Radiology Training Research Articles

Radiology Resident Diagnostic In-Training Exam Scores: Impact of Subspecialty Imaging Volume and Rotation Scheduling

PurposeTo determine the relationship between resident imaging volumes and number of subspecialty rotations with Diagnostic Radiology In-Training (DXIT) subspecialty scores. MethodsDXIT-scaled subspecialty scores from a single large diagnostic radiology training program from 2014 to 2020 were obtained. The cumulative number of imaging studies dictated by each resident and specific rotations were mapped to each subspecialty for each year of training. DXIT subspecialty scores were compared against the total subspecialty imaging volume and the total number of rotations in a subspecialty for each resident year. A total of 52 radiology residents were trained during the study period and included in the dataset. ResultsThere was a positive linear relationship between the number of neuro studies and scaled neuro DXIT scores for R1s (Pearson coefficient: 0.29; p-value: 0.034) and between the number of breast studies and the number of neuro studies with DXIT scores for R2s (Pearson coefficients: 0.50 and 0.45, respectively; p-values: 0.001 and 0.003, respectively). Furthermore, a positive significant linear relationship between the total number of rotations in cardiac, breast, neuro, and thoracic subspecialties and their scaled DXIT scores for R2 residents (Pearson coefficients: 0.34, 0.49, 0.33, and 0.32, respectively; p-value: 0.025, 0.001, 0.03, and 0.036, respectively) and between the total number of nuclear medicine rotations with DXIT scores for R3s (Pearson coefficient: 0.41; p-value: 0.016). ConclusionResident subspecialty imaging volumes and rotations have a variable impact on DXIT scores. Understanding the impact of study volume and the number of subspecialty rotations on resident medical knowledge will help residents and program directors determine how much emphasis to place on these factors during residency.

Better safe than so ray: national survey of radiation protection amongst interventional radiology trainees in the United Kingdom.

To establish the provision and use of radiation personal protective equipment (PPE) and dosimetry amongst UK interventional radiology (IR) trainees and highlight areas of improvement in order to enhance the radiation safety. A survey questionnaire was designed by members of the British Society of Interventional Radiology (BSIR) trainee committee via survey monkey and distributed to UK IR trainees via the BSIR membership mailing list, local representatives and Twitter. The survey was open from 04/01/2021 to 20/02/2021. Only IR trainees in years ST4 and above were included. Of the 73 respondents, 62 qualified for analysis. Respondents (81% male) spent a median of 5.5 sessions (half day list) per week in the angiography suite and 58% (n=36) had difficulty finding appropriately sized lead aprons at least once a week. Overall 53% (n=33) had concerns about their radiation PPE. Furthermore 56% of trainees (n=35) experienced back pain among other symptoms attributed to wearing the lead aprons available to them. 77% (n=48) regularly wore lead glasses. For trainees requiring prescription glasses (n=22) overfit goggles were provided however 17 (77%) of these trainees felt the goggles compromised their ability to perform the procedure. Eye and finger dosimeters were used by 50% and 52% of respondents respectively. Compliance with body dosimetry was 99%. Provision of radiation PPE and dose monitoring for IR trainees is suboptimal, particularly access to adequate eye protection or suitably fitting leads. Based on the findings of this survey, recommendations have been made to promote the safety and radiation awareness of IR trainees. Radiation protection practices for IR trainees nationally are poor. Provision of suitable eye protection and well fitting lead body protection is low.

An MRI-based radiomics nomogram for differentiating spinal metastases from multiple myeloma.

