Artificial Intelligence for Detecting Acute Fractures in Patients Admitted to an Emergency Department: Real-Life Performance of Three Commercial Algorithms.

RATIONALE AND OBJECTIVES: Interpreting radiographs in emergency settings is stressful and a burden for radiologists. The main objective was to assess the performance of three commercially available artificial intelligence (AI) algorithms for detecting acute peripheral fractures on radiographs in daily emergency practice. MATERIALS AND METHODS: Radiographs were collected from consecutive patients admitted for skeletal trauma at our emergency department over a period of 2 months. Three AI algorithms-SmartUrgence, Rayvolve, and BoneView-were used to analyze 13 body regions. Four musculoskeletal radiologists determined the ground truth from radiographs. The diagnostic performance of the three AI algorithms was calculated at the level of the radiography set. Accuracies, sensitivities, and specificities for each algorithm and two-by-two comparisons between algorithms were obtained. Analyses were performed for the whole population and for subgroups of interest (sex, age, body region). RESULTS: A total of 1210 patients were included (mean age 41.3 ± 18.5 years; 742 [61.3%] men), corresponding to 1500 radiography sets. The fracture prevalence among the radiography sets was 23.7% (356/1500). Accuracy was 90.1%, 71.0%, and 88.8% for SmartUrgence, Rayvolve, and BoneView, respectively; sensitivity 90.2%, 92.6%, and 91.3%, with specificity 92.5%, 70.4%, and 90.5%. Accuracy and specificity were significantly higher for SmartUrgence and BoneView than Rayvolve for the whole population (P < .0001) and for subgroups. The three algorithms did not differ in sensitivity (P = .27). For SmartUrgence, subgroups did not significantly differ in accuracy, specificity, or sensitivity. For Rayvolve, accuracy and specificity were significantly higher with age 27-36 than ≥53 years (P = .0029 and P = .0019). Specificity was higher for the subgroup knee than foot (P = .0149). For BoneView, accuracy was significantly higher for the subgroups knee than foot (P = .0006) and knee than wrist/hand (P = .0228). Specificity was significantly higher for the subgroups knee than foot (P = .0003) and ankle than foot (P = .0195). CONCLUSION: The performance of AI detection of acute peripheral fractures in daily radiological practice in an emergency department was good to high and was related to the AI algorithm, patient age, and body region examined.

Application of artificial intelligence to imaging interpretations in the musculoskeletal area: Where are we? Where are we going?

The interest of researchers, clinicians and radiologists, in artificial intelligence (AI) continues to grow. Deep learning is a subset of machine learning, in which the computer algorithm itself can determine the optimal imaging features to answer a clinical question. Convolutional neural networks are the most common architecture for performing deep learning on medical images. The various musculoskeletal applications of deep learning are the detection of abnormalities on X-rays or cross-sectional images (CT, MRI), for example the detection of fractures, meniscal tears, anterior cruciate ligament tears, degenerative lesions of the spine, bone metastases, classification of e.g., dural sac stenosis, degeneration of intervertebral discs, assessment of skeletal age, and segmentation, for example of cartilage. Software developments are already impacting the daily practice of orthopedic imaging by automatically detecting fractures on radiographs. Improving image acquisition protocols, improving the quality of low-dose CT images, reducing acquisition times in MRI, or improving MR image resolution is possible through deep learning. Deep learning offers an automated way to offload time-consuming manual processes and improve practitioner performance. This article reviews the current state of AI in musculoskeletal imaging.

Correction to: A rare presentation of skull-base osteomyelitis with neurovascular sheath extension following external otitis resolved by PET/MRI.

The figure in the original published version of this article was omitted.

Oncologic outcomes after laparoscopic partial nephrectomy: mid-term results.

INTRODUCTION: To describe the oncologic outcomes of renal cell carcinoma (RCC) diagnosed in patients and submitted to laparoscopic partial nephrectomy (LPN) in a laparoscopic referral center. PATIENTS AND METHODS: We retrospectively analyzed data of 150 consecutive patients with small renal masses and treated with LPN between 2000 and 2010 at a laparoscopic referral center. Pathologic RCC was diagnosed in 137 patients and were included in the oncologic outcome analysis. Kaplan-Meyer methods were used to estimate the probability of disease recurrence and cancer-specific survival. RESULTS: Median follow-up for patients without recurrence was 38 months (interquartile range [IQR] 19-70). The majority of the patients (88%) were found to have pT1a disease at the final pathology report; eight patients (6%) were classified as pT3a. The median tumor size was 25 mm (IQR 20-32). Clear cell type histology was found in 97 patients (66%); most of the patients had Fuhrman grade 2 (72%) or 3 (21%). The 2- and 5-year recurrence-free survival rates were 98% and 95%, respectively. The positive surgical margin was found in 1.4% of the patients. The 2-year and 5-year CSS rates were 99% and 97%, respectively. Kaplan-Meyer methods showed that patients with pT3a were more likely to experience disease recurrence and patients with Fuhrman grade 3 to die of the disease. CONCLUSIONS: LPN seems to provide excellent cancer control rates and to be an oncologically feasible and safe option for treating patients with small renal masses. Recurrence and death from the disease are extremely uncommon and mostly related to a higher pathologic stage or Fuhrman grade, but not positive surgical margins.

Radical prostatectomy: evolution of surgical technique from the laparoscopic point of view.

