4.5 Article

Automated Tracking of Quantitative Assessments of Tumor Burden in Clinical Trials

期刊

TRANSLATIONAL ONCOLOGY
卷 7, 期 1, 页码 23-35

出版社

ELSEVIER SCIENCE INC
DOI: 10.1593/tlo.13796

关键词

-

类别

资金

  1. National Cancer Institute, National Institutes of Health [U01CA142555]
  2. National Council for Scientific and Technological Development (CNPq grant) [481837/2008-6]

向作者/读者索取更多资源

There are two key challenges hindering effective use of quantitative assessment of imaging in cancer response assessment: 1) Radiologists usually describe the cancer lesions in imaging studies subjectively and sometimes ambiguously, and 2) it is difficult to repurpose imaging data, because lesion measurements are not recorded in a format that permits machine interpretation and interoperability. We have developed a freely available software platform on the basis of open standards, the electronic Physician Annotation Device (ePAD), to tackle these challenges in two ways. First, ePAD facilitates the radiologist in carrying out cancer lesion measurements as part of routine clinical trial image interpretation workflow. Second, ePAD records all image measurements and annotations in a data format that permits repurposing image data for analyses of alternative imaging biomarkers of treatment response. To determine the impact of ePAD on radiologist efficiency in quantitative assessment of imaging studies, a radiologist evaluated computed tomography (CT) imaging studies from 20 subjects having one baseline and three consecutive follow-up imaging studies with and without ePAD. The radiologist made measurements of target lesions in each imaging study using Response Evaluation Criteria in Solid Tumors 1.1 criteria, initially with the aid of ePAD, and then after a 30-day washout period, the exams were reread without ePAD. The mean total time required to review the images and summarize measurements of target lesions was 15% (P < .039) shorter using ePAD than without using this tool. In addition, it was possible to rapidly reanalyze the images to explore lesion cross-sectional area as an alternative imaging biomarker to linear measure. We conclude that ePAD appears promising to potentially improve reader efficiency for quantitative assessment of CT examinations, and it may enable discovery of future novel image-based biomarkers of cancer treatment response.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.5
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

Article Computer Science, Artificial Intelligence

Fuzzy directional enlacement landscapes for the evaluation of complex spatial relations

Michael Clement, Camille Kurtz, Laurent Wendling

PATTERN RECOGNITION (2020)

Article Computer Science, Artificial Intelligence

Supervised quality evaluation of binary partition trees for object segmentation

Jimmy Francky Randrianasoa, Pierre Cettour-Janet, Camille Kurtz, Eric Desjardin, Pierre Gancarski, Nathalie Bednarek, Francois Rousseau, Nicolas Passat

Summary: The binary partition tree (BPT) provides a hierarchical representation of images at multiple scales, facilitating optimization-based segmentation methods. The evaluation framework for BPT quality is supervised and considers user objectives expressed through chosen ground-truth and quality metrics.

PATTERN RECOGNITION (2021)

Article Computer Science, Artificial Intelligence

Deep-STaR: Classification of image time series based on spatio-temporal representations

Mohamed Chelali, Camille Kurtz, Anne Puissant, Nicole Vincent

Summary: Image time series (ITS) are complex 3D data widely used in various domains. This work introduces Deep-STaR, a method that learns features from ITS data for classification by exploring novel 2D planar data representations. The results show the benefits of this method in enhancing interpretability of spatio-temporal phenomena in remote sensing applications.

COMPUTER VISION AND IMAGE UNDERSTANDING (2021)

Article Gastroenterology & Hepatology

Pembrolizumab with Capox Bevacizumab in patients with microsatellite stable metastatic colorectal cancer and a high immune infiltrate: The FFCD 1703-POCHI trial

Claire Gallois, Jean-Francois Emile, Stefano Kim, Carole Monterymard, Marine Gilabert, Jeremie Bez, Astrid Lievre, Laetitia Dahan, Pierre Laurent-Puig, Laurent Mineur, Romain Coriat, Jean-Louis Legoux, Vincent Hautefeuille, Jean-Marc Phelip, Thierry Lecomte, Harry Sokol, Claude Capron, Violaine Randrian, Come Lepage, Nicolas Lomenie, Camille Kurtz, Julien Taieb, David Tougeron

Summary: Pembrolizumab has shown great efficacy in MSI/dMMR mCRC patients, but not in MSS/pMMR mCRC patients. The POCHI trial aims to evaluate the efficacy of Pembrolizumab with Capox Bevacizumab in MSS/pMMR mCRC patients with high immune infiltrate.