Spinal metastasis and multiple myeloma share many overlapping conventional radiographic imaging characteristics, thus, their differentiation may be challenging. The purpose of this study was to develop and validate an MRI-based radiomics nomogram for the differentiation of spinal metastasis and multiple myeloma. A total of 312 patients (training set: n = 146, validation set: n = 65, our center; external test set: n = 101, two other centers) with spinal metastasis (n = 196) and multiple myeloma (n = 116) were retrospectively enrolled. Demographics and MRI findings were assessed to build a clinical factor model. Radiomics features were extracted from MRI images. A radiomics model was constructed by the least absolute shrinkage and selection operator method. A radiomics nomogram combining the radiomics signature and independent clinical factors was constructed. And, one experienced radiologist reviewed the MRI images for all case. The diagnostic performance of the different models was evaluated by receiver operating characteristic curves. A clinical factors model was built based on heterogeneous appearance and shape. Twenty-one features were used to build the radiomics signature. The area under the curve (AUC) values of the radiomics nomogram (0.853 and 0.762, respectively) were significantly higher than that of the clinical factor model (0.692 and 0.540, respectively) in both validation (p = 0.048) and external test (p < 0.001) sets. The AUC values of the radiomics nomogram model were higher than that of radiologist in training, validation and external test sets (all p < 0.05). Moreover, no significant difference in AUC values of radiomics nomogram model was found between the validation set and external test set (p = 0.212). The radiomics nomogram can differentiate spinal metastasis and multiple myeloma with a moderate to good performance, and may be as a valuable method to assist in the clinical diagnosis and preoperative decision-making.

The Potential Usefulness of ChatGPT in Oral and Maxillofacial Radiology.

Aim This study aimed to evaluate the potential usefulness of Chat Generated Pre-Trained Transformer-3 (ChatGPT-3) in oral and maxillofacial radiology for report writing by identifying radiographic anatomical landmarksand learning about oral and maxillofacial pathologiesand their radiographic features. The study also aimed to evaluate the performance of ChatGPT-3 and its usage in oral and maxillofacial radiology training. Materials and methods A questionnaire consisting of 80 questions was queried on the OpenAI app ChatGPT-3. The questions were stratified based on three categories. The categorization was based on random anatomical landmarks, oral and maxillofacial pathologies, and the radiographic features of some of these pathologies. One oral and maxillofacial radiologist evaluated queries that were answered by the ChatGPT-3 model and rated them on a 4-point, modified Likert scale. The post-survey analysis for the performance of ChatGPT-3 was based on the Strengths, Weaknesses, Opportunities, and Threats (SWOT) analysis,its application in oral and maxillofacial radiology training, and its recommended use. Results In order of efficiency, Chat GPT-3 gave 100%accuracy in describing radiographic landmarks. However, the content of the oral and maxillofacial pathologies was limited to major or characteristic radiographic features. The mean scores for the queries related to the anatomic landmarks, oral and maxillofacial pathologies, and radiographic features of the oral and maxillofacial pathologies were 3.94, 3.85, and 3.96, respectively. However, the median and mode scores were 4 and were similar to all categories. The data for the oral and maxillofacial pathologies when the questions were not specifically included in the format of the introduction of the pathology, causes, symptoms, and treatment. Out of two abbreviations, one was not answered correctly. Conclusion The study showed that ChatGPT-3 is efficient in describing the pathology, characteristic radiographic features, and describing anatomical landmarks. ChatGPT-3 can be used as an adjunct when an oral radiologist needs additional information on any pathology, however, it cannot be the mainstay for reference. ChatGPT-3 is less detail-oriented, and the data has a risk of infodemics and the possibility of medical errors. However, Chat GPT-3 can be an excellent tool in helping the community in increasing the knowledge and awareness of various pathologies and decreasing the anxiety of the patients while dental healthcare professionals formulate an appropriate treatment plan.

COVID-Necessitated Online Radiology Elective Improves Student Imaging Appropriateness in Clinical Case Vignettes

