Radiomics in Abdominopelvic Solid-Organ Oncologic Imaging: Current Status.

Radiomics is the process of extraction of high-throughput quantitative imaging features from medical images. These features represent noninvasive quantitative biomarkers that go beyond the traditional imaging features visible to the human eye. This article first reviews the steps of the radiomics pipeline, including image acquisition, ROI selection and image segmentation, image preprocessing, feature extraction, feature selection, and model development and application. Current evidence for the application of radiomics in abdominopelvic solid-organ cancers is then reviewed. Applications including diagnosis, subtype determination, treatment response assessment, and outcome prediction are explored within the context of hepatobiliary and pancreatic cancer, renal cell carcinoma, prostate cancer, gynecologic cancer, and adrenal masses. This literature review focuses on the strongest available evidence, including systematic reviews, meta-analyses, and large multicenter studies. Limitations of the available literature are highlighted, including marked heterogeneity in radiomics methodology, frequent use of small sample sizes with high risk of overfitting, and lack of prospective design, external validation, and standardized radiomics workflow. Thus, although studies have laid a foundation that supports continued investigation into radiomics models, stronger evidence is needed before clinical adoption.

Artificial Intelligence in Diagnostic Radiology: Where Do We Stand, Challenges, and Opportunities.

ABSTRACT: Artificial intelligence (AI) is the most revolutionizing development in the health care industry in the current decade, with diagnostic imaging having the greatest share in such development. Machine learning and deep learning (DL) are subclasses of AI that show breakthrough performance in image analysis. They have become the state of the art in the field of image classification and recognition. Machine learning deals with the extraction of the important characteristic features from images, whereas DL uses neural networks to solve such problems with better performance. In this review, we discuss the current applications of machine learning and DL in the field of diagnostic radiology.Deep learning applications can be divided into medical imaging analysis and applications beyond analysis. In the field of medical imaging analysis, deep convolutional neural networks are used for image classification, lesion detection, and segmentation. Also used are recurrent neural networks when extracting information from electronic medical records and to augment the use of convolutional neural networks in the field of image classification. Generative adversarial networks have been explicitly used in generating high-resolution computed tomography and magnetic resonance images and to map computed tomography images from the corresponding magnetic resonance imaging. Beyond image analysis, DL can be used for quality control, workflow organization, and reporting.In this article, we review the most current AI models used in medical imaging research, providing a brief explanation of the various models described in the literature within the past 5 years. Emphasis is placed on the various DL models, as they are the most state-of-art in imaging analysis.

Preresection Radiologic Assessment and Imaging Features of 156 Pathologically Proven Adrenal Adenomas.

PURPOSE: The aims of the study were to assess the typical and atypical radiologic features of pathologically proven adrenal adenomas and to determine the relationship between the radiologic and histopathologic classification. METHODS: We retrospectively studied 156 pathologically proven adrenal adenomas in 154 patients from our institutional databases who have computed tomography (CT) and/or magnetic resonance imaging (MRI) examinations before intervention. We determined the histopathologic diagnosis (typical or atypical) using Weiss scoring and classified the adenomas radiologically into typical, atypical, or indeterminate based on lesion size, precontrast CT attenuation, absolute percentage washout, calcification, and necrosis. The κ statistic was used to assess the agreement between radiologists. The Fisher exact test was used to compare the radiologic and pathological classifications. RESULTS: In consensus, there were 83 typical, 42 atypical, and 31 indeterminate adrenal lesions. Logistic regression model showed that radiologically atypical adenoma was significantly associated with larger size, lobulated shape, higher unenhanced CT attenuation, heterogeneous appearance, nonfunctioning status, absolute percentage washout of less than 60%, and a signal intensity index of less than 16.5%.Pathologically, 147 adenomas were pathologically typical (Weiss 0), and 9 adenomas were pathologically atypical (Weiss 1-2). Radiologically, there was substantial agreement between both readers, with Cohen κ at 0.71. Approximately 98% of radiologically typical adenomas were pathologically typical. Only 17% of radiologically atypical adenomas were pathologically atypical. All radiologically indeterminate adenomas were pathologically typical. However, some of the radiologically indeterminate and typical adenomas still had an atypical component on pathologic analysis, such as necrosis, nuclear atypia, or oncocytic features. CONCLUSIONS: Radiologically atypical lesion was significantly associated with larger size and higher unenhanced CT attenuation. Approximately 27% of the cases demonstrated atypical features on imaging. Most radiologically atypical adrenal adenomas are pathologically typical.

