The Effectiveness of an Adaptive Method to Analyse the Transition between Tumour and Peritumour for Answering Two Clinical Questions in Cancer Imaging.

Based on the well-known role of peritumour characterization in cancer imaging to improve the early diagnosis and timeliness of clinical decisions, this study innovated a state-of-the-art approach for peritumour analysis, mainly relying on extending tumour segmentation by a predefined fixed size. We present a novel, adaptive method to investigate the zone of transition, bestriding tumour and peritumour, thought of as an annular-like shaped area, and detected by analysing gradient variations along tumour edges. For method validation, we applied it on two datasets (hepatocellular carcinoma and locally advanced rectal cancer) imaged by different modalities and exploited the zone of transition regions as well as the peritumour ones derived by adopting the literature approach for building predictive models. To measure the zone of transition's benefits, we compared the predictivity of models relying on both "standard" and novel peritumour regions. The main comparison metrics were informedness, specificity and sensitivity. As regards hepatocellular carcinoma, having circular and regular shape, all models showed similar performance (informedness = 0.69, sensitivity = 84%, specificity = 85%). As regards locally advanced rectal cancer, with jagged contours, the zone of transition led to the best informedness of 0.68 (sensitivity = 89%, specificity = 79%). The zone of transition advantages include detecting the peritumour adaptively, even when not visually noticeable, and minimizing the risk (higher in the literature approach) of including adjacent diverse structures, which was clearly highlighted during image gradient analysis.

An Apparent Diffusion Coefficient-Based Machine Learning Model Can Improve Prostate Cancer Detection in the Grey Area of the Prostate Imaging Reporting and Data System Category 3: A Single-Centre Experience.

The Prostate Imaging and Reporting Data System (PI-RADS) has a key role in the management of prostate cancer (PCa). However, the clinical interpretation of PI-RADS 3 score lesions may be challenging and misleading, thus postponing PCa diagnosis to biopsy outcome. Multiparametric magnetic resonance imaging (mpMRI) radiomic analysis may represent a stand-alone noninvasive tool for PCa diagnosis. Hence, this study aims at developing a mpMRI-based radiomic PCa diagnostic model in a cohort of PI-RADS 3 lesions. We enrolled 133 patients with 155 PI-RADS 3 lesions, 84 of which had PCa confirmation by fusion biopsy. Local radiomic features were generated from apparent diffusion coefficient maps, and the four most informative were selected using LASSO, the Wilcoxon rank-sum test (p < 0.001), and support vector machines (SVMs). The selected features where augmented and used to train an SVM classifier, externally validated on a holdout subset. Linear and second-order polynomial kernels were exploited, and their predictive performance compared through receiver operating characteristics (ROC)-related metrics. On the test set, the highest performance, equally for both kernels, was specificity = 76%, sensitivity = 78%, positive predictive value = 80%, and negative predictive value = 74%. Our findings substantially improve radiologist interpretation of PI-RADS 3 lesions and let us advance towards an image-driven PCa diagnosis.

Radiomic Features from Post-Operative 18F-FDG PET/CT and CT Imaging Associated with Locally Recurrent Rectal Cancer: Preliminary Findings.

Locally Recurrent Rectal Cancer (LRRC) remains a major clinical concern; it rapidly invades pelvic organs and nerve roots, causing severe symptoms. Curative-intent salvage therapy offers the only potential for cure but it has a higher chance of success when LRRC is diagnosed at an early stage. Imaging diagnosis of LRRC is very challenging due to fibrosis and inflammatory pelvic tissue, which can mislead even the most expert reader. This study exploited a radiomic analysis to enrich, through quantitative features, the characterization of tissue properties, thus favoring an accurate detection of LRRC by Computed Tomography (CT) and 18F-FDG-Positron Emission Tomography/CT (PET/CT). Of 563 eligible patients undergoing radical resection (R0) of primary RC, 57 patients with suspected LRRC were included, 33 of which were histologically confirmed. After manually segmenting suspected LRRC in CT and PET/CT, 144 Radiomic Features (RFs) were generated, and RFs were investigated for univariate significant discriminations (Wilcoxon rank-sum test, p < 0.050) of LRRC from NO LRRC. Five RFs in PET/CT (p < 0.017) and two in CT (p < 0.022) enabled, individually, a clear distinction of the groups, and one RF was shared by PET/CT and CT. As well as confirming the potential role of radiomics to advance LRRC diagnosis, the aforementioned shared RF describes LRRC as tissues having high local inhomogeneity due to the evolving tissue's properties.