The use of imaging in medicine has increased considerably over the previous decades, contributing to significant inefficiency of use. Radiology education varies amongst institutions without standardized learning objectives. Consequently, many physicians and student doctors are unprepared to make appropriate choices regarding imaging. In response to COVID-19-engendered restrictions, we created a fully online, image-intensive radiology curriculum to introduce students to clinical radiology and appropriate imaging usage. A 2-week radiology elective curriculum was created that adopted accessible, free, online-based learning to foster student education and patient safety while upholding academic standards. Each unit included an emphasis on imaging appropriateness. Students assembled an elective portfolio including self-assessments and prepared a clinical radiology conference to present as a radiologist in training. Two final assessments were required. One consisted of clinical vignettes based on American College of Radiology (ACR) Appropriateness Criteria (AC). The second was an MRI safety quiz. Third and fourth year students at five institutions (N=97) completed the elective. Examination scores on an assessment adapted from the ACR AC were significantly improved compared to previously published scores of medical students who took ACR AC-based assessments without taking a radiology course. The course was published and shared with medical schools worldwide. The elective successfully educated students in radiology through a virtual platform and introduced them to the concept of appropriateness in medical imaging. These goals were accomplished using a free, online, easily accessible curriculum. Incorporation of additional topics within the discipline of radiology should be included in the curriculum in the future.

Awareness of interventional radiology and image guided musculoskeletal interventions among orthopaedic surgeons, rheumatologists, and physiatrists: A multi-site analysis

PurposeEvaluate physicians who treat musculoskeletal (MSK) disorders in their knowledge of image-guided MSK interventions, and identify areas that could benefit from education. Materials and methodsA 17-question survey was distributed to orthopaedic surgeons, physiatrists, and rheumatologists in the 14-hospital health system. It inquired about demographics, practice environment, awareness of interventional radiology (IR) and MSK radiology (MSKR) training, referral patterns, and knowledge of image-guided MSK interventions. ResultsIn total, 59 of 303 physicians completed the survey (41% orthopaedists, 35% physiatrists, and 24% rheumatologists). Most (93%) were attendings and 41% were female. A minority of survey respondents (17%) recognized the designation of IR as a distinct specialty of medicine per the American Board of Medical Specialties, in contrast to MSKR, which is not designated as a distinct specialty. When queried about IR procedures not under investigation, 24% selected genicular artery embolization and 31% selected embolization for adhesive capsulitis. Barriers to referral were as follows: 21% of specialists performed the procedure, 17% listed electronic medical record challenges, 14% reported scheduling difficulty, 13% reported no barriers, 11% reported difficulty consulting, 11% referred to another specialty, 10% did not have enough knowledge of image guided procedures, and 3% reported the procedure is not performed by IR or MSKR. ConclusionsSurvey data reveal a knowledge gap among surveyed physicians regarding IR as a specialty as well as areas of IR research in MSK disorders. Findings suggest areas where referring physicians can be educated and identify barriers to referral.

Peering Into the Future: A First Look at the CBME Transition to Practice Stage in Diagnostic Radiology

Queen's University (Kingston, ON, Canada) adopted a competency-based medical education (CBME) curriculum for Diagnostic Radiology residency training in an accelerated manner in 2017, with the curriculum comprised of four stages of training. This article focuses on the final stage (Transition to Practice), during which assessment methods of the new national curriculum (implemented in July 2022) were piloted. This study aims to highlight the challenges and opportunities associated with the implementation of CBME in Diagnostic Radiology training and specific considerations for programs undergoing this curricular transition. Ethics approval was provided by the affiliated hospital Research Ethics Board. All relevant electronic assessments pertaining to all trainees who had completed the Transition to Practice stage (n=3) were collated, deidentified, analyzed, and presented in tabulated format. A total of 39 evaluations completed by 13 assessors were assessed, with an average time of 3minutes and 6seconds to complete an assessment form. Also, 95% of evaluations were rated as entrustments. However, no residents met the minimum number of required entrustments for all five stage-specific Entrustable Professional Activities. These 39 evaluations included 219 milestone rating scores, with 86% rated as "achieved." Following review by the residency program Competence Committee, all three residents were promoted from the Transition to Practice stage. Challenges in CBME implementation include the number and quality of resident assessments. Strategies for success may include providing clear guidelines and training for both faculty and residents, early identification and intervention, and adopting a holistic evaluation strategy. CBME has the potential to enhance medical education quality by emphasizing learner progress toward competency and providing personalized feedback and support.

Machine Learning Classification of Body Part, Imaging Axis, and Intravenous Contrast Enhancement on CT Imaging.

