RESUMEN
RATIONALE AND OBJECTIVES: Deep learning can enhance the performance of multimodal image analysis, which is known for its noninvasive attributes and complementary efficacy, in predicting axillary lymph node (ALN) metastasis. Therefore, we established a multimodal deep learning model incorporating ultrasound (US) and magnetic resonance imaging (MRI) images to predict ALN metastasis in patients with breast cancer. MATERIALS AND METHODS: A retrospective cohort of patients with histologically confirmed breast cancer from two hospitals composed of the primary cohort (n = 465) and the external validation cohort (n = 123). All patients had undergone both preoperative US and MRI scans. After data preprocessing, three convolutional neural network models were used to analyze the US and MRI images, respectively. After integrating the US and MRI deep learning prediction results (DLUS and DLMRI, respectively), a multimodal deep learning (DLMRI+US+Clinical parameter) model was constructed. The predictive ability of the proposed model was compared to that of the DLUS, DLMRI, combined bimodal (DLMRI+US), and clinical parameter models. Evaluation was performed using the area under the receiver operating characteristic curves (AUCs) and decision curves. RESULTS: A total of 588 patients with breast cancer participated in this study. The DLMRI+US+Clinical parameter model outperformed the alternative models, achieving the highest AUCs of 0.819 (95% confidence interval [CI] 0.734-0.903) and 0.809 (95% CI 0.723-0.895) on the internal and external validation sets, respectively. The decision curve analysis confirmed its clinical usefulness. CONCLUSION: The DLMRI+USï¼Clinical parameter model demonstrates the feasibility and reliability of its performance for ALN metastasis prediction in patients with breast cancer.
RESUMEN
BACKGROUND: Babesia spp. are protozoan parasites that infect the red blood cells of domesticated animals, wildlife and humans. A few cases of giant pandas (a flagship species in terms of wildlife conservation) infected with a putative novel Babesia sp. have been reported. However, comprehensive research on the morphological and molecular taxonomic classification of this novel Babesia sp. is still lacking. This study was designed to close this gap and formally describe this new Babesia sp. infecting giant pandas. METHODS: Detailed morphological, molecular and phylogenetic analyses were conducted to characterise this Babesia sp. and to assess its systematic relationships with other Babesia spp. Blood samples from giant pandas infected with Babesia were subjected to microscopic examination. The 18S ribosomal RNA (18S rRNA), cytochrome b (cytb) and mitochondrial genome (mitogenome) of the new Babesia sp. were amplified, sequenced and assembled using DNA purified from blood samples taken from infected giant pandas. Based on the newly generated 18S rRNA, cytb and mitogenome sequences, phylogenetic trees were constructed. RESULTS: Morphologically, the Babesia sp. from giant pandas exhibited various forms, including round to oval ring-shaped morphologies, resembling those found in other small canine Babesia spp. and displaying typical tetrads. Phylogenetic analyses with the 18S rRNA, cytb and mitogenome sequences revealed that the new Babesia sp. forms a monophyletic group, with a close phylogenetic relationship with the Babesia spp. that infect bears (Ursidae), raccoons (Procyonidae) and canids (Canidae). Notably, the mitogenome structure consisted of six ribosomal large subunit-coding genes (LSU1-6) and three protein-coding genes (cytb, cox3 and cox1) arranged linearly. CONCLUSIONS: Based on coupled morphological and genetic analyses, we describe a novel species of the genus Babesia, namely, Babesia ailuropodae n. sp., which infects giant pandas.