Artificial intelligence (AI) is, in essence, the concept of ‘computer thinking’, encompassing methods that train computers to perform and learn from executing certain tasks, called machine learning, and methods to build intricate computer models that both learn and adapt, called complex neural networks. Computer vision is a function of AI by which machine learning and complex neural networks can be applied to enable computers to capture, analyze, and interpret information from clinical images and visual inputs. This annotation summarizes key considerations and future perspectives concerning computer vision, questioning the need for this technology (the ‘why’), the current applications (the ‘what’), and the approach to unlocking its full potential (the ‘how’). Cite this article:
The aims of this study were to compare clinically relevant measurements of hip dysplasia on radiographs taken in the supine and standing position, and to compare Hip2Norm software and Picture Archiving and Communication System (PACS)-derived digital radiological measurements. Preoperative supine and standing radiographs of 36 consecutive patients (43 hips) who underwent periacetabular osteotomy surgery were retrospectively analyzed from a single-centre, two-surgeon cohort. Anterior coverage (AC), posterior coverage (PC), lateral centre-edge angle (LCEA), acetabular inclination (AI), sharp angle (SA), pelvic tilt (PT), retroversion index (RI), femoroepiphyseal acetabular roof (FEAR) index, femoroepiphyseal horizontal angle (FEHA), leg length discrepancy (LLD), and pelvic obliquity (PO) were analyzed using both Hip2Norm software and PACS-derived measurements where applicable.Aims
Methods
The number of convolutional neural networks (CNN) available for fracture detection and classification is rapidly increasing. External validation of a CNN on a temporally separate (separated by time) or geographically separate (separated by location) dataset is crucial to assess generalizability of the CNN before application to clinical practice in other institutions. We aimed to answer the following questions: are current CNNs for fracture recognition externally valid?; which methods are applied for external validation (EV)?; and, what are reported performances of the EV sets compared to the internal validation (IV) sets of these CNNs? The PubMed and Embase databases were systematically searched from January 2010 to October 2020 according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. The type of EV, characteristics of the external dataset, and diagnostic performance characteristics on the IV and EV datasets were collected and compared. Quality assessment was conducted using a seven-item checklist based on a modified Methodologic Index for NOn-Randomized Studies instrument (MINORS).Aims
Methods
The Intraosseous Transcutaneous Amputation Prosthesis (ITAP)
may improve quality of life for amputees by avoiding soft-tissue
complications associated with socket prostheses and by improving
sensory feedback and function. It relies on the formation of a seal
between the soft tissues and the implant and currently has a flange
with drilled holes to promote dermal attachment. Despite this, infection
remains a significant risk. This study explored alternative strategies
to enhance soft-tissue integration. The effect of ITAP pins with a fully porous titanium alloy flange
with interconnected pores on soft-tissue integration was investigated.
The flanges were coated with fibronectin-functionalised hydroxyapatite
and silver coatings, which have been shown to have an antibacterial
effect, while also promoting viable fibroblast growth Aims
Materials and Methods
Massive endoprostheses rely on extra-cortical bone bridging (ECBB)
to enhance fixation. The aim of this study was to investigate the
role of selective laser sintered (SLS) porous collars in augmenting
the osseointegration of these prostheses. The two novel designs of porous SLS collars, one with small pores
(Ø700 μm, SP) and one with large pores (Ø1500 μm, LP), were compared
in an ovine tibial diaphyseal model. Osseointegration of these collars
was compared with that of a clinically used solid, grooved design
(G). At six months post-operatively, the ovine tibias were retrieved and
underwent radiological and histological analysis.Aims
Materials and Methods
It has been suggested that cemented fixation of total hip arthroplasty
(THA) is associated with an increased peri-operative mortality compared
with cementless THA. Our aim was to investigate this through a nationwide
matched cohort study adjusting for age, comorbidity, and socioeconomic
background. A total of 178 784 patients with osteoarthritis who underwent
either cemented or cementless THA from the Swedish Hip Arthroplasty
Register were matched with 862 294 controls from the general population.
Information about the causes of death, comorbidities, and socioeconomic
background was obtained. Mortality within the first 90 days after
the operation was the primary outcome measure.Aims
Patients and Methods
While an increasing amount of arthroplasty articles
report comorbidity measures, none have been validated for outcomes.
In this study, we compared commonly used International Classification
of Diseases-based comorbidity measures with re-operation rates after
total hip replacement (THR). Scores used included the Charlson,
the Royal College of Surgeons Charlson, and the Elixhauser comorbidity
score. We identified a nationwide cohort of 134 423 THRs from the
Swedish Hip Arthroplasty Register. Re-operations were registered
post-operatively for up to 12 years. The hazard ratio was estimated
by Cox’s proportional hazards regression, and we used C-statistics
to assess each measure’s ability to predict re-operation. Confounding
variables were age, gender, type of implant fixation, hospital category,
hospital implant volume and year of surgery. In the first two years only the Elixhauser score showed any significant
relationship with increased risk of re-operation, with increased
scores for both one to two and three or more comorbidities. However,
the predictive C-statistic in this period for the Elixhauser score
was poor (0.52). None of the measures proved to be of any value between
two and 12 years. They might be of value in large cohort or registry
studies, but not for the individual patient. Cite this article:
We reviewed the records of 107 consecutive patients who had undergone surgery for disruption of the knee extensor mechanism to test whether an association existed between rupture of the quadriceps tendon and the presence of a patellar spur. The available standard pre-operative lateral radiographs were examined to see if a patellar spur was an indicator for rupture of the quadriceps tendon in this group of patients. Of the 107 patients, 12 underwent repair of a ruptured patellar tendon, 59 had an open reduction and internal fixation of a patellar fracture and 36 repair of a ruptured quadriceps tendon. In the 88 available lateral radiographs, patellar spurs were present significantly more commonly (p <
0.0005) in patients operated on for rupture of the quadriceps tendon (79%) than in patients with rupture of the patellar tendon (27%) or fracture of the patella (15%). In patients presenting with failure of the extensor mechanism of the knee in the presence of a patellar spur, rupture of the quadriceps tendon should be considered as a possible diagnosis.
