ABSTRACT
BACKGROUND: Head and neck cancer is highly prevalent in Taiwan. Its treatment mainly relies on clinical staging, usually diagnosed from images. A major part of the diagnosis is whether lymph nodes are involved in the tumor. We present an algorithm for analyzing clinical images that integrates a deep learning model with image processing and attempt to analyze the features it uses to classify lymph nodes. METHODS: We retrospectively collected pretreatment computed tomography images and surgery pathological reports for 271 patients diagnosed with, and subsequently treated for, naïve oral cavity, oropharynx, hypopharynx, and larynx cancer between 2008 and 2018. We chose a 3D UNet model trained for semantic segmentation, which was evaluated for inference in a test dataset of 29 patients. RESULTS: We annotated 2527 lymph nodes. The detection rate of all lymph nodes was 80%, and Dice score was 0.71. The model has a better detection rate at larger lymph nodes. For those identified lymph nodes, we found a trend where the shorter the short axis, the more negative the lymph nodes. This is consistent with clinical observations. CONCLUSIONS: The model showed a convincible lymph node detection on clinical images. We will evaluate and further improve the model in collaboration with clinical physicians.
ABSTRACT
OBJECTIVE: To investigate the effect of polycaprolactone-ascobic acid (PCL-AA) scaffolds in promoting repair of articular cartilage defects in a rabbit model. METHODS: The cartilage defects (3.5 mm in diameter and 3.0 mm in depth) were created in the trochlear groove of the bilateral knees of eight 6-month-old male New Zealand white rabbits. The rabbit models were then randomized into 3 groups to receive implantation of PCL-AA scaffolds (group A, n=8), implantation of PCL scaffolds without AA (group B, n=5), or no treatment (group C, n=3). In groups A and B, the mixture of fibrin gel (10 µg) and thrombinogen (10 µg) was injected into the defects to fix the scaffolds during the surgery. Histological analyses and quantitative assessments of defect repair were conducted at 6 and 12 weeks after implantation of the scaffold. RESULTS: At 6 weeks after scaffold implantation, macroscopic observation showed better filling of the cartilage defects in group A than in group B, while no obvious defect repair was observed in group C. The rabbits in group A showed a significant improvement of the Wakitani score than those in group B (4.05∓1.11 vs 7.05∓0.98, P<0.05). HE staining revealed the presence of newly generated cells in and around the PCL-AA scaffolds without inflammatory cells. Safranin O staining showed a significantly greater ECM of the newly regenerated tissue in groups A and B than in group C (P<0.05), and the volume of the regenerated cartilage and cells was significantly greater in group A than in group B (P<0.05). Samples harvested at 12 weeks showed more hyalione-like cartilage formation than that at 6 weeks in group A. CONCLUSION: PCL-AA scaffolds have a good biocompatibility and promotes the healing of articular cartilage defects. Adding ascorbic acid into PCL scaffolds better promotes cartilage formation in terms of both quantity and quality of the regenerated tissues. PCL-AA scaffolds can serve as a promising biomaterial to promote the regeneration of articular cartilage using tissue engineering techniques.
