A deep learning algorithm to detect cutaneous squamous cell carcinoma on frozen sections in Mohs micrographic surgery: A retrospective assessment.

Intraoperative margin analysis is crucial for the successful removal of cutaneous squamous cell carcinomas (cSCC). Artificial intelligence technologies (AI) have previously demonstrated potential for facilitating rapid and complete tumour removal using intraoperative margin assessment for basal cell carcinoma. However, the varied morphologies of cSCC present challenges for AI margin assessment. The aim of this study was to develop and evaluate the accuracy of an AI algorithm for real-time histologic margin analysis of cSCC. To do this, a retrospective cohort study was conducted using frozen cSCC section slides. These slides were scanned and annotated, delineating benign tissue structures, inflammation and tumour to develop an AI algorithm for real-time margin analysis. A convolutional neural network workflow was used to extract histomorphological features predictive of cSCC. This algorithm demonstrated proof of concept for identifying cSCC with high accuracy, highlighting the potential for integration of AI into the surgical workflow. Incorporation of AI algorithms may improve efficiency and completeness of real-time margin assessment for cSCC removal, particularly in cases of moderately and poorly differentiated tumours/neoplasms. Further algorithmic improvement incorporating surrounding tissue context is necessary to remain sensitive to the unique epidermal landscape of well-differentiated tumours, and to map tumours to their original anatomical position/orientation.

A deep learning algorithm to detect cutaneous squamous cell carcinoma on frozen sections in Mohs micrographic surgery: a retrospective assessment.

Importance: Intraoperative margin analysis is crucial for the successful removal of cutaneous squamous cell carcinomas (cSCC). Artificial intelligence technologies (AI) have previously demonstrated potential for facilitating rapid and complete tumor removal using intraoperative margin assessment for basal cell carcinoma. However, the varied morphologies of cSCC present challenges for AI margin assessment. Objective: To develop and evaluate the accuracy of an AI algorithm for real-time histologic margin analysis of cSCC. Design: A retrospective cohort study was conducted using frozen cSCC section slides and adjacent tissues. Setting: This study was conducted in a tertiary care academic center. Participants: Patients undergoing Mohs micrographic surgery for cSCC between January and March 2020. Exposures: Frozen section slides were scanned and annotated, delineating benign tissue structures, inflammation, and tumor to develop an AI algorithm for real-time margin analysis. Patients were stratified by tumor differentiation status. Epithelial tissues including epidermis and hair follicles were annotated for moderate-well to well differentiated cSCC tumors. A convolutional neural network workflow was used to extract histomorphological features predictive of cSCC at 50-micron resolution. Main Outcomes and Measures: The performance of the AI algorithm in identifying cSCC at 50-micron resolution was reported using the area under the receiver operating characteristic curve. Accuracy was also reported by tumor differentiation status and by delineation of cSCC from epidermis. Model performance using histomorphological features alone was compared to architectural features (i.e., tissue context) for well-differentiated tumors. Results: The AI algorithm demonstrated proof of concept for identifying cSCC with high accuracy. Accuracy differed by differentiation status, driven by challenges in separating cSCC from epidermis using histomorphological features alone for well-differentiated tumors. Consideration of broader tissue context through architectural features improved the ability to delineate tumor from epidermis. Conclusions and Relevance: Incorporating AI into the surgical workflow may improve efficiency and completeness of real-time margin assessment for cSCC removal, particularly in cases of moderately and poorly differentiated tumors/neoplasms. Further algorithmic improvement is necessary to remain sensitive to the unique epidermal landscape of well-differentiated tumors, and to map tumors to their original anatomical position/orientation. Future studies should assess the efficiency improvements and cost benefits and address other confounding pathologies such as inflammation and nuclei. Funding sources: JL is supported by NIH grants R24GM141194, P20GM104416 and P20GM130454. Support for this work was also provided by the Prouty Dartmouth Cancer Center development funds. Key Points: Question: How can the efficiency and accuracy of real-time intraoperative margin analysis for the removal of cutaneous squamous cell carcinoma (cSCC) be improved, and how can tumor differentiation be incorporated into this approach?Findings: A proof-of-concept deep learning algorithm was trained, validated, and tested on frozen section whole slide images (WSI) for a retrospective cohort of cSCC cases, demonstrating high accuracy in identifying cSCC and related pathologies. Histomorphology alone was found to be insufficient to delineate tumor from epidermis in histologic identification of well-differentiated cSCC. Incorporation of surrounding tissue architecture and shape improved the ability to delineate tumor from normal tissue.Meaning: Integrating artificial intelligence into surgical procedures has the potential to enhance the thoroughness and efficiency of intraoperative margin analysis for cSCC removal. However, accurately accounting for the epidermal tissue based on the tumor's differentiation status requires specialized algorithms that consider the surrounding tissue context. To meaningfully integrate AI algorithms into clinical practice, further algorithmic refinement is needed, as well as the mapping of tumors to their original surgical site, and evaluation of the cost and efficacy of these approaches to address existing bottlenecks.

Multi-method assessment of palatable food exposure in women with and without eating disorders.

