Magnetic resonance imaging patterns of tumor response to chemotherapy in desmoid-type fibromatosis.

BACKGROUND: We aimed to investigate changes in volume and MRI T2-weighted intensity in desmoid-type fibromatosis (DF) receiving methotrexate plus vinca-alkaloids (MTX-VA) at Istituto Nazionale dei Tumori, Milan. METHODS: All cases of sporadic DF treated with MTX-VA from 1999 to 2019 were reviewed. MRIs at baseline, 6 and 12 months of chemotherapy and at treatment withdrawal were retrospectively reviewed, contouring the tumor lesion and measuring diameters, volume, and mean T2-signal intensity (normalized to muscle) changes. These parameters were also evaluated according to clinical variables. RESULTS: Thirty-two DF patients were identified. Best RECIST response was: 25% partial response, 69% stable disease, 6% progression. A ≥65% tumor volume reduction was observed in 38%, <65% reduction in 53%, an increase in 9%. 22% had RECIST stable disease with a ≥65% tumor volume reduction. T2-signal intensity decreased by ≥50% in 47%, <50% in 41% and increased in 12%. In patients with symptomatic improvement while on therapy and in patients maintaining symptomatic improvement during follow-up, median T2-signal intensity showed a reduction along the time points (3.0, 1.9, 1.2, 1.1; 2.9, 2.0, 1.2, 1.2, respectively); in patients without symptomatic improvement and in those clinically progressing during follow-up, a reduction was not observed. High T2-signal intensity at baseline was observed in patients showing RECIST progression during follow-up. CONCLUSIONS: In this series, RECIST detected a lower proportion of responses as compared to volumetric and T2-signal changes. T2-signal reduction seemed to better reflect symptomatic improvement. High T2-signal intensity at baseline was related to a higher proportion of further progression.

MRI radiomics-based machine-learning classification of bone chondrosarcoma.

PURPOSE: To evaluate the diagnostic performance of machine learning for discrimination between low-grade and high-grade cartilaginous bone tumors based on radiomic parameters extracted from unenhanced magnetic resonance imaging (MRI). METHODS: We retrospectively enrolled 58 patients with histologically-proven low-grade/atypical cartilaginous tumor of the appendicular skeleton (n = 26) or higher-grade chondrosarcoma (n = 32, including 16 appendicular and 16 axial lesions). They were randomly divided into training (n = 42) and test (n = 16) groups for model tuning and testing, respectively. All tumors were manually segmented on T1-weighted and T2-weighted images by drawing bidimensional regions of interest, which were used for first order and texture feature extraction. A Random Forest wrapper was employed for feature selection. The resulting dataset was used to train a locally weighted ensemble classifier (AdaboostM1). Its performance was assessed via 10-fold cross-validation on the training data and then on the previously unseen test set. Thereafter, an experienced musculoskeletal radiologist blinded to histological and radiomic data qualitatively evaluated the cartilaginous tumors in the test group. RESULTS: After feature selection, the dataset was reduced to 4 features extracted from T1-weighted images. AdaboostM1 correctly classified 85.7 % and 75 % of the lesions in the training and test groups, respectively. The corresponding areas under the receiver operating characteristic curve were 0.85 and 0.78. The radiologist correctly graded 81.3 % of the lesions. There was no significant difference in performance between the radiologist and machine learning classifier (P = 0.453). CONCLUSIONS: Our machine learning approach showed good diagnostic performance for classification of low-to-high grade cartilaginous bone tumors and could prove a valuable aid in preoperative tumor characterization.

Generative models: an upcoming innovation in musculoskeletal radiology? A preliminary test in spine imaging.