Predicting tumor recurrence on baseline MR imaging in patients with early-stage hepatocellular carcinoma using deep machine learning.

Tumor recurrence affects up to 70% of early-stage hepatocellular carcinoma (HCC) patients, depending on treatment option. Deep learning algorithms allow in-depth exploration of imaging data to discover imaging features that may be predictive of recurrence. This study explored the use of convolutional neural networks (CNN) to predict HCC recurrence in patients with early-stage HCC from pre-treatment magnetic resonance (MR) images. This retrospective study included 120 patients with early-stage HCC. Pre-treatment MR images were fed into a machine learning pipeline (VGG16 and XGBoost) to predict recurrence within six different time frames (range 1-6 years). Model performance was evaluated with the area under the receiver operating characteristic curves (AUC-ROC). After prediction, the model's clinical relevance was evaluated using Kaplan-Meier analysis with recurrence-free survival (RFS) as the endpoint. Of 120 patients, 44 had disease recurrence after therapy. Six different models performed with AUC values between 0.71 to 0.85. In Kaplan-Meier analysis, five of six models obtained statistical significance when predicting RFS (log-rank p < 0.05). Our proof-of-concept study indicates that deep learning algorithms can be utilized to predict early-stage HCC recurrence. Successful identification of high-risk recurrence candidates may help optimize follow-up imaging and improve long-term outcomes post-treatment.

Thermal ablation alone vs thermal ablation combined with transarterial chemoembolization for patients with small (<3 cm) hepatocellular carcinoma.

PURPOSE: Thermal ablation (TA) and transarterial chemoembolization (TACE) may be used alone or in combination (TACE+TA) for the treatment of hepatocellular carcinoma (HCC). The aim of our study was to compare the time to tumor progression (TTP) and overall survival (OS) for patients who received TA alone or TACE+TA for HCC tumors under 3 cm. MATERIALS AND METHODS: This HIPAA-compliant IRB-approved retrospective analysis included 85 therapy-naïve patients from 2010 to 2018 (63 males, 22 females, mean age 62.4 ± 8.5 years) who underwent either TA alone (n = 64) or TA in combination with drug-eluting beads (DEB)-TACE (n = 18) or Lipiodol-TACE (n = 3) for locoregional therapy of early stage HCC with maximum tumor diameter under 3 cm. Kaplan-Meier analysis was performed using the log-rank test to assess TTP and OS. RESULTS: All TA and TACE+TA treatments included were technically successful. TTP was 23.0 months in the TA group and 22.0 months in the TACE+TA group. There was no statistically significant difference in TTP (p = 0.64). Median OS was 69.7 months in the TA group and 64.6 months in the TACE+TA group. There was no statistically significant difference in OS (p = 0.14). The treatment cohorts had differences in AFP levels (p = 0.03) and BCLC stage (p = 0.047). Complication rates between patient groups were similar (p = 0.61). CONCLUSION: For patients with HCC under 3 cm, TA alone and TACE+TA have similar outcomes in terms of TTP and OS, suggesting that TACE+TA may not be needed for these tumors unless warranted by tumor location or other technical consideration.

A Prospective Phase II Study of Safety and Efficacy of Sorafenib Followed by 90Y Glass Microspheres for Patients with Advanced or Metastatic Hepatocellular Carcinoma.

