Differential Diagnosis of Diabetic Foot Osteomyelitis and Charcot Neuropathic Osteoarthropathy with Deep Learning Methods

Our study aims to evaluate the potential of a deep learning (DL) algorithm for differentiating the signal intensity of bone marrow between osteomyelitis (OM), Charcot neuropathic osteoarthropathy (CNO), and trauma (TR). The local ethics committee approved this retrospective study. From 148 patients, segmentation resulted in 679 labeled regions for T1-weighted images (comprising 151 CNO, 257 OM, and 271 TR) and 714 labeled regions for T2-weighted images (consisting of 160 CNO, 272 OM, and 282 TR). We employed both multi-class classification (MCC) and binary-class classification (BCC) approaches to compare the classification outcomes of CNO, TR, and OM. The ResNet-50 and the EfficientNet-b0 accuracy values were computed at 96.2% and 97.1%, respectively, for T1-weighted images. Additionally, accuracy values for ResNet-50 and the EfficientNet-b0 were determined at 95.6% and 96.8%, respectively, for T2-weighted images. Also, according to BCC for CNO, OM, and TR, the sensitivity of ResNet-50 is 91.1%, 92.4%, and 96.6% and the sensitivity of EfficientNet-b0 is 93.2%, 97.6%, and 98.1% for T1, respectively. For CNO, OM, and TR, the sensitivity of ResNet-50 is 94.9%, 83.6%, and 97.9% and the sensitivity of EfficientNet-b0 is 95.6%, 85.2%, and 98.6% for T2, respectively. The specificity values of ResNet-50 for CNO, OM, and TR in T1-weighted images are 98.1%, 97.9%, and 94.7% and 98.6%, 97.5%, and 96.7% in T2-weighted images respectively. Similarly, for EfficientNet-b0, the specificity values are 98.9%, 98.7%, and 98.4% and 99.1%, 98.5%, and 98.7% for T1-weighted and T2-weighted images respectively. In the diabetic foot, deep learning methods serve as a non-invasive tool to differentiate CNO, OM, and TR with high accuracy.

Histopathological assessment of a two-stage reconstructive procedure of the infected Charcot foot

INTRODUCTION

Charcot neuropathic osteoarthropathy (CN) can be complicated by osteomyelitis (OM). Surgery is a standard procedure to treat OM including debridement and interposition of antibiotic-loaded cement (ABLC) spacer. The course of CN and OM was investigated on a histopathological level.

MATERIALS AND METHODS

Diabetic patients (n = 15) suffering from CN and midfoot OM underwent surgical debridement and interposition of ABLC was interposed. 6 weeks later, ABLC was removed and bone samples were taken again. Histopathological Charcot Score (HCS), Histopathological Osteomyelitis Evaluation Score (HOES) and microbiological assessment were used to evaluate osteomyelitic and neuroosteoarthropathic activity at both time points.

RESULTS

Interposition of ABLC leads to microbiological/histopathological eradication of OM in 73%/87% of patients. CN activity-measured by HCS-could be reduced from moderate to low activity by ABLC spacer and correlated with HOES.

CONCLUSIONS

CN activity could be reduced by surgery. It can be suggested that neuroosteoarthropathic activity measured by HCS is triggered by OM.

Inappropriate antibiotic administration in the setting of Charcot arthropathy: A case series and literature review

AIMS

Differentiating Charcot neuropathic osteoarthropathy (CN) from infection is challenging. The diagnosis of CN is often missed or delayed, resulting in inappropriate and delayed treatment. We hypothesized that the misdiagnosis of CN results in inappropriate antibiotic prescriptions and explore the sequelae of unnecessary antibiotic use.

METHODS

A retrospective review of patient electronic medical records from January 2010 to December 2017 was conducted for those diagnosed with CN after being referred to an orthopaedic foot and ankle specialist.

RESULTS

Our review showed 58 of 103 (56%) patients received antibiotics on the date, or within the next 7 days, of referral to foot and ankle orthopaedic specialist. The antibiotic of choice given on referral were as follows: Sulfamethoxazole/Trimethoprim 18 of 58 (31%), doxycycline 13 of 58 (22%), clindamycin 13 of 58 (22%), cephalexin 9 of 58 (16%), minocycline 5 of 58 (9%).

CONCLUSION

Missed diagnoses for CN are common and result in complications stemming from inappropriate treatment, delays in appropriate therapy, and may accelerate antibiotic resistance. Misdiagnosis of CN contributes to the inappropriate use of prescription antibiotics.

[Histopathological Charcot score on intraoperative tissue samples from the foot : A prospective investigation]

BACKGROUND

Charcot neuropathy is a severe complication in patients with neuropathy. Without treatment, CN can lead to a destruction and collapse of the foot, with subsequent ulceration and infection. Finding an early diagnosis is essential and is based on clinical and radiological parameters (X-ray and MRI) because there is still no specific and reliable test.

GOAL

Defining and validation of a Charcot score with defined histopathologic criteria.

METHOD

Tissue samples from 37 surgeries (Charcot-group n = 20, control-group n = 17) from tarsal bones were taken prospectively. A semiquantitative histopathological score based on four defined criteria of fibrous-osteo-cartilage tissues (maximum 21 points) was defined, the scoring modalities were orientated towards the evaluated HOES score (histopathological osteomyelitis evaluation score) for osteomyelitis. A comparison of the Charcot-group with diabetes mellitus and verified CN as well as neuropathy with the control group with signs of CN or neuropathy was performed.

RESULTS

Significant differences could be shown between the Charcot group and the control group in the score (10.5 vs 3.5 pts, p-value <0.001). There was a high significant correlation between the established tools for diagnostics of CN and the score (p-value <0,001).

CONCLUSION

The histopathological Charcot score can detect a CN with high significance and correlates with high significance to established diagnostic tools for CN. It could represent a simple and cost-effective additive tool to verify CN in uncertain cases.