Purpose: The development and evaluation of machine learning models that automatically identify the body part(s) imaged, axis of imaging, and the presence of intravenous contrast material of a CT series of images. Methods: This retrospective study included 6955 series from 1198 studies (501 female, 697 males, mean age 56.5years) obtained between January 2010 and September 2021. Each series was annotated by a trained board-certified radiologist with labels consisting of 16 body parts, 3 imaging axes, and whether an intravenous contrast agent was used. The studies were randomly assigned to the training, validation and testing sets with a proportion of 70%, 20% and 10%, respectively, to develop a 3D deep neural network for each classification task. External validation was conducted with a total of 35,272 series from 7 publicly available datasets. The classification accuracy for each series was independently assessed for each task to evaluate model performance. Results: The accuracies for identifying the body parts, imaging axes, and the presence of intravenous contrast were 96.0% (95% CI: 94.6%, 97.2%), 99.2% (95% CI: 98.5%, 99.7%), and 97.5% (95% CI: 96.4%, 98.5%) respectively. The generalizability of the models was demonstrated through external validation with accuracies of 89.7 - 97.8%, 98.6 - 100%, and 87.8 - 98.6% for the same tasks. Conclusions: The developed models demonstrated high performance on both internal and external testing in identifying key aspects of a CT series.

Survey of factors affecting satisfaction and success of residents enrolled in European College of Veterinary Diagnostic Imaging (ECVDI) residency programs.

Several published studies have described the success and satisfaction of residents enrolled in human radiology training programs, however comparable studies for veterinary radiology residents are currently lacking. The purpose of this descriptive, survey study was to evaluate resident perceptions of the European College of Veterinary Diagnostic Imaging (ECVDI) residency training programs. A web-based survey was sent to all listed 114 ECVDI residents and received a 57.0% response (65/114). Of these, 88% of respondents enjoyed their training and 73.5% of finishing respondents agreed they felt ready to work as a veterinary radiologist. First-time pass rates for the theoretical and practical components of the board certifying examinations were >80%. Regarding research and exam preparation, 41.5% and 49.2% of respondents, respectively, did not feel they received appropriate guidance. Eleven percent of respondents felt a lack of mentoring and 7.7% reported not receiving annual appraisals. Findings from this study can be used as background for future studies on perceptions of ECVDI residents and ECVDI residency program directors and for future policy decisions regarding ECVDI residency training programs.

Automated Brain Tumour Detection and Classification using Deep Features and Bayesian Optimised Classifiers.

Brain tumour detection and classification require trained radiologists for efficient diagnosis. The proposed work aims to build a Computer Aided Diagnosis (CAD) tool to automate brain tumour detection using Machine Learning (ML) and Deep Learning (DL) techniques. Magnetic Resonance Image (MRI) collected from the publicly available Kaggle dataset is used for brain tumour detection and classification. Deep features extracted from the global pooling layer of Pretrained Resnet18 network are classified using 3 different ML Classifiers, such as Support vector Machine (SVM), K-Nearest Neighbour (KNN), and Decision Tree (DT). The above classifiers are further hyperparameter optimised using Bayesian Algorithm (BA) to enhance the performance. Fusion of features extracted from shallow and deep layers of the pretrained Resnet18 network followed by BA-optimised ML classifiers is further used to enhance the detection and classification performance. The confusion matrix derived from the classifier model is used to evaluate the system's performance. Evaluation metrics, such as accuracy, sensitivity, specificity, precision, F1 score, Balance Classification Rate (BCR), Mathews Correlation Coefficient (MCC) and Kappa Coefficient (Kp), are calculated. Maximum accuracy, sensitivity, specificity, precision, F1 score, BCR, MCC, and Kp of 99.11 %, 98.99 %, 99.22 %, 99.09 %, 99.09 %, 99.10 %, 98.21 %, 98.21 %, respectively, were obtained for detection using fusion of shallow and deep features of Resnet18 pretrained network classified by BA optimized SVM classifier. Feature fusion performs better for classification task with accuracy, sensitivity, specificity, precision, F1 score, BCR, MCC and Kp of 97.31 %, 97.30 %, 98.65 %, 97.37 %, 97.34 %, 97.97%, 95.99 %, 93.95 %, respectively. The proposed brain tumour detection and classification framework using deep feature extraction from Resnet 18 pretrained network in conjunction with feature fusion and optimised ML classifiers can improve the system performance. Henceforth, the proposed work can be used as an assistive tool to aid the radiologist in automated brain tumour analysis and treatment.