DIGESTIVE AND LIVER DISEASE (2021)

Article Computer Science, Artificial Intelligence

Influence of Data Representations and Deep Architectures in Image Time Series Classification

Mohamed Chelali, Camille Kurtz, Anne Puissant, Nicole Vincent

Summary: This paper proposes a strategy based on Random Walk to reduce the dimension of image time series data from 2D+t to 2D, making it more easily manipulable without losing too much spatial information. By feeding the new data representation into a classical Convolutional Neural Network, spatio-temporal features can be learned effortlessly and used for various classification problems.

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE (2021)

Article Computer Science, Software Engineering

AGAT: Building and evaluating binary partition trees for image segmentation

Jimmy Francky Randrianasoa, Camille Kurtz, Eric Desjardin, Nicolas Passat

Summary: AGAT is a Java library designed for constructing, handling, and evaluating binary partition trees, offering a wide range of functionalities for multiscale partitioning of images and graph-based analysis. Beyond imaging applications, it has potential applications in computer vision, image data analysis, and machine learning, providing users with tools for developing new methods and paradigms in the field.

SOFTWAREX (2021)

Article Computer Science, Artificial Intelligence

Description and recognition of complex spatial configurations of object pairs with Force Banner 2D features

Robin Delearde, Camille Kurtz, Laurent Wendling

Summary: A major challenge in scene understanding is handling spatial relations between objects or object parts. Researchers propose a descriptor called (discrete) Force Banner, which computes the interaction between objects under different forces to describe complex spatial configurations. Experimental results demonstrate the potential of this approach in classification and spatial configuration description.

PATTERN RECOGNITION (2022)

Proceedings Paper Computer Science, Artificial Intelligence

FINE-TUNE YOUR CLASSIFIER: FINDING CORRELATIONS WITH TEMPERATURE

Benjamin Chamand, Olivier Risser-Maroix, Camille Kurtz, Philippe Joly, Nicolas Lomenie

Summary: This article explores the impact of temperature on classification tasks, proposes a heuristic analysis using a set of statistics to obtain a default temperature value, and studies the correlation between these statistics and the optimal temperature.

2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP (2022)

Proceedings Paper Computer Science, Artificial Intelligence

Discovering Respects for Visual Similarity

Olivier Risser-Maroix, Camille Kurtz, Nicolas Lomenie

Summary: Similarity is a fundamental concept in artificial intelligence and cognitive sciences, but defining and measuring similarity between concepts and images remains challenging. This paper proposes a novel approach to retrospectively identify similarities between different concepts and provides a pipeline to explain the similarity of image pairs.

STRUCTURAL, SYNTACTIC, AND STATISTICAL PATTERN RECOGNITION, S+SSPR 2022 (2022)

Proceedings Paper Computer Science, Artificial Intelligence

Embedding Spatial Relations in Visual Question Answering for Remote Sensing

Maxime Faure, Sylvain Lobry, Camille Kurtz, Laurent Wendling

Summary: This article proposes a method that uses histograms of forces to model spatial relations in remote sensing images and constructs a ground-truth database of image/question/answer triplets. The performances of a classical VQA model are evaluated using this method, and a curriculum learning strategy is proposed to account for the varying difficulty of questions embedding spatial relations. The results show an improvement in the performances of the model, highlighting the interest of embedding spatial relations in VQA for remote sensing applications.

2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) (2022)

Proceedings Paper Computer Science, Artificial Intelligence

Text-guided visual representation learning for medical image retrieval systems

Guillaume Serieys, Camille Kurtz, Laure Fournier, Florence Cloppet

Summary: Radiologists face the challenge of interpreting cross-sectional studies with thousands of images. Integrating a Content-Based Image Retrieval (CBIR) system into a picture archiving and communication system (PACS) can improve the diagnosis of new cases. However, the current state-of-the-art deep learning methods for extracting visual features have limitations. This study explores the use of semantic information from radiological reports to enhance the learning of neural models and improve visual representation of images.

