Machine learning methods in automated detection of CT enterography findings in Crohn's disease: A feasibility study.

PURPOSE: Qualitative findings in Crohn's disease (CD) can be challenging to reliably report and quantify. We evaluated machine learning methodologies to both standardize the detection of common qualitative findings of ileal CD and determine finding spatial localization on CT enterography (CTE). MATERIALS AND METHODS: Subjects with ileal CD and a CTE from a single center retrospective study between 2016 and 2021 were included. 165 CTEs were reviewed by two fellowship-trained abdominal radiologists for the presence and spatial distribution of five qualitative CD findings: mural enhancement, mural stratification, stenosis, wall thickening, and mesenteric fat stranding. A Random Forest (RF) ensemble model using automatically extracted specialist-directed bowel features and an unbiased convolutional neural network (CNN) were developed to predict the presence of qualitative findings. Model performance was assessed using area under the curve (AUC), sensitivity, specificity, accuracy, and kappa agreement statistics. RESULTS: In 165 subjects with 29,895 individual qualitative finding assessments, agreement between radiologists for localization was good to very good (κ = 0.66 to 0.73), except for mesenteric fat stranding (κ = 0.47). RF prediction models had excellent performance, with an overall AUC, sensitivity, specificity of 0.91, 0.81 and 0.85, respectively. RF model and radiologist agreement for localization of CD findings approximated agreement between radiologists (κ = 0.67 to 0.76). Unbiased CNN models without benefit of disease knowledge had very similar performance to RF models which used specialist-defined imaging features. CONCLUSION: Machine learning techniques for CTE image analysis can identify the presence, location, and distribution of qualitative CD findings with similar performance to experienced radiologists.

ACR Appropriateness Criteria® Management of Uterine Fibroids: 2023 Update.

Uterine fibroids are the most common benign tumor in women of reproductive age and can present with symptoms including bleeding, bulk related symptoms, and infertility. Several treatment options are available for the management of uterine fibroids, including medical management, minimally invasive therapies such as uterine artery embolization and MR-guided focused ultrasound ablation, and surgical interventions ranging from laparoscopic myomectomy to open hysterectomy. Given this wide range of therapeutic interventions, it is important to understand the data supporting these interventions and to be able to apply it in different clinical settings. This document provides a summary of recent trials supporting various therapies for uterine fibroids, including recent evidence for MR-guided focused ultrasound ablation and a detailed discussion of fertility outcomes in myomectomy and uterine fibroid embolization. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

ACR Appropriateness Criteria® Clinically Suspected Adnexal Mass, No Acute Symptoms: 2023 Update.

Asymptomatic adnexal masses are commonly encountered in daily radiology practice. Although the vast majority of these masses are benign, a small subset have a risk of malignancy, which require gynecologic oncology referral for best treatment outcomes. Ultrasound, using a combination of both transabdominal, transvaginal, and duplex Doppler technique can accurately characterize the majority of these lesions. MRI with and without contrast is a useful complementary modality that can help characterize indeterminate lesions and assess the risk of malignancy is those that are suspicious. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

ACR Appropriateness Criteria® Acute Pelvic Pain in the Reproductive Age Group: 2023 Update.

This review focuses on the initial imaging in the reproductive age adult population with acute pelvic pain, including patients with positive and negative beta-human chorionic gonadotropin (ß-hCG) levels with suspected gynecological and nongynecological etiology. For all patients, a combination of transabdominal and transvaginal pelvic ultrasound with Doppler is usually appropriate as an initial imaging study. If nongynecological etiology in patients with negative ß-hCG is suspected, then CT of the abdomen and pelvis with or without contrast is also usually appropriate. In patients with positive ß-hCG and suspected nongynecological etiology, CT of the abdomen and pelvis with contrast and MRI of the abdomen and pelvis without contrast may be appropriate. In patients with negative ß-hCG and suspected gynecological etiology, CT of the abdomen and pelvis with contrast, MRI of pelvis without contrast, or MRI of pelvis with and without contrast may be appropriate. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

ACR Appropriateness Criteria® Clinically suspected adnexal mass, no acute symptoms: 2023 update

Asymptomatic adnexal masses are commonly encountered in daily radiology practice. Although the vast majority of these masses are benign, a small subset have a risk of malignancy, which require gynecologic oncology referral for best treatment outcomes. Ultrasound, using a combination of both transabdominal, transvaginal, and duplex Doppler technique can accurately characterize the majority of these lesions. MRI with and without contrast is a useful complementary modality that can help characterize indeterminate lesions and assess the risk of malignancy is those that are suspicious. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