Interrater Agreement of CT Grading of Blunt Splenic Injuries: Does the AAST Grading Need to Be Reimagined?

Introduction: The Revised Organ Injury Scale (OIS) of the American Association for Surgery of Trauma (AAST) is the most widely accepted classification of splenic trauma. The objective of this study was to evaluate inter-rater agreement for CT grading of blunt splenic injuries. Methods: CT scans in adult patients with splenic injuries at a level 1 trauma centre were independently graded by 5 fellowship trained abdominal radiologists using the AAST OIS for splenic injuries - 2018 revision. The inter-rater agreement for AAST CT injury score, as well as low-grade (IIII) versus high-grade (IV-V) splenic injury was assessed. Disagreement in two key clinical scenarios (no injury versus injury, and high versus low grade) were qualitatively reviewed to identify possible sources of disagreement. Results: A total of 610 examinations were included. The inter-rater absolute agreement was low (Fleiss kappa statistic 0.38, P < 0.001), but improved when comparing agreement between low and high grade injuries (Fleiss kappa statistic of 0.77, P < .001). There were 34 cases (5.6%) of minimum two-rater disagreement about no injury vs injury (AAST grade ≥ I). There were 46 cases (7.5%) of minimum two-rater disagreement of low grade (AAST grade I-III) versus high grade (AAST grade IV-V) injuries. Likely sources of disagreement were interpretation of clefts versus lacerations, peri-splenic fluid versus subcapsular hematoma, application of adding multiple low grade injuries to higher grade injuries, and identification of subtle vascular injuries. Conclusion: There is low absolute agreement in grading of splenic injuries using the existing AAST OIS for splenic injuries.

The Impact of a Hands-On Interventional Radiology Training Course on Radiology Resident's Training: A Single Academic Institution Experience

Abstract Purpose The aim of this study was to investigate the outcomes of an instructional hands-on training course that introduces radiology residents to the essential tools and skills needed to perform basic interventional radiology (IR) procedures. Materials and Methods This study was performed over a single academic year at a single academic institution. A precourse survey was sent to all radiology residents to identify areas of weakness and potential opportunities for improvement. In view of the responses, a hands-on training course was designed to cover the basics of vascular and soft-tissue access, catheters, wires, embolics, and closure devices. The training was provided in a one-to-one setting by a single IR attending over a period of 45 minutes and was concluded with hands-on training on an ultrasound (US) vascular access phantom whenever possible. An anonymous postcourse survey was then distributed and the results were analyzed. Results The average reported comfort level with basic IR concepts prior to course attendance was 1.7 on a 5-point scale (1 = not comfortable, 5 = very comfortable). This increased to an average of 4 following the course. Ninety-three percent of residents reported they have more confidence getting into the IR suite and assisting in IR procedures following the course. Residents who had an opportunity to train on the US vascular access phantom gave an average response of 4.6 out of 5 to a question of how helpful the experience was in improving their US hand skills (1 = not helpful, 5 = extremely helpful). One hundred percent of responders reported that the course successfully met its goal. Finally, the overall responses were unanimously in favor of continuing the hands-on training course. Conclusion A personalized, cost-effective, hands-on training course can improve the IR training experience of radiology residents, especially in the early training phase. This model is of particular value for smaller to medium-sized academic institutions with limited financial and educational resources.

Appropriate Reliance on Artificial Intelligence in Radiology Education

Users of artificial intelligence (AI) can become overreliant on AI, negatively affecting the performance of human-AI teams. For a future in which radiologists use interpretive AI tools routinely in clinical practice, radiology education will need to evolve to provide radiologists with the skills to use AI appropriately and wisely. In this work, we examine how overreliance on AI may develop in radiology trainees and explore how this problem can be mitigated, including through the use of AI-augmented education. Radiology trainees will still need to develop the perceptual skills and mastery of knowledge fundamental to radiology to use AI safely. We propose a framework for radiology trainees to use AI tools with appropriate reliance, drawing on lessons from human-AI interactions research.

