A Radiologist's Guide to Treatment Response Criteria in Oncologic Imaging: Anatomic Imaging Biomarkers

Rezai, Pedram; Pisaneschi, Mark; Feng, Chun; Yaghmai, Vahid

doi:10.2214/ajr.12.9862

Cited by 15 publications

(13 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, the RECIST criteria are applied to evaluating the treatment response based on the current therapeutic timepoint instead of predicting the response in advance, which may delay the time for intervention. In addition, due to the movement of the stomach and the irregular and nonspherical shape of lesions in the stomach wall, measuring the longest tumor diameter as the only criterion is difficult to reproduce for the purposes of making predictions [7]. Given the current drawbacks, it is crucial to improve the efficacy in evaluating the chemotherapeutic response.…”

Section: Ivyspringmentioning

confidence: 99%

“…The combination of tumor morphology and delta radiomics, showing tumor burden and heterogeneity, respectively, has the potential to provide a large amount of information for predicting the chemotherapeutic response. Nevertheless, manually delineating the entire tumor slice by slice, especially for thin-section CT images, is observer inconsistent and time consuming [7]. For delta radiomics, which requires repeated delineation at different timepoints, highly efficient segmentation is urgently needed.…”

Section: Ivyspringmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Chemotherapeutic Response for Far-advanced Gastric Cancer by Radiomics with Deep Learning Semi-automatic Segmentation

Tan¹,

Wang²,

Chen³

et al. 2020

J. Cancer

View full text Add to dashboard Cite

Purpose: To build a dual-energy computed tomography (DECT) delta radiomics model to predict chemotherapeutic response for far-advanced gastric cancer (GC) patients. A semi-automatic segmentation method based on deep learning was designed, and its performance was compared with that of manual segmentation. Methods: This retrospective study included 86 patients with far-advanced GC treated with chemotherapy from September 2016 to December 2017 (66 and 20 in the training and testing cohorts, respectively). Delta radiomics features between the baseline and first follow-up DECT were modeled by random forest to predict the chemotherapeutic response evaluated by the second follow-up DECT. Nine feature subsets from confounding factors and delta radiomics features were used to choose the best model with 10-fold cross-validation in the training cohort. A semi-automatic segmentation method based on deep learning was developed to predict the chemotherapeutic response and compared with manual segmentation in the testing cohort, which was further validated in an independent validation cohort of 30 patients. Results: The best model, constructed by confounding factors and texture features, reached an average AUC of 0.752 in the training cohort. Our proposed semi-automatic segmentation method was more time-effective than manual segmentation, with average saving-time of 11.2333 ± 6.3989 minutes and 9.9889 ±5.5086 minutes in the testing cohort and the independent validation cohort, respectively (both p < 0.05). The predictive ability of the semi-automatic segmentation was also better than that of the manual segmentation both in the testing cohort and the independent validation cohort (AUC: 0.728 vs. 0.687 and 0.828 vs. 0.749, respectively). Conclusion: DECT delta radiomics serves as a promising biomarker for predicting chemotherapeutic response for far-advanced GC. Semi-automatic segmentation based on deep learning shows the potential for clinical use with increased reproducibility and decreased labor costs compared to the manual version.

show abstract

Section: Ivyspringmentioning

confidence: 99%

Section: Ivyspringmentioning

confidence: 99%

Predicting Chemotherapeutic Response for Far-advanced Gastric Cancer by Radiomics with Deep Learning Semi-automatic Segmentation

Tan¹,

Wang²,

Chen³

et al. 2020

J. Cancer

View full text Add to dashboard Cite

show abstract

“…Given that both primary and metastatic tumors in GIST tend to be irregular rather than spherical (as assumed by RECIST), it is often argued that volume is a better representation of the actual number of tumor cells than single longest diameter (38). Accordingly, moderate changes in size can be detected better using volumetric analysis rather than RECIST (39).…”

Section: Response Assessment In Gistmentioning

confidence: 99%

Update on Gastrointestinal Stromal Tumors for Radiologists

et al. 2017

View full text Add to dashboard Cite

The management of gastrointestinal stromal tumors (GISTs) has evolved significantly in the last two decades due to better understanding of their biologic behavior as well as development of molecular targeted therapies. GISTs with exon 11 mutation respond to imatinib whereas GISTs with exon 9 or succinate dehydrogenase subunit mutations do not. Risk stratification models have enabled stratifying GISTs according to risk of recurrence and choosing patients who may benefit from adjuvant therapy. Assessing response to targeted therapies in GIST using conventional response criteria has several potential pitfalls leading to search for alternate response criteria based on changes in tumor attenuation, volume, metabolic and functional parameters. Surveillance of patients with GIST in the adjuvant setting is important for timely detection of recurrences.

show abstract

“…The maximum slice thickness is also specified in order to further standardize assessments. The disadvantage of this method is the absence of detection of necrosis [13] ( • " Table 1). …”

Section: Recistmentioning

confidence: 99%

Radiological Evaluation of the Therapeutic Response of Malignant Diseases: Status Quo, Innovative Developments and Requirements for Radiology

Höink¹,

Heindel²,

Buerke³

2014

Fortschr Röntgenstr

View full text Add to dashboard Cite

!In consequence of the rapid development of newer targeted and personalized tumor therapies, radiology as an essential component of the treatment concept of numerous malignant diseases needs to improve in order to adequately capture and evaluate the effects, but also the side effects of these novel therapeutic agents. The early recognition of therapy response or failure is crucial for the optimal planning of the further treatment and can therefore have direct impact on the chances of recovery and the survival time of oncological patients. In previous years, the goal of medical imaging was to just qualitatively assess the increase or reduction in the size of tumors and their metastases, which was often achieved by a simple subjective estimation of the tumor findings by the diagnosing radiologist. Nowadays, radiology is faced with the challenge of evaluating changes during therapy quantitatively and of visualizing therapeutic effects that are more discrete (e. g. necrosis, altered tumor perfusion). The importance of an adequate assessment of therapy response is further underlined by the fact that in these days, a good portion of oncological patients are enrolled in clinical trials, in which the quantitative radiological evaluation of malignant disorders is an important surrogate parameter. On the basis of this development, the demands for radiology to provide more sophisticated assessments of therapy response and documentation of imaging findings have been constantly growing.The following article provides an overview of the established and still widely spread but in particular also the latest imaging modalities and evaluation criteria with regard to oncological diseases as well as of the increasing demands on radiology that result from these developments. Beyond that, future advancements in tumor imaging are taken into account and the new challenges these developments will bring are discussed.

show abstract

A Radiologist's Guide to Treatment Response Criteria in Oncologic Imaging: Anatomic Imaging Biomarkers

Cited by 15 publications

References 63 publications

Predicting Chemotherapeutic Response for Far-advanced Gastric Cancer by Radiomics with Deep Learning Semi-automatic Segmentation

Predicting Chemotherapeutic Response for Far-advanced Gastric Cancer by Radiomics with Deep Learning Semi-automatic Segmentation

Update on Gastrointestinal Stromal Tumors for Radiologists

Radiological Evaluation of the Therapeutic Response of Malignant Diseases: Status Quo, Innovative Developments and Requirements for Radiology

Contact Info

Product

Resources

About