Single color virtual H&E staining with In-and-Out Net.

Virtual staining streamlines traditional staining procedures by digitally generating stained images from unstained or differently stained images. While conventional staining methods involve time-consuming chemical processes, virtual staining offers an efficient and low infrastructure alternative. Leveraging microscopy-based techniques, such as confocal microscopy, researchers can expedite tissue analysis without the need for physical sectioning. However, interpreting grayscale or pseudo-color microscopic images remains a challenge for pathologists and surgeons accustomed to traditional histologically stained images. To fill this gap, various studies explore digitally simulating staining to mimic targeted histological stains. This paper introduces a novel network, In-and-Out Net, specifically designed for virtual staining tasks. Based on Generative Adversarial Networks (GAN), our model efficiently transforms Reflectance Confocal Microscopy (RCM) images into Hematoxylin and Eosin (H&E) stained images. We enhance nuclei contrast in RCM images using aluminum chloride preprocessing for skin tissues. Training the model with virtual H\&E labels featuring two fluorescence channels eliminates the need for image registration and provides pixel-level ground truth. Our contributions include proposing an optimal training strategy, conducting a comparative analysis demonstrating state-of-the-art performance, validating the model through an ablation study, and collecting perfectly matched input and ground truth images without registration. In-and-Out Net showcases promising results, offering a valuable tool for virtual staining tasks and advancing the field of histological image analysis.

Undergarment Needs and Challenges for Breast Cancer Survivors: A Qualitative Study.

Purpose: Breast cancer surgery, even with reconstruction, can make it difficult for patients to find a bra that fits properly, is comfortable, and meets their aesthetic standards. We explored breast cancer survivors' experiences with bras over time to identify preferences, needs, and challenges throughout their journeys. Methods: Fifteen women who had undergone mastectomy and either delayed or immediate breast reconstruction participated in the study. Focus groups were conducted to explore the participants' current experiences with bras. They were also prompted to recall their experiences before mastectomy and immediately after reconstruction. The discussion included bra materials, styles, construction techniques, color, quality, and price. Results: Thematic analysis generated five major themes: "Sense of normalcy and personal well-being," "Struggles immediately following surgery," "Transitions in bra experiences and preference," "Practicality with outfit," and "Association between quality and price". Conclusion: Breast cancer survivors' well-being is linked to their experiences with bras and the associated purchasing process, and bra needs change throughout the cancer care journey. Survivors' experiences with bras impact their sense of normalcy and sense of control over significant bodily changes arising from cancer and its treatment. The study underscores the importance of future research on examining the relationship between survivors' quality of life and garment experiences, including factors such as color choices, closure options, and adjustability for individual needs.

Impact of autologous breast reconstruction on bra fit.

PURPOSE: To inform bra design by analyzing 3D surface images of breast cancer patients who underwent autologous breast reconstruction. METHODS: We computed bra design measurements on 3D surface images of patients who underwent unilateral and bilateral autologous breast reconstruction. Breast measurements and right-left symmetry between preoperative baseline and postoperative time points were compared using either paired Student t-test or Wilcoxon signed-rank test, depending on the data's distribution. Regression analysis determined associations between measurements and patient characteristics such as age. Postoperative measurements and symmetry differences were also compared between autologous and implant-based breast reconstruction. RESULTS: Among participants who underwent bilateral autologous breast reconstruction, the reconstructed breasts were smaller and positioned higher on the chest wall than their native breasts. For patients who underwent unilateral reconstruction, similar postoperative changes were observed in the contralateral breast due to symmetry procedures. Overall, for participants whose baseline breast measurements showed substantial asymmetry, unilateral reconstruction decreased right-left asymmetry whereas bilateral reconstruction amplified right-left asymmetry. Preoperative baseline breast measurements, age, and BMI were statistically significantly associated with most postoperative breast measurements for participants who underwent bilateral autologous reconstruction. Compared to implant-based reconstruction, autologous reconstruction resulted in fewer changes in breast shape and symmetry that are pertinent to bra fit. CONCLUSION: Preoperative baseline breast measurements, age, and BMI can impact bra designs for breast cancer survivors who undergo autologous reconstruction due to size, shape, and symmetry changes. Bra needs of people who undergo autologous reconstruction differ from those who undergo implant-based reconstruction.

Machine Learning of Physiologic Waveforms and Electronic Health Record Data: A Large Perioperative Data Set of High-Fidelity Physiologic Waveforms.

