Rapid, automated nerve histomorphometry through open-source artificial intelligence.

We aimed to develop and validate a deep learning model for automated segmentation and histomorphometry of myelinated peripheral nerve fibers from light microscopic images. A convolutional neural network integrated in the AxonDeepSeg framework was trained for automated axon/myelin segmentation using a dataset of light-microscopic cross-sectional images of osmium tetroxide-stained rat nerves including various axonal regeneration stages. In a second dataset, accuracy of automated segmentation was determined against manual axon/myelin labels. Automated morphometry results, including axon diameter, myelin sheath thickness and g-ratio were compared against manual straight-line measurements and morphometrics extracted from manual labels with AxonDeepSeg as a reference standard. The neural network achieved high pixel-wise accuracy for nerve fiber segmentations with a mean (± standard deviation) ground truth overlap of 0.93 (± 0.03) for axons and 0.99 (± 0.01) for myelin sheaths, respectively. Nerve fibers were identified with a sensitivity of 0.99 and a precision of 0.97. For each nerve fiber, the myelin thickness, axon diameter, g-ratio, solidity, eccentricity, orientation, and individual x -and y-coordinates were determined automatically. Compared to manual morphometry, automated histomorphometry showed superior agreement with the reference standard while reducing the analysis time to below 2.5% of the time needed for manual morphometry. This open-source convolutional neural network provides rapid and accurate morphometry of entire peripheral nerve cross-sections. Given its easy applicability, it could contribute to significant time savings in biomedical research while extracting unprecedented amounts of objective morphologic information from large image datasets.

Clue to the diagnosis on chest X-ray in a child with neck swelling.

Differentiated thyroid cancer is a rare disease in children and adolescents and manifests exclusively in the form of papillary thyroid cancer (PTC). We present a rare case of PTC who presented initially with lung symptoms and miliary nodules on chest X-ray. This case emphasises the important differential of miliary mottling of the lungs.

Type I regressed pleuropulmonary blastoma in a 10-year-old boy.

Pleuropulmonary blastoma (PPB) is a rare, malignant tumor of the lung and is the most common primary pulmonary malignancy in children. Here, we report a case of a boy who was diagnosed with type I regressed PPB after being mislabeled with congenital pulmonary malformation. A 10-year-old boy presented to our hospital with a history of worsening dyspnea. Since birth, his clinical status and radiographic images were concerning for congenital lobar emphysema that was managed conservatively. A chest computed tomography (CT) scan confirmed the persistence of a large cystic lesion and a diagnostic and therapeutic cystectomy was performed. Microscopic examination confirmed the presence of PPB type Ir. Patient was managed surgically alone with no added chemotherapy, as there was no overall survival benefit. PPB Ir has an overall favorable clinical outcome. Limited follow-up data are available due to the rarity of the lesion and the overlap with other congenital cystic lung malformations.

Uncommon metastasis of laryngeal cancer to small bowel causing intestinal obstruction treated by laparoscopic approach.

Metastatic laryngeal cancer to the small bowel is extremely rare. Management of small bowel obstruction used to constitute a relative contraindication for the use of laparoscopic modality. We are reporting a case of an elderly man known to have laryngeal cancer who presented with small bowel obstruction due to metastatic deposit to the small bowel. The condition was successfully treated by laparoscopic assisted approach. A review of the natural history of advanced laryngeal cancer, common and uncommon sites of metastasis, and the rare presentation as small bowel obstruction is illustrated in this review.