Human colorectal cancer tissue assessment using optical coherence tomography catheter and deep learning.

Optical coherence tomography (OCT) can differentiate normal colonic mucosa from neoplasia, potentially offering a new mechanism of endoscopic tissue assessment and biopsy targeting, with a high optical resolution and an imaging depth of ~1 mm. Recent advances in convolutional neural networks (CNN) have enabled application in ophthalmology, cardiology, and gastroenterology malignancy detection with high sensitivity and specificity. Here, we describe a miniaturized OCT catheter and a residual neural network (ResNet)-based deep learning model manufactured and trained to perform automatic image processing and real-time diagnosis of the OCT images. The OCT catheter has an outer diameter of 3.8 mm, a lateral resolution of ~7 µm, and an axial resolution of ~6 µm. A customized ResNet is utilized to classify OCT catheter colorectal images. An area under the receiver operating characteristic (ROC) curve (AUC) of 0.975 is achieved to distinguish between normal and cancerous colorectal tissue images.

Outcomes of Gamma Knife surgery for trigeminal neuralgia secondary to vertebrobasilar ectasia.

OBJECT: Vertebrobasilar ectasia (VBE) is an unusual cause of trigeminal neuralgia (TN). The surgical options for patients with medically refractory pain include percutaneous or microsurgical rhizotomy and microvascular decompression (MVD). All such procedures can be technically challenging. This report evaluates the response to a minimally invasive procedure, Gamma Knife surgery (GKS), in patients with TN associated with severe vascular compression caused by VBE. METHODS: Twenty patients underwent GKS for medically refractory TN associated with VBE. The median patient age was 74 years (range 48-95 years). Prior surgical procedures had failed in 11 patients (55%). In 9 patients (45%), GKS was the first procedure they had undergone. The median target dose for GKS was 80 Gy (range 75-85 Gy). The median follow-up was 29 months (range 8-123 months) after GKS. The treatment outcomes were compared with 80 case-matched controls who underwent GKS for TN not associated with VBE. RESULTS: Intraoperative MR imaging or CT scanning revealed VBE that deformed the brainstem in 50% of patients. The trigeminal nerve was displaced in cephalad or lateral planes in 60%. In 4 patients (20%), the authors could identify only the distal cisternal component of the trigeminal nerve as it entered into the Meckel cave. After GKS, 15 patients (75%) achieved initial pain relief that was adequate or better, with or without medication (Barrow Neurological Institute [BNI] pain scale, Grades I-IIIb). The median time until pain relief was 5 weeks (range 1 day-6 months). Twelve patients (60%) with initial pain relief reported recurrent pain between 3 and 43 months after GKS (median 12 months). Pain relief was maintained in 53% at 1 year, 38% at 2 years, and 10% at 5 years. Some degree of facial sensory dysfunction occurred in 10% of patients. Eventually, 14 (70%) of the 20 patients underwent an additional surgical procedure including repeat GKS, percutaneous procedure, or MVD at a median of 14 months (range 5-50 months) after the initial GKS. At the last follow-up, 15 patients (75%) had satisfactory pain control (BNI Grades I-IIIb), but 5 patients (25%) continued to have unsatisfactory pain control (BNI Grade IV or V). Compared with patients without VBE, patients with VBE were much less likely to have initial (p = 0.025) or lasting (p = 0.006) pain relief. CONCLUSIONS: Pain control rates of GKS in patients with TN associated with VBE were inferior to those of patients without VBE. Multimodality surgical or medical management strategies were required in most patients with VBE.