Perioperative morbidity and mortality are significantly associated with both static and dynamic perioperative factors. The studies investigating static perioperative factors have been reported; however, there are a limited number of previous studies and data sets analyzing dynamic perioperative factors, including physiologic waveforms, despite its clinical importance. To fill the gap, the authors introduce a novel large size perioperative data set: Machine Learning Of physiologic waveforms and electronic health Record Data (MLORD) data set. They also provide a concise tutorial on machine learning to illustrate predictive models trained on complex and diverse structures in the MLORD data set.

Impact of Autologous Breast Reconstruction on Bra Fit.

Purpose: To inform bra design by analyzing 3D surface images of breast cancer patients who underwent autologous breast reconstruction. Methods: We computed bra design measurements on 3D surface images of patients who underwent unilateral and bilateral autologous breast reconstruction. Breast measurements and right-left symmetry between preoperative baseline and postoperative time points were compared using either paired Student t test or Wilcoxon signed rank test, depending on the data's distribution. Regression analysis determined associations between measurements and patient characteristics such as age. Postoperative measurements and symmetry differences were also compared between autologous and implant-based breast reconstruction. Results: Among participants who underwent bilateral autologous breast reconstruction, the reconstructed breasts were smaller and positioned higher on the chest wall than their native breasts. For patients who underwent unilateral reconstruction, similar postoperative changes were observed in the contralateral breast due to symmetry procedures. Overall, for participants whose baseline breast measurements showed substantial asymmetry, unilateral reconstruction decreased right-left asymmetry whereas bilateral reconstruction amplified right-left asymmetry. Preoperative baseline breast measurements, age, and BMI were statistically significantly associated with most postoperative breast measurements for participants who underwent bilateral autologous reconstruction. Compared to implant-based reconstruction, autologous reconstruction resulted in fewer changes in breast shape and symmetry that are pertinent to bra fit. Conclusion: Preoperative baseline breast measurements, age, and BMI can impact bra designs for breast cancer survivors who undergo autologous reconstruction due to size, shape, and symmetry changes. Bra needs of people who undergo autologous reconstruction differ from those who undergo implant-based reconstruction.

Assessing saliency models of observers' visual attention on acquired facial differences.

Purpose: Saliency models that predict observers' visual attention to facial differences could enable psychosocial interventions to help patients and their families anticipate staring behaviors. The purpose of this study was to assess the ability of existing saliency models to predict observers' visual attention to acquired facial differences arising from head and neck cancer and its treatment. Approach: Saliency maps predicted by graph-based visual saliency (GBVS), an artificial neural network (ANN), and a face-specific model were compared to observer fixation maps generated from eye-tracking of lay observers presented with clinical facial photographs of patients with a visible or functional impairment manifesting in the head and neck region. We used a linear mixed-effects model to investigate observer and stimulus factors associated with the saliency models' accuracy. Results: The GBVS model predicted many irrelevant regions (e.g., shirt collars) as being salient. The ANN model underestimated observers' attention to facial differences relative to the central region of the face. Compared with GBVS and ANN, the face-specific saliency model was more accurate on this task; however, the face-specific model underestimated the saliency of deviations from the typical structure of human faces. The linear mixed-effects model revealed that the location of the facial difference (midface versus periphery) was significantly associated with saliency model performance. Model performance was also significantly impacted by interobserver variability. Conclusions: Existing saliency models are not adequate for predicting observers' visual attention to facial differences. Extensions of face-specific saliency models are needed to accurately predict the saliency of acquired facial differences arising from head and neck cancer and its treatment.

A cognitive behavioral therapy-based intervention to address body image in patients with facial cancers: Results from a randomized controlled trial.

OBJECTIVES: Body image adjustment is a crucial issue for patients with facial cancer, but body image-specific interventions are scarce. We report results of a novel psychotherapeutic intervention to address body image concerns during acute postoperative recovery following facial reconstructive surgery. Our primary aims were to evaluate the intervention's feasibility, acceptability, and efficacy on body image concerns, psychological distress, and quality of life (QOL). METHODS: Adults with facial cancers who endorsed body image concerns were recruited to participate in a randomized controlled trial. The intervention group participated in 4 in-person counseling sessions. The control group received an educational booklet and a brief phone call. Participants completed measures of body image, distress, and QOL at baseline and at the 4-week follow-up to assess the impact of the intervention. Intervention outcomes were assessed with 2 sample t-tests or Mann-Whitney U tests as appropriate. RESULTS: Twenty-nine participants completed both the baseline and follow-up assessments. The intervention demonstrated good feasibility with a high retention rate (79%), visit completion rate (81%), and high satisfaction scores (75% reported mean satisfaction score of >3). Intervention did not result in an observed statistically significant difference in reduction in body image dissatisfaction and disturbance, psychological distress, or improvement in QOL compared with the control group. However, intervention resulted in statistically significant difference in perceived social impact (-1 vs. -8.3, p = 0.033) compared to control group. SIGNIFICANCE OF RESULTS: Our study highlights the potential clinical benefits of a novel psychotherapeutic intervention that targets body image concerns and suggests the need for further evaluation.

