Development and validation of a clinical decision support system based on PSA, microRNAs, and MRI for the detection of prostate cancer

OBJECTIVES

The aims of this study are to develop and validate a clinical decision support system based on demographics, prostate-specific antigen (PSA), microRNA (miRNA), and MRI for the detection of prostate cancer (PCa) and clinical significant (cs) PCa, and to assess if this system performs better compared to MRI alone.

METHODS

This retrospective, multicenter, observational study included 222 patients (mean age 66, range 46-75 years) who underwent prostate MRI, miRNA (let-7a-5p and miR-103a-3p) assessment, and biopsy. Monoparametric and multiparametric models including age, PSA, miRNA, and MRI outcome were trained on 65% of the data and then validated on the remaining 35% to predict both PCa (any Gleason grade [GG]) and csPCa (GG ≥ 2 vs GG = 1/negative). Accuracy, sensitivity, specificity, positive and negative predictive value (NPV), and area under the receiver operating characteristic curve were calculated.

RESULTS

MRI outcome was the best predictor in the monoparametric model for both detection of PCa, with sensitivity of 90% (95%CI 73-98%) and NPV of 93% (95%CI 82-98%), and for csPCa identification, with sensitivity of 91% (95%CI 72-99%) and NPV of 95% (95%CI 84-99%). Sensitivity and NPV of PSA + miRNA for the detection of csPCa were not statistically different from the other models including MRI alone.

CONCLUSION

MRI stand-alone yielded the best prediction models for both PCa and csPCa detection in biopsy-naïve patients. The use of miRNAs let-7a-5p and miR-103a-3p did not improve classification performances compared to MRI stand-alone results.

CLINICAL RELEVANCE STATEMENT

The use of miRNA (let-7a-5p and miR-103a-3p), PSA, and MRI in a clinical decision support system (CDSS) does not improve MRI stand-alone performance in the detection of PCa and csPCa.

KEY POINTS

• Clinical decision support systems including MRI improve the detection of both prostate cancer and clinically significant prostate cancer with respect to PSA test and/or microRNA. • The use of miRNAs let-7a-5p and miR-103a-3p did not significantly improve MRI stand-alone performance. • Results of this study were in line with previous works on MRI and microRNA.

Development and Validation of an Explainable Radiomics Model to Predict High-Aggressive Prostate Cancer: A Multicenter Radiomics Study Based on Biparametric MRI

In the last years, several studies demonstrated that low-aggressive (Grade Group (GG) ≤ 2) and high-aggressive (GG ≥ 3) prostate cancers (PCas) have different prognoses and mortality. Therefore, the aim of this study was to develop and externally validate a radiomic model to noninvasively classify low-aggressive and high-aggressive PCas based on biparametric magnetic resonance imaging (bpMRI). To this end, 283 patients were retrospectively enrolled from four centers. Features were extracted from apparent diffusion coefficient (ADC) maps and T2-weighted (T2w) sequences. A cross-validation (CV) strategy was adopted to assess the robustness of several classifiers using two out of the four centers. Then, the best classifier was externally validated using the other two centers. An explanation for the final radiomics signature was provided through Shapley additive explanation (SHAP) values and partial dependence plots (PDP). The best combination was a naïve Bayes classifier trained with ten features that reached promising results, i.e., an area under the receiver operating characteristic (ROC) curve (AUC) of 0.75 and 0.73 in the construction and external validation set, respectively. The findings of our work suggest that our radiomics model could help distinguish between low- and high-aggressive PCa. This noninvasive approach, if further validated and integrated into a clinical decision support system able to automatically detect PCa, could help clinicians managing men with suspicion of PCa.

MI-Common Data Model: Extending Observational Medical Outcomes Partnership-Common Data Model (OMOP-CDM) for Registering Medical Imaging Metadata and Subsequent Curation Processes

PURPOSE

The explosion of big data and artificial intelligence has rapidly increased the need for integrated, homogenized, and harmonized health data. Many common data models (CDMs) and standard vocabularies have appeared in an attempt to offer harmonized access to the available information, with Observational Medical Outcomes Partnership (OMOP)-CDM being one of the most prominent ones, allowing the standardization and harmonization of health care information. However, despite its flexibility, still capturing imaging metadata along with the corresponding clinical data continues to pose a challenge. This challenge arises from the absence of a comprehensive standard representation for image-related information and subsequent image curation processes and their interlinkage with the respective clinical information. Successful resolution of this challenge holds the potential to enable imaging and clinical data to become harmonized, quality-checked, annotated, and ready to be used in conjunction, in the development of artificial intelligence models and other data-dependent use cases.

METHODS

To address this challenge, we introduce medical imaging (MI)-CDM-an extension of the OMOP-CDM specifically designed for registering medical imaging data and curation-related processes. Our modeling choices were the result of iterative numerous discussions among clinical and AI experts to enable the integration of imaging and clinical data in the context of the ProCAncer-I project, for answering a set of clinical questions across the prostate cancer's continuum.

RESULTS

Our MI-CDM extension has been successfully implemented for the use case of prostate cancer for integrating imaging and curation metadata along with clinical information by using the OMOP-CDM and its oncology extension.

CONCLUSION

By using our proposed terminologies and standardized attributes, we demonstrate how diverse imaging modalities can be seamlessly integrated in the future.

Virtual Biopsy in abdominal pathology: where do we stand?

In recent years researchers have explored new ways to obtain information from pathological tissues, also exploring non-invasive techniques, such as virtual biopsy (VB). VB can be defined as a test that provides promising outcomes compared to traditional biopsy by extracting quantitative information from radiological images not accessible through traditional visual inspection. Data is processed in such a way that it can be correlated with the patient’s phenotypic expression, or with molecular patterns and mutations, creating a bridge between traditional radiology, pathology, genomics, and artificial intelligence (AI). Radiomics is the backbone of VB, since it allows the extraction and selection of features from radiological images, feeding them into AI models in order to derive lesions' pathological characteristics and molecular status. Presently the output of VB provides only a gross approximation of the findings of tissue biopsy. However, in the future, with the improvement of imaging resolution and processing techniques, VB could partially substitute the classical surgical or percutaneous biopsy with the advantage of being non-invasive, comprehensive, accounting for lesion heterogeneity, and low cost. In this review, we investigate the concept of VB in abdominal pathology, focusing on its pipeline development and potential benefits.

Hemodynamic effects of heart rate lowering in patients admitted for acute heart failure: the RedRate-HF Study (Reduction of heart Rate in Heart Failure)

BACKGROUND

In patients admitted for acute heart failure (HF) indication for drugs which reduce the heart rate (HR) is debated. The multicentre prospective study Reduction of heart Rate in Heart Failure (RedRate-HF) was designed to analyse the hemodynamic effects of an early reduction of HR in acute HF.

METHODS

Hemodynamic parameters were recorded by using the bioimpedance technique, which was shown to be accurate, highly reproducible and sensitive to intra-observer changes. Lowering HR was obtained by ivabradine 5 mg bd, given 48-72 h after admission on the top of optimized treatment. Patients were followed at 24, 48, 72 h after drug assumption and at hospital discharge.

RESULTS

Twenty patients of a mean age of 67 ± 15 years, BNP at entry 1348 ± 1198 pg/ml were enrolled. Despite a clinical stabilization, after 48-72 h from admission, HR was persistently >70 bpm. Ivabradine was well tolerated in all patients with a significant increase in RR interval from 747 ± 69 ms at baseline to 948 ± 121 ms at discharge, P < 0.0001. Change in HR was associated with a significant increase in stroke volume (baseline 73 ± 22 vs. 84 ± 19 ml at discharge, P = 0.03), and reduction in left cardiac work index (baseline 3.6 ± 1.2 vs. 3.1 ± 1.1 kg/m2 at discharge, P = 0.04). Other measures of heart work were also significantly affected while cardiac output remained unchanged.

