Automatic Detection and Segmentation of Thrombi in Abdominal Aortic Aneurysms Using a Mask Region-Based Convolutional Neural Network with Optimized Loss Functions.

The detection and segmentation of thrombi are essential for monitoring the disease progression of abdominal aortic aneurysms (AAAs) and for patient care and management. As they have inherent capabilities to learn complex features, deep convolutional neural networks (CNNs) have been recently introduced to improve thrombus detection and segmentation. However, investigations into the use of CNN methods is in the early stages and most of the existing methods are heavily concerned with the segmentation of thrombi, which only works after they have been detected. In this work, we propose a fully automated method for the whole process of the detection and segmentation of thrombi, which is based on a well-established mask region-based convolutional neural network (Mask R-CNN) framework that we improve with optimized loss functions. The combined use of complete intersection over union (CIoU) and smooth L1 loss was designed for accurate thrombus detection and then thrombus segmentation was improved with a modified focal loss. We evaluated our method against 60 clinically approved patient studies (i.e., computed tomography angiography (CTA) image volume data) by conducting 4-fold cross-validation. The results of comparisons to multiple other state-of-the-art methods suggested the superior performance of our method, which achieved the highest F1 score for thrombus detection (0.9197) and outperformed most metrics for thrombus segmentation.

Abdominal Aortic Thrombus Segmentation in Postoperative Computed Tomography Angiography Images Using Bi-Directional Convolutional Long Short-Term Memory Architecture.

Abdominal aortic aneurysm (AAA) is a fatal clinical condition with high mortality. Computed tomography angiography (CTA) imaging is the preferred minimally invasive modality for the long-term postoperative observation of AAA. Accurate segmentation of the thrombus region of interest (ROI) in a postoperative CTA image volume is essential for quantitative assessment and rapid clinical decision making by clinicians. Few investigators have proposed the adoption of convolutional neural networks (CNN). Although these methods demonstrated the potential of CNN architectures by automating the thrombus ROI segmentation, the segmentation performance can be further improved. The existing methods performed the segmentation process independently per 2D image and were incapable of using adjacent images, which could be useful for the robust segmentation of thrombus ROIs. In this work, we propose a thrombus ROI segmentation method to utilize not only the spatial features of a target image, but also the volumetric coherence available from adjacent images. We newly adopted a recurrent neural network, bi-directional convolutional long short-term memory (Bi-CLSTM) architecture, which can learn coherence between a sequence of data. This coherence learning capability can be useful for challenging situations, for example, when the target image exhibits inherent postoperative artifacts and noises, the inclusion of adjacent images would facilitate learning more robust features for thrombus ROI segmentation. We demonstrate the segmentation capability of our Bi-CLSTM-based method with a comparison of the existing 2D-based thrombus ROI segmentation counterpart as well as other established 2D- and 3D-based alternatives. Our comparison is based on a large-scale clinical dataset of 60 patient studies (i.e., 60 CTA image volumes). The results suggest the superior segmentation performance of our Bi-CLSTM-based method by achieving the highest scores of the evaluation metrics, e.g., our Bi-CLSTM results were 0.0331 higher on total overlap and 0.0331 lower on false negative when compared to 2D U-net++ as the second-best.

Clinical Case of a Transfusion-Associated Canine Mycoplasma haemocanis Infection in the Republic of Korea: A Case Report.

This report describes the first clinical case of a transfusion-associated Mycoplasma haemocanis infection in a dog in Korea. A 6-year-old male Maltese underwent a red blood cell transfusion for idiopathic immune-mediated hemolytic anemia. Eighteen days after the blood transfusion, the recipient's packed cell volume decreased and basophilic organisms were found on erythrocytes. A polymerase chain reaction and sequential analysis showed that both the donor dog and recipient dog had M. haemocanis. Six weeks after doxycycline administration, no organisms were detected and the recipient's anemia had improved.

Cell-Free DNA as a Diagnostic and Prognostic Biomarker in Dogs With Tumors.

