Vulnerabilities of radiomic signature development: The need for safeguards

Radiotherapy and Oncology, Год журнала: 2018, Номер 130, С. 2 - 9

Опубликована: Ноя. 8, 2018

Refinement of radiomic results and methodologies is required to ensure progression the field. In this work, we establish a set safeguards designed improve support current through detailed analysis signature.A model (MW2018) was fitted externally validated using features extracted from previously reported lung head neck (H&N) cancer datasets gross-tumour-volume contours, as well images with randomly permuted voxel index values; i.e. without meaningful texture. To determine MW2018's added benefit, prognostic accuracy tumour volume alone calculated baseline.MW2018 had an external validation concordance (c-index) 0.64. However, similar performance achieved randomized signal intensities (c-index = 0.64 0.60 for H&N lung, respectively). Tumour c-index correlated strongly three four features. It determined that signature surrogate intensity texture values were not pertinent prognostication.Our experiments reveal vulnerabilities in development processes suggest can be used refine methodologies, productive objective independent

Язык: Английский

---

The Biological Meaning of Radiomic Features

Radiology, Год журнала: 2021, Номер 299(2), С. E256 - E256

Опубликована: Апрель 26, 2021

Язык: Английский

---

Association of Peritumoral Radiomics With Tumor Biology and Pathologic Response to Preoperative Targeted Therapy for HER2 (ERBB2)–Positive Breast Cancer

JAMA Network Open, Год журнала: 2019, Номер 2(4), С. e192561 - e192561

Опубликована: Апрель 19, 2019

Importance

There has been significant recent interest in understanding the utility of quantitative imaging to delineate breast cancer intrinsic biological factors and therapeutic response. No clinically accepted biomarkers are as yet available for estimation response human epidermal growth factor receptor 2 (currently known asERBB2, but referred asHER2in this study)–targeted therapy cancer.

Objective

To determine whether signatures on clinical magnetic resonance (MRI) could noninvasively characterizeHER2-positive tumor estimate toHER2-targeted neoadjuvant therapy.

Design, Setting, Participants

In a retrospective diagnostic study encompassing 209 patients with cancer, textural features extracted within annular peritumoral tissue regions MRI were examined means identify increasingly granular subgroups relevant approach First, among cohort 117 who received an prior chemotherapy (NAC) at single institution from April 27, 2012, through September 4, 2015, that distinguishedHER2+ tumors other subtypes identified. Next, 42 withHER2+ cancers RNaseq data accumulated multicenter, preoperative trial (BrUOG 211B), signature response-associatedHER2-enriched (HER2-E) molecular subtype withinHER2+ (n = 42) was The association pathologic complete explored patient cohorts different institutions, where all receivedHER2-targeted NAC 28, n 50). Finally, between lymphocyte distribution BrUOG 211B had corresponding biopsy hematoxylin-eosin–stained slide images. Data analysis conducted January 15, 2017, February 14, 2019.

Main Outcomes Measures

Evaluation by area under receiver operating characteristic curve (AUC) identifyingHER2+ distinguishing (ypT0/is) withHER2-targeting.

Results

included (mean [SD] age, 51.1 [11.7] years), better discriminatedHER2-E (maximum AUC, 0.85; 95% CI, 0.79-0.90; 9-12 mm tumor) compared intratumoral (AUC, 0.76; 0.69-0.84). A classifier combining identified theHER2-E 0.89; 0.84-0.93) significantly associated both validation 0.80; 0.61-0.98 0.69; 0.53-0.84). Features 0- 3-mm region density tumor-infiltrating lymphocytes (R² 0.57; 0.39-0.75;P .002).

Conclusions Relevance

combination characteristics appears ofHER2+ imaging, offering insights into immune environment suggesting potential benefit treatment guidance.

Язык: Английский

---

Radiogenomics: bridging imaging and genomics

Abdominal Radiology, Год журнала: 2019, Номер 44(6), С. 1960 - 1984

Опубликована: Май 2, 2019

From diagnostics to prognosis response prediction, new applications for radiomics are rapidly being developed. One of the fastest evolving branches involves linking imaging phenotypes tumor genetic profile, a field commonly referred as "radiogenomics." In this review, general outline radiogenomic literature concerning prominent mutations across different sites will be provided. The radiogenomics originates from image processing techniques developed decades ago; however, many technical and clinical challenges still need addressed. Nevertheless, increasingly accurate robust models presented future appears bright.