Objective Analysis of Breast Symmetry in Female Patients Undergoing Breast Reconstruction After Total Mastectomy.

Background: Satisfaction with the breast aesthetic outcome is an expectation of breast reconstruction surgery, which is an integral part of cancer treatment for many patients. We evaluated postreconstruction breast symmetry in 82 female patients using distance and volume measurements. Objectives: Clinical factors, such as reconstruction type (implant-based and autologous reconstruction), laterality, timing of reconstruction (immediate, delayed, and sequential), radiation therapy (RT), and demographic factors (age, BMI, race, and ethnicity), were evaluated as predictors of postoperative symmetry. Matched preoperative and postoperative measurements for a subset of 46 patients were used to assess correlation between preoperative and postoperative symmetry. Methods: We used standardized differences between the left and right breasts for the sternal notch to lowest visible point distance and breast volume as metrics for breast, positional symmetry, and volume symmetry, respectively. We performed statistical tests to compare symmetry between subgroups of patients based on reconstruction type, laterality, timing, RT, and demographics. Results: Overall, reconstruction type, reconstruction timing, and RT were observed to be factors significantly associated with postoperative symmetry, with implant reconstructions and immediate reconstruction procedures, and no RT showing better postoperative breast volume symmetry. Subgroup analyses, for both reconstruction type and laterality, showed superior volume symmetry for the bilateral implant reconstructions. No correlation was observed between preoperative and postoperative breast symmetry. Demographic factors were not significant predictors of postreconstruction symmetry. Conclusions: This comprehensive analysis examines multiple clinical factors in a single study and will help both patients and surgeons make informed decisions about reconstruction options at their disposal.

Impact of implant-based breast reconstruction on bra fit.

Comfortable and well-fitting bras are necessary for good quality of life but hard to find for women who undergo reconstruction after breast cancer treatment. This study aimed to provide data to inform bra designs for breast cancer survivors. We measured anatomical distances used in bra design on 3D clinical photographs of patients who underwent unilateral and bilateral implant-based reconstruction to quantify changes after reconstruction relative to the measured values before the person underwent surgery. We performed additional assessments of symmetry before surgery and after reconstruction, and we used regression analyses to identify associations between the measurements and patient characteristics, such as BMI. Overall, almost all measurements changed significantly in implant-based reconstructed breasts relative to native breasts. We highlight several aspects of ergonomic bra design that will be impacted by the changes in anatomical distances. Practitioner summary: Implant-based breast reconstruction surgery changes the breast so that off-the-rack bras are inadequate. This study provides designers with measurement data from women who underwent implant-based reconstruction to inform bra designs for this population. The key factor designers need to account for is the semi-spherical shape of the reconstructed breast.

Breast Decisions: Recommender System for Appearance Counseling about Breast Reconstruction.

Appearance counseling is an important component of the consent process for breast reconstruction. The purpose of appearance counseling is to help the patient form realistic expectations of what she might look like after breast reconstruction. In this article, we introduce a recommender system, "BreastDecisions," for appearance counseling that suggests photographs of previous patients that are tailored to a specific patient to help her form realistic expectations of her own reconstruction. Methods: We present user specifications and algorithm parameters needed to incorporate the recommender system into the appearance counseling workflow. We demonstrate the system for a common counseling scenario using a knowledgebase of previous breast reconstruction patients. The medical appropriateness of the recommended photographs for use in appearance counseling was evaluated by experts using a four-point rating system. Results: The recommender system presents photographs that are medically appropriate for counseling a specific patient, depicts typical outcomes, and adapts to a variety of clinical workflows. For each of 33 patients taken as examples of breast reconstruction patients, we used the system to identify photographs for appearance counseling. The baseline average medical appropriateness of the recommended photographs was between mostly appropriate (some explanation needed) and medically appropriate (minimal explanation needed). We demonstrate filtering and ranking steps to reduce the number of recommended photographs and increase the average medical appropriateness. Conclusions: Our recommender system automatically suggests photographs of previous breast reconstruction patients for use in counseling a patient about appearance outcomes. The system is patient-specific and customizable to a