From quantitative metrics to clinical success: assessing the utility of deep learning for tumor segmentation in breast surgery.

PURPOSE: Preventing positive margins is essential for ensuring favorable patient outcomes following breast-conserving surgery (BCS). Deep learning has the potential to enable this by automatically contouring the tumor and guiding resection in real time. However, evaluation of such models with respect to pathology outcomes is necessary for their successful translation into clinical practice. METHODS: Sixteen deep learning models based on established architectures in the literature are trained on 7318 ultrasound images from 33 patients. Models are ranked by an expert based on their contours generated from images in our test set. Generated contours from each model are also analyzed using recorded cautery trajectories of five navigated BCS cases to predict margin status. Predicted margins are compared with pathology reports. RESULTS: The best-performing model using both quantitative evaluation and our visual ranking framework achieved a mean Dice score of 0.959. Quantitative metrics are positively associated with expert visual rankings. However, the predictive value of generated contours was limited with a sensitivity of 0.750 and a specificity of 0.433 when tested against pathology reports. CONCLUSION: We present a clinical evaluation of deep learning models trained for intraoperative tumor segmentation in breast-conserving surgery. We demonstrate that automatic contouring is limited in predicting pathology margins despite achieving high performance on quantitative metrics.

A Review of Materials and Medications with Religious or Dietary Significance in the Interventional Radiology Suite.

A holistic approach to patient-centered care should include cultural and religious considerations. Certain cultural groups have beliefs that may restrict the use of particular animal-derived products and chemicals. A working knowledge of ingredients commonly used in the interventional suite with religious and cultural connotations may be helpful. This review article highlights medications and medical devices with cultural or religiously sensitive ingredients used in interventional radiology departments and provides a framework for addressing this common scenario.

Automatic measurement of kidney dimensions in two-dimensional ultrasonography is comparable to expert sonographers.

Purpose: Length and width measurements of the kidneys aid in the detection and monitoring of structural abnormalities and organ disease. Manual measurement results in intra- and inter-rater variability, is complex and time-consuming, and is fraught with error. We propose an automated approach based on machine learning for quantifying kidney dimensions from two-dimensional (2D) ultrasound images in both native and transplanted kidneys. Approach: An nnU-net machine learning model was trained on 514 images to segment the kidney capsule in standard longitudinal and transverse views. Two expert sonographers and three medical students manually measured the maximal kidney length and width in 132 ultrasound cines. The segmentation algorithm was then applied to the same cines, region fitting was performed, and the maximum kidney length and width were measured. Additionally, single kidney volume for 16 patients was estimated using either manual or automatic measurements. Results: The experts resulted in length of 84.8±26.4 mm [95% CI: 80.0, 89.6] and a width of 51.8±10.5 mm [49.9, 53.7]. The algorithm resulted a length of 86.3±24.4 [81.5, 91.1] and a width of 47.1±12.8 [43.6, 50.6]. Experts, novices, and the algorithm did not statistically significant differ from one another (p>0.05). Bland-Altman analysis showed the algorithm produced a mean difference of 2.6 mm (SD = 1.2) from experts, compared to novices who had a mean difference of 3.7 mm (SD = 2.9 mm). For volumes, mean absolute difference was 47 mL (31%) consistent with ∼1 mm error in all three dimensions. Conclusions: This pilot study demonstrates the feasibility of an automatic tool to measure in vivo kidney biometrics of length, width, and volume from standard 2D ultrasound views with comparable accuracy and reproducibility to expert sonographers. Such a tool may enhance workplace efficiency, assist novices, and aid in tracking disease progression.

An Artificial Intelligence Training Workshop for Diagnostic Radiology Residents.

Purpose: To develop, implement, and evaluate feedback for an artificial intelligence (AI) workshop for radiology residents that has been designed as a condensed introduction of AI fundamentals suitable for integration into an existing residency curriculum. Materials and Methods: A 3-week AI workshop was designed by radiology faculty, residents, and AI engineers. The workshop was integrated into curricular academic half-days of a competency-based medical education radiology training program. The workshop consisted of live didactic lectures, literature case studies, and programming examples for consolidation. Learning objectives and content were developed for foundational literacy rather than technical proficiency. Identical prospective surveys were conducted before and after the workshop to gauge the participants' confidence in understanding AI concepts on a five-point Likert scale. Results were analyzed with descriptive statistics and Wilcoxon rank sum tests to evaluate differences. Results: Twelve residents participated in the workshop, with 11 completing the survey. An average score of 4.0 ± 0.7 (SD), indicating agreement, was observed when asking residents if the workshop improved AI knowledge. Confidence in understanding AI concepts increased following the workshop for 16 of 18 (89%) comprehension questions (P value range: .001 to .04 for questions with increased confidence). Conclusion: An introductory AI workshop was developed and delivered to radiology residents. The workshop provided a condensed introduction to foundational AI concepts, developed positive perception, and improved confidence in AI topics.Keywords: Medical Education, Machine Learning, Postgraduate Training, Competency-based Medical Education, Medical Informatics Supplemental material is available for this article. © RSNA, 2023.

Relationship Between Macular Thickness and Visual Acuity in the Treatment of Diabetic Macular Edema With Anti-VEGF Therapy: Systematic Review.