CONCLUSION

The strategy of an early lowering of HR in patients admitted for acute HF on top of usual care is feasible and safe. The HR reduction causes a positive increase in stroke volume and may contribute to saving energy without affecting cardiac output.

Twenty-year trends in heart failure among U.S. adults, 1999-2018: The growing impact of obesity and diabetes

BACKGROUND

The aim of this study is to evaluate trends in heart failure (HF) prevalence, impact of accompanying risk factors and use of effective therapeutic regimens during the last two decades in the general adult US population.

METHODS

We analyzed data obtained from the 1999-2018 cycles of the National Health and Nutrition Examination Survey (NHANES). Among a total of 34,403 participants 40 years or older who attended the mobile examination center visit, 1690 reported a diagnosis of HF. Trends in participant features across calendar periods were assessed by linear regression for continuous variables and logistic regression for binary variables.

RESULTS

Prevalence of self-reported HF did not change significantly from 1999 to 2002 to 2015-2018 (~3.5%), while obesity and diabetes showed a progressive increase in prevalence, affecting ~65% and ~ 45% of patients with HF in the most recent calendar period, respectively. In parallel, use of glucose lowering drugs (especially metformin and insulin) as well as statins increased from 1999 to 2010, with significant improvement of the lipid control. A modest improvement in blood pressure control was achieved in association with a significant increase in the use of angiotensin receptor blockers and beta-blockers.

CONCLUSIONS

In the last 20 years, the prevalence of HF in US adults remained stable, while both obesity and diabetes increased, with the two conditions affecting half of patients with HF. Improvements in the control of dyslipidemia and, to a lesser extent, blood pressure, was detected; nonetheless, a significant gap remains in guideline-directed use of HF and diabetes medications.

Effect of dose splitting of a low-volume bowel preparation macrogol-based solution on CT colonography tagging quality

Purpose

To compare examination quality and acceptability of three different low-volume bowel preparation regimens differing in scheduling of the oral administration of a Macrogol-based solution, in patients undergoing computed tomographic colonography (CTC). The secondary aim was to compare CTC quality according to anatomical and patient variables (dolichocolon, colonic diverticulosis, functional and secondary constipation).

Methods

One-hundred-eighty patients were randomized into one of three regimens where PEG was administered, respectively: in a single dose the day prior to (A), or in a fractionated dose 2 (B) and 3 days (C) before the examination. Two experienced radiologists evaluated fecal tagging (FT) density and homogeneity both qualitatively and quantitatively by assessing mean segment density (MSD) and relative standard deviation (RSD). Tolerance to the regimens and patient variables were also recorded.

Results

Compared to B and C, regimen A showed a lower percentage of segments with inadequate FT and a significantly higher median FT density and/or homogeneity scores as well as significantly higher MSD values in some colonic segments. No statistically significant differences were found in tolerance of the preparations. A higher number of inadequate segments were observed in patients with dolichocolon (p < 0.01) and secondary constipation (p < 0.01). Interobserver agreement was high for the assessment of both FT density (k = 0.887) and homogeneity (k = 0.852).

Conclusion

The best examination quality was obtained when PEG was administered the day before CTC in a single session. The presence of dolichocolon and secondary constipation represent a risk factor for the presence of inadequately tagged colonic segments.

A fully automatic deep learning algorithm to segment rectal Cancer on MR images: a multi-center study

The aim of the study is to present and tune a fully automatic deep learning algorithm to segment colorectal cancers (CRC) on MR images, based on a U-Net structure. It is a multicenter study, including 3 different Italian institutions, that used 4 different MRI scanners. Two of them were used for training and tuning the systems, while the other two for the validation. The implemented algorithm consists of a pre-processing step to normalize and to highlight the tumoral area, followed by the CRC segmentation using different U-net structures. Automatic masks were compared with manual segmentations performed by three experienced radiologists, one at each center. The two best performing systems (called mdl2 and mdl3), obtained a median Dice Similarity Coefficient of 0.68(mdl2) - 0.69(mdl3), precision of 0.75(md/2) - 0.71(md/3), and recall of 0.69(mdl2) - 0.73(mdl3) on the validation set. Both systems reached high detection rates, 0.98 and 0.95, respectively, on the validation set. These encouraging results, if confirmed on larger dataset, might improve the management of patients with CRC, since it can be used as a fast and precise tool for further radiomics analyses. Clinical Relevance - To provide a reliable tool able to automatically segment CRC tumors that can be used as first step in future radiomics studies aimed at predicting response to chemotherapy and personalizing treatment.

P240 SHORT–TERM EFFECT OF SGLT2I ON ECHOCARDIOGRAPHIC PARAMETERS IN HFREF PATIENTS TREATED WITH ARNI

Background

Treatment with Sacubitril / Valsartan (ARNI) in patients with heart failure and reduced ejection fraction (HFrEF) promotes significant improvement of left ventricular remodeling along with positive outcomes in terms of hospitalization for heart failure, quality of life and mortality. In a previous study we demonstrated that ARNI significantly modifies myocardial longitudinal strain (GLS), one of the most reliable markers of myocardial contractility. It is still debated whether this effect remains unchanged regardless of the presence of diabetes and if it can be further increased by SGLT2 inhibitors, which in turn have been shown to reduce hospitalizations for heart failure and cardiovascular mortality.

Purpose

of this ongoing study is to measure, in HFrEF patients with or without T2DM, treated with ARNI and SGLT2i, short–term changes (6 months follow up) of the main echocardiographic parameters, including GLS Methods We enrolled 40 outpatients (32 male, age 65 + 10 years, EF 29,7 + 6,5%) on optimized medical treatment with class I medications, including ARNI at the maximum tolerated dose (starting dose 75 + 15mg, maximum titrated dose 190 + 10mg). Population was then divided into three groups: group 1 (20 pts) without T2DM; group 2 (11 pts) with T2DMI; group 3 (9 pts) with T2DM on SGLT2i treatment (4 with empaglifozin 10 mg, 5 with dapaglifozin 10 mg). No hemodynamic or metabolic complications related with therapy were observed, and no patients needed discontinuation or down–titration of therapy All patient underwent echocardiographic study at baseline and after six–month follow–up.

Conclusions

This ongoing study confirms that, in HFrEF patients, ARNI positively modifies left ventricular contraction and remodeling, and this effect is still verified regardless of the presence of T2DM. The association with SGLT2i, conversely, does not appear to provide further positive benefits on remodeling.

MRI-based radiomics to predict response in locally advanced rectal cancer: comparison of manual and automatic segmentation on external validation in a multicentre study

Background

Pathological complete response after neoadjuvant chemoradiotherapy in locally advanced rectal cancer (LARC) is achieved in 15–30% of cases. Our aim was to implement and externally validate a magnetic resonance imaging (MRI)-based radiomics pipeline to predict response to treatment and to investigate the impact of manual and automatic segmentations on the radiomics models.

Methods

Ninety-five patients with stage II/III LARC who underwent multiparametric MRI before chemoradiotherapy and surgical treatment were enrolled from three institutions. Patients were classified as responders if tumour regression grade was 1 or 2 and nonresponders otherwise. Sixty-seven patients composed the construction dataset, while 28 the external validation. Tumour volumes were manually and automatically segmented using a U-net algorithm. Three approaches for feature selection were tested and combined with four machine learning classifiers.