Structured feedback-How to improve radiology training

Structured feedback-How to improve radiology training

News from the European Journal of Therapeutics: A new issue and a new editorial board

News from the European Journal of Therapeutics: A new issue and a new editorial board

Whitepaper: Training in Diagnostic and Interventional Breast Radiology.

Breast imaging represents an integral part of radiology and is subject to strict quality controls. Regarding this, precise diagnostics including multimodal assessment by mammography, sonography, and MRI, including image-guided biopsy and localization procedures, is often decisive and must be performed by experts with profound knowledge and skills in all of these procedures.However, due to numerous restructurings, breast imaging has been shifted more and more towards large, specialized centers, resulting in less patient exposition and training opportunities for radiologists in smaller sites. The following whitepaper summarizes the current circumstances and discusses opinions of the participating societies. Under the leadership of the German Roentgen Society (DRG) and with the participation of the DRG's AG Mammadiagnostik, the CAFRAD (Chefarztforum Radiologie), the KLR (Konferenz der Lehrstuhlinhaber für Radiologie e. V.), the DRG's Forum Junge Radiologie (FJR) and the Berufsverband der Deutschen Radiologen e. V. (BDR), possible solutions were discussed and consented for a structured training in breast radiology in the future. In addition to the teaching provided at the primary workplace, qualified training should be ensured through flexible, multi-institutional, interdisciplinary, and cross-sectoral collaboration. Furthermore, the integration of online case collections and close cooperation with certified breast cancer centers and mammography screening units is recommended. It is indispensible that online courses and case collections adhere to the standards of the national societies and include a maximum of one third of the required cases. In order to provide training in breast radiology at a high professional level, a paradigm shift with closer cooperation of all participants is necessary. This includes close collaboration of the breast imaging societies with the federal medical associations to establish new teaching concepts like e-learning in the training schedule of radiologists. · Breast diagnostics is an integral part of radiology training.. · Due to recent restructurings, smaller training centers have difficulties in meeting the case numbers demanded by the Specialist Training Regulations (WBO). Improved integration of the new structures and their adaptation to the needs of education are necessary to guarantee standardized high-quality training of young radiologists.. · The integration of certified case collections enables quality-assured training, even across regions in online-based formats. In accordance with the "blended learning principle", up to one-third of the required number of patient studies can be substituted with cases from a certified case collection.. · Legally secured short- and medium-term internships may complement training in radiology.. · Sauer ST, Bley TA, Wenkel E et al. Whitepaper: Training in Diagnostic and Interventional Breast Radiology. Fortschr Röntgenstr 2023; 195: 699 - 706.

Improved Segmentation of Pulmonary Nodules Using Soft Computing Techniques with SegNet and Adversarial Networks

Lung cancer is seen as one of the most common lung diseases. For the patients having symptoms, the presence of lung nodules is checked by using various imaging techniques. Pulmonary nodules are detected in most of the cases having symptoms. But identifying the type of the nodule and the categorization still remains as a challenge. After confirming the presence of a nodule (benign or malignant) it takes several other steps to identify its characteristics. Improved imaging methods produce results within a short span of time. Research works are being conducted to increase the overall efficiency of the system. The proposed system considers authentic data sources for the study. The benign and malignant samples are considered for the generation of realistic large image sets. The generation of a large data set with the help of a generative adversarial network (GAN) is the first part of the work. The generated images using GAN cannot be differentiated from the original images even by a trained radiologist. This proves the importance of images generated using GAN. A GAN is able to generate 1024 × 1024 resolutions for natural images. Real data images are used to finetune the SegNet output. Through transfer learning, these weights are transferred to the system for segmentation of the images. The training process use real and generated images, which improve theefficiency of the network. The original data from LUNA 16 was used to further generate benign and malignant samples using GAN. A total of 440 images and their augmented images were used for training the GAN, and it generated 1,001,000 images. Hence the overall efficiency of the system was improved. To verify the results, the same various combinations and methods were considered and tabulated with various parameters. Methods with SegNet, GAN, and other combinations were evaluated to verify the efficiency of the system. Receiver operating characteristics were also plotted and compared with the area under the curve for verification of the results.