PURPOSE: To review the literature and present a current picture of the evolution in radical prostatectomy from the laparoscopic point of view. MATERIALS AND METHODS: We conducted an extensive Medline literature search. Articles obtained regarding laparoscopic radical prostatectomy (LRP) and our experience at Institut Montsouris were used for reassessing anatomical and technical issues in radical prostatectomy. RESULTS: LRP nuances were reassessed by surgical teams in order to verify possible weaknesses in their performance. Our basic approach was to carefully study the anatomy and pioneer open surgery descriptions in order to standardized and master a technique. The learning curve is presented in terms of an objective evaluation of outcomes for cancer control and functional results. In terms of technique-outcomes, there are several key elements in radical prostatectomy, such as dorsal vein control-apex exposure and nerve sparing with particular implications in oncological and functional results. Major variations among the surgical teams' performance and follow-up prevented objective comparisons in radical prostatectomy. The remarkable evolution of LRP needs to be supported by comprehensive results. CONCLUSIONS: Radical prostatectomy is a complex surgical operation with difficult objectives. Surgical technique should be standardized in order to allow an adequate and reliable performance in all settings, keeping in mind that cancer control remains the primary objective. Reassessing anatomy and a return to basics in surgical technique is the means to improve outcomes and overcome the difficult task of the learning curve, especially in minimally access urological surgery.

Radical prostatectomy: evolution of surgical technique from the laparoscopic point of view: [review]

PURPOSE: To review the literature and present a current picture of the evolution in radical prostatectomy from the laparoscopic point of view. MATERIALS AND METHODS: We conducted an extensive Medline literature search. Articles obtained regarding laparoscopic radical prostatectomy (LRP) and our experience at Institut Montsouris were used for reassessing anatomical and technical issues in radical prostatectomy. RESULTS: LRP nuances were reassessed by surgical teams in order to verify possible weaknesses in their performance. Our basic approach was to carefully study the anatomy and pioneer open surgery descriptions in order to standardized and master a technique. The learning curve is presented in terms of an objective evaluation of outcomes for cancer control and functional results. In terms of technique-outcomes, there are several key elements in radical prostatectomy, such as dorsal vein control-apex exposure and nerve sparing with particular implications in oncological and functional results. Major variations among the surgical teams' performance and follow-up prevented objective comparisons in radical prostatectomy. The remarkable evolution of LRP needs to be supported by comprehensive results. CONCLUSIONS: Radical prostatectomy is a complex surgical operation with difficult objectives. Surgical technique should be standardized in order to allow an adequate and reliable performance in all settings, keeping in mind that cancer control remains the primary objective. Reassessing anatomy and a return to basics in surgical technique is the means to improve outcomes and overcome the difficult task of the learning curve, especially in minimally access urological surgery.

A transition to laparoendoscopic single-site surgery (LESS) radical prostatectomy: human cadaver experimental and initial clinical experience.

BACKGROUND AND PURPOSE: Laparoendoscopic single-site surgery (LESS) represents a novel approach to abdominal surgery. Several applications have already been described. Drawbacks include limited range of motion and need for articulated instruments. Robotic technology could overcome such technical difficulties. We report our experience with LESS radical prostatectomy (LESS-RP) in a cadaver and LESS robot-assisted radical prostatectomy (LESS-RARP) in a human patient. MATERIAL AND METHODS: Standard laparoscopic instruments (SLI) and articulated laparoscopic instruments were used in the cadaveric LESS-RP. The da Vinci system was used in the LESS-RARP. Both procedures reproduced standard extraperitoneal laparoscopic prostatectomy as performed at Institut Montsouris. Control of the dorsal venous complex (DVC) and urethrovesical anastomosis (UVA) were key elements evaluated for feasibility. RESULTS: Cadaveric model: Total operative time (TOT) was 160 minutes, with 5 minutes for the DVC (one stitch) and 35 minutes for the UVA (six stitches). Although articulated instruments were helpful in the operation, SLI remained essential for the procedure. Clinical experience: LESS-RARP was performed for T(1c) prostate cancer. TOT was 150 minutes, including 5 minutes for the DVC (one figure-of-eight stitch) and 30 minutes for the UVA (six interrupted stitches). Blood loss was 500 mL. Bilateral neurovascular preservation was performed, and results of final pathologic examination showed negative surgical margins. CONCLUSIONS: The human cadaver is an adequate model for LESS-RP, and LESS-RARP is feasible to be performed in the clinical arena. The synergy of robotic technology and LESS represents a new generation of surgery.

Cirugía y tratamiento sistémico en cáncer de vejiga invasor / Surgery and systemic treatment for invasive bladder cancer

El tratamiento del cáncer vesical de células transicionales con invasión muscular sigue siendo difícil, debido a los múltiples patrones de comportamiento biológico que muestra esta enfermedad. Existe controversia en cuanto a la aplicación de tratamiento sistémico en cáncer invasor vesical y el tiempo ideal de indicación de la quimioterapia perioperatoria. Se presenta una visión general de la terapia sistémica en cáncer invasor vesical.

Defining adequate therapy in every patient with invasive transitional cell carcinoma remains difficult, because multiple biologic behavior patterns can be found in this disease. There is controversy regarding the use of systemic treatment in invasive bladder carcinoma and the momentum for chemotherapy deployment. We present an overview of current trends for systemic treatment in bladder carcinoma.