Results

Using manual segmentation, the best result reached an accuracy of 68% on the validation set, with sensitivity 60%, specificity 77%, negative predictive value (NPV) 63%, and positive predictive value (PPV) 75%. The automatic segmentation achieved an accuracy of 75% on the validation set, with sensitivity 80%, specificity 69%, and both NPV and PPV 75%. Sensitivity and NPV on the validation set were significantly higher (p = 0.047) for the automatic versus manual segmentation.

Conclusion

Our study showed that radiomics models can pave the way to help clinicians in the prediction of tumour response to chemoradiotherapy of LARC and to personalise per-patient treatment. The results from the external validation dataset are promising for further research into radiomics approaches using both manual and automatic segmentations.

Supplementary Information

The online version contains supplementary material available at 10.1186/s41747-022-00272-2.

Delta-Radiomics Predicts Response to First-Line Oxaliplatin-Based Chemotherapy in Colorectal Cancer Patients with Liver Metastases

Simple Summary

Oxaliplatin-based chemotherapy remains the mainstay of first-line therapy in patients with metastatic colorectal cancer (mCRC). Unfortunately, only approximately 60% of treated patients achieve response, and half of responders will experience an early onset of disease progression. Furthermore, some individuals will develop a mixed response due to the emergence of resistant tumor subclones. The ability to predicting which patients will acquire resistance could help them avoid the unnecessary toxicity of oxaliplatin therapies. Furthermore, sorting out lesions that do not respond, in the context of an overall good response, could trigger further investigation into their mutational landscape, providing mechanistic insight towards the planning of a more comprehensive treatment. In this study, we validated a delta-radiomics signature capable of predicting response to oxaliplatin-based first-line treatment of individual liver colorectal cancer metastases. Findings could pave the way to a more personalized treatment of patients with mCRC.

Abstract

The purpose of this paper is to develop and validate a delta-radiomics score to predict the response of individual colorectal cancer liver metastases (lmCRC) to first-line FOLFOX chemotherapy. Three hundred one lmCRC were manually segmented on both CT performed at baseline and after the first cycle of first-line FOLFOX, and 107 radiomics features were computed by subtracting textural features of CT at baseline from those at timepoint 1 (TP1). LmCRC were classified as nonresponders (R−) if they showed progression of disease (PD), according to RECIST1.1, before 8 months, and as responders (R+), otherwise. After feature selection, we developed a decision tree statistical model trained using all lmCRC coming from one hospital. The final output was a delta-radiomics signature subsequently validated on an external dataset. Sensitivity, specificity, positive (PPV), and negative (NPV) predictive values in correctly classifying individual lesions were assessed on both datasets. Per-lesion sensitivity, specificity, PPV, and NPV were 99%, 94%, 95%, 99%, 85%, 92%, 90%, and 87%, respectively, in the training and validation datasets. The delta-radiomics signature was able to reliably predict R− lmCRC, which were wrongly classified by lesion RECIST as R+ at TP1, (93%, averaging training and validation set, versus 67% of RECIST). The delta-radiomics signature developed in this study can reliably predict the response of individual lmCRC to oxaliplatin-based chemotherapy. Lesions forecasted as poor or nonresponders by the signature could be further investigated, potentially paving the way to lesion-specific therapies.

Deep learning model for automatic prostate segmentation on bicentric T2w images with and without endorectal coil

Automatic segmentation of the prostate on Magnetic Resonance Imaging (MRI) is one of the topics on which research has focused in recent years as it is a fundamental first step in the building process of a Computer aided diagnosis (CAD) system for cancer detection. Unfortunately, MRI acquired in different centers with different scanners leads to images with different characteristics. In this work, we propose an automatic algorithm for prostate segmentation, based on a U-Net applying transfer learning method in a bi-center setting. First, T2w images with and without endorectal coil from 80 patients acquired at Center A were used as training set and internal validation set. Then, T2w images without endorectal coil from 20 patients acquired at Center B were used as external validation. The reference standard for this study was manual segmentation of the prostate gland performed by an expert operator. The results showed a Dice similarity coefficient >85% in both internal and external validation datasets.Clinical Relevance- This segmentation algorithm could be integrated into a CAD system to optimize computational effort in prostate cancer detection.

Comparison of radiomics approaches to predict resistance to 1st line chemotherapy in liver metastatic colorectal cancer

Colorectal cancer (CRC) has the second-highest tumor incidence and is a leading cause of death by cancer. Nearly 20% of patients with CRC will have metastases (mts) at the time of diagnosis, and more than 50% of patients with CRC develop metastases during their disease. Unfortunately, only 45% of patients after a chemotherapy will respond to treatment. The aim of this study is to develop and validate a machine learning algorithm to predict response of individual liver mts, using CT scans. Understanding which mts will respond or not will help clinicians in providing a more efficient per-lesion treatment based on patient specific response and not only following a standard treatment. A group of 92 patients was enrolled from two Italian institutions. CT scans were collected, and the portal venous phase was manually segmented by an expert radiologist. Then, 75 radiomics features were extracted both from 7x7 ROIs that moved across the image and from the whole 3D mts. Feature selection was performed using a genetic algorithm. Results are presented as a comparison of the two different approaches of features extraction and different classification algorithms. Accuracy (ACC), sensitivity (SE), specificity (SP), negative and positive predictive values (NPV and PPV) were evaluated for all lesions (per-lesion analysis) and patients (per-patient analysis) in the construction and validation sets. Best results were obtained in the per-lesion analysis from the 3D approach using a Support Vector Machine as classifier. We reached on the training set an ACC of 81%, while on test set, we obtained SE of 76%, SP of 67%, PPV of 69% and NPV of 75%. On the validation set a SE of 61%, SP of 60%, PPV of 57% and NPV of 64% were reached. The promising results obtained in the validation dataset should be extended to a larger cohort of patient to further validate our method.Clinical Relevance- to develop a radiomics signatures predicting single liver mts response to therapy. A personalized mts approach is important to avoid unnecessary toxicity offering more suitable treatments and a better quality of life to oncological patients.

Virtual biopsy in prostate cancer: can machine learning distinguish low and high aggressive tumors on MRI?

In the last decades, MRI was proven a useful tool for the diagnosis and characterization of Prostate Cancer (PCa). In the literature, many studies focused on characterizing PCa aggressiveness, but a few have distinguished between low-aggressive (Gleason Grade Group (GG) <=2) and high-aggressive (GG>=3) PCas based on biparametric MRI (bpMRI). In this study, 108 PCas were collected from two different centers and were divided into training, testing, and validation set. From Apparent Diffusion Coefficient (ADC) map and T2-Weighted Image (T2WI), we extracted texture features, both 3D and 2D, and we implemented three different methods of Feature Selection (FS): Minimum Redundance Maximum Relevance (MRMR), Affinity Propagation (AP), and Genetic Algorithm (GA). From the resulting subsets of predictors, we trained Support Vector Machine (SVM), Decision Tree, and Ensemble Learning classifiers on the training set, and we evaluated their prediction ability on the testing set. Then, for each FS method, we chose the best classifier, based on both training and testing performances, and we further assessed their generalization capability on the validation set. Between the three best models, a Decision Tree was trained using only two features extracted from the ADC map and selected by MRMR, achieving, on the validation set, an Area Under the ROC (AUC) equal to 81%, with sensitivity and specificity of 77% and 93%, respectively.Clinical Relevance- Our best model demonstrated to be able to distinguish low-aggressive from high-aggressive PCas with high accuracy. Potentially, this approach could help clinician to noninvasively distinguish between PCas that might need active treatment and those that could potentially benefit from active surveillance, avoiding biopsy-related complications.

