Deep HT: A deep neural network for diagnose on MR images of tumors of the hand

Clinical characteristics and management experience of schwannoma in extremities: Lessons learned from a 10-year retrospective study

Introduction

Schwannomas are the most common neoplastic lesions of the peripheral nerves when growing on the extremities, they usually have adverse effects on patients due to the exposed and functional nature of the region.

Methods

In the present single-center retrospective study, we included all patients with pathologically confirmed schwannoma located in extremities between 2011 and 2021 totaling 183 patients. Data on gender, age, duration history, clinical presentation, occurrence region, nerve affiliation, imaging data, modus operation, mass volume, immunohistochemistry, postoperative neurological function, and recurrence were collected.

Results

As in previous studies, patients were predominantly middle-aged with a mean age of 49.5, without gender preference and a male-to-female ratio of 1.2:1. Most patients are first seen for this disease, and only five of them are recurrent. The majority presented with an isolated (91.26%), asymptomatic (37.7%) mass, with tenderness (34.97%) being the second frequent complaint. 60% of lesions occurred in the upper extremity, more commonly on the left side (55.26%) than the right. The average duration of onset was 47.50 months. MRI is more sensitive for neurogenic tumors than ultrasound, as it owns 78.93% correct. In immunohistochemistry, the top three markers for positive labeling schwannoma are S-100 (98.95%), Ki67 (98.68%) and β-Catenin. 98.36% of patients underwent complete resection of the lesion, of which 14.44% required partial sacrifice of the nerve fibers. Thanks to the application of intraoperative peripheral nerve microscopic operation, only 6 patients showed symptoms of postoperative nerve injury, and 3 of them received second surgery. Intraoperative microscopic manipulation, preservation of the main nerve, and the need for reconstruction of the affected nerve fibers are some of the points worth noting.

Discussion

In summary, the possibility of schwannoma should not be overlooked in the identification of masses that occur in the upper extremities of the middle-aged population. Preoperative ultrasound and MR are useful for determining the nature of the mass, and S100, Ki67, and β-Catenin are sensitive to it. Surgical resection can achieve satisfying functional results and a low risk of nerve injury.

Deep CTS: a Deep Neural Network for Identification MRI of Carpal Tunnel Syndrome

Carpal tunnel syndrome (CTS) is a common peripheral nerve disease in adults; it can cause pain, numbness, and even muscle atrophy and will adversely affect patients' daily life and work. There are no standard diagnostic criteria that go against the early diagnosis and treatment of patients. MRI as a novel imaging technique can show the patient's condition more objectively, and several characteristics of carpal tunnel syndrome have been found. However, various image sequences, heavy artifacts, small lesion characteristics, high volume of imagine reading, and high difficulty in MRI interpretation limit its application in clinical practice. With the development of automatic image segmentation technology, the algorithm has great potential in medical imaging. The challenge is that the segmentation target is too small, and there are two categories of images with the proximal border of the carpal tunnel as the boundary. To meet the challenge, we propose an end-to-end deep learning framework called Deep CTS to segment the carpal tunnel from the MR image. The Deep CTS consists of the shape classifier with a simple convolutional neural network and the carpal tunnel region segmentation with simplified U-Net. With the specialized structure for the carpal tunnel, Deep CTS can segment the carpal tunnel region efficiently and improve the intersection over union of results. The experimental results demonstrated that the performance of the proposed deep learning framework is better than other segmentation networks for small objects. We trained the model with 333 images, tested it with 82 images, and achieved 0.63 accuracy of intersection over union and 0.17 s segmentation efficiency, which indicate great promise for the clinical application of this algorithm.

A deep learning approach for medical waste classification

As the demand for health grows, the increase in medical waste generation is gradually outstripping the load. In this paper, we propose a deep learning approach for identification and classification of medical waste. Deep learning is currently the most popular technique in image classification, but its need for large amounts of data limits its usage. In this scenario, we propose a deep learning-based classification method, in which ResNeXt is a suitable deep neural network for practical implementation, followed by transfer learning methods to improve classification results. We pay special attention to the problem of medical waste classification, which needs to be solved urgently in the current environmental protection context. We applied the technique to 3480 images and succeeded in correctly identifying 8 kinds of medical waste with an accuracy of 97.2%; the average F1-score of five-fold cross-validation was 97.2%. This study provided a deep learning-based method for automatic detection and classification of 8 kinds of medical waste with high accuracy and average precision. We believe that the power of artificial intelligence could be harnessed in products that would facilitate medical waste classification and could become widely available throughout China.

A solitary giant neurofibroma of inguinal region: A case report

Neurofibroma is a rare nerve sheath tumor of neuroectodermal origin, especially the huge and isolated neurofibroma located in the inguinal region. To our knowledge, no such case has previously been reported. We report a case of 34-year-old male patient with a 4-year history of progressive enlargement of the medial root mass in his left thigh with sitting and standing disorders along with pain. The tumor was completely removed by operation, and pathological diagnosis showed neurofibroma. There was no obvious neurologic defect after surgery, and no recurrence tendency was found in the follow-up of 2 years. For a large solitary mass with slow growth and no malignant clinical manifestations for a long time, clinicians cannot rule out the hypothetical diagnosis of neurofibroma, even though its growth site is very rare, such as this case of a huge tumor located in the groin. For neurogenic tumors, early operation should be performed, and the prognosis of patients after tumor resection is excellent.