MRI-based radiomic features for identifying recurrent prostate cancer after proton radiation therapy.

PURPOSE: Magnetic Resonance Imaging (MRI) evaluation of recurrent prostate cancer (PCa) following proton beam therapy is challenging due to radiation-induced tissue changes. This study aimed to evaluate MRI-based radiomic features so as to identify the recurrent PCa after proton therapy. METHODS: We retrospectively studied 12 patients with biochemical recurrence (BCR) following proton therapy. Two experienced radiologists identified prostate lesions from multi-parametric MRI (mpMRI) images post-proton therapy and marked control regions of interest (ROIs) on the contralateral side of the prostate gland. A total of 210 radiomic features were extracted from lesions and control regions on the T2-weighted (T2WI) and Apparent Diffusion Coefficient (ADC) image series. Recursive Feature Elimination with Cross-Validation method (RFE-CV) was used for feature selection. A Multilayer Perceptron (MLP) neural network was developed to classify three classes: cancerous, benign, and healthy tissue. The 12-core biopsy results were used as the gold standard for the segmentations. The classifier performance was measured using specificity, sensitivity, the area under receiver operating characteristic curve (AUC), and other statistical indicators. RESULTS: Based on biopsy results, 10 lesions were identified as PCa recurrence while eight lesions were confirmed to be benign. Ten radiomic features (10/210) were selected to build the multi-class classifier. The radiomics classifier gave an accuracy of 0.83 in identifying cancerous, benign, and healthy tissue with a sensitivity of 0.80 and specificity of 0.85. The model yielded an AUC of 0.87, 95% CI [0.72-1.00] in differentiating cancer from the benign and healthy tissues. CONCLUSIONS: Our proof-of-concept study demonstrates the potential of using radiomic features as part of the differential diagnosis of PCa on mpMRI following proton therapy. The results need to be validated in a larger cohort.

MRI-based nomograms and radiomics in presurgical prediction of extraprostatic extension in prostate cancer: a systematic review.

PURPOSE: Prediction of extraprostatic extension (EPE) is essential for accurate surgical planning in prostate cancer (PCa). Radiomics based on magnetic resonance imaging (MRI) has shown potential to predict EPE. We aimed to evaluate studies proposing MRI-based nomograms and radiomics for EPE prediction and assess the quality of current radiomics literature. METHODS: We used PubMed, EMBASE, and SCOPUS databases to find related articles using synonyms for MRI radiomics and nomograms to predict EPE. Two co-authors scored the quality of radiomics literature using the Radiomics Quality Score (RQS). Inter-rater agreement was measured using the intraclass correlation coefficient (ICC) from total RQS scores. We analyzed the characteristic s of the studies and used ANOVAs to associate the area under the curve (AUC) to sample size, clinical and imaging variables, and RQS scores. RESULTS: We identified 33 studies-22 nomograms and 11 radiomics analyses. The mean AUC for nomogram articles was 0.783, and no significant associations were found between AUC and sample size, clinical variables, or number of imaging variables. For radiomics articles, there were significant associations between number of lesions and AUC (p < 0.013). The average RQS total score was 15.91/36 (44%). Through the radiomics operation, segmentation of region-of-interest, selection of features, and model building resulted in a broader range of results. The qualities the studies lacked most were phantom tests for scanner variabilities, temporal variability, external validation datasets, prospective designs, cost-effectiveness analysis, and open science. CONCLUSION: Utilizing MRI-based radiomics to predict EPE in PCa patients demonstrates promising outcomes. However, quality improvement and standardization of radiomics workflow are needed.

Magnetic Resonance Imaging Virtual Biopsy of Common Solid Renal Masses-A Pictorial Review.

ABSTRACT: The expanded application of radiologic imaging resulted in an increased incidence of renal masses in the recent decade. Clinically, it is difficult to determine the malignant potential of the renal masses, thus resulting in complex management. Image-guided biopsies are the ongoing standard of care to identify molecular variance but are limited by tumor accessibility and heterogeneity. With the evolving importance of individualized cancer therapies, radiomics has displayed promising results in the identification of tumoral mutation status on routine imaging. This article discusses how magnetic resonance imaging features can guide a radiologist toward identifying renal mass characteristics.

Intraindividual Reliability of Opportunistic Computed Tomography-Assessed Adiposity and Skeletal Muscle Among Breast Cancer Patients.