Ultrasound simulation training to meet the 2021 Royal College of Radiologists' curriculum for radiology trainees: South East London experience

To enhance ultrasound teaching delivery to radiology trainees using a simulation course matched to the 2021 Royal College of Radiologists (RCR) curriculum. An ultrasound simulation training course was designed for specialty trainees (ST) 1 in radiology, which was based on the 2021 RCR curriculum and covered the top ultrasound training priorities. The course was piloted initially on two occasions in a 1-day format to the August 2021 and the March 2022 ST1 intake trainees. Based on the feedback, a comprehensive 4-day course was developed and delivered between October and December 2022 for the August 2022 ST1 intake, funded by Health Education England. The outcomes measured were subjective trainee feedback using numerical scores and free text. All King's College Hospital NHS Foundation Trust radiology ST1 trainees from the August 2021 to the August 2022 intake participated in ultrasound simulation training. The training matched the RCR curriculum and increased the trainees' confidence and competency in medical ultrasound. Ultrasound simulation training can be successfully delivered to ST1 trainees to match the 2021 RCR curriculum and enhance training in medical ultrasound for radiologists.

The Impact of the Dobbs Decision on Diagnostic Radiology Applicants, Residents, and Program Directors

In the Dobbs decision the United States Supreme Court overturned Roe v. Wade, returning the issue of abortion to the states. To date, there is little published data on the impact this might have on where future residents choose to pursue graduate medical education. We investigated the potential effects of the resultant varied political landscape of abortion care access laws with respect to influence on the selection of prospective diagnostic radiology training programs by medical students, comparing application rates for the 2022 recruitment cycle to the prior 4 years across a geographically diverse group of 22 academic and community sites across the United States. We provide strategies for program directors to consider in dealing with topics related to this continually evolving issue as it pertains to resident recruitment and retention.

Automated Classification of Lung Cancer Subtypes Using Deep Learning and CT-Scan Based Radiomic Analysis

Artificial intelligence and emerging data science techniques are being leveraged to interpret medical image scans. Traditional image analysis relies on visual interpretation by a trained radiologist, which is time-consuming and can, to some degree, be subjective. The development of reliable, automated diagnostic tools is a key goal of radiomics, a fast-growing research field which combines medical imaging with personalized medicine. Radiomic studies have demonstrated potential for accurate lung cancer diagnoses and prognostications. The practice of delineating the tumor region of interest, known as segmentation, is a key bottleneck in the development of generalized classification models. In this study, the incremental multiple resolution residual network (iMRRN), a publicly available and trained deep learning segmentation model, was applied to automatically segment CT images collected from 355 lung cancer patients included in the dataset “Lung-PET-CT-Dx”, obtained from The Cancer Imaging Archive (TCIA), an open-access source for radiological images. We report a failure rate of 4.35% when using the iMRRN to segment tumor lesions within plain CT images in the lung cancer CT dataset. Seven classification algorithms were trained on the extracted radiomic features and tested for their ability to classify different lung cancer subtypes. Over-sampling was used to handle unbalanced data. Chi-square tests revealed the higher order texture features to be the most predictive when classifying lung cancers by subtype. The support vector machine showed the highest accuracy, 92.7% (0.97 AUC), when classifying three histological subtypes of lung cancer: adenocarcinoma, small cell carcinoma, and squamous cell carcinoma. The results demonstrate the potential of AI-based computer-aided diagnostic tools to automatically diagnose subtypes of lung cancer by coupling deep learning image segmentation with supervised classification. Our study demonstrated the integrated application of existing AI techniques in the non-invasive and effective diagnosis of lung cancer subtypes, and also shed light on several practical issues concerning the application of AI in biomedicine.