PURPOSE: The most common cause of death in advanced/metastatic hepatocellular carcinoma (HCC) is liver failure due to tumor progression. While retrospective studies and meta-analyses of systemic therapy combined with liver-directed therapy have been performed, prospective studies of safety/efficacy of antiangiogenesis followed by intra-arterial therapies are lacking. We tested our hypothesis that sorafenib followed by yttrium 90 glass microspheres (90Y GMs) is safe and that survival outcomes may improve by controlling hepatic tumors. METHODS: We enrolled 38 Child-Pugh A patients with advanced/metastatic HCC. In sum, 34 received sorafenib, followed after 4 weeks by 90Y GMs. Analysis of safety and survival outcomes was performed to assess adverse events, median progression-free survival, and overall survival. RESULTS: A total of 34 patients were evaluable: 14 (41.2%) with chronic hepatitis, nine (26.5%) with vascular invasion, and eleven (32.4%) with extrahepatic diseases. Safety analysis revealed that the combination therapy was well tolerated. Grade III-IV adverse events comprised fatigue (n=3), diarrhea (n=2), nausea (n=1), vomiting (n=2), hypertension (n=4), thrombocytopenia (n=1), hyperbilirubinemia (n=1), proteinuria (n=1), hyponatremia (n=1), and elevated alanine or aspartate aminotransferase (n=5). Median progression-free and overall survival were 10.4 months (95% CI 5.8-14.4) and 13.2 months (95% CI 7.9-18.9), respectively. Twelve patients (35.3%) achieved partial responses and 16 (47.0%) stable disease. Median duration of sorafenib was 20 (3-90) weeks, and average dose was 622 (466-800) mg daily. Dosimetry showed similar mean doses between planned and delivered calculations to normal liver and tumor:normal liver uptake ratio, with no significant correlation with adverse events at 3 and 6 months post-90Y treatment. CONCLUSION: This is the first prospective study to evaluate sorafenib followed by 90Y in patients with advanced HCC. The study validated our hypothesis of safety with encouraging efficacy signals of the sequencing treatment, and provides proof of concept for future combination modalities for patients with advanced or metastatic HCC. CLINICAL TRIAL REGISTRATION NUMBER: NCT01900002.

Adrenal cortical adenoma: current update, imaging features, atypical findings, and mimics.

Adrenal adenoma is the most common adrenal lesion. Due to its wide prevalence, adrenal adenomas may demonstrate various imaging features. Thus, it is important to identify typical and atypical imaging features of adrenal adenomas and to be able to differentiate atypical adrenal adenomas from potentially malignant lesions. In this article, we will discuss the diagnostic approach, typical and atypical imaging features of adrenal adenomas, as well as other lesions that mimic adrenal adenomas.

Understanding Idiopathic Spinal Cord Herniation - A Comprehensive Review of Imaging and Literature.

Idiopathic spinal cord herniation (ISCH) is displacement of spinal cord through a dural or arachnoidal defect. Most patients present with back pain or myelopathy, paresthesia, and sensory or motor weakness. Imaging findings include anterior displacement of the cord with possible kink, no filling defect on CT myelography, and no restricted diffusion/mass lesion on magnetic resonance imaging. Abrupt kink in the spinal cord or widened cerebrospinal fluid (CSF) space can be caused by a variety of reasons. The differential considerations include arachnoid web, intradural extramedullary epidermoid or arachnoid cyst, abscess or cystic schwannoma. We discuss the features, imaging, differentials, and treatment of ISCH as a rare cause of such kink in the cord. While reading such cases, a radiologist should include the location, segments involved, cord signal abnormality, visible defect, scalpel sign or C-sign, ventral cord kink, nuclear trail sign, the ventral CSF space preservation, or obliteration and the type.

Targeted Therapy in Advanced Thyroid Cancer to Resensitize Tumors to Radioactive Iodine.

Context: Many differentiated thyroid cancers (DTC) dedifferentiate and become radioactive iodine (RAI)-refractory (RAIR) with worse outcomes. Targeted therapy (TTx) may downregulate MAPK signaling and sensitize tumors to RAI. Objective: We describe patients with RAIR DTC receiving TTx with demonstrated RAI uptake allowing for iodine-131 (I131) administration. Design: Charts of patients with metastatic, progressive, RAIR DTC in whom TTx increased RAI uptake on a diagnostic whole-body scan (WBS), were reviewed. Results of WBS, I131 administration, thyroglobulin (TG) panels, and cross-sectional studies were recorded. Setting: Thirteen patients [median age (range), 56 (45 to 75) years; seven men] were included; 11 (85%) had DTC, two (15%) had poorly DTC. Nine (69%) had BRAF mutations, three (23%) had RAS mutations, and one (8%) was wild type. Selective BRAF or an MEK inhibitor TTx was continued for a median (range) of 14.3 (1 to 76.4) months before diagnostic WBS. Results: Nine (69%) patients were treated with I131 [median (range) activity, 204.4 (150 to 253) mCi], after which TTx was discontinued. Median (range) follow-up was 8.3 (0 to 17.4) months after I131 therapy. All nine patients had durable disease control (three had partial response, six had stable disease). TG and TG antibody levels increased in patients who demonstrated uptake before TTx, and declined in eight of the nine patients after I131 treatment. Adverse events included pneumonitis and sialadenitis. Conclusion: TTx in BRAF-/RAS-mutated RAIR DTC resensitizes tumors to iodine. Subsequent I131 administration results in meaningful responses. Patient selection, adverse events, response duration, and survival impact require additional study.

