Multi-omics staging of locally advanced rectal cancer predicts treatment response: a pilot study.

Treatment response assessment of rectal cancer patients is a critical component of personalized cancer care and it allows to identify suitable candidates for organ-preserving strategies. This pilot study employed a novel multi-omics approach combining MRI-based radiomic features and untargeted metabolomics to infer treatment response at staging. The metabolic signature highlighted how tumor cell viability is predictively down-regulated, while the response to oxidative stress was up-regulated in responder patients, showing significantly reduced oxoproline values at baseline compared to non-responder patients (p-value < 10-4). Tumors with a high degree of texture homogeneity, as assessed by radiomics, were more likely to achieve a major pathological response (p-value < 10-3). A machine learning classifier was implemented to summarize the multi-omics information and discriminate responders and non-responders. Combining all available radiomic and metabolomic features, the classifier delivered an AUC of 0.864 (± 0.083, p-value < 10-3) with a best-point sensitivity of 90.9% and a specificity of 81.8%. Our results suggest that a multi-omics approach, integrating radiomics and metabolomic data, can enhance the predictive value of standard MRI and could help to avoid unnecessary surgical treatments and their associated long-term complications.

MRI-based clinical-radiomics model predicts tumor response before treatment in locally advanced rectal cancer.

Neoadjuvant chemo-radiotherapy (CRT) followed by total mesorectal excision (TME) represents the standard treatment for patients with locally advanced (≥ T3 or N+) rectal cancer (LARC). Approximately 15% of patients with LARC shows a complete response after CRT. The use of pre-treatment MRI as predictive biomarker could help to increase the chance of organ preservation by tailoring the neoadjuvant treatment. We present a novel machine learning model combining pre-treatment MRI-based clinical and radiomic features for the early prediction of treatment response in LARC patients. MRI scans (3.0 T, T2-weighted) of 72 patients with LARC were included. Two readers independently segmented each tumor. Radiomic features were extracted from both the "tumor core" (TC) and the "tumor border" (TB). Partial least square (PLS) regression was used as the multivariate, machine learning, algorithm of choice and leave-one-out nested cross-validation was used to optimize hyperparameters of the PLS. The MRI-Based "clinical-radiomic" machine learning model properly predicted the treatment response (AUC = 0.793, p = 5.6 × 10-5). Importantly, the prediction improved when combining MRI-based clinical features and radiomic features, the latter extracted from both TC and TB. Prospective validation studies in randomized clinical trials are warranted to better define the role of radiomics in the development of rectal cancer precision medicine.

Diagnostic accuracy of biparametric vs multiparametric MRI in clinically significant prostate cancer: Comparison between readers with different experience.

BACKGROUND: MRI plays a crucial role to identify men with a high likelihood of clinically significant prostate cancer who require immediate biopsy. The added value of DCE MRI in combination with T2-weighted imaging and DWI is controversial (risks related to gadolinium administration, duration of MR exam, financial burden, effects on diagnostic performance). A comparison of a biparametric and a standard multiparametric MR imaging protocol, taking into account the different experience of the readers, may help to choose the best MR approach regarding diagnostic performance. PURPOSE: To determine the added value of dynamic contrasted-enhanced imaging (DCE) over T2-weighted imaging (T2-WI) and diffusion weighted imaging (DWI) for the detection of clinically significant prostate cancer, and to evaluate how it affects the diagnostic performance of three readers with different grade of experience in prostate imaging. MATERIALS AND METHODS: Eighty-five patients underwent prostate MR examination at 1.5 T MR scanner performed because of elevated prostate-specific antigen level and/or suspicion of prostate cancer at digital rectal examination. Two MR images sets (Set 1 = biparametric, Set 2 = multiparametric) were retrospectively and independently scored by three radiologists with 7, 3 and 1 years of experience in prostate MR imaging respectively, according to PI-RADS v2. Sensitivity, specificity, positive predictive value, and negative predictive value were calculated by dichotomizing reader scores. Receiver operating characteristic (ROC) analysis was performed and areas under the curve (AUCs) were calculated for each reader and image set. A comparison of ROC curves was performed to test the difference between the areas under the ROC curves among the three readers. RESULTS: There was no significant difference regarding the detection of clinically significant tumor among the three readers between the two image sets. The AUC for the bi-parametric and multi-parametric MR imaging protocol was respectively 0.68-0.72 (Reader 1), 0.72-0.70 (Reader 2) and 0.60-0.54 (Reader 3). ROC curve comparison revealed no statistically significant differences for each protocol among the most experienced (Reader 1) and the other readers (Readers 2-3). CONCLUSION: The diagnostic accuracy of a bi-parametric MR imaging protocol consisting of T2-weighted imaging and DWI is comparable with that of a standard multi-parametric imaging protocol for the detection of clinically significant prostate cancer. The experience of the reader does not significantly modify the diagnostic performance of both MR protocols.