Sequential Learning on Liver Tumor Boundary Semantics and Prognostic Biomarker Mining
Johns Hopkins University（约翰斯·霍普金斯大学）；PAII Inc.（PAII公司）；The First Affiliated Hospital of Nanjing Medical University（南京医科大学第一附属医院）；Ping An Technology（平安科技）；Shanghai Jiao Tong University（上海交通大学）
Jieneng Chen, Ke Yan, Yu-Dong Zhang, Youbao Tang, Xun Xu, Shuwen Sun, Qiuping Liu, Lingyun Huang, Jing Xiao, Alan L. Yuille, Ya Zhang, Le Lu
The boundary of tumors (hepatocellular carcinoma, or HCC) contains rich semantics: capsular invasion, visibility, smoothness, folding and protuberance, etc. Capsular invasion on tumor boundary has proven to be clinically correlated with the prognostic indicator, microvascular invasion (MVI). Investigating tumor boundary semantics has tremendous clinical values. In this paper, we propose the first and novel computational framework that disentangles the task into two components: spatial vertex localization and sequential semantic classification. (1) A HCC tumor segmentor is built for tumor mask boundary extraction, followed by polar transform representing the boundary with radius and angle. Vertex generator is used to produce fixed-length boundary vertices where vertex features are sampled on the corresponding spatial locations. (2) The sampled deep vertex features with positional embedding are mapped into a sequential space and decoded by a multilayer perceptron (MLP) for semantic classification. Extensive experiments on tumor capsule semantics demonstrate the effectiveness of our framework. Mining the correlation between the boundary semantics and MVI status proves the feasibility to integrate this boundary semantics as a valid HCC prognostic biomarker.
Finding Reproducible and Prognostic Radiomic Features in Variable Slice Thickness Contrast Enhanced CT of Colorectal Liver Metastases
Islamic Azad University（伊斯兰阿扎德大学）；Memorial Sloan Kettering Cancer Center（纪念斯隆凯特琳癌症中心）；The University of Texas MD Anderson Cancer Center（德克萨斯大学 MD 安德森癌症中心）
Deep learning for prediction of hepatocellular carcinoma recurrence after resection or liver transplantation: a discovery and validation study
Affiliated Hangzhou First People’s Hospital, Zhejiang University School of Medicine（浙江大学医学院附属杭州市第一人民医院）；Syracuse University（雪城大学）；Zhejiang University（浙江大学）；The First Affiliated Hospital, Zhejiang University School of Medicine（浙江大学医学院附属第一医院）
Methodological Explainability Evaluation of an Interpretable Deep Learning Model for Post-Hepatectomy Liver Failure Prediction Incorporating Counterfactual Explanations and Layerwise Relevance Propagation: A Prospective In Silico Trial
Maastricht University（马斯特里赫特大学）；Maastricht University Medical Center+（马斯特里赫特大学医学中心+）；The First Affiliated Hospital of Sun Yat-sen University（中山大学附属第一医院）；Guizhou University（贵州大学）；Université Libre de Bruxelles（布鲁塞尔自由大学）
BioFact-MoE: Biologically Factorized Mixture of Experts for Vision-Language Prognostic Modeling in Hepatocellular Carcinoma
Department of Radiology \& Biomedical Imaging, Department of Biomedical Engineering, Department of Electrical Engineering, Department of Statistics \& Data Science Yale University, New Haven, CT, 06510, USA
Live(r) Die: Predicting Survival in Colorectal Liver Metastasis
Department of Medical Biophysics, University of Toronto, Toronto, ON, Canada（多伦多大学医学生物物理学系）；Department of Medical Imaging, University of Toronto, Toronto, ON, Canada（多伦多大学医学影像学系）；Sunnybrook Research Institute, Toronto, ON, Canada（辛普森研究学院）
Novel Radiomic Measurements of Tumor- Associated Vasculature Morphology on Clinical Imaging as a Biomarker of Treatment Response in Multiple Cancers
Case Western Reserve University（凯斯西储大学）；Picture Health（Picture Health公司）；Stony Brook University（石溪大学）；University Hospitals Cleveland Medical Center（克利夫兰大学医院医学中心）；Yale School of Medicine（耶鲁医学院）；The Cleveland Clinic Foundation (CCF)（克利夫兰诊所基金会（CCF））；New York University (NYU) Langone Medical Center（纽约大学（NYU）朗格尼医学中心）；Louis Stokes Cleveland Veterans Medical Center（路易斯·斯托克斯克利夫兰退伍军人医学中心）
目的：肿瘤相关血管系统与健康血管的不同之处在于其混乱的结构和扭曲性，这会促进治疗抵抗。这些属性的可测量差异可能有助于根据全身治疗（例如化疗）的可能获益对患者进行分层。在这项工作中，我们提出了一类新的放射性生物标志物，称为定量肿瘤相关血管系统（QuanTAV）特征，并证明了它们预测多种癌症，成像方式和治疗方案的反应和生存的能力。实验设计：我们对558名患者的常规治疗前放射学（CT或对比增强MRI）进行了肿瘤血管分割并计算了扭曲和组织的数学测量值，这些患者接受了乳腺癌（n=371）或非小细胞肺癌（NSCLC，n=187）的四种一线化疗治疗干预策略之一。结果如下：在4种基于化疗的治疗策略中，QuanTAV测量的分类器显著（p<0.05）预测了单独保持测试队列的反应（AUC=0.63-0.71），并且当添加到单独的重要临床变量模型中时，AUC增加了0.06-0.12。QuanTAV风险评分是乳腺癌化疗（p=0.002，HR=1.25，95% CI 1.08-1.44，C指数= 0.66）和NSCLC放化疗（p=0.039，HR=1.28，95% CI 1.01-1.62，C指数=0.66）治疗队列中无复发生存期的预后指标。在所有治疗组中，包括接受化疗的NSCLC患者（p=0.034，HR=2.29，95% CI 1.07-4.94，C指数=0.62），分类QuanTAV风险组具有独立预后。…