2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) (2022)

Proceedings Paper Optics

Combination of Visual and Semantic Criteria for Automated Selection of Region Proposals in a Bounding Box

Mohamed-Hicham Leghettas, Robin Delearde, Camille Kurtz, Laurent Wendling

Summary: A segmentation pipeline called ComViSe is proposed, which only requires high-level annotations for image segmentation and is easier to obtain compared to pixel-level annotations. The pipeline generates image region proposals by embedding a pre-trained segmentation framework on a semantically different dataset and selects the optimal segmentation mask using multiple criteria.

FOURTEENTH INTERNATIONAL CONFERENCE ON MACHINE VISION (ICMV 2021) (2022)

Proceedings Paper Computer Science, Artificial Intelligence

LEARNING AN ADAPTATION FUNCTION TO ASSESS IMAGE VISUAL SIMILARITIES

Olivier Risser-Maroix, Camille Kurtz, Nicolas Lomenie

Summary: This study focuses on recognizing similarities between images, especially when analogy is important, by using neural networks and metric learning framework for image feature learning. Experimental results show that this method has a significant advantage in improving image retrieval accuracy.

2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) (2021)

Proceedings Paper Computer Science, Artificial Intelligence

VIOLENCE DETECTION FROM VIDEO UNDER 2D SPATIO-TEMPORAL REPRESENTATIONS

Mohamed Chelali, Camille Kurtz, Nicole Vincent

Summary: The article introduces a method for violence recognition in videos using a classical 2D convolutional neural network. The strategy involves building multiple 2D spatio-temporal representations from input videos and feeding them to the CNN for the train/test process. The classification decision is made based on aggregating individual decisions from different spatio-temporal representations. Experimentation on public datasets containing violent videos shows the effectiveness of the proposed method.

2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Segment My Object: A Pipeline to Extract Segmented Objects in Images based on Labels or Bounding Boxes

Robin Delearde, Camille Kurtz, Philippe Dejean, Laurent Wendling

Summary: The SegMyO pipeline is a solution for automatically extracting segmented objects from images based on given labels or bounding boxes, by finding the closest label or choosing the best coverage based on geometric criteria. This approach is effective for weakly-supervised segmentation and datasets with weak object annotations, providing a simple solution without specific training.

VISAPP: PROCEEDINGS OF THE 16TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS - VOL. 5: VISAPP (2021)

Article Oncology

Diagnostic plasma small extracellular vesicles miRNA signatures for pancreatic cancer using machine learning methods

Xiaofan Pu, Chaolei Zhang, Guoping Ding, Hongpeng Gu, Yang Lv, Tao Shen, Tianshu Pang, Liping Cao, Shengnan Jia

Summary: This study demonstrated the potential utility of the sEV-miRNA d-signature in the diagnosis of PDAC via machine learning methods. A novel sEV biomarker, miR-664a-3p, was identified for the diagnosis of PDAC. It can also potentially promote angiogenesis and metastasis, provide insight into PDAC pathogenesis, and reveal novel regulators of this disease.

TRANSLATIONAL ONCOLOGY (2024)

Article Oncology

Silencing of PD-1 combined with EBV-specific killer T cells for the treatment of EBV-associated B lymphoma

Jiaping Wang, Zhijuan Xu, Yanli Lai, Yanli Zhang, Ping Zhang, Qitian Mu, Shujun Yang, Yongcheng Sun, Lixia Sheng, Guifang Ouyang

Summary: This study demonstrates the significance of PD-1 in EBV-infected lymphoma cells. Silencing PD-1 enhances the tumor targeting effect of EBV-specific killer T cells on B lymphocytes and attenuates the immune escape effect.

TRANSLATIONAL ONCOLOGY (2024)

Article Oncology

Lipid metabolism-associated genes serve as potential predictive biomarkers in neoadjuvant chemoradiotherapy combined with immunotherapy in rectal cancer

Qiliang Peng, Jialong Tao, Yingjie Xu, Yi Shen, Yong Wang, Yang Jiao, Yiheng Mao, Yaqun Zhu, Yulong Liu, Ye Tian

Summary: This study investigates the potential role of lipid metabolism-associated genes (LMAGs) in neoadjuvant chemoradiotherapy (nCRT) and immunotherapy for rectal cancer. The results suggest that the SREBF2 gene is a highly predictive factor for nCRT in rectal cancer and is associated with favorable prognosis. SREBF2 is also closely associated with immune cell infiltration and immunotherapy-related genes.