A Fully Automatic Artificial Intelligence System Able to Detect and Characterize Prostate Cancer Using Multiparametric MRI: Multicenter and Multi-Scanner Validation

In the last years, the widespread use of the prostate-specific antigen (PSA) blood examination to triage patients who will enter the diagnostic/therapeutic path for prostate cancer (PCa) has almost halved PCa-specific mortality. As a counterpart, millions of men with clinically insignificant cancer not destined to cause death are treated, with no beneficial impact on overall survival. Therefore, there is a compelling need to develop tools that can help in stratifying patients according to their risk, to support physicians in the selection of the most appropriate treatment option for each individual patient. The aim of this study was to develop and validate on multivendor data a fully automated computer-aided diagnosis (CAD) system to detect and characterize PCas according to their aggressiveness. We propose a CAD system based on artificial intelligence algorithms that a) registers all images coming from different MRI sequences, b) provides candidates suspicious to be tumor, and c) provides an aggressiveness score of each candidate based on the results of a support vector machine classifier fed with radiomics features. The dataset was composed of 131 patients (149 tumors) from two different institutions that were divided in a training set, a narrow validation set, and an external validation set. The algorithm reached an area under the receiver operating characteristic (ROC) curve in distinguishing between low and high aggressive tumors of 0.96 and 0.81 on the training and validation sets, respectively. Moreover, when the output of the classifier was divided into three classes of risk, i.e., indolent, indeterminate, and aggressive, our method did not classify any aggressive tumor as indolent, meaning that, according to our score, all aggressive tumors would undergo treatment or further investigations. Our CAD performance is superior to that of previous studies and overcomes some of their limitations, such as the need to perform manual segmentation of the tumor or the fact that analysis is limited to single-center datasets. The results of this study are promising and could pave the way to a prediction tool for personalized decision making in patients harboring PCa.

Computer-Aided Diagnosis Improves the Detection of Clinically Significant Prostate Cancer on Multiparametric-MRI: A Multi-Observer Performance Study Involving Inexperienced Readers

Recently, Computer Aided Diagnosis (CAD) systems have been proposed to help radiologists in detecting and characterizing Prostate Cancer (PCa). However, few studies evaluated the performances of these systems in a clinical setting, especially when used by non-experienced readers. The main aim of this study is to assess the diagnostic performance of non-experienced readers when reporting assisted by the likelihood map generated by a CAD system, and to compare the results with the unassisted interpretation. Three resident radiologists were asked to review multiparametric-MRI of patients with and without PCa, both unassisted and assisted by a CAD system. In both reading sessions, residents recorded all positive cases, and sensitivity, specificity, negative and positive predictive values were computed and compared. The dataset comprised 90 patients (45 with at least one clinically significant biopsy-confirmed PCa). Sensitivity significantly increased in the CAD assisted mode for patients with at least one clinically significant lesion (GS > 6) (68.7% vs. 78.1%, p = 0.018). Overall specificity was not statistically different between unassisted and assisted sessions (94.8% vs. 89.6, p = 0.072). The use of the CAD system significantly increases the per-patient sensitivity of inexperienced readers in the detection of clinically significant PCa, without negatively affecting specificity, while significantly reducing overall reporting time.

Compassionate use of ruxolitinib in patients with SARS-Cov-2 infection not on mechanical ventilation: Short-term effects on inflammation and ventilation

Ruxolitinib is an anti-inflammatory drug that inhibits the Janus kinase-signal transducer (JAK-STAT) pathway on the surface of immune cells. The potential targeting of this pathway using JAK inhibitors is a promising approach in patients affected by coronavirus disease 2019 (COVID-19). Ruxolitinib was provided as a compassionate use in patients consecutively admitted to our institution for severe acute respiratory syndrome-coronavirus 2 (SARS-CoV-2) infection. Inclusion criteria were oxygen saturation less than or equal to 92%, signs of interstitial pneumonia, and no need of mechanical ventilation. Patients received 5 mg b.i.d. of ruxolitinib for 15 days, data were collected at baseline and on days 4, 7, and 15 during treatment. Two main targets were identified, C-reactive protein (CRP) and PaO2 /FiO2 ratio. In the 31 patients who received ruxolitinib, symptoms improved (dyspnea scale) on day 7 in 25 of 31 patients (80.6%); CRP decreased progressively from baseline (79.1 ± 73.4 mg/dl) to day 15 (18.6 ± 33.2, p = 0.022). In parallel with CRP, PO2/FiO2 ratio increased progressively during the 3 steps from 183 ± 95 to 361 ± 144 mmHg (p < 0.001). In those patients with a reduction of polymerase chain reaction less than or equal to 80%, delta increase of the PO2/FiO2 ratio was significantly more pronounced (129 ± 118 vs. 45 ± 35 mmHg, p = 0.02). No adverse side effects were recorded during treatment. In patients hospitalized for COVID-19, compassionate-use of ruxolitinib determined a significant reduction of biomarkers of inflammation, which was associated with a more effective ventilation and reduced need for oxygen support. Data on ruxolitinib reinforces the hypothesis that targeting the hyperinflammation state, may be of prognostic benefit in patients with SARS-CoV-2 infection. Study Highlights WHAT IS THE CURRENT KNOWLEDGE ON THE TOPIC? Some evidence suggest that patients affected by coronavirus disease 2019 (COVID-19) present an exuberant inflammatory response represented by a massive production of type I interferons and different pro-inflammatory cytokines. Nonetheless, as for the present, there are no proven therapeutic agents for COVID-19, in particular anti-inflammatory and antiviral, with a significant and reproducible positive clinical response. WHAT QUESTION DID THIS STUDY ADDRESS? Targeted therapeutic management of pro-inflammatory pathways appears to be a promising strategy against COVID-19, and ruxolitinib, due to its established broad and fast anti-inflammatory effect, appears to be a promising candidate worthy of focused investigations in this field. WHAT DOES THIS STUDY ADD TO OUR KNOWLEDGE? Ruxolitinib rapidly reduces the systemic inflammation, which accompanies the disease, thereby improving respiratory function and the need of oxygen support. This effect may contribute to avoid progression of the disease and the use of invasive ventilation. HOW MIGHT THIS CHANGE CLINICAL PHARMACOLOGY OR TRANSLATIONAL SCIENCE? Data on ruxolitinib contributes the reinforcement of the hypothesis that it is crucial to counteract the early hyperinflammation state, particularly of the lungs, induced by COVID-19 infection.

Nonalcoholic Fatty Liver Disease, Liver Fibrosis and Cardiovascular Disease in the Adult US Population

BACKGROUND

Cardiovascular disease (CVD) risk is higher in patients with nonalcoholic fatty liver disease (NAFLD).

AIM

To evaluate whether this can be attributed to the link between NAFLD and known CVD risk factors or to an independent contribution of liver steatosis and fibrosis.

METHODS

This is an analysis of data from the 2017-2018 cycle of the National Health and Nutrition Examination Survey. We included participants older than 40 years with available data on vibration-controlled transient elastography (VCTE) and without viral hepatitis and significant alcohol consumption. Steatosis and fibrosis were diagnosed by the median value of controlled attenuation parameter (CAP) and liver stiffness measurement (LSM), respectively. History of CVD was self-reported and defined as a composite of coronary artery disease and stroke/transient ischemic attacks.