Beyond Multiparametric MRI and towards Radiomics to Detect Prostate Cancer: A Machine Learning Model to Predict Clinically Significant Lesions.

The risk of misclassifying clinically significant prostate cancer (csPCa) by multiparametric magnetic resonance imaging is consistent, also using the updated PIRADS score and although different definitions of csPCa, patients with Gleason Grade group (GG) ≥ 3 have a significantly worse prognosis. This study aims to develop a machine learning model predicting csPCa (i.e., any GG ≥ 3 lesion at target biopsy) by mpMRI radiomic features and analyzing similarities between GG groups. One hundred and two patients with 117 PIRADS ≥ 3 lesions at mpMRI underwent target+systematic biopsy, providing histologic diagnosis of PCa, 61 GG < 3 and 56 GG ≥ 3. Features were generated locally from an apparent diffusion coefficient and selected, using the LASSO method and Wilcoxon rank-sum test (p < 0.001), to achieve only four features. After data augmentation, the features were exploited to train a support vector machine classifier, subsequently validated on a test set. To assess the results, Kruskal−Wallis and Wilcoxon rank-sum tests (p < 0.001) and receiver operating characteristic (ROC)-related metrics were used. GG1 and GG2 were equivalent (p = 0.26), whilst clear separations between either GG[1,2] and GG ≥ 3 exist (p < 10−6). On the test set, the area under the curve = 0.88 (95% CI, 0.68−0.94), with positive and negative predictive values being 84%. The features retain a histological interpretation. Our model hints at GG2 being much more similar to GG1 than GG ≥ 3.

Automatically Extracted Machine Learning Features from Preoperative CT to Early Predict Microvascular Invasion in HCC: The Role of the Zone of Transition (ZOT).

BACKGROUND: Microvascular invasion (MVI) is a consolidated predictor of hepatocellular carcinoma (HCC) recurrence after treatments. No reliable radiological imaging findings are available for preoperatively diagnosing MVI, despite some progresses of radiomic analysis. Furthermore, current MVI radiomic studies have not been designed for small HCC nodules, for which a plethora of treatments exists. This study aimed to identify radiomic MVI predictors in nodules ≤3.0 cm by analysing the zone of transition (ZOT), crossing tumour and peritumour, automatically detected to face the uncertainties of radiologist's tumour segmentation. METHODS: The study considered 117 patients imaged by contrast-enhanced computed tomography; 78 patients were finally enrolled in the radiomic analysis. Radiomic features were extracted from the tumour and the ZOT, detected using an adaptive procedure based on local image contrast variations. After data oversampling, a support vector machine classifier was developed and validated. Classifier performance was assessed using receiver operating characteristic (ROC) curve analysis and related metrics. RESULTS: The original 89 HCC nodules (32 MVI+ and 57 MVI-) became 169 (62 MVI+ and 107 MVI-) after oversampling. Of the four features within the signature, three are ZOT heterogeneity measures regarding both arterial and venous phases. On the test set (19MVI+ and 33MVI-), the classifier predicts MVI+ with area under the curve of 0.86 (95%CI (0.70-0.93), p∼10-5), sensitivity = 79% and specificity = 82%. The classifier showed negative and positive predictive values of 87% and 71%, respectively. CONCLUSIONS: The classifier showed the highest diagnostic performance in the literature, disclosing the role of ZOT heterogeneity in predicting the MVI+ status.

Human, All Too Human? An All-Around Appraisal of the "Artificial Intelligence Revolution" in Medical Imaging.

Artificial intelligence (AI) has seen dramatic growth over the past decade, evolving from a niche super specialty computer application into a powerful tool which has revolutionized many areas of our professional and daily lives, and the potential of which seems to be still largely untapped. The field of medicine and medical imaging, as one of its various specialties, has gained considerable benefit from AI, including improved diagnostic accuracy and the possibility of predicting individual patient outcomes and options of more personalized treatment. It should be noted that this process can actively support the ongoing development of advanced, highly specific treatment strategies (e.g., target therapies for cancer patients) while enabling faster workflow and more efficient use of healthcare resources. The potential advantages of AI over conventional methods have made it attractive for physicians and other healthcare stakeholders, raising much interest in both the research and the industry communities. However, the fast development of AI has unveiled its potential for disrupting the work of healthcare professionals, spawning concerns among radiologists that, in the future, AI may outperform them, thus damaging their reputations or putting their jobs at risk. Furthermore, this development has raised relevant psychological, ethical, and medico-legal issues which need to be addressed for AI to be considered fully capable of patient management. The aim of this review is to provide a brief, hopefully exhaustive, overview of the state of the art of AI systems regarding medical imaging, with a special focus on how AI and the entire healthcare environment should be prepared to accomplish the goal of a more advanced human-centered world.