OBJECTIVE: Eating disorders (EDs) are characterized by dysregulated responses to palatable food. Using a multi-method approach, this study examined responses to palatable food exposure and subsequent ad libitum eating in women with binge-eating disorder (BED: n = 64), anorexia nervosa (AN: n = 16), and bulimia nervosa (BN: n = 35) and 26 healthy controls (HCs). METHOD: Participants were exposed to palatable food followed by an ad libitum eating opportunity. Affective and psychophysiological responses were measured before and during the task. RESULTS: Participants with EDs reported greater negative affect, particularly fear, following the food cue exposure, whereas HCs reported no change. BN and BED groups reported greater urge to binge after the food cue exposure, whereas AN and HC groups reported no change. Respiratory sinus arrhythmia levels, skin conductance and tonic skin conductance levels increased during food exposure for all groups. Across baseline and during the food exposure, the BED group had lower respiratory sinus arrhythmia levels relative to the BN and HC groups. The BED group consumed significantly more palatable food than the AN group. CONCLUSIONS: 'Palatable' food stimuli elicited more negative affect, particularly fear, in individuals with EDs; and this, rather than psychophysiological responses, distinguishes individuals with EDs from those without.

Assessment of executive functioning in binge-eating disorder independent of weight status.

OBJECTIVE: Executive functioning (EF) problems may serve as vulnerability or maintenance factors for Binge-Eating Disorder (BED). However, it is unclear if EF problems observed in BED are related to overweight status or BED status. The current study extends this literature by examining EF in overweight and normal-weight BED compared to weight-matched controls. METHOD: Participants were normal-weight women with BED (n = 23), overweight BED (n = 32), overweight healthy controls (n = 48), and normal-weight healthy controls (n = 29). The EF battery utilized tests from the National Institutes of Health (NIH) Toolbox and Delis-Kaplan Executive Function System (D-KEFS). RESULTS: After controlling for years of education and minority status, overweight individuals performed more poorly than normal-weight individuals on a task of cognitive flexibility requiring generativity (p < .01), and speed on psychomotor performance tasks (p = .01). Normal-weight and overweight BED performed worse on working memory tasks compared to controls (p = .04). Unexpectedly, normal-weight BED individuals out-performed all other groups on an inhibitory control task (p < .01). No significant differences were found between the four groups on tasks of planning. DISCUSSION: Regardless of weight status, BED is associated with working memory problems. Replication of the finding that normal-weight BED is associated with enhanced inhibitory control is needed.

Taste assessment in normal weight and overweight individuals with co-occurring Binge Eating Disorder.

BACKGROUND: Taste perception influences food choice, and may contribute to both weight status and disordered eating. Relatively little work has attempted to disentangle contributions of weight status and Binge Eating Disorder (BED) to human taste perception. We predicted weight status and BED would interact, showing difference in taste perception from non-eating disorder matched groups. METHODS: The four study groups included: normal weight BED (NW BED), normal weight healthy controls (NW HC), overweight BED (OW BED), and overweight healthy controls (OW HC) (N = 60). Groups were matched for age (±5 years), ethnicity, and weight status. Participants were assessed using the Structured Clinical Interview for DSM-IV Axis I Disorders, the Eating Disorder Examination Version 16.0, and the NIH Toolbox Gustatory Assessment with additional taste solutions and taste stimulus delivered with edible taste strips. RESULTS: Interactions were found between weight status and diagnosis on measures of regional taste intensity for quinine hydrochloride (CI 95% [44.61, 56.31], p = 0.018), sucrose (CI 95% [46.79, 56.45], p = 0.003), and 6-n-propylthiouracil (CI 95% [25.557, 39.269], p = 0.015). OW BED participants perceived these taste stimuli significantly less intensely than OW HC and NW BED. Whole mouth taste intensity tests at suprathreshold amounts did not reveal group differences. All four groups reported similar hedonic response to taste stimuli. Edible taste strips had medium to large significant correlations with NIH Gustatory Assessment taste stimuli. CONCLUSIONS: There were significant differences in the taste perception of OW BED relative to the other three groups. These findings may provide partial explanation as to why previous studies correlating taste and weight status have mixed results. Replication in larger samples assessed longitudinally is needed to extend this work.

Digging into Debt: The Financial Burden Associated with the Otolaryngology Match.

Objective To quantify the cost incurred during the match process for otolaryngology applicants, determine sources of expenditures, and highlight potential methods to alleviate financial burden of the match process. Study Design Cross-sectional. Study Setting Online survey. Subjects and Methods An electronic survey was sent via email to those who applied to the otolaryngology residency programs at Dartmouth-Hitchcock Medical Center and MedStar Georgetown University Hospital during the 2016 application cycle. Questions regarding demographics and experiences with the match were multiple choice, and questions regarding cost were open answer. Data were downloaded and analyzed on Excel and Minitab software. Results Twenty-eight percent of the total 370 applicants completed the survey. The mean cost of away rotations was $2500 (95% confidence interval [CI], $2224-$2776). With application fees and the cost of interviewing, the mean total cost of applying for the 2016 otolaryngology match was $6400 (95% CI, $5710-$7090), with a total range of $1200 to $20,000. Twenty-eight percent of students did not have sufficient funds for applying and interviewing despite seeking out additional monetary resources. Conclusion In 2016, otolaryngology applicants spent a mean of $8900 (95% CI, $7935-$9865) on away rotations, applications, and interviewing. Half of the applicants obtained additional funding to cover this cost, while 28% still did not have sufficient funding. Methods of decreasing cost may include instituting a cap on application number, videoconferencing interviews, regionalizing interviews, and adjusting the interview timeline.