scholarly journals Transcriptomic Determinants of Response to Pembrolizumab Monotherapy Across Solid Tumor Types

2021 ◽  
pp. clincanres.3329.2021
Author(s):  
Razvan Cristescu ◽  
Michael Nebozhyn ◽  
Chunsheng Zhang ◽  
Andrew Albright ◽  
Julie Kobie ◽  
...  
Keyword(s):  
Solid Tumor ◽  
Tumor Types

scholarly journals 833 A scalable deep learning framework for rapid automated annotation of histologic and morphologic features from large unlabeled pan-cancer H&E datasets

2021 ◽  
Vol 9 (Suppl 3) ◽  
pp. A874-A874
Author(s):  
David Soong ◽  
David Soong ◽  
David Soong ◽  
Anantharaman Muthuswamy ◽  
Clifton Drew ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Solid Tumor ◽  
Blood Cells ◽  
White Blood Cells ◽  
Digital Pathology ◽  
Area Under The Curve ◽  
Morphological Characteristics ◽  
Learning Framework ◽  
Tumor Types

BackgroundRecent advances in machine learning and digital pathology have enabled a variety of applications including predicting tumor grade and genetic subtypes, quantifying the tumor microenvironment (TME), and identifying prognostic morphological features from H&E whole slide images (WSI). These supervised deep learning models require large quantities of images manually annotated with cellular- and tissue-level details by pathologists, which limits scale and generalizability across cancer types and imaging platforms. Here we propose a semi-supervised deep learning framework that automatically annotates biologically relevant image content from hundreds of solid tumor WSI with minimal pathologist intervention, thus improving quality and speed of analytical workflows aimed at deriving clinically relevant features.MethodsThe dataset consisted of >200 H&E images across >10 solid tumor types (e.g. breast, lung, colorectal, cervical, and urothelial cancers) from advanced disease patients. WSI were first partitioned into small tiles of 128μm for feature extraction using a 50-layer convolutional neural network pre-trained on the ImageNet database. Dimensionality reduction and unsupervised clustering were applied to the resultant embeddings and image clusters were identified with enriched histological and morphological characteristics. A random subset of representative tiles (<0.5% of whole slide tissue areas) from these distinct image clusters was manually reviewed by pathologists and assigned to eight histological and morphological categories: tumor, stroma/connective tissue, necrotic cells, lymphocytes, red blood cells, white blood cells, normal tissue and glass/background. This dataset allowed the development of a multi-label deep neural network to segment morphologically distinct regions and detect/quantify histopathological features in WSI.ResultsAs representative image tiles within each image cluster were morphologically similar, expert pathologists were able to assign annotations to multiple images in parallel, effectively at 150 images/hour. Five-fold cross-validation showed average prediction accuracy of 0.93 [0.8–1.0] and area under the curve of 0.90 [0.8–1.0] over the eight image categories. As an extension of this classifier framework, all whole slide H&E images were segmented and composite lymphocyte, stromal, and necrotic content per patient tumor was derived and correlated with estimates by pathologists (p<0.05).ConclusionsA novel and scalable deep learning framework for annotating and learning H&E features from a large unlabeled WSI dataset across tumor types was developed. This automated approach accurately identified distinct histomorphological features, with significantly reduced labeling time and effort required for pathologists. Further, this classifier framework was extended to annotate regions enriched in lymphocytes, stromal, and necrotic cells – important TME contexture with clinical relevance for patient prognosis and treatment decisions.

Abstract 3404: Landscape and genomic correlates of ctDNA-based tumor mutational burden across six solid tumor types

2019 ◽  
Author(s):  
Katie Quinn ◽  
Elena Helman ◽  
Tracy Nance ◽  
Jennifer Yen ◽  
John Latham ◽  
...  
Keyword(s):  
Solid Tumor ◽  
Mutational Burden ◽  
Tumor Mutational Burden ◽  
Tumor Types

scholarly journals Patterns of TPD52 overexpression in multiple human solid tumor types analyzed by quantitative PCR

2013 ◽  
Vol 44 (2) ◽  
pp. 609-615 ◽  
Author(s):  
PIERRE TENNSTEDT ◽  
CHARLOTTE BÖLCH ◽  
GUNDULA STROBEL ◽  
SARAH MINNER ◽  
LIA BURKHARDT ◽  
...  
Keyword(s):  
Quantitative Pcr ◽  
Solid Tumor ◽  
Human Solid Tumor ◽  
Tumor Types

scholarly journals Mining the adenovirus virome for oncolytics against multiple solid tumor types

2011 ◽  
Vol 18 (10) ◽  
pp. 744-750 ◽  
Author(s):  
C Y Chen ◽  
E A Weaver ◽  
R Khare ◽  
S M May ◽  
M A Barry
Keyword(s):  
Solid Tumor ◽  
Tumor Types

scholarly journals A Pilot Study of Comprehensive Genomic Profiling for Pediatric and Adolescent and Young Adult Solid Tumor Patients in Japan