Reproducibility of CT-based radiomic features against image resampling and perturbations for tumour and healthy kidney in renal cancer patients.

Computed Tomography (CT) is widely used in oncology for morphological evaluation and diagnosis, commonly through visual assessments, often exploiting semi-automatic tools as well. Well-established automatic methods for quantitative imaging offer the opportunity to enrich the radiologist interpretation with a large number of radiomic features, which need to be highly reproducible to be used reliably in clinical practice. This study investigates feature reproducibility against noise, varying resolutions and segmentations (achieved by perturbing the regions of interest), in a CT dataset with heterogeneous voxel size of 98 renal cell carcinomas (RCCs) and 93 contralateral normal kidneys (CK). In particular, first order (FO) and second order texture features based on both 2D and 3D grey level co-occurrence matrices (GLCMs) were considered. Moreover, this study carries out a comparative analysis of three of the most commonly used interpolation methods, which need to be selected before any resampling procedure. Results showed that the Lanczos interpolation is the most effective at preserving original information in resampling, where the median slice resolution coupled with the native slice spacing allows the best reproducibility, with 94.6% and 87.7% of features, in RCC and CK, respectively. GLCMs show their maximum reproducibility when used at short distances.

The Primacy of High B-Value 3T-DWI Radiomics in the Prediction of Clinically Significant Prostate Cancer.

Predicting clinically significant prostate cancer (csPCa) is crucial in PCa management. 3T-magnetic resonance (MR) systems may have a novel role in quantitative imaging and early csPCa prediction, accordingly. In this study, we develop a radiomic model for predicting csPCa based solely on native b2000 diffusion weighted imaging (DWIb2000) and debate the effectiveness of apparent diffusion coefficient (ADC) in the same task. In total, 105 patients were retrospectively enrolled between January-November 2020, with confirmed csPCa or ncsPCa based on biopsy. DWIb2000 and ADC images acquired with a 3T-MRI were analyzed by computing 84 local first-order radiomic features (RFs). Two predictive models were built based on DWIb2000 and ADC, separately. Relevant RFs were selected through LASSO, a support vector machine (SVM) classifier was trained using repeated 3-fold cross validation (CV) and validated on a holdout set. The SVM models rely on a single couple of uncorrelated RFs (ρ < 0.15) selected through Wilcoxon rank-sum test (p ≤ 0.05) with Holm-Bonferroni correction. On the holdout set, while the ADC model yielded AUC = 0.76 (95% CI, 0.63-0.96), the DWIb2000 model reached AUC = 0.84 (95% CI, 0.63-0.90), with specificity = 75%, sensitivity = 90%, and informedness = 0.65. This study establishes the primary role of 3T-DWIb2000 in PCa quantitative analyses, whilst ADC can remain the leading sequence for detection.

The Heterogeneity of Skewness in T2W-Based Radiomics Predicts the Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer.

Our study aimed to investigate whether radiomics on MRI sequences can differentiate responder (R) and non-responder (NR) patients based on the tumour regression grade (TRG) assigned after surgical resection in locally advanced rectal cancer (LARC) treated with neoadjuvant chemoradiotherapy (nCRT). Eighty-five patients undergoing primary staging with MRI were retrospectively evaluated, and 40 patients were finally selected. The ROIs were manually outlined in the tumour site on T2w sequences in the oblique-axial plane. Based on the TRG, patients were grouped as having either a complete or a partial response (TRG = (0,1), n = 15). NR patients had a minimal or poor nCRT response (TRG = (2,3), n = 25). Eighty-four local first-order radiomic features (RFs) were extracted from tumour ROIs. Only single RFs were investigated. Each feature was selected using univariate analysis guided by a one-tailed Wilcoxon rank-sum. ROC curve analysis was performed, using AUC computation and the Youden index (YI) for sensitivity and specificity. The RF measuring the heterogeneity of local skewness of T2w values from tumour ROIs differentiated Rs and NRs with a p-value ≈ 10-5; AUC = 0.90 (95%CI, 0.73-0.96); and YI = 0.68, corresponding to 80% sensitivity and 88% specificity. In conclusion, higher heterogeneity in skewness maps of the baseline tumour correlated with a greater benefit from nCRT.