth was 0.6 cases per thousand. Treatment with the Malmo splint was the normal routine. The Pavlik harness was applied if splintage was poorly tolerated by the infant, or in the rare instance of limited hip abduction. Failure to maintain reduction by splintage occurred in 3.3 per cent. The incidence of pressure deformities of the femoral head was 2.95 per cent and there was a residual deformity in later childhood of 1.1 per cent. It is presumed that this lesion can be attributed to the effect of splintage and it was notably avoided in the later period of the review when greater mobility of the abducted hips was encouraged.

The work capacity of 26 women after a Chiari pelvic osteotomy for symptomatic unilateral subluxation of the hip was assessed using two simple exercise tests: the maximal walking speed during a 12-minute test and the time taken to climb stairs. A significant linear decline in walking speed occurred with increasing age, despite the operation, and only one patient over the age of 25 years was able to walk at a normal rate. Compared to the results in a control group of women of similar age the stair climbing time was increased in 54 per cent of the patients and showed a significant negative correlation with the maximal walking speed. Age-adjusted walking speed was closely associated with the degree of pain experienced but there was no relationship between observed function and conventional clinical assessment based on the range of movement and the radiographic appearances of the hip.

In cases of established calcaneus after anterior poliomyelitis the deformity can be greatly reduced by combining an extensive plantar release with an oblique transverse osteotomy of the calcaneus that permits displacement upwards and backwards of the posterior weight-bearing part of the bone. The procedure greatly improves the mechanical advantage of subsequent tendon transplantations to the heel. Between 1956 and 1969 fifteen such osteotomies were carried out and the long-term results have been reviewed.