ACR Appropriateness Criteria® Acute pelvic pain in the reproductive age group: 2023 update

This review focuses on the initial imaging in the reproductive age adult population with acute pelvic pain, including patients with positive and negative beta-human chorionic gonadotropin (ß-hCG) levels with suspected gynecological and nongynecological etiology. For all patients, a combination of transabdominal and transvaginal pelvic ultrasound with Doppler is usually appropriate as an initial imaging study. If nongynecological etiology in patients with negative ß-hCG is suspected, then CT of the abdomen and pelvis with or without contrast is also usually appropriate. In patients with positive ß-hCG and suspected nongynecological etiology, CT of the abdomen and pelvis with contrast and MRI of the abdomen and pelvis without contrast may be appropriate. In patients with negative ß-hCG and suspected gynecological etiology, CT of the abdomen and pelvis with contrast, MRI of pelvis without contrast, or MRI of pelvis with and without contrast may be appropriate. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

ACR Appropriateness Criteria® Management of uterine fibroids: 2023 update

Uterine fibroids are the most common benign tumor in women of reproductive age and can present with symptoms including bleeding, bulk related symptoms, and infertility. Several treatment options are available for the management of uterine fibroids, including medical management, minimally invasive therapies such as uterine artery embolization and MR-guided focused ultrasound ablation, and surgical interventions ranging from laparoscopic myomectomy to open hysterectomy. Given this wide range of therapeutic interventions, it is important to understand the data supporting these interventions and to be able to apply it in different clinical settings. This document provides a summary of recent trials supporting various therapies for uterine fibroids, including recent evidence for MR-guided focused ultrasound ablation and a detailed discussion of fertility outcomes in myomectomy and uterine fibroid embolization. The American College of Radiology Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed annually by a multidisciplinary expert panel. The guideline development and revision process support the systematic analysis of the medical literature from peer reviewed journals. Established methodology principles such as Grading of Recommendations Assessment, Development, and Evaluation or GRADE are adapted to evaluate the evidence. The RAND/UCLA Appropriateness Method User Manual provides the methodology to determine the appropriateness of imaging and treatment procedures for specific clinical scenarios. In those instances where peer reviewed literature is lacking or equivocal, experts may be the primary evidentiary source available to formulate a recommendation.

Local Assessment and Small Bowel Crohn's Disease Severity Scoring using AI.

RATIONALE AND OBJECTIVES: We present a machine learning and computer vision approach for a localized, automated, and standardized scoring of Crohn's disease (CD) severity in the small bowel, overcoming the current limitations of manual measurements CT enterography (CTE) imaging and qualitative assessments, while also considering the complex anatomy and distribution of the disease. MATERIALS AND METHODS: Two radiologists introduced a severity score and evaluated disease severity at 7.5 mm intervals along the curved planar reconstruction of the distal and terminal ileum using 236 CTE scans. A hybrid model, combining deep-learning, 3-D CNN, and Random Forest model, was developed to classify disease severity at each mini-segment. Precision, sensitivity, weighted Cohen's score, and accuracy were evaluated on a 20% hold-out test set. RESULTS: The hybrid model achieved precision and sensitivity ranging from 42.4% to 84.1% for various severity categories (normal, mild, moderate, and severe) on the test set. The model's Cohen's score (κ = 0.83) and accuracy (70.7%) were comparable to the inter-observer agreement between experienced radiologists (κ = 0.87, accuracy = 76.3%). The model accurately predicted disease length, correlated with radiologist-reported disease length (r = 0.83), and accurately identified the portion of total ileum containing moderate-to-severe disease with an accuracy of 91.51%. CONCLUSION: The proposed automated hybrid model offers a standardized, reproducible, and quantitative local assessment of small bowel CD severity and demonstrates its value in CD severity assessment.

Ultrasound of palpable lesions: a pictorial review.

Ultrasound (US) is the imaging modality of choice for evaluation of superficial palpable lesions. A large proportion of these lesions have characteristic sonographic appearance and can be confidently diagnosed with US without the need for biopsy or other intervention. The Society of Radiologists in Ultrasound (SRU) recently published a Consensus Conference Statement on superficial soft tissue masses. The goal of this manuscript is (a) to serve as a sonographic pictorial review for palpable lesions based on the SRU statement, (b) present the typical sonographic features of palpable lesions that can be confidently diagnosed with US, and (c) provide an overview of other palpable lesions with a framework to interpret the US studies and advise on appropriate further management.

