Reinforcement learning-based anatomical maps for pancreas subregion and duct segmentation.

BACKGROUND: The pancreas is a complex abdominal organ with many anatomical variations, and therefore automated pancreas segmentation from medical images is a challenging application. PURPOSE: In this paper, we present a framework for segmenting individual pancreatic subregions and the pancreatic duct from three-dimensional (3D) computed tomography (CT) images. METHODS: A multiagent reinforcement learning (RL) network was used to detect landmarks of the head, neck, body, and tail of the pancreas, and landmarks along the pancreatic duct in a selected target CT image. Using the landmark detection results, an atlas of pancreases was nonrigidly registered to the target image, resulting in anatomical probability maps for the pancreatic subregions and duct. The probability maps were augmented with multilabel 3D U-Net architectures to obtain the final segmentation results. RESULTS: To evaluate the performance of our proposed framework, we computed the Dice similarity coefficient (DSC) between the predicted and ground truth manual segmentations on a database of 82 CT images with manually segmented pancreatic subregions and 37 CT images with manually segmented pancreatic ducts. For the four pancreatic subregions, the mean DSC improved from 0.38, 0.44, and 0.39 with standard 3D U-Net, Attention U-Net, and shifted windowing (Swin) U-Net architectures, to 0.51, 0.47, and 0.49, respectively, when utilizing the proposed RL-based framework. For the pancreatic duct, the RL-based framework achieved a mean DSC of 0.70, significantly outperforming the standard approaches and existing methods on different datasets. CONCLUSIONS: The resulting accuracy of the proposed RL-based segmentation framework demonstrates an improvement against segmentation with standard U-Net architectures.

Delayed dorsal scapular artery hematoma following blunt thoracic trauma: a case report and review of the literature.

BACKGROUND: The present case contributes to the limited literature on delayed chest wall hematomas following blunt trauma. The literature review provides a summary of similar previously reported cases. CASE PRESENTATION: We report the case of a 59-year-old Caucasian male who presented to the emergency department with a rapidly expanding chest wall hematoma. Six weeks earlier, he had sustained multiple rib fractures and a pneumothorax after falling 4 m from a ladder. Computed tomography angiography was used to identify two sources of active bleeding on the left dorsal scapular artery. The patient underwent surgery with evacuation of the hematoma and ligation of the artery. The patient was hospitalized for 3 days and recovered with no sequelae. CONCLUSIONS: A literature review revealed eight previously reported cases of chest wall hematomas exterior to the endothoracic fascia following blunt trauma. Most cases were initially diagnosed by computed tomography of the chest and finally by angiogram. Management options range from surgical drainage to angiographic embolization. This case is unusual regarding the delay in the development of the hematoma and illustrates the importance of considering this diagnosis even weeks after relevant trauma.