BACKGROUND: Deep learning is a ground-breaking technology that is revolutionising many research and industrial fields. Generative models are recently gaining interest. Here, we investigate their potential, namely conditional generative adversarial networks, in the field of magnetic resonance imaging (MRI) of the spine, by performing clinically relevant benchmark cases. METHODS: First, the enhancement of the resolution of T2-weighted (T2W) images (super-resolution) was tested. Then, automated image-to-image translation was tested in the following tasks: (1) from T1-weighted to T2W images of the lumbar spine and (2) vice versa; (3) from T2W to short time inversion-recovery (STIR) images; (4) from T2W to turbo inversion recovery magnitude (TIRM) images; (5) from sagittal standing x-ray projections to T2W images. Clinical and quantitative assessments of the outputs by means of image quality metrics were performed. The training of the models was performed on MRI and x-ray images from 989 patients. RESULTS: The performance of the models was generally positive and promising, but with several limitations. The number of disc protrusions or herniations showed good concordance (κ = 0.691) between native and super-resolution images. Moderate-to-excellent concordance was found when translating T2W to STIR and TIRM images (κ ≥ 0.842 regarding disc degeneration), while the agreement was poor when translating x-ray to T2W images. CONCLUSIONS: Conditional generative adversarial networks are able to generate perceptually convincing synthetic images of the spine in super-resolution and image-to-image translation tasks. Taking into account the limitations of the study, deep learning-based generative methods showed the potential to be an upcoming innovation in musculoskeletal radiology.

Synchronous colorectal cancer using CT colonography vs. other means: a systematic review and meta-analysis.

OBJECTIVES: The objective of our study was to systematically review the evidence about synchronous colorectal cancer diagnosed with or without computed tomography colonography (CTC). MATERIALS AND METHODS: Two systematic searches were performed (PubMed and EMBASE) for studies reporting the prevalence of synchronous colorectal cancer (CRC): one considering patients who underwent CTC and the another one considering patients who did not undergo CTC. A three-level analysis was performed to determine the prevalence of patients with synchronous CRC in both groups of studies. Heterogeneity was explored for multiple variables. Pooled prevalence and 95% confidence interval (CI) were calculated. A quality assessment (STROBE) was done for the studies. RESULTS: For CTC studies, among 2645 articles initially found, 21 including 1673 patients, published from 1997 to 2018, met the inclusion criteria. For non-CTC studies, among 6192 articles initially found, 27 including 111,873 patients published from 1974 to 2015 met the inclusion criteria. The pooled synchronous CRC prevalence was 5.7% (95% CI 4.7%-7.1%) for CTC studies, and 3.9% (95% CI 3.3%-4.4%) for non-CTC studies, with a significant difference (p = 0.004). A low heterogeneity was found for the CTC group (I2 = 10.3%), whereas a high heterogeneity was found in the non-CTC group of studies (I2 = 93.5%), and no significant explanatory variables were found. Of the 22 STROBE items, a mean of 18 (82%) was fulfilled by CTC studies, and a mean of 16 (73%) by non-CTC studies. CONCLUSIONS: The prevalence of synchronous CRC was about 4-6%. The introduction of CTC is associated with a significant increase of the prevalence of synchronous CRCs.

The prostate cancer focal therapy.

Despite prostate cancer (PCa) is the leading form of non-cutaneous cancer in men, most patients with PCa die with disease rather than of the disease. Therefore, the risk of overtreatment should be considered by clinicians who have to distinguish between patients with high risk PCa (who would benefit from radical treatment) and patients who may be managed more conservatively, such as through active surveillance or emerging focal therapy (FT). The aim of FT is to eradicate clinically significant disease while protecting key genito-urinary structures and function from injury. While effectiveness studies comparing FT with conventional care options are still lacking, the rationale supporting FT relies on evidence-based advances such as the understanding of the index lesion's central role in the natural history of the PCa and the improvement of multiparametric magnetic resonance imaging (mpMRI) in the detection and risk stratification of PCa. In this literature review, we want to highlight the rationale for FT in PCa management and the current evidence on patient eligibility. Furthermore, we summarize the best imaging modalities to localize the target lesion, describe the current FT techniques in PCa, provide an update on their oncological outcomes and highlight trends for future research.

Diverticular Disease of the Colon: News From Imaging.

Different scenarios embrace computed tomography imaging and diverticula, including asymptomatic (diverticulosis) and symptomatic patients (acute diverticulitis, follow-up of acute diverticulitis, chronic diverticulitis). If the role of computed tomography is validated and widely supported by evidence in case of acute diverticulitis, this is not the case of patients in their follow-up for acute diverticulitis or with symptoms related to diverticula, but without acute inflammation. In these settings, computed tomography colonography is gaining consensus as the preferred radiologic test.