Artificial Intelligence for Quantifying Cumulative Small Bowel Disease Severity on CT-Enterography in Crohn's Disease.

INTRODUCTION: Assessing the cumulative degree of bowel injury in ileal Crohn's disease (CD) is difficult. We aimed to develop machine learning (ML) methodologies for automated estimation of cumulative ileal injury on computed tomography-enterography (CTE) to help predict future bowel surgery. METHODS: Adults with ileal CD using biologic therapy at a tertiary care center underwent ML analysis of CTE scans. Two fellowship-trained radiologists graded bowel injury severity at granular spatial increments along the ileum (1 cm), called mini-segments. ML segmentation methods were trained on radiologist grading with predicted severity and then spatially mapped to the ileum. Cumulative injury was calculated as the sum (S-CIDSS) and mean of severity grades along the ileum. Multivariate models of future small bowel resection were compared with cumulative ileum injury metrics and traditional bowel measures, adjusting for laboratory values, medications, and prior surgery at the time of CTE. RESULTS: In 229 CTE scans, 8,424 mini-segments underwent analysis. Agreement between ML and radiologists injury grading was strong (κ = 0.80, 95% confidence interval 0.79-0.81) and similar to inter-radiologist agreement (κ = 0.87, 95% confidence interval 0.85-0.88). S-CIDSS (46.6 vs 30.4, P = 0.0007) and mean cumulative injury grade scores (1.80 vs 1.42, P < 0.0001) were greater in CD biologic users that went to future surgery. Models using cumulative spatial metrics (area under the curve = 0.76) outperformed models using conventional bowel measures, laboratory values, and medical history (area under the curve = 0.62) for predicting future surgery in biologic users. DISCUSSION: Automated cumulative ileal injury scores show promise for improving prediction of outcomes in small bowel CD. Beyond replicating expert judgment, spatial enterography analysis can augment the personalization of bowel assessment in CD.

Neoadjuvant chemotherapy for high-grade serous ovarian cancer: radiologic-pathologic correlation of response assessment and predictors of progression.

PURPOSE: Neoadjuvant chemotherapy is often administered for high-grade serous ovarian carcinoma (HGSC) prior to cytoreductive surgery. We evaluated treatment response by CT (simplified peritoneal carcinomatosis index [S-PCI]), pathology (chemotherapy response score [CRS]), laboratory markers (serum CA-125), and surgical outcomes, to identify predictors of disease-free survival. METHODS: For this retrospective, HIPAA-compliant, IRB-approved study, we identified 396 women with HGSC receiving neoadjuvant chemotherapy between 2010 and 2019. Two hundred and ninety-nine patients were excluded (surgery not performed; imaging/pathology unavailable). Pre- and post-treatment abdominopelvic CTs were assigned CT S-PCI scores 0-24 (higher score indicating more tumor). Specimens were assigned CRS of 1-3 (minimal to complete response). Clinical data were obtained via chart review. Univariate, multivariate, and survival analyses were performed. RESULTS: Ninety-seven women were studied, with mean age of 65 years ± 10. Interreader agreement was good to excellent for CT S-PCI scores (ICC 0.64-0.77). Despite a significant decrease in CT S-PCI scores after treatment (p < 0.001), mean decrease in CT S-PCI did not differ significantly among CRS categories (p = 0.20) or between patients who were optimally versus suboptimally debulked (p = 0.29). In a survival analysis, lower CRS (more viable tumor) was associated with shorter time to progression (p < 0.001). A joint Cox proportional-hazard models showed that only residual pathologic disease (CRS 1/2) (HR 4.19; p < 0.001) and change in CA-125 (HR 1.79; p = 0.01) predicted progression. CONCLUSION: HGSC response to neoadjuvant therapy by CT S-PCI did not predict pathologic CRS score, optimal debulking, or progression, revealing discordance between imaging, pathologic, biochemical, and surgical assessments of tumor response.

A Review of the Clinical Applications of Artificial Intelligence in Abdominal Imaging.

Artificial intelligence (AI) has been a topic of substantial interest for radiologists in recent years. Although many of the first clinical applications were in the neuro, cardiothoracic, and breast imaging subspecialties, the number of investigated and real-world applications of body imaging has been increasing, with more than 30 FDA-approved algorithms now available for applications in the abdomen and pelvis. In this manuscript, we explore some of the fundamentals of artificial intelligence and machine learning, review major functions that AI algorithms may perform, introduce current and potential future applications of AI in abdominal imaging, provide a basic understanding of the pathways by which AI algorithms can receive FDA approval, and explore some of the challenges with the implementation of AI in clinical practice.