TRANSLATIONAL ONCOLOGY (2024)

Article Oncology

Transcriptionally activates CCL28 expression to inhibit M2 polarization of macrophages and prevent immune escape in colorectal cancer cells

Shiquan Li, Nan Zhang, Yongping Yang, Tongjun Liu

Summary: This study investigated the potential molecular mechanism of SPDEF in immune evasion of colorectal cancer (CRC) and found that it suppresses immune evasion by activating CCL28 through the modulation of M2 polarization of macrophages. These findings provide a new research direction and potential therapeutic target for immunotherapy in CRC.

TRANSLATIONAL ONCOLOGY (2024)

Article Oncology

Characterizing heterogeneity along EMT and metabolic axes in colorectal cancer reveals underlying consensus molecular subtype-specific trends

Manas Sehgal, Soundharya Ramu, Joel Markus Vaz, Yogheshwer Raja Ganapathy, Srinath Muralidharan, Sankalpa Venkatraghavan, Mohit Kumar Jolly

Summary: This study investigates the relationship between gene expression patterns and phenotypic plasticity and heterogeneity in colorectal cancer (CRC). The results demonstrate the interconnectedness between different Consensus Molecular Subtypes (CMS) of CRC and specific phenotypes such as epithelial and mesenchymal characteristics. Additionally, the study reveals correlations between metabolic pathways and phenotypic scores, as well as between PD-L1 activity and mesenchymal phenotype. Single-cell RNA sequencing analysis further confirms the heterogeneity of different CMS subtypes. These findings have important implications for understanding CRC heterogeneity and developing targeted therapies.

TRANSLATIONAL ONCOLOGY (2024)

Article Oncology

Ceramide metabolism-related prognostic signature and immunosuppressive function of ST3GAL1 in osteosarcoma

Yutong Zou, Siyao Guo, Yan Liao, Weidong Chen, Ziyun Chen, Junkai Chen, Lili Wen, Xianbiao Xie

Summary: This study found that ceramide metabolism is associated with the progression and clinical outcome of osteosarcoma by analyzing data from osteosarcoma patients. The gene ST3GAL1 plays an important role in osteosarcoma, regulating the tumor immune microenvironment and affecting T cell function. It may become a new target for the treatment of osteosarcoma.

TRANSLATIONAL ONCOLOGY (2024)

Article Oncology

GPR37-centered ceRNA network contributes to metastatic potential in lung adenocarcinoma: Evidence from high-throughput sequencing

Chuanhui Chen, Mengzhi Wan, Xiong Peng, Qing Zhang, Yu Liu

Summary: This study examines the function and mechanism of the ceRNA network centered around GPR37 in LUAD. The findings show that high expression of GPR37 in LUAD tissue samples is associated with poor prognosis, and it may regulate the expression of downstream target genes by competitively binding to lncRNA DLEU1 and miR-4458.

TRANSLATIONAL ONCOLOGY (2024)

Article Oncology

Effective sequential combined therapy with carboplatin and a CDC7 inhibitor in ovarian cancer

Junping Li, Hong Hu, Jinping He, Yuling Hu, Manting Liu, Bihui Cao, Dongni Chen, Xiaodie Ye, Jian Zhang, Zhiru Zhang, Wen Long, Hui Lian, Deji Chen, Likun Chen, Lili Yang, Zhenfeng Zhang

Summary: Sequential administration of CDC7 inhibitor XL413 after carboplatin enhances the chemotherapeutic effect of carboplatin on ovarian cancer cells, possibly by inhibiting homologous recombination repair activity and increasing the accumulation of chemotherapy-induced DNA damage.