Cell-free DNA (cfDNA) is derived from apoptosis/necrosis, active cellular secretion, and lysis of circulating cancer cells or micrometastases. In humans, cfDNA is widely used in cancer diagnosis, but veterinary research has yet to be actively conducted to establish it as a cancer biomarker. This retrospective study analyzed cfDNA levels in samples collected from dogs with neoplastic disease (n = 38), clinically ill dogs without neoplasia (n = 47), and healthy dogs (n = 35). cfDNA levels and clinical data were compared among groups, and prognostic analyses were performed within the neoplastic group. Furthermore, continual cfDNA measurements were performed during the chemotherapy of six dogs with lymphoma. Dogs with neoplasia showed significantly higher cfDNA concentrations than dogs without neoplasm, and the cfDNA oncentration in the lymphoid neoplasia group was significantly elevated among all neoplastic groups. Dogs with neoplasia and a plasma cfDNA concentration above 1,247.5 µg/L had shorter survival rates than those with levels below this threshold (26.5 vs. 86.1%, respectively, P < 0.05). In cases with complete remission in response to chemotherapy, the cfDNA concentration was significantly decreased compared with the first visit, whereas the cfDNA concentration was increased in cases with disease progression or death. Interestingly, a significant correlation was found between lymph node diameter and cfDNA concentration in dogs with multicentric lymphoma (R 2 = 0.26, P < 0.01). These data suggest that changes in cfDNA concentration could be used as a diagnostic biomarker for canine neoplasia. Furthermore, increased plasma DNA levels might be associated with shorter survival time, and cfDNA concentrations may reflect the response to chemotherapy.

Comparison of clinical and inflammatory parameters in dogs with pyometra before and after ovariohysterectomy.

This study aimed to identify potential biomarkers of canine pyometra and their correlations with clinical parameters. First, 90 dogs with pyometra and 26 healthy female dogs were compared. Then, paired samples (before and after ovariohysterectomy) from 22 dogs with pyometra and 9 healthy controls from the initial cohort were compared. Concentrations of acute inflammatory proteins, C-reactive protein (CRP) and serum amyloid A (SAA), and cell-free DNA (cfDNA), were significantly higher in dogs with pyometra than in clinically healthy dogs. Cell-free DNA was the most sensitive biomarker for systemic inflammation, based on the receiver operating characteristic curve analysis (area under the curve = 0.959). In addition, cfDNA and CRP were significantly associated with inflammation and organ injury-related clinical parameters. Following the surgical removal of the inflamed uterus, interleukin-6 (IL-6), high-mobility group box 1 (HMGB1), and procalcitonin (PCT) significantly decreased, whereas changes in CRP, SAA, and cfDNA were not significant. These findings indicate that cfDNA, CRP, and SAA are potential clinical biomarkers of systemic inflammation in dogs with pyometra and PCT, IL-6, and HMGB1 are potential biomarkers of clinical recovery.

Cette étude visait à identifier les biomarqueurs potentiels du pyomètre canin et leurs corrélations avec les paramètres cliniques. Tout d'abord, 90 chiens avec pyomètre et 26 chiennes en bonne santé ont été comparés. Ensuite, des échantillons appariés (avant et après ovariohystérectomie) de 22 chiens avec pyomètre et neuf témoins sains de la cohorte initiale, ont été comparés.Les concentrations des protéines inflammatoires aiguës, protéine C réactive (CRP) et amyloïde sérique A (SAA), et d'ADN acellulaire (cfDNA), étaient significativement plus élevées chez les chiens atteints de pyomètre que chez les chiens cliniquement sains. L'ADN acellulaire était le biomarqueur le plus sensible pour l'inflammation systémique, sur la base de l'analyse de la courbe caractéristique de fonctionnement du récepteur (aire sous la courbe = 0,959). De plus, le cfDNA et la CRP étaient significativement associés à l'inflammation et aux paramètres cliniques liés aux lésions aux organes.Après l'ablation chirurgicale de l'utérus enflammé, l'interleukine-6 (IL-6), la protéine HMGB1 (« high-mobility groupe box 1 ¼) et la procalcitonine (PCT) ont significativement diminué, alors que les changements de CRP, SAA et cfDNA n'étaient pas significatifs. Ces résultats indiquent que cfDNA, CRP et SAA sont des biomarqueurs cliniques potentiels de l'inflammation systémique chez les chiens avec pyomètre et PCT, IL-6 et HMGB1 sont des biomarqueurs potentiels de récupération clinique.(Traduit par Docteur Serge Messier).

Idiopathic ulcerative dermatitis in a cat with feline infectious peritonitis.

A 1-year-old, castrated, male, domestic short-haired cat with pruritic, multifocal, crusted ulceration of the skin over the dorsal aspect of the neck and scapulae was presented. The cat also had a history of depression and anorexia. A causative agent for the lesion was not identified on a general dermatological examination. Histopathology revealed diffuse epidermal ulceration and loss with replacement by neutrophilic inflammation and necrotic debris. Idiopathic ulcerative dermatitis (IUD) was diagnosed based on history, physical examination and histopathology. To prevent self-trauma and secondary bacterial infection, light bandages and glucocorticoid ointment were applied. After a month of management, the lesions markedly improved. Approximately 3 months after the initial presentation, the cat died; necropsy confirmed an IUD and non-effusive (dry form) feline infectious peritonitis (FIP). This report describes a rare case of IUD in a cat with concurrent FIP. However, no association between IUD and FIP was found.