Pancreatic Transplantation: Surgical Anatomy and Complications.

Pancreatic transplantation is a complex surgical procedure performed for patients with chronic severe diabetes, often performed in combination with renal transplantation. Vascular and exocrine drainage anatomy varies depending on the surgical technique. Radiology plays a critical role in the diagnosis of postoperative complications, requiring an understanding of grayscale/Doppler ultrasound as well as computed tomography and MR imaging. In this review, we detail usual surgical methods and normal postoperative imaging appearances. We then review the most common complications following pancreatic transplants, emphasizing diagnostic features of vascular (arterial/venous), surgical, and diffuse parenchymal pathologic conditions on multiple imaging modalities.

Adnexal Mass Imaging: Contemporary Guidelines for Clinical Practice.

Several recent guidelines have been published to improve accuracy and consistency of adnexal mass imaging interpretation and to guide management. Guidance from the American College of Radiology (ACR) Appropriateness Criteria establishes preferred adnexal imaging modalities and follow-up. Moreover, the ACR Ovarian-Adnexal Reporting Data System establishes a comprehensive, unified set of evidence-based guidelines for classification of adnexal masses by both ultrasound and MR imaging, communicating risk of malignancy to further guide management.

A primer on rectal MRI in patients on watch-and-wait treatment for rectal cancer.

Total neoadjuvant treatment (TNT) for rectal cancer is becoming an accepted treatment paradigm and is changing the landscape of this disease, wherein up to 50% of patients who undergo TNT are able to avoid surgery. This places new demands on the radiologist in terms of interpreting degrees of response to treatment. This primer summarizes the Watch-and-Wait approach and the role of imaging, with illustrative "atlas-like" examples as an educational guide for radiologists. We present a brief literature summary of the evolution of rectal cancer treatment, with a focus on magnetic resonance imaging (MRI) assessment of response. We also discuss recommended guidelines and standards. We outline the common TNT approach entering mainstream practice. A heuristic and algorithmic approach to MRI interpretation is also offered. To illustrate management and common scenarios, we arranged the illustrative figures as follows: (I) Clinical complete response (cCR) achieved at the immediate post-TNT "decision point" scan time; (II) cCR achieved at some point during surveillance, later than the first post-TNT MRI; (III) near clinical complete response (nCR); (IV) incomplete clinical response (iCR); (V) discordant findings between MRI and endoscopy where MRI is falsely positive, even at follow-up; (VI) discordant cases where MRI seems to be falsely positive but is proven truly positive on follow-up endoscopy; (VII) cases where MRI is falsely negative; (VIII) regrowth of tumor in the primary tumor bed; (IX) regrowth outside the primary tumor bed; and (X) challenging scenarios, i.e., mucinous cases. This primer is offered to achieve its intended goal of educating radiologists on how to interpret MRI in patients with rectal cancer undergoing treatment using a TNT-type treatment paradigm and a Watch-and-Wait approach.

Sonographic Predictors of Ovarian Torsion in Premenarchal Girls.

STUDY OBJECTIVE: To identify preoperative transabdominal sonographic predictors of surgically confirmed ovarian torsion (OT) in premenarchal girls METHODS: We conducted a retrospective case-control study of 32 premenarchal girls aged 0-12 undergoing surgery for OT (cases) or a non-torsed ovarian mass (controls) from 2006 to 2017 at a single academic center. Cases had ICD-9/10 codes for torsion of the ovary, adnexa, ovarian pedicle, or fallopian tube and surgically confirmed OT; controls had codes for ovarian mass or cyst and surgically confirmed absence of OT. Preoperative transabdominal ultrasounds were analyzed by 3 radiologists blinded to final diagnosis. We used χ2, Fisher[s exact, and Student's t tests for statistical comparisons. RESULTS: From 2016 to 2017, 32 patients presented with acute abdominal pain or symptoms concerning for ovarian mass requiring ultrasound imaging and subsequent diagnostic laparoscopy; 24 (75.0%) had confirmed OT by laparoscopy, and 8 (25.0%) did not. The mean age in both groups was similar (7.3 ± 2.9 years). Preoperative sonographic variables significantly associated with OT included presence of a simple cyst (20.8% vs 12.5%), ovarian heterogeneity (100% vs 12.5%), presence of peripheralized follicles (70.8% vs 0%), and asymmetry of color Doppler (75.0% vs 37.5%; all P < .05). Presence of free fluid, arterial color Doppler, and a whirlpool sign were not predictive of OT. CONCLUSION: In premenarchal patients, although certain variables on transabdominal sonography predicted surgically confirmed OT, only the presence of peripheralized follicles was unique to girls with OT. The decision to proceed with diagnostic laparoscopy for suspected OT can be aided by these specific sonographic findings but should ultimately be based on high clinical suspicion.