RESULTS

Among the 2734 included participants, prevalence of NAFLD was 48.6% (95% CI 45.1-51.4), 316 participants (9.7%, 95% CI 8.1-11.6) had evidence of significant liver fibrosis and 371 (11.5%, 95% CI 9.5-13.9) had a history of CVD. In univariate analysis, patients with CVD had a higher prevalence of steatosis (59.6% vs 47.1%, p=0.013), but not fibrosis (12.9% vs 9.3%, p=0.123). After adjustment for potential confounders in a multivariable logistic regression model, neither steatosis nor significant fibrosis were independently associated with CVD and heart failure.

CONCLUSIONS

In this population-based study, we did not identify an independent association between steatosis and fibrosis and CVD. Large prospective cohort studies are needed to provide a more definitive evidence on this topic.

Radiomics predicts response of individual HER2-amplified colorectal cancer liver metastases in patients treated with HER2-targeted therapy

The aim of our study was to develop and validate a machine learning algorithm to predict response of individual HER2-amplified colorectal cancer liver metastases (lmCRC) undergoing dual HER2-targeted therapy. Twenty-four radiomics features were extracted after 3D manual segmentation of 141 lmCRC on pretreatment portal CT scans of a cohort including 38 HER2-amplified patients; feature selection was then performed using genetic algorithms. lmCRC were classified as nonresponders (R-), if their largest diameter increased more than 10% at a CT scan performed after 3 months of treatment, responders (R+) otherwise. Sensitivity, specificity, negative (NPV) and positive (PPV) predictive values in correctly classifying individual lesion and overall patient response were assessed on a training dataset and then validated on a second dataset using a Gaussian naïve Bayesian classifier. Per-lesion sensitivity, specificity, NPV and PPV were 89%, 85%, 93%, 78% and 90%, 42%, 73%, 71% respectively in the testing and validation datasets. Per-patient sensitivity and specificity were 92% and 86%. Heterogeneous response was observed in 9 of 38 patients (24%). Five of nine patients were carriers of nonresponder lesions correctly classified as such by our radiomics signature, including four of seven harboring only one nonresponder lesion. The developed method has been proven effective in predicting behavior of individual metastases to targeted treatment in a cohort of HER2 amplified patients. The model accurately detects responder lesions and identifies nonresponder lesions in patients with heterogeneous response, potentially paving the way to multimodal treatment in selected patients. Further validation will be needed to confirm our findings.

Impact of inter-reader contouring variability on textural radiomics of colorectal liver metastases

BACKGROUND

Radiomics is expected to improve the management of metastatic colorectal cancer (CRC). We aimed at evaluating the impact of liver lesion contouring as a source of variability on radiomic features (RFs).

METHODS

After Ethics Committee approval, 70 liver metastases in 17 CRC patients were segmented on contrast-enhanced computed tomography scans by two residents and checked by experienced radiologists. RFs from grey level co-occurrence and run length matrices were extracted from three-dimensional (3D) regions of interest (ROIs) and the largest two-dimensional (2D) ROIs. Inter-reader variability was evaluated with Dice coefficient and Hausdorff distance, whilst its impact on RFs was assessed using mean relative change (MRC) and intraclass correlation coefficient (ICC). For the main lesion of each patient, one reader also segmented a circular ROI on the same image used for the 2D ROI.

RESULTS

The best inter-reader contouring agreement was observed for 2D ROIs according to both Dice coefficient (median 0.85, interquartile range 0.78-0.89) and Hausdorff distance (0.21 mm, 0.14-0.31 mm). Comparing RF values, MRC ranged 0-752% for 2D and 0-1567% for 3D. For 24/32 RFs (75%), MRC was lower for 2D than for 3D. An ICC > 0.90 was observed for more RFs for 2D (53%) than for 3D (34%). Only 2/32 RFs (6%) showed a variability between 2D and circular ROIs higher than inter-reader variability.

CONCLUSIONS

A 2D contouring approach may help mitigate overall inter-reader variability, albeit stable RFs can be extracted from both 3D and 2D segmentations of CRC liver metastases.

A Convolutional Neural Network based system for Colorectal cancer segmentation on MRI images

The aim of the study is to present a new Convolutional Neural Network (CNN) based system for the automatic segmentation of the colorectal cancer. The algorithm implemented consists of several steps: a pre-processing to normalize and highlights the tumoral area, the classification based on CNNs, and a post-processing aimed at reducing false positive elements. The classification is performed using three CNNs: each of them classifies the same regions of interest acquired from three different MR sequences. The final segmentation mask is obtained by a majority voting. Performances were evaluated using a semi-automatic segmentation revised by an experienced radiologist as reference standard. The system obtained Dice Similarity Coefficient (DSC) of 0.60, Precision (Pr) of 0.76 and Recall (Re) of 0.55 on the testing set. After applying the leave-one-out validation, we obtained a median DSC=0.58, Pr=0.74, Re=0.54. The promising results obtained by this system, if validated on a larger dataset, could strongly improve personalized medicine.

Heart Failure With Mid-range or Recovered Ejection Fraction: Differential Determinants of Transition

The recent definition of an intermediate clinical phenotype of heart failure (HF) based on an ejection fraction (EF) of between 40% and 49%, namely HF with mid-range EF (HFmrEF), has fuelled investigations into the clinical profile and prognosis of this patient group. HFmrEF shares common clinical features with other HF phenotypes, such as a high prevalence of ischaemic aetiology, as in HF with reduced EF (HFrEF), or hypertension and diabetes, as in HF with preserved EF (HFpEF), and benefits from the cornerstone drugs indicated for HFrEF. Among the HF phenotypes, HFmrEF is characterised by the highest rate of transition to either recovery or worsening of the severe systolic dysfunction profile that is the target of disease-modifying therapies, with opposite prognostic implications. This article focuses on the epidemiology, clinical characteristics and therapeutic approaches for HFmrEF, and discusses the major determinants of transition to HFpEF or HFrEF.

An innovative radiomics approach to predict response to chemotherapy of liver metastases based on CT images

Liver metastases (mts) from colorectal cancer (CRC) can have different responses to chemotherapy in the same patient. The aim of this study is to develop and validate a machine learning algorithm to predict response of individual liver mts. 22 radiomic features (RF) were computed on pretreatment portal CT scans following a manual segmentation of mts. RFs were extracted from 7x7 Region of Interests (ROIs) that moved across the image by step of 2 pixels. Liver mts were classified as non-responder (R-) if their largest diameter increased more than 3 mm after 3 months of treatment and responder (R+), otherwise. Features selection (FS) was performed by a genetic algorithm and classification by a Support Vector Machine (SVM) classifier. Sensitivity, specificity, negative (NPV) and positive (PPV) predictive values were evaluated for all lesions in the training and validation sets, separately. On the training set, we obtained sensitivity of 86%, specificity of 67%, PPV of 89% and NPV of 61%, while, on the validation set, we reached a sensitivity of 73%, specificity of 47%, PPV of 64% and NPV of 57%. Specificity was biased by the low number of R- lesions on the validation set. The promising results obtained in the validation dataset should be extended to a larger cohort of patient to further validate our method.Clinical Relevance- to personalize treatment of patients with metastastic colorectal cancer, based on the likelihood of response to chemotherapy of each liver metastasis.

