Combining multiparametric MRI with receptor information to optimize prediction of pathologic response to neoadjuvant therapy in breast cancer: preliminary results

Kang, Hakmook; Hainline, Allison E.; Arlinghaus, Lori R.; Elderidge, Stephanie; Li, Xia; Abramson, Vandana G.; Chakravarthy, A. Bapsi; Abramson, Richard G.; Bingham, Brian; Fakhoury, Kareem; Yankeelov, Thomas E.

doi:10.1117/1.jmi.5.1.011015

Cited by 5 publications

(9 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The top 4 texture features were then included as predictors in the final logistic ridge regression models. Because of the number of subjects being fewer (n = 28) than the number of explanatory variables, we used logistic ridge regression models to avoid overfitting ( 10 , 11 ).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Texture Analysis of F-18 Fluciclovine PET/CT to Predict Biochemically Recurrent Prostate Cancer: Initial Results

et al. 2020

Self Cite

View full text Add to dashboard Cite

Predicting biochemical recurrence of prostate cancer is imperative for initiating early treatment, which can improve the outcome of cancer treatment. However, because of inter- and intrareader variability in interpretation of F-18 fluciclovine positron emission tomography/computed tomography (PET/CT), it is difficult to reliably discern between necrotic tissue owing to radiation therapy and tumor tissue. Our goal is to develop a computational methodology using Haralick texture analysis that can be used as an adjunct tool to improve and standardize the interpretation of F-18 fluciclovine PET/CT to identify biochemical recurrence of prostate cancer. Four main textural features were chosen by variable selection procedure using least absolute shrinkage and selection operator logistic regression and bootstrapping, and then included as predictors in subsequent logistic ridge regression model for prediction (n = 28). Age at prostatectomy, prostate-specific antigen (PSA) level before the PET/CT imaging, and number of days between the prostate-specific antigen measurement and PET/CT imaging were also included in the prediction model. The overfitting-corrected area under the curve and Brier score of the proposed model were 0.94 (95% CI: 0.81, 1.00) and 0.12 (95% CI: 0.03, 0.23), respectively. Compared with a model with textural features (TI model) and that with only clinical information (CI model), the proposed model achieved 2% and 32% increase in AUC and 8% and 48% reduction in Brier score, respectively. Combining Haralick textural features based on the PET/CT imaging data with clinical information shows a high potential of enhanced prediction of the biochemical recurrence of prostate cancer.

show abstract

Section: Methodsmentioning

confidence: 99%

“…In each logistic ridge regression, the tuning parameter was estimated as described in by Cule et al ( 12 ). The performance of the 3 models was compared in terms of overfitting-corrected AUC (area under the receiver operating characteristic [ROC] curve) and Brier scores ( 11 , 13 ).…”

Section: Methodsmentioning

confidence: 99%

Texture Analysis of F-18 Fluciclovine PET/CT to Predict Biochemically Recurrent Prostate Cancer: Initial Results

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…For this reason, it is not surprising that studies evaluating early response after a single cycle of therapy have found success with multiparametric models combining pharmacokinetic DCE-MRI and diffusion-weighted (DWI) MRI, yielding high areas under the curve (AUCs) of 0.88-0.94. 23,24 A study evaluating changes in DWI at seven timepoints through treatment found that changes in the apparent diffusion coefficient (ADC) between baseline and either timepoints 1 or 2 were FIGURE 3: A 59-year-old woman with invasive ductal carcinoma (triple-negative). (a) Prior to neoadjuvant therapy, early-phase postcontrast T 1 -weighted image demonstrate a 3.0 cm mass in the superior breast (arrow).…”

Section: Enhancement and Pharmacokinetic Assessment Of Treatment Respmentioning

confidence: 99%

Role of MRI to Assess Response to Neoadjuvant Therapy for Breast Cancer

Reig

Heacock

Lewin

et al. 2020

Magnetic Resonance Imaging

View full text Add to dashboard Cite

The goals of imaging after neoadjuvant therapy for breast cancer are to monitor the response to therapy and facilitate surgical planning. MRI has been found to be more accurate than mammography, ultrasound, or clinical exam in evaluating treatment response. However, MRI may both overestimate and underestimate residual disease. The accuracy of MRI is dependent on tumor morphology, histology, shrinkage pattern, and molecular subtype. Emerging MRI techniques that combine functional information such as diffusion, metabolism, and hypoxia may improve MR accuracy. In addition, machine-learning techniques including radiomics and radiogenomics are being studied with the goal of predicting View this article online at wileyonlinelibrary.com.

show abstract

“…The MRI approach in question seems to accurately predict a treatment response right after a single cycle of therapy. Moreover, this method may improve the accuracy of evaluating a tumor’s response to NAT, showing a higher predictive power than models based on tumor size changes, and it may be used as a short-term surrogate marker of outcome in breast cancer patients [122].…”

Section: Magnetic Resonance Imaging Sequences In the Translationalmentioning

confidence: 99%

Magnetic Resonance Imaging for Translational Research in Oncology

Fiordelisi

Cavaliere

Auletta

et al. 2019

JCM

View full text Add to dashboard Cite

The translation of results from the preclinical to the clinical setting is often anything other than straightforward. Indeed, ideas and even very intriguing results obtained at all levels of preclinical research, i.e., in vitro, on animal models, or even in clinical trials, often require much effort to validate, and sometimes, even useful data are lost or are demonstrated to be inapplicable in the clinic. In vivo, small-animal, preclinical imaging uses almost the same technologies in terms of hardware and software settings as for human patients, and hence, might result in a more rapid translation. In this perspective, magnetic resonance imaging might be the most translatable technique, since only in rare cases does it require the use of contrast agents, and when not, sequences developed in the lab can be readily applied to patients, thanks to their non-invasiveness. The wide range of sequences can give much useful information on the anatomy and pathophysiology of oncologic lesions in different body districts. This review aims to underline the versatility of this imaging technique and its various approaches, reporting the latest preclinical studies on thyroid, breast, and prostate cancers, both on small laboratory animals and on human patients, according to our previous and ongoing research lines.

show abstract

Combining multiparametric MRI with receptor information to optimize prediction of pathologic response to neoadjuvant therapy in breast cancer: preliminary results

Cited by 5 publications

References 61 publications

Texture Analysis of F-18 Fluciclovine PET/CT to Predict Biochemically Recurrent Prostate Cancer: Initial Results

Texture Analysis of F-18 Fluciclovine PET/CT to Predict Biochemically Recurrent Prostate Cancer: Initial Results

Role of MRI to Assess Response to Neoadjuvant Therapy for Breast Cancer

Magnetic Resonance Imaging for Translational Research in Oncology

Contact Info

Product

Resources

About