Язык: Английский

---

Tracking tumor biology with radiomics: A systematic review utilizing a radiomics quality score

Radiotherapy and Oncology, Год журнала: 2018, Номер 127(3), С. 349 - 360

Опубликована: Май 18, 2018

In this review we describe recent developments in the field of radiomics along with current relevant literature linking it to tumor biology. We furthermore explore methodologic quality these studies our in-house scoring (RQS) tool. Finally, offer vision on necessary future steps for development stable radiomic features and their links biology.Two authors (S.S. H.W.) independently performed a thorough systematic search outcome extraction identify published MEDLINE/PubMed (National Center Biotechnology Information, NCBI), EMBASE (Ovid) Web Science (WoS). Two (S.S, H.W) separately two (J.v.T E.d.J) concordantly scored articles methodology analyses according previously score (RQS).In summary, total 655 records were identified till 25-09-2017 based specified terms, from which n = 236 MEDLINE/PubMed, 215 204 Science. After determining full article availability reading available articles, 41 included review. The RQS resulted some discrepancies between reviewers, e.g. reviewer H.W 4 ≥50%, S.S 3 ≥50% while reviewers J.v.T E.d.J 1 study ≥50%. Up nine given 0%. majority below 50%.In study, All but (n 39) revealed that derived ultrasound, CT, PET and/or MR are significantly associated one or several specific biologic substrates, somatic mutation status histopathologic grading metabolism. Considerable inter-observer differences found regard scoring, important questions raised concerning interpretability such scores.

Язык: Английский

---

Towards clinical application of image mining: a systematic review on artificial intelligence and radiomics

European Journal of Nuclear Medicine and Molecular Imaging, Год журнала: 2019, Номер 46(13), С. 2656 - 2672

Опубликована: Июнь 18, 2019

The aim of this systematic review was to analyse literature on artificial intelligence (AI) and radiomics, including all medical imaging modalities, for oncological non-oncological applications, in order assess how far the image mining research stands from routine application. To do this, we applied a trial phases classification inspired drug development process. Among articles considered inclusion PubMed were multimodality AI radiomics investigations, with validation analysis aimed at relevant clinical objectives. Quality assessment selected papers performed according QUADAS-2 criteria. We developed criteria studies. Overall 34,626 retrieved, 300 applying inclusion/exclusion criteria, 171 high-quality (QUADAS-2 ≥ 7) identified analysed. In 27/171 (16%), 141/171 (82%), 3/171 (2%) studies an AI-based algorithm, model, combined radiomics/AI approach, respectively, described. A total 26/27(96%) 1/27 (4%) classified as phase II III, respectively. Consequently, 13/141 (9%), 10/141 (7%), 111/141 (79%), 7/141 (5%) 0, I, II, All three categorised trials. results are promising but still not mature enough tools be implemented setting widely used. transfer learning well-known process, some specific adaptations discipline could represent most effective way algorithms become standard care tools.

Язык: Английский

---

Radiomics and deep learning in lung cancer

Strahlentherapie und Onkologie, Год журнала: 2020, Номер 196(10), С. 879 - 887

Опубликована: Май 4, 2020

Язык: Английский

---

Ultrasound-based radiomics score: a potential biomarker for the prediction of microvascular invasion in hepatocellular carcinoma

European Radiology, Год журнала: 2018, Номер 29(6), С. 2890 - 2901

Опубликована: Ноя. 12, 2018

Язык: Английский

---

An MRI radiomics approach to predict survival and tumour-infiltrating macrophages in gliomas

Brain, Год журнала: 2021, Номер 145(3), С. 1151 - 1161

Опубликована: Сен. 10, 2021

Abstract Preoperative MRI is one of the most important clinical results for diagnosis and treatment glioma patients. The objective this study was to construct a stable validatable preoperative T2-weighted MRI-based radiomics model predicting survival gliomas. A total 652 patients across three independent cohorts were covered in including their images, RNA-seq data. Radiomic features (1731) extracted from images 167 gliomas (discovery cohort) collected Beijing Tiantan Hospital then used develop prediction through machine learning-based method. performance validated two 261 Cancer Genomae Atlas database (external validation 224 prospective (prospective cohort). data discovery external applied establish relationship between biological function key features, which further by single-cell sequencing immunohistochemical staining. 14 radiomic features-based constructed cohort, showed highly robust predictive power overall cohorts. associated with immune response, especially tumour macrophage infiltration. can stably predict assist preoperatively assessing extent infiltration tumours.

Язык: Английский

---

Preoperative prediction of microvascular invasion in hepatocellular cancer: a radiomics model using Gd-EOB-DTPA-enhanced MRI

European Radiology, Год журнала: 2019, Номер 29(9), С. 4648 - 4659

Опубликована: Янв. 28, 2019

Язык: Английский

---