Enchondroma Detection from Hand Radiographs with an Interactive Deep Learning Segmentation Tool-A Feasibility Study.

Enchondromas are common benign bone tumors, usually presenting in the hand. They can cause symptoms such as swelling and pain but often go un-noticed. If the tumor expands, it can diminish the bone cortices and predispose the bone to fracture. Diagnosis is based on clinical investigation and radiographic imaging. Despite their typical appearance on radiographs, they can primarily be misdiagnosed or go totally unrecognized in the acute trauma setting. Earlier applications of deep learning models to image classification and pattern recognition suggest that this technique may also be utilized in detecting enchondroma in hand radiographs. We trained a deep learning model with 414 enchondroma radiographs to detect enchondroma from hand radiographs. A separate test set of 131 radiographs (47% with an enchondroma) was used to assess the performance of the trained deep learning model. Enchondroma annotation by three clinical experts served as our ground truth in assessing the deep learning model's performance. Our deep learning model detected 56 enchondromas from the 62 enchondroma radiographs. The area under receiver operator curve was 0.95. The F1 score for area statistical overlapping was 69.5%. Our deep learning model may be a useful tool for radiograph screening and raising suspicion of enchondroma.

Factors predicting chronic pain after open mesh based inguinal hernia repair: ​A prospective cohort study.

INTRODUCTION: Chronic postherniorrhaphy pain is the foremost setback of today's inguinal hernia repair. Finding predictors for it affects implants, operative techniques and allows for preventive measures. METHODS: Prospectively collected data from 932 outpatient open inguinal hernia operations between 2003 and 2010 were subjected to regression analysis. Visual analogue scale score (VAS) at least a year after operation and a measurement of chronic pain at one year were the target variables. RESULTS: Chronic pain was present in 99 (11.5%) patients one year after operation. Independent predictors for the occurrence of chronic pain were positively recurrence (Odds ratio, OR 6.77 vs. no recurrence, P = 0.005), complication (OR 5.16 vs. no complication, P = 0.002), mid-density mesh (OR 2.28 vs. lightweight mesh, P = 0.012), higher preoperative VAS score (OR 1.15, P = 0.006) and negatively higher age (OR 0.98, P = 0.027). Predictors for a higher postoperative VAS score were recurrence (regression coefficient, RC, 1.49 vs. no recurrence, P = 0.001), complication (RC 0.76 vs. no complication, P = 0.016), heavyweight mesh (RC 0.50 vs. lightweight mesh, P = 0.046) and higher preoperative VAS level (RC 0.10, P < 0.001). CONCLUSIONS: Recurrence, complication, mesh weight, preoperative VAS score and age are predictors for the occurrence chronic pain after open mesh based inguinal hernia repair. Recurrence, complication, mesh weight and preoperative VAS score are predictors of postherniorrhaphy VAS level.

A prospective randomized clinical trial comparing the Prolene Hernia System® and the Lichtenstein patch technique for inguinal hernia repair in long term: 2- and 5-Year results.

BACKGROUND: Long-term sequelae in open inguinal hernia repair with either a bilayer mesh (Prolene Hernia System [PHS]) or an onlay mesh (Lichtenstein patch) were compared. METHODS: Questionnaires, phone calls, and clinical evaluation were applied as follow-up at 2 and 5 years postoperatively. RESULTS: Five percent of patients in the PHS group and 14% in the Lichtenstein group (P = .022) reported sensory dysfunction of the skin in the operated groin at 5 years. Chronic postoperative pain decreased over time and was reported by 11% of all patients at 5 years. Discomfort in the operated groin was found in 25% of all patients 5 years after the operation. The cumulative recurrence rate at 5 years was .8% for the PHS and 1.7% for the Lichtenstein procedure (P = .620). CONCLUSIONS: The 2 approaches resulted in comparable rates of recurrence and long-term chronic postoperative pain. The Lichtenstein patch caused significantly more often long-term sensory dysfunction of the skin in the operated groin.