Search

Supplementary Material 1

The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection. The subchallenges were based on the SeaDronesSee and MODS benchmarks. This report summarizes the main findings of the individual subchallenges and introduces a new benchmark, called SeaDronesSee Object Detection v2, which extends the previous benchmark by including more classes and footage. We provide statistical and qualitative analyses, and assess trends in the best-performing methodologies of over 130 submissions. The methods are summarized in the appendix. The datasets, evaluation code and the leaderboard are publicly available at https://seadronessee.cs.uni-tuebingen.de/macvi., MaCVi 2023 was part of WACV 2023. This report (38 pages) discusses the competition as part of MaCVi

Shuman Li,1,* Li Jiang,1,2,* Qingmei He,1,3,* Weidong Wei,1,4 Yun Wang,1,5 Xinke Zhang,1,3 Jun Liu,1,3 Keming Chen,1,3 Jiewei Chen,1,3 Dan Xie1,3 1Sun Yat-Sen University Cancer Center; State Key Laboratory of Oncology in South China; Collaborative Innovation Center for Cancer Medicine, Guangzhou 510060, People’s Republic of China; 2Department of the VIP Region, Sun Yat-Sen University Cancer Center, Guangzhou 510060, People’s Republic of China; 3Department of Pathology, Sun Yat-Sen University Cancer Center, Guangzhou 510060, People’s Republic of China; 4Department of Thoracic Surgery, Sun Yat-Sen University Cancer Center, Guangzhou 510060, People’s Republic of China; 5Department of Hematologic Oncology, Sun Yat-Sen University Cancer Center, Guangzhou, People’s Republic of China*These authors contributed equally to this workCorrespondence: Dan Xie; Jiewei ChenDepartment of Pathology, Sun Yat-Sen University Cancer Center, No. 651, Dongfeng East Road, Guangzhou 510060, People’s Republic of ChinaTel +86-20-87343268Email xiedan@sysucc.org.cn; chenjiew@sysucc.org.cnIntroduction: Primary sarcomatoid carcinoma of the lung (PSC) is a rare subtype of non-small cell lung cancer, which has a bad prognosis and lacks biomarkers for its diagnosis and prognosis. Recent studies suggested that KDM6B (lysine demethylase 6B), also known as Jumonji domain-containing protein D3 (JMJD3), plays an oncogenic role in various human cancers. However, abnormalities of JMJD3 in sarcomatoid carcinoma of the lung and its clinical prognostic significance have not been determined. Therefore, the present study aimed to ascertain the relationship between JMJD3 and PSC.Materials and methods: In this study, immunohistochemistry (IHC) was performed to examine the expression of JMJD3 in a tissue microarray (TMA) containing 96 cases of PSC.Result: Overexpression of JMJD3 was observed in nuclei of the PSC cells. Further analyses indicated that the overexpression of JMJD3 was significantly associated with tumor size, pN stage, and clinical stage. By univariate survival analysis, positive expression of JMJD3 was significantly correlated with shortened patient survival. More importantly, multivariate analysis identified JMJD3 as an independent prognostic factor for sarcomatoid carcinoma of the lung.Conclusion: These findings provide evidence that JMJD3 protein levels, as examined by IHC, may act as a novel prognostic biomarker for patients with primary sarcomatoid carcinoma of the lung.Keywords: primary sarcomatoid carcinoma of the lung, JMJD3, IHC, prognosis

Children and the elderly are vulnerable in body conditions and financial situations. They are special groups under the new rural cooperative medical insurance system. This article aimed at providing suggestions for policy making by analyzing hospitalization expenses and reimbursement of children and the elderly. The children concerned in this article are focused on the age of 14 years and under, while the elderly is for the age of 60 years and above. SAS software was used to analyze the hospitalization costs and reimbursements for these two populations using the datasets of one county in 2011. The results show that, the average hospitalization rate of children was 14.09%, while the highest was for children aged under 2 years due to some unnecessary hospitalization. The majority of hospitalization expenses of children were within 3000 Yuan. However, some hospitalization costs were still over 10000 Yuan. For the newborns, most hospitalization stays were within 14 days, and more than half of which were under 7 days. When they are growing up, newborns and children are getting stronger in physiques and resistances, and have lower rate in hospitalization. For the elderly inpatients, the average reimbursement rate for the hospitalization expenses was 55.52%. The minority of the aged people were hospitalized outside their residential area. This resulted in that the average hospitalization expenditure was 4.45 times the county level hospitalization, and 11 times the township level hospitalization. The article concluded that, the government needs to take actions to reduce unnecessary hospitalization percentage. More importantly, age-related diseases should be prevented effectively. Maternal and child’s protection needs to be strengthened urgently. The government should also encourage healthy lifestyles and prevent the senile diseases. After all, more attention should be given to children and newborns for their medical security.

The 1st Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection. The subchallenges were based on the SeaDronesSee and MODS benchmarks. This report summarizes the main findings of the individual subchallenges and introduces a new benchmark, called SeaDronesSee Object Detection v2, which extends the previous benchmark by including more classes and footage. We provide statistical and qualitative analyses, and assess trends in the best-performing methodologies of over 130 submissions. The methods are summarized in the appendix. The datasets, evaluation code and the leaderboard are publicly available (https:// seadronessee.cs.uni-tuebingen.de/macvi).