Systemic therapy for unresectable, mixed hepatocellular-cholangiocarcinoma: treatment of a rare malignancy.

BACKGROUND: Combined hepatocellular-cholangiocarcinoma (HCC-CC) has a reported incidence of less than 5% of primary hepatic malignancies. The treatment approach to this malignancy is undefined. Our objective of this case series is to provide some insight into chemotherapy and/or targeted therapy in this setting. METHODS: Pathologic and radiographic review confirmed seven combined HCC-CC patients during a 5-year time frame [2009-2014]. Data points were demographics, chemotherapy and/or targeted therapy given in the first and second-line setting, localized treatment if given, first radiographic result, progression-free survival (PFS), and overall survival (OS). RESULTS: Seven patients were identified. Front-line treatment showed a median PFS of 3.4 months. Total median OS was 8.3 months. Regimens given included gemcitabine alone +/- bevacizumab, gemcitabine + platinum (GP) +/- bevacizumab, and sorafenib. Front-line treatment with these regimens showed progressive disease in 71% (5 patients) on first radiographic scan with all patients who received sorafenib front-line progressing at that restaging. Disease-control (complete response + partial response + stable disease) was seen in 29% of patients (2 patients) with 1 patient receiving GP and 1 patient receiving gemcitabine + bevacizumab. Of note, 2 patients that received GP +/- bevacizumab in the second-line setting had disease control on first radiographic scan. CONCLUSIONS: Our retrospective review speaks to the rarity of this malignancy and challenges that are associated with its diagnosis and treatment. GP +/- bevacizumab showed disease control in first or second-line treatment in 3 patients. Treatment with this regimen in this rare malignancy subgroup warrants further investigation.

Imaging Genomics in Gliomas.

During the last decade, imaging has become the cornerstone for noninvasive diagnosis of different disorders and is currently being used by physicians all over the world. With the emergence of novel advanced imaging techniques that allow microstructural as well as functional tissue characterization along with the extensive work done by The Cancer Genome Atlas focusing on mapping genomic changes in glioblastoma, new correlations have been discovered between alterations at the genomics level and radiological imaging features in cancer patients. This has marked the beginning of a new era in clinical sciences, the era of "imaging genomics," which aims at establishing relationship between radiological imaging features and genomic characteristics of tumors. This article reviews the fundamentals of imaging genomics in glioma, its role in noninvasive genomic detection, and its future potential in personalized treatment planning.

Imaging Genomics of Glioblastoma: Biology, Biomarkers, and Breakthroughs.

Glioblastoma is regarded as the most aggressive and most common primary malignant brain tumor in adults. Despite advancements in chemotherapy and radiotherapy, prognosis and overall survival of glioblastoma patients remain dismal. Recently, progresses in genetic profiling have increased our understanding of the underlying heterogenous molecular nature of this aggressive tumor. Several prognostic and predictive molecular biomarkers have been identified that have been linked to patient's survival and response to treatment, respectively. Imaging genomics represents a novel entity in clinical sciences that bidirectionally links imaging features with underlying molecular profile and thus can serve as a surrogate for noninvasive genomic correlation, prediction, and identification.

Imaging genomics of Glioblastoma: state of the art bridge between genomics and neuroradiology.

Glioblastoma (GBM) is the most common and most aggressive primary malignant tumor of the central nervous system. Recently, researchers concluded that the "one-size-fits-all" approach for treatment of GBM is no longer valid and research should be directed toward more personalized and patient-tailored treatment protocols. Identification of the molecular and genomic pathways underlying GBM is essential for achieving this personalized and targeted therapeutic approach. Imaging genomics represents a new era as a noninvasive surrogate for genomic and molecular profile identification. This article discusses the basics of imaging genomics of GBM, its role in treatment decision-making, and its future potential in noninvasive genomic identification.