2021 ◽  
Author(s):  
Shotaro Matsudera ◽  
Yoshihito Kano ◽  
Yasuko Aoyagi ◽  
Kohki Tohyama ◽  
Kei Ogino ◽  
...  
Keyword(s):  
Solid Tumor ◽  
Wilms Tumor ◽  
Adolescent And Young Adult ◽  
Genomic Alteration ◽  
Genomic Profiling ◽  
Tumor Patients ◽  
Comprehensive Genomic Profiling ◽  
Healthcare Insurance ◽  
Tumor Types ◽  
Basket Trials

Background: Comprehensive genomic profiling (CGP) was widely adopted in Japan after its coverage by national healthcare insurance began in June 2019. We investigated the clinical utility of CGP in pediatric and adolescent young adults (AYA) solid tumor patients. Procedure: Between November 2017 and December 2019, 13 patients who progressed with or who were likely to progress with standard therapies were recruited to the PROFILE-F study to undergo CGP using either FoundationOne® CDx or FoundationOne® Heme. Results: The median age was 28 years old. Tumor types were as follows: neuroblastoma (n=1), Wilms’ tumor (n=1), rhabdomyosarcoma (n=2), Ewing sarcoma (n=1), gastric cancer (n=1), rectal cancer (n=1), osteosarcoma (n=1), neuroendocrine tumor (n=2), salivary gland carcinoma (n=1), tracheal adenoid cystic carcinoma (n=1), and thymic cancer (n=1). In 92% of cases, at least one genomic alteration was identified, including CDKN2A (four cases), TP53 (three cases), and MYC (two cases). Actionable aberrations were found in 10 cases (77%), and a clinical trial candidate was found in seven cases (54%). However, no patients were able to receive biomarker-matched therapy according to their genomic alterations. Conclusions: Further efforts to increase basket trials and collection of clinical genomic data to predict response are necessary to advance precision cancer medicine in pediatric and AYA populations.

Oncogenic FGFR3 gene fusions in solid tumors among Chinese cancer patients.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e15072-e15072
Author(s):  
Libin Xu ◽  
Ming Liu ◽  
Jingxian Duan ◽  
Tao Wang
Keyword(s):  
Cancer Patients ◽  
Solid Tumors ◽  
Solid Tumor ◽  
Coiled Coil ◽  
Genetic Alterations ◽  
Chinese Patients ◽  
Driver Mutations ◽  
Gene Fusions ◽  
Fgfr3 Gene ◽  
Tumor Types

e15072 Background: Oncogenic FGFR3 (fibroblast growth factor receptor 3) gene fusions have been identified as driver mutations that lead to the activation of FGFR3 in many solid tumor types and serve as a novel therapeutic target for FGFR inhibitors in clinical development. TACC3 (transforming acid coiled coil 3) is the most common partner of these FGFR3 fusions. Methods: The study enrolled over ten thousand cases of Chinese patients with different types of solid tumors. We performed targeted sequencing assay with our 605 gene panel that covered all the exon and intron regions of the FGFR3 gene, so that we could identify nearly all the FGFR3 translocation events. Results: The prevalence and form of FGFR3 fusions in different tumor types were shown in Table. We identified seven patients harboring FGFR3 fusion events, with six cases of FGFR3-TACC3 and one case of FGFR3-UBE2K. In the seven patients, three of them were also harbored concomitant TP53 gene mutations, and six of them were microsatellite stability (MSS), and one was microsatellite instability-low (MSI-L). Conclusions: FGFR3 gene rearrangements were identified in different solid tumor types in our study, and they were relatively rare compared to other novel mutations. However, clinical testing for the identification of FGFR3 fusions should be prioritized in bladder cancer patients. Consistent with other studies, the most common FGFR3 fusion form was FGFR3-TACC3. Co-occurring genetic alterations in FGFR3 gene fusions cases were also common. From our limited number of cases, most of FGFR3 gene fusions patients were MSS.[Table: see text]

Modulation of DNA Damage Response by Samhd1 Determines Prognosis and Treatment Efficacy in Different Solid Tumor Types

2021 ◽  
Author(s):  
Eudald Felip ◽  
Lucia Gutierrez-Chamorro ◽  
Maica Gómez ◽  
Edurne Garcia-Vidal ◽  
Margarita Romeo ◽  
...  
Keyword(s):  
Dna Damage ◽  
Dna Damage Response ◽  
Solid Tumor ◽  
Treatment Efficacy ◽  
Damage Response ◽  
Tumor Types
Sign in / Sign up

Export Citation Format

Share Document