TRANSLATIONAL ONCOLOGY (2024)

Article Oncology

Dual role of CASP8AP2/FLASH in regulating epithelial-to-mesenchymal transition plasticity (EMP)

Madison Catalanotto, Joel Markus Vaz, Camille Abshire, Reneau Youngblood, Min Chu, Herbert Levine, Mohit Kumar Jolly, Ana -Maria Dragoi

Summary: The study demonstrates that loss of FLASH in cancer cells leads to a hybrid E/M phenotype with high epithelial scores, suggesting FLASH acts as a repressor of the epithelial phenotype. Additionally, FLASH expression is inversely correlated with the epithelial score and subsets of mesenchymal markers are distinctly up-regulated in FLASH, NPAT, or SLBP-depleted cells.

TRANSLATIONAL ONCOLOGY (2024)

Article Oncology

Acetylation and deacetylation of histone in adipocyte differentiation and the potential significance in cancer

Xiaorui Wang, Na Li, Minying Zheng, Yongjun Yu, Shiwu Zhang

Summary: Adipocytes are derived from pluripotent mesenchymal stem cells and histone modifications play a key role in their differentiation. Recent studies have shown that cancer stem cells can differentiate into adipocytes, reducing the malignancy of cancer cells.

TRANSLATIONAL ONCOLOGY (2024)

Article Oncology

Epigenetic modifications: Key players in cancer heterogeneity and drug resistance

Hana Q. Sadida, Alanoud Abdulla, Sara Al Marzooqi, Sheema Hashem, Muzafar A. Macha, Ammira S. Al-Shabeeb Akil, Ajaz A. Bhat

Summary: Cancer heterogeneity and drug resistance are major obstacles to effective cancer treatment, and epigenetic modifications play a pivotal role in these processes. This review explores essential epigenetic modifications, including DNA methylation, histone modifications, and chromatin remodeling, and discusses their complex contributions to cancer biology. However, the interplay of epigenetic and genetic changes in cancer cells presents unique challenges that must be addressed to fully exploit the potential of epigenetic modifications.

TRANSLATIONAL ONCOLOGY (2024)

Article Oncology

Gene expression profiles (GEPs) of immuno-oncologic pathways as predictors of response to checkpoint inhibitors in advanced NSCLC

Pedro De Marchi, Leticia Ferro Leal, Luciane Sussuchi da Silva, Rodrigo de Oliveira Cavagna, Flavio Augusto Ferreira da Silva, Vinicius Duval da Silva, Eduardo C. A. da Silva, Augusto O. Saito, Vladmir C. Cordeiro de Lima, Rui Manuel Reis

Summary: The TIS and IFN-gamma signatures are predictive biomarkers for identifying NSCLC patients who could potentially benefit from immune checkpoint inhibitor therapies.

TRANSLATIONAL ONCOLOGY (2024)

Article Oncology

Extensive mutational ctDNA profiles reflect High-grade serous cancer tumors and reveal emerging mutations at recurrence

Giovanni Marchi, Anna Rajavuori, Mai T. N. Nguyen, Kaisa Huhtinen, Sinikka Oksa, Sakari Hietanen, Sampsa Hautaniemi, Johanna Hynninen, Jaana Oikkonen

Summary: The study shows that ctDNA can adequately represent high-grade serous ovarian carcinoma (HGSC), and the mutations observed at relapse suggest personalized therapy options.

TRANSLATIONAL ONCOLOGY (2024)

Article Oncology

Cell surface GRP78-directed CAR-T cells are effective at treating human pancreatic cancer in preclinical models

Yuncang Yuan, Jiawei Fan, Dandan Liang, Shijie Wang, Xu Luo, Yongjie Zhu, Nan Liu, Tingxiu Xiang, Xudong Zhao

Summary: This study demonstrates that csGRP78-directed CAR-T cells can selectively kill pancreatic cancer cells, and the combination with chemotherapy enhances cytotoxicity.

TRANSLATIONAL ONCOLOGY (2024)

Article Oncology

Bulky glycocalyx shields cancer cells from invasion-associated stresses

Niyati Piplani, Tanusri Roy, Neha Saxena, Shamik Sen

Summary: The glycocalyx, a protective barrier surrounding cells, has been found to play a role in cancer cell proliferation, survival, and metastasis. However, its function in maintaining DNA/nuclear integrity during migration through dense matrices has not been explored. This study shows that the bulkiness of the glycocalyx is inversely associated with nuclear stresses, and highlights its mechanical role in shielding migration-associated stresses.

TRANSLATIONAL ONCOLOGY (2024)