Purpose: To examine the relationship between central macular thickness (CMT) measured by optical coherence tomography (OCT) and visual acuity (VA) in patients with center-involving diabetic macular edema (DME) receiving antivascular endothelial growth factor (anti-VEGF) treatment. Methods: Peer-reviewed articles from 2016 to 2020 reporting intravitreal injections of bevacizumab, ranibizumab, or aflibercept that provided data on pretreatment (baseline) and final retinal thickness (CMT) and visual acuity (VA) were identified. The relationship between relative changes was assessed via a linear random-effects regression model controlling for treatment group. Results: No significant association between the logarithm of the minimum angle of resolution (logMAR) VA and CMT was found in 41 eligible studies evaluating 2667 eyes. The observed effect estimate was a 0.12 increase (95% CI, -0.124 to 2.47) in logMAR VA per 100 µm reduction in CMT after treatment change. There were no significant differences in logMAR VA between the anti-VEGF treatment groups. Conclusions: There was no statistically significant relationship between the change in logMAR VA and change in CMT as well as no significant effect of the type of anti-VEGF treatment on the change in logMAR VA. Although OCT analysis, including measurements of CMT, will continue to be an integral part of the management of DME, further exploration is needed on additional anatomic factors that might contribute to visual outcomes.

Tempering Expectations on the Medical Artificial Intelligence Revolution: The Medical Trainee Viewpoint.

The rapid development of artificial intelligence (AI) in medicine has resulted in an increased number of applications deployed in clinical trials. AI tools have been developed with goals of improving diagnostic accuracy, workflow efficiency through automation, and discovery of novel features in clinical data. There is subsequent concern on the role of AI in replacing existing tasks traditionally entrusted to physicians. This has implications for medical trainees who may make decisions based on the perception of how disruptive AI may be to their future career. This commentary discusses current barriers to AI adoption to moderate concerns of the role of AI in the clinical setting, particularly as a standalone tool that replaces physicians. Technical limitations of AI include generalizability of performance and deficits in existing infrastructure to accommodate data, both of which are less obvious in pilot studies, where high performance is achieved in a controlled data processing environment. Economic limitations include rigorous regulatory requirements to deploy medical devices safely, particularly if AI is to replace human decision-making. Ethical guidelines are also required in the event of dysfunction to identify responsibility of the developer of the tool, health care authority, and patient. The consequences are apparent when identifying the scope of existing AI tools, most of which aim to be physician assisting rather than a physician replacement. The combination of the limitations will delay the onset of ubiquitous AI tools that perform standalone clinical tasks. The role of the physician likely remains paramount to clinical decision-making in the near future.

Insights from teaching artificial intelligence to medical students in Canada.

Clinical artificial intelligence (AI) applications are rapidly developing but existing medical school curricula provide limited teaching covering this area. Here we describe an AI training curriculum we developed and delivered to Canadian medical undergraduates and provide recommendations for future training.

Real-time automatic tumor segmentation for ultrasound-guided breast-conserving surgery navigation.

PURPOSE: Ultrasound-based navigation is a promising method in breast-conserving surgery, but tumor contouring often requires a radiologist at the time of surgery. Our goal is to develop a real-time automatic neural network-based tumor contouring process for intraoperative guidance. Segmentation accuracy is evaluated by both pixel-based metrics and expert visual rating. METHODS: This retrospective study includes 7318 intraoperative ultrasound images acquired from 33 breast cancer patients, randomly split between 80:20 for training and testing. We implement a u-net architecture to label each pixel on ultrasound images as either tumor or healthy breast tissue. Quantitative metrics are calculated to evaluate the model's accuracy. Contour quality and usability are also assessed by fellowship-trained breast radiologists and surgical oncologists. Additionally, the viability of using our u-net model in an existing surgical navigation system is evaluated by measuring the segmentation frame rate. RESULTS: The mean dice similarity coefficient of our u-net model is 0.78, with an area under the receiver-operating characteristics curve of 0.94, sensitivity of 0.95, and specificity of 0.67. Expert visual ratings are positive, with 93% of responses rating tumor contour quality at or above 7/10, and 75% of responses rating contour quality at or above 8/10. Real-time tumor segmentation achieved a frame rate of 16 frames-per-second, sufficient for clinical use. CONCLUSION: Neural networks trained with intraoperative ultrasound images provide consistent tumor segmentations that are well received by clinicians. These findings suggest that neural networks are a promising adjunct to alleviate radiologist workload as well as improving efficiency in breast-conserving surgery navigation systems.

Health Care Students' Perspectives on Artificial Intelligence: Countrywide Survey in Canada.

BACKGROUND: Artificial intelligence (AI) is no longer a futuristic concept; it is increasingly being integrated into health care. As studies on attitudes toward AI have primarily focused on physicians, there is a need to assess the perspectives of students across health care disciplines to inform future curriculum development. OBJECTIVE: This study aims to explore and identify gaps in the knowledge that Canadian health care students have regarding AI, capture how health care students in different fields differ in their knowledge and perspectives on AI, and present student-identified ways that AI literacy may be incorporated into the health care curriculum. METHODS: The survey was developed from a narrative literature review of topics in attitudinal surveys on AI. The final survey comprised 15 items, including multiple-choice questions, pick-group-rank questions, 11-point Likert scale items, slider scale questions, and narrative questions. We used snowball and convenience sampling methods by distributing an email with a description and a link to the web-based survey to representatives from 18 Canadian schools. RESULTS: A total of 2167 students across 10 different health professions from 18 universities across Canada responded to the survey. Overall, 78.77% (1707/2167) predicted that AI technology would affect their careers within the coming decade and 74.5% (1595/2167) reported a positive outlook toward the emerging role of AI in their respective fields. Attitudes toward AI varied by discipline. Students, even those opposed to AI, identified the need to incorporate a basic understanding of AI into their curricula. CONCLUSIONS: We performed a nationwide survey of health care students across 10 different health professions in Canada. The findings would inform student-identified topics within AI and their preferred delivery formats, which would advance education across different health care professions.