BACKGROUND: Adiposity and skeletal muscle levels assessed on computed tomography (CT) scans are prognostic indicators for patients with breast cancer. However, the intraindividual reliability of temporal changes in body composition assessed on opportunistic CT scans is unclear. METHODS: This retrospective study included 50 patients newly diagnosed with breast cancer who had archived CT scans pre- and postsurgery for breast cancer. The third lumbar CT image was segmented for areas of 3 types of adipose tissues and 5 different densities of skeletal muscles. Mean and percent changes in areas pre- vs postsurgery were compared using Wilcoxon signed rank tests. Intraclass correlation coefficients (ICCs) with 95% confidence intervals were assessed. A 2-sided P less than .05 was considered statistically significant. RESULTS: Mean (SD) age at diagnosis was 58.3 (12.5) years, and the interval between CT scans was 590.6 (536.8) days. Areas for body composition components were unchanged except for intermuscular adipose tissue (mean change = 1.45 cm2, 6.74% increase, P = .008) and very high-density muscle (mean change = -0.37 cm2, 11.08% decrease, P = .01) during the interval. There was strong intraindividual reliability in adipose tissue and skeletal muscle areas on pre- vs postsurgery scans overall (ICC = 0.763-0.998) and for scans collected 3 or less years apart (ICC = 0.802-0.999; 42 patients). CONCLUSIONS: Although some body composition components may change after breast cancer surgery, CT scan assessments of body composition were reliable for a 3-year interval including the surgery. These findings inform measurement characteristics of body composition on opportunistic CT scans of patients undergoing surgery for breast cancer.

Neuroendocrine Neoplasms of the Gynecologic Tract.

Gynecological tract neuroendocrine neoplasms (NEN) are rare, aggressive tumors from endocrine cells derived from the neuroectoderm, neural crest, and endoderm. The primary gynecologic NENs constitute 2% of gynecologic malignancies, and the cervix is the most common site of NEN in the gynecologic tract. The updated WHO classification of gynecologic NEN is based on the Ki-67 index, mitotic index, and tumor characteristics such as necrosis, and brings more uniformity in the terminology of NENs like other disease sites. Imaging plays a crucial role in the staging, triaging, restaging, and surveillance of NENs. The expression of the somatostatin receptors on the surface of neuroendocrine cells forms the basis of increasing evaluation with functional imaging modalities using traditional and new tracers, including 68Ga-DOTA-Somatostatin Analog-PET/CT. Management of NENs involves a multidisciplinary approach. New targeted therapies could improve the paradigm of care for these rare malignancies. This article focuses on the updated staging classifications, clinicopathological characteristics, imaging, and management of gynecologic NENs of the cervix, ovary, endometrium, vagina, and vulva, emphasizing the relatively common cervical neuroendocrine carcinomas among these entities.

Associations of Computed Tomography Image-Assessed Adiposity and Skeletal Muscles with Triple-Negative Breast Cancer.

Obesity measured by anthropometrics is associated with increased risk of triple-negative breast cancer (TNBC). It is unclear to what extent specific adipose tissue components, aside from muscle, are associated with TNBC. This retrospective study included 350 breast cancer patients who received treatment between October 2011 and April 2020 with archived abdominal or pelvic computed tomography (CT) images. We measured the areas of adipose tissue and five-density levels of skeletal muscle on patients' third lumbar vertebra (L3) image. Logistic regression was performed to examine the associations of specific adiposity and skeletal muscles components and a four-category body composition phenotype with the TNBC subtype. Results showed that higher vs. lower areas (3rd vs. 1st tertiles) of visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT) were associated with increased odds of TNBC vs. non-TNBC after adjusting for age, race, stage, tumor grade, tumor size, and skeletal muscle areas (adjusted odds ratio [AOR], 11.25 [95% CI = 3.46-36.52]) and (AOR, 10.34 [95% CI = 2.90-36.90]) respectively. Higher areas of low density muscle was also associated with increased odds of TNBC (AOR, 3.15 [95% CI = 1.05-10.98]). Compared to normal body composition (low adipose tissue/high muscle), high adiposity/high muscle was associated with higher odds of TNBC (AOR, 5.54 [95% CI = 2.12-14.7]). These associations were mainly in premenopausal women and among patients with the CT performed after breast cancer surgery. Specific adipose tissue and low-density muscle can be associated with the TNBC subtype in breast cancer patients. The direction of association warrants confirmation by prospective studies.

Pancreatic neuroendocrine neoplasms: a 2022 update for radiologists.