Standardization of CT radiomics features for multi-center analysis: impact of software settings and parameters

The aim of this multicentric study is an inter-center benchmarking, to assess how different set tools applied to the same radiomics workflow affected the radiomics features (RFs) values. This topic is of key importance to start collaboration between different centers and to bring radiomic studies from benchmark to bedside. A per-lesion analysis was performed on 56 metastases (mts) selected from 14 patients. A single radiologist performed the segmentation of all mts, and RFs were extracted from the same segmentation of each mts, using two different software and file formats. Potential sources of discrepancies were evaluated. The intraclass correlation coefficient was used to describe how strongly the same radiomic measurements calculated in the two different centers resemble each other. Moreover, means of the relative changes of each RF were calculated, compared and gradually reduced. We showed that, after matching all formulas, discrepancies in RFs calculation between two centers ranged from 1% to 277%. Therefore, we evaluated other sources of variability using a stepwise approach, which led us to reduce the inter-center discrepancies to 0% for 22/25 RFs and below 2% for 3 RFs out of 25. In this study we demonstrated that different radiomic applications and masks formats might strongly impact the computation of some RFs. Therefore, when dealing with multi-center studies it is mandatory to adopt all strategies that can help in limiting the differences, thus keeping in mind the feasibility of these strategies in large cohort studies.

Renal protection: a leading mechanism for cardiovascular benefit in patients treated with SGLT2 inhibitors

Initially developed as glucose-lowering drugs, sodium-glucose co-transporter type 2 inhibitors (SGLT2i) have demonstrated to be effective agents for the risk reduction of cardiovascular (CV) events in patients with type 2 diabetes mellitus (T2DM). Subsequently, data has emerged showing a significant CV benefit in patients treated with SGLT2i regardless of diabetes status. Renal protection has been initially evaluated in CV randomized trials only as secondary endpoints; nonetheless, the positive results gained have rapidly led to the evaluation of nephroprotection as primary outcome in the CREDENCE trial. Different renal and vascular mechanisms can account for the CV and renal benefits enlightened in recent literature. As clinical guidelines rapidly evolve and the role of SGLT2i appears to become pivotal for CV, T2DM, and kidney disease management, in this review, we analyze the renal effects of SGLT2, the benefits derived from its inhibition, and how this may result in the multiple CV and renal benefits evidenced in recent clinical trials.

Risk stratification tools for heart failure in the diabetes clinic

The advent of Sodium Glucose Transporter 2-inhibitors (SGLT2-i) in recent years gave endocrinologists the opportunity to actively treat and prevent heart failure (HF) in patients with type 2 diabetes (T2DM). While the relationship between T2DM and HF has been extensively reviewed, previous works focused mostly on epidemiology, pathophysiology and treatment of HF in T2DM. The aim of our work was to aid health care professionals in identifying individuals at high risk for this dreadful complication. Recent guidelines recommend to use drugs with proven cardiovascular benefits (Glucagon-like peptide-1 receptor agonists (GLP1-RA) and SGLT2-i) in patients with previous cardiovascular disease (CVD) and to prefer SGLT2-i in patients with known HF. In everyday clinical practice, the choice between these two drug classes in patients without known HF or atherosclerotic CVD is mostly arbitrary and based on the side effect profile. Recently, risk stratification tools to estimate HF incidence have been developed in order to guide treatment with a view to bring precision medicine into diabetes care. With this purpose, we provide a review of the tools able to predict HF incidence for patients in primary CVD prevention as well as risk of future hospitalizations for patients with known HF.

Short-term echocardiographic evaluation by global longitudinal strain in patients with heart failure treated with sacubitril/valsartan

AIMS

The angiotensin receptor neprilysin inhibitor (ARNI) sacubitril/valsartan reduces mortality and hospitalizations in patients with heart failure and reduced ejection fraction (HFrEF). Favourable effects on haemodynamic and functional parameters have been observed in patients with HFrEF undergoing ARNI therapy, using standard transthoracic echocardiography. Global longitudinal strain (GLS) assessment uses a semi-automatic procedure to provide a reliable and repeatable method that improves the detection of early changes of contractile function. We aimed to assess the effects of ARNI on GLS and myocardial mechanics in patients with HFrEF.

METHODS AND RESULTS

Thirty patients with New York Heart Association class II-III HFrEF were treated with ARNI and monitored using standard echocardiographic examination and GLS measurements at baseline, 3 months, and 6 months. ARNI therapy resulted in a significant reduction of ventricular volumes and a significant increase in left ventricular ejection fraction at 6 months but not 3 months by standard transthoracic echocardiography (left ventricular ejection fraction from 28 ± 8% at baseline to 34 ± 12% at 6 months, P < 0.001). Non-significant differences in the size of the left atrium, right ventricular function, and pulmonary pressures were found at 6 months. By using GLS, there was a progressive improvement of all strain parameters by 3 months. The improvement showed a progressive trend over time and maintained significance at 6 months: GLS 4ch -7.2 ± 4.8% at baseline vs. -7.5 ± 3.9% at 3 months (P = 0.025) and - 9.2 ± 5.2% at 6 months (P = 0.0001); AVG GLS -6.9 ± 4.3 at baseline vs. -7.9 ± 4.2 at 3 months (P = 0.04) and - 8.8 ± 4.4 at 6 months (P = 0.035); GLS endo 8.2 ± 4.8 at baseline vs. -9.0 ± 4.8 at 3 months (P = 0.05) and - 10.1 ± 5.1 at 6 months (P = 0.001).

CONCLUSIONS

Sacubitril/valsartan induces an early benefit on left ventricular remodelling, which is captured by myocardial strain and not by standard echocardiography. Strain method represents a practical tool to assess early and minimal variations of left ventricular systolic function.

Abstract 1412: CT texture analysis to predict response to target therapy of hepatic metastases from colorectal cancer

Introduction Colorectal cancer (CRC), the 2nd cause of cancer death worldwide, is an indolent disease with 50% of patients eventually developing liver metastases (mCRC). Repeated cycles of different chemotherapies, combined with surgery in oligo-metastatic cases, are the therapeutic standard in mCRC. However, this strategy is resolutive in less than 15% of cases. Differentiating non- and short-term responders from potentially “cured” patients will spare patients needless toxicity and allow alternative treatments earlier, with conceivable cost and life savings. In this study we aimed to use CT texture analysis (CTTA) to identify specific imaging biomarkers of hepatic metastases, able to predict patient’s response to therapy and overall survival.

Methods We exploited the imaging data-set of the HERACLES trial (NCT03225937): 23 patients with amplified Human Epidermal growth factor Receptor 2 (HER2) mCRC were included in the study. All had received anti HER2 treatment, and underwent CT examination every 8 weeks, until disease progression. CT scans were semi-automatically segmented to extract for each patient all liver metastases. Texture analysis was performed on each segmented area, computing for each lesion 34 quantitative parameters. Both mono-parametric and multi-parametric analysis were assessed to identify features most correlated to therapy response. We also performed a correlative survival (OS) analysis, considering subjects with good survival those with OS &gt; 9 months.

Results In 23 patients we found 124 metastases, 55 of which were classified as responding and 69 as non-responding. Nine parameters reached statistical significance in the mono-parametric analysis (best AUC=0.67, p=0.001), while in the multivariate regression ten parameters were used in the model, achieving and AUC equal to 0.82, with sensitivity of 82% and specificity 72%. For OS analysis, 12 patients were “good” and 11 “poor” survivors. In the mono-parametric analysis “cluster prominence” and “sum entropy” predicted OS with AUC equal to 0.78 and 0.83, respectively. The regression model with two variables (“cluster prominence” and “dissimilarity”) reached a sensitivity of 83% and a specificity of 82%.