MRI assessment of rectal cancer response to neoadjuvant therapy: a multireader study.

OBJECTIVES: A watch and wait strategy with the goal of organ preservation is an emerging treatment paradigm for rectal cancer following neoadjuvant treatment. However, the selection of appropriate patients remains a challenge. Most previous efforts to measure the accuracy of MRI in assessing rectal cancer response used a small number of radiologists and did not report variability among them. METHODS: Twelve radiologists from 8 institutions assessed baseline and restaging MRI scans of 39 patients. The participating radiologists were asked to assess MRI features and to categorize the overall response as complete or incomplete. The reference standard was pathological complete response or a sustained clinical response for > 2 years. RESULTS: We measured the accuracy and described the interobserver variability of interpretation of rectal cancer response between radiologists at different medical centers. Overall accuracy was 64%, with a sensitivity of 65% for detecting complete response and specificity of 63% for detecting residual tumor. Interpretation of the overall response was more accurate than the interpretation of any individual feature. Variability of interpretation was dependent on the patient and imaging feature investigated. In general, variability and accuracy were inversely correlated. CONCLUSIONS: MRI-based evaluation of response at restaging is insufficiently accurate and has substantial variability of interpretation. Although some patients' response to neoadjuvant treatment on MRI may be easily recognizable, as seen by high accuracy and low variability, that is not the case for most patients. KEY POINTS: • The overall accuracy of MRI-based response assessment is low and radiologists differed in their interpretation of key imaging features. • Some patients' scans were interpreted with high accuracy and low variability, suggesting that these patients' pattern of response is easier to interpret. • The most accurate assessments were those of the overall response, which took into consideration both T2W and DWI sequences and the assessment of both the primary tumor and the lymph nodes.

Imaging Care for Transgender and Gender Diverse Patients: Best Practices and Recommendations.

Transgender and gender diverse (TGD) people experience health disparities, and many avoid necessary medical care because of fears of discrimination or mistreatment. Disparate care is further compounded by limited understanding of gender-affirming hormone therapy (GAHT) and gender-affirming surgery among the medical community. Specific to radiology, TGD patients report more negative imaging experiences than negative general health encounters, highlighting the need for guidance and best practices for inclusive imaging care. A patient's imaging journey provides numerous opportunities for improvement. Inclusive practice in a radiology department starts with ordering and scheduling the examination, facilitated by staff education on appropriate use of a patient's chosen name, gender identity, and pronouns. Contemporary electronic health record systems have the capacity for recording detailed sexual orientation and gender identity data, but staff must be trained to solicit and use this information. A welcoming environment can help TGD patients to feel safe during the imaging experience and may include institutional nondiscrimination policies, gender-neutral signage, and all-gender single-user dressing rooms and bathrooms. Image acquisition should be performed using trauma-informed and patient-centered care. Finally, radiologists should be aware of reporting considerations for TGD patients, such as avoiding the use of gender in reports when it is not medically relevant and using precise, respectful language for findings related to GAHT and gender-affirming surgical procedures. As a field, radiology has a range of opportunities for improving care delivery for TGD patients, and the authors summarize recommended best practices. See the invited commentary by Stowell in this issue. © RSNA, 2023 Quiz questions for this article are available in the supplemental material.

Virtual Mentoring: A Guide to Navigating a New Age in Mentorship.

Mentorship is a fundamental part of professional and personal growth. Over time, the fabric of mentorship has been transforming from typical one-on-one mentor-mentee relationship to other types including peer, group, speed, and virtual mentoring. When the COVID-19 pandemic hit, it caused major disruptions in many facets of life and career, including mentoring. In response to the COVID-19 pandemic, live meetings were canceled, and social distancing measures were enacted at many institutions. Thus, the traditional set-up, with a face-to-face mentor and mentee interaction, was impossible. Many virtual platforms were utilized to navigate through these restrictions. In this review, we highlight challenges in mentorship during the COVID-19 pandemic and how we implemented different strategies to promote mentorship.