Pancreatic neuroendocrine neoplasms (PaNENs) are a unique group of pancreatic neoplasms with a wide range of clinical presentations and behaviors. Given their heterogeneous appearance and increasing detection on cross-sectional imaging, it is essential that radiologists understand the variable presentation and distinctions PaNENs display compared to other pancreatic neoplasms. Additionally, some of these neoplasms may be hormonally functional, and it is imperative that radiologists be aware of the common clinical presentations of hormonally active PaNENs. Knowledge of PaNEN pathology and treatments may influence which imaging modality is optimal for each patient. Each imaging modality used for PaNENs has distinct advantages and disadvantages, particularly in different treatment settings. Thus, the focus of this manuscript is to provide an update for the radiologist on PaNEN pathology, imaging, and treatments.

Rectal neuroendocrine neoplasms: what the radiologists should know.

Neuroendocrine neoplasms of the rectum (R-NENs) are rare; however, their incidence has increased almost threefold in the last few decades. Imaging of R-NENs includes two primary categories: anatomic/morphologic imaging comprised of endoscopic ultrasound (EUS), computed tomography (CT), magnetic resonance imaging (MRI), and functional/molecular imaging comprising of planar scintigraphy, single-photon emission computed tomography (SPECT), and positron emission tomography (PET). The management depends on stage, dimension, atypical features, histological grade, and lymphovascular invasion (LVI). Low-risk local R-NENs can be resected endoscopically, and high-risk or locally advanced neoplasms can be treated with radical surgery and lymphadenectomy and/or chemoradiation. The review article focuses on imaging illustrations and discusses applications of different imaging modalities in diagnosing and managing R-NENs.

Mimics and Pitfalls of Primary Ovarian Malignancy Imaging.

The complex anatomy and similarity of imaging features of various pathologies in the pelvis can make accurate radiology interpretation difficult. While prompt recognition of ovarian cancer remains essential, awareness of processes that mimic ovarian tumors can avoid potential misdiagnosis and unnecessary surgery. This article details the female pelvic anatomy and highlights relevant imaging features that mimic extra-ovarian tumors, to help the radiologists accurately build a differential diagnosis of a lesion occupying the adnexa.

A rare complication of pyogenic hepatic abscess after laparoscopic sleeve gastrectomy-case report and literature review emphasizing the role of imaging.

A pyogenic hepatic abscess is an uncommon complication after laparoscopic sleeve gastrectomy (LSG) that can develop secondary to an infected hematoma or a staple line leak due to bacterial seeding. Appropriate screening for and management of a pyogenic hepatic abscess are essential in patients with clinical suspicion for complications after LSG. Early diagnosis is essential as pyogenic hepatic abscess can be fatal if not treated early. Only five cases have been reported in the literature so far. We present a case of pyogenic hepatic abscess that occurred two weeks after LSG in a 46-year-old female without immunosuppressive conditions or early postoperative leak. The abscess was diagnosed by computed tomography (CT) and was successfully treated with antibiotics and CT-guided drainage.

Response criteria for immunotherapy and the radiologic patterns of immune-related adverse events.

Immunotherapy has revolutionized clinical outcomes in both early-stage and advanced-stage malignancies. Immunotherapy has improved patient survival in both solid and hematologic disorders with the potential added benefit of less toxicity compared to conventional cytotoxic chemotherapy. Imaging plays a fundamental role in monitoring treatment response and assessment of immune-related adverse events, e.g. pneumonitis, colitis, etc. Familiarity with the current strategies of immune-related response evaluation and their limitations is essential for radiologists to guide clinicians with their treatment decisions. Radiologists should be aware of the wide spectrum of immune-related adverse events and their various radiological features as well as the patterns of treatment response associated with immunotherapies.

MRI and CT bladder segmentation from classical to deep learning based approaches: Current limitations and lessons.

Precise determination and assessment of bladder cancer (BC) extent of muscle invasion involvement guides proper risk stratification and personalized therapy selection. In this context, segmentation of both bladder walls and cancer are of pivotal importance, as it provides invaluable information to stage the primary tumor. Hence, multiregion segmentation on patients presenting with symptoms of bladder tumors using deep learning heralds a new level of staging accuracy and prediction of the biologic behavior of the tumor. Nevertheless, despite the success of these models in other medical problems, progress in multiregion bladder segmentation, particularly in MRI and CT modalities, is still at a nascent stage, with just a handful of works tackling a multiregion scenario. Furthermore, most existing approaches systematically follow prior literature in other clinical problems, without casting a doubt on the validity of these methods on bladder segmentation, which may present different challenges. Inspired by this, we provide an in-depth look at bladder cancer segmentation using deep learning models. The critical determinants for accurate differentiation of muscle invasive disease, current status of deep learning based bladder segmentation, lessons and limitations of prior work are highlighted.