Conclusions Our study demonstrated CTTA as a potential biomarker to predict response of hepatic metastases to chemotherapy treatment, possibly saving patients predicted as non-responder from toxicity. Moreover, CTTA could give indications on patients OS, without the need for additional tests.

Acknowledgments This study was funded by the Italian Association for Cancer Research (AIRC), ref. 21091.

Citation Format: Simone Mazzetti, Valentina Giannini, Lorenzo Vassallo, Arianna Defeudis, Angelo Vanzulli, Rita Golfieri, Silvia Marsoni, Daniele Regge. CT texture analysis to predict response to target therapy of hepatic metastases from colorectal cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2019; 2019 Mar 29-Apr 3; Atlanta, GA. Philadelphia (PA): AACR; Cancer Res 2019;79(13 Suppl):Abstract nr 1412.

Radiomics features on CT scans to predict response to HER2-targeted therapy of hepatic metastases from colorectal cancer

e15086

Background: Metastatic Colorectal cancer (mCRC) is the 2nd cause of cancer death worldwide. Repeated cycles of therapies, combined with surgery in oligo-metastatic cases, are the therapeutic standard in mCRC. However, this strategy is seldom resolutive. Different lesions in in the same patient could have different responses to systemic therapy. Recently, CT texture analysis (CTTA) had been shown to potentially provide with prognostic and predictive markers, overcoming the limitations of biopsy sampling in defining tumor heterogeneity. The aim of this study is to use CT texture analysis (CTTA) to identify imaging biomarkers of HER2+ mCRC able to predict lesion response to therapy. Methods: The dataset is composed of 39 extended RAS wild type patients with amplified HER2 mCRC enrolled in the HERACLES trial (NCT03225937) that received either a lapatinib+trastuzumab treatment (n = 23) or a pertuzumab+ trastuzumab-emtansine treatment (n = 16). All patients underwent CT examination every 8 weeks, until disease progression. All mCRC on baseline CT were semi-automatically segmented and quantitative features extracted: size, mean, percentiles, 28 texture features. A logistic regression model was created using: (i) the whole dataset of mCRC as training and test set and (ii) 100 randomly generated training sets (with 70% of responder (R+) mCRC and an equal number of non-responder (R-) mCRC), and 100 test sets including the remaining mCRC. A mCRC was classified as R+ if size decreased (-10%) or was stable (±10%); as R- if size increased (+10%), during subsequent CT scans. Results: A total of 199 metastases were included (75R+ and 124R-). The training set was composed of 53R+ and 53R- mCRC and the test set of 22R+ and 71R- mCRC. Using the whole dataset, the model reached an AUC = 0.82 (sensitivity = 84%, specificity = 70%), while it reached a mean AUC of 0.70 (sensitivity = 68%, specificity = 67%) within the 100 repetitions. Conclusions: CTTA might help in stratifying different behaviors of mCRC, opening the way for lesion-specific therapies, with conceivable cost and life savings. Further extended analysis is needed to better characterize and validate predictive value of these biomarkers.

Takotsubo cardiomyopathy associated with Kounis syndrome: A clinical case of the "ATAK complex"

A 60-year-old female developed cardiac arrest after experiencing an anaphylactic shock during administration of plasma-expanders. An electrocardiogram registered after restoration of sinus rhythm showed mild ST-elevation in the anterior precordial leads and T waves changes followed by appearance of echocardiographic alterations of left ventricular apex kinesis. Coronary angiography revealed normal coronary arteries, and cardiovascular magnetic resonance confirmed apical ballooning with late gadolinium enhancement in the segments with abnormal contractility. This uncommon clinical case confirms how takotsubo and Kounis syndrome may converge in a single nosological entity, the so-called "ATAK complex" (Adrenaline, Tako-Tsubo, Anaphylaxis, and Kounis), with a specific management and prognostic implications. <Learning objective: The Kounis syndrome has a clinical presentation that poses a difficult differential diagnosis with takotsubo cardiomyopathy. Despite recent significant improvements in the understanding of these two clinical conditions, the pathogenesis of these two entities and, in particular, how they may converge into the clinical scenario of the "ATAK complex" remain to be clarified. We believe that this rare clinical case may help physicians in the correct identification and management of this frequently misdiagnosed clinical disease.>.

Predicting locally advanced rectal cancer response to neoadjuvant therapy with 18F-FDG PET and MRI radiomics features

PURPOSE

Pathological complete response (pCR) following neoadjuvant chemoradiotherapy or radiotherapy in locally advanced rectal cancer (LARC) is reached in approximately 15-30% of cases, therefore it would be useful to assess if pretreatment of ¹⁸F-FDG PET/CT and/or MRI texture features can reliably predict response to neoadjuvant therapy in LARC.

METHODS

Fifty-two patients were dichotomized as responder (pR+) or non-responder (pR-) according to their pathological tumor regression grade (TRG) as follows: 22 as pR+ (nine with TRG = 1, 13 with TRG = 2) and 30 as pR- (16 with TRG = 3, 13 with TRG = 4 and 1 with TRG = 5). First-order parameters and 21 second-order texture parameters derived from the Gray-Level Co-Occurrence matrix were extracted from semi-automatically segmented tumors on T2w MRI, ADC maps, and PET/CT acquisitions. The role of each texture feature in predicting pR+ was assessed with monoparametric and multiparametric models.

RESULTS

In the mono-parametric approach, PET homogeneity reached the maximum AUC (0.77; sensitivity = 72.7% and specificity = 76.7%), while PET glycolytic volume and ADC dissimilarity reached the highest sensitivity (both 90.9%). In the multiparametric analysis, a logistic regression model containing six second-order texture features (five from PET and one from T2w MRI) yields the highest predictivity in distinguish between pR+ and pR- patients (AUC = 0.86; sensitivity = 86%, and specificity = 83% at the Youden index).

CONCLUSIONS

If preliminary results of this study are confirmed, pretreatment PET and MRI could be useful to personalize patient treatment, e.g., avoiding toxicity of neoadjuvant therapy in patients predicted pR-.

Computer-aided diagnosis of prostate cancer using multi-parametric MRI: comparison between PUN and Tofts models

Computer-aided diagnosis (CAD) systems are increasingly being used in clinical settings to report multi-parametric magnetic resonance imaging (mp-MRI) of the prostate. Usually, CAD systems automatically highlight cancer-suspicious regions to the radiologist, reducing reader variability and interpretation errors. Nevertheless, implementing this software requires the selection of which mp-MRI parameters can best discriminate between malignant and non-malignant regions. To exploit functional information, some parameters are derived from dynamic contrast-enhanced (DCE) acquisitions. In particular, much CAD software employs pharmacokinetic features, such as K ^trans and k _ep, derived from the Tofts model, to estimate a likelihood map of malignancy. However, non-pharmacokinetic models can be also used to describe DCE-MRI curves, without any requirement for prior knowledge or measurement of the arterial input function, which could potentially lead to large errors in parameter estimation. In this work, we implemented an empirical function derived from the phenomenological universalities (PUN) class to fit DCE-MRI. The parameters of the PUN model are used in combination with T2-weighted and diffusion-weighted acquisitions to feed a support vector machine classifier to produce a voxel-wise malignancy likelihood map of the prostate. The results were all compared to those for a CAD system based on Tofts pharmacokinetic features to describe DCE-MRI curves, using different quality aspects of image segmentation, while also evaluating the number and size of false positive (FP) candidate regions. This study included 61 patients with 70 biopsy-proven prostate cancers (PCa). The metrics used to evaluate segmentation quality between the two CAD systems were not statistically different, although the PUN-based CAD reported a lower number of FP, with reduced size compared to the Tofts-based CAD. In conclusion, the CAD software based on PUN parameters is a feasible means with which to detect PCa, without affecting segmentation quality, and hence it could be successfully applied in clinical settings, improving the automated diagnosis process and reducing computational complexity.

MRI to predict nipple-areola complex (NAC) involvement: An automatic method to compute the 3D distance between the NAC and tumor

OBJECTIVES

To assess the role in predicting nipple-areola complex (NAC) involvement of a newly developed automatic method which computes the 3D tumor-NAC distance.

PATIENTS AND METHODS

Ninety-nine patients scheduled to nipple sparing mastectomy (NSM) underwent magnetic resonance (MR) examination at 1.5 T, including sagittal T2w and dynamic contrast enhanced (DCE)-MR imaging. An automatic method was developed to segment the NAC and the tumor and to compute the 3D distance between them. The automatic measurement was compared with manual axial and sagittal 2D measurements. NAC involvement was defined by the presence of invasive ductal or lobular carcinoma and/or ductal carcinoma in situ or ductal intraepithelial neoplasia (DIN1c - DIN3).

RESULTS

Tumor-NAC distance was computed on 95/99 patients (25 NAC+), as three tumors were not correctly segmented (sensitivity = 97%), and 1 NAC was not detected (sensitivity = 99%). The automatic 3D distance reached the highest area under the receiver operating characteristic (ROC) curve (0.830) with respect to the manual axial (0.676), sagittal (0.664), and minimum distances (0.664). At the best cut-off point of 21 mm, the 3D distance obtained sensitivity = 72%, specificity = 80%, positive predictive value = 56%, and negative predictive value = 89%.

CONCLUSIONS

This method could provide a reproducible biomarker to preoperatively select breast cancer patients candidates to NSM, thus helping surgical planning and intraoperative management of patients.

A computer-aided diagnosis (CAD) scheme for pretreatment prediction of pathological response to neoadjuvant therapy using dynamic contrast-enhanced MRI texture features

OBJECTIVE

To assess whether a computer-aided, diagnosis (CAD) system can predict pathological Complete Response (pCR) to neoadjuvant chemotherapy (NAC) prior to treatment using texture features.

METHODS

Response to treatment of 44 patients was defined according to the histopatology of resected tumour and extracted axillary nodes in two ways: (a) pCR+ (Smith's Grade = 5) vs pCR- (Smith's Grade < 5); (b) pCRN+ (pCR+ and absence of residual lymph node metastases) vs pCRN - . A CAD system was developed to: (i) segment the breasts; (ii) register the DCE-MRI sequence; (iii) detect the lesion and (iv) extract 27 3D texture features. The role of individual texture features, multiparametric models and Bayesian classifiers in predicting patients' response to NAC were evaluated.

RESULTS

A cross-validated Bayesian classifier fed with 6 features was able to predict pCR with a specificity of 72% and a sensitivity of 67%. Conversely, 2 features were used by the Bayesian classifier to predict pCRN, obtaining a sensitivity of 69% and a specificity of 61%.

CONCLUSION

A CAD scheme, that extracts texture features from an automatically segmented 3D mask of the tumour, could predict pathological response to NAC. Additional research should be performed to validate these promising results on a larger cohort of patients and using different classification strategies. Advances in knowledge: This is the first study assessing the role of an automatic CAD system in predicting the pathological response to NAC before treatment. Fully automatic methods represent the backbone of standardized analysis and may help in timely managing patients candidate to NAC.

Big data in oncologic imaging

Cancer is a complex disease and unfortunately understanding how the components of the cancer system work does not help understand the behavior of the system as a whole. In the words of the Greek philosopher Aristotle "the whole is greater than the sum of parts." To date, thanks to improved information technology infrastructures, it is possible to store data from each single cancer patient, including clinical data, medical images, laboratory tests, and pathological and genomic information. Indeed, medical archive storage constitutes approximately one-third of total global storage demand and a large part of the data are in the form of medical images. The opportunity is now to draw insight on the whole to the benefit of each individual patient. In the oncologic patient, big data analysis is at the beginning but several useful applications can be envisaged including development of imaging biomarkers to predict disease outcome, assessing the risk of X-ray dose exposure or of renal damage following the administration of contrast agents, and tracking and optimizing patient workflow. The aim of this review is to present current evidence of how big data derived from medical images may impact on the diagnostic pathway of the oncologic patient.

A fully automatic computer aided diagnosis system for peripheral zone prostate cancer detection using multi-parametric magnetic resonance imaging

Multiparametric (mp)-Magnetic Resonance Imaging (MRI) is emerging as a powerful test to diagnose and stage prostate cancer (PCa). However, its interpretation is a time consuming and complex feat requiring dedicated radiologists. Computer-aided diagnosis (CAD) tools could allow better integration of data deriving from the different MRI sequences in order to obtain accurate, reproducible, non-operator dependent information useful to identify and stage PCa. In this paper, we present a fully automatic CAD system conceived as a 2-stage process. First, a malignancy probability map for all voxels within the prostate is created. Then, a candidate segmentation step is performed to highlight suspected areas, thus evaluating both the sensitivity and the number of false positive (FP) regions detected by the system. Training and testing of the CAD scheme is performed using whole-mount histological sections as the reference standard. On a cohort of 56 patients (i.e. 65 lesions) the area under the ROC curve obtained during the voxel-wise step was 0.91, while, in the second step, a per-patient sensitivity of 97% was reached, with a median number of FP equal to 3 in the whole prostate. The system here proposed could be potentially used as first or second reader to manage patients suspected to have PCa, thus reducing both the radiologist's reporting time and the inter-reader variability. As an innovative setup, it could also be used to help the radiologist in setting the MRI-guided biopsy target.

Texture features on T2-weighted magnetic resonance imaging: new potential biomarkers for prostate cancer aggressiveness

To explore contrast (C) and homogeneity (H) gray-level co-occurrence matrix texture features on T2-weighted (T2w) Magnetic Resonance (MR) images and apparent diffusion coefficient (ADC) maps for predicting prostate cancer (PCa) aggressiveness, and to compare them with traditional ADC metrics for differentiating low- from intermediate/high-grade PCas. The local Ethics Committee approved this prospective study of 93 patients (median age, 65 years), who underwent 1.5 T multiparametric endorectal MR imaging before prostatectomy. Clinically significant (volume ≥0.5 ml) peripheral tumours were outlined on histological sections, contoured on T2w and ADC images, and their pathological Gleason Score (pGS) was recorded. C, H, and traditional ADC metrics (mean, median, 10th and 25th percentile) were calculated on the largest lesion slice, and correlated with the pGS through the Spearman correlation coefficient. The area under the receiver operating characteristic curve (AUC) assessed how parameters differentiate pGS = 6 from pGS ≥ 7. The dataset included 49 clinically significant PCas with a balanced distribution of pGS. The Spearman ρ and AUC values on ADC were: -0.489, 0.823 (mean); -0.522, 0.821 (median); -0.569, 0.854 (10th percentile); -0.556, 0.854 (25th percentile); -0.386, 0.871 (C); 0.533, 0.923 (H); while on T2w they were: -0.654, 0.945 (C); 0.645, 0.962 (H). AUC of H on ADC and T2w, and C on T2w were significantly higher than that of the mean ADC (p = 0.05). H and C calculated on T2w images outperform ADC parameters in correlating with pGS and differentiating low- from intermediate/high-risk PCas, supporting the role of T2w MR imaging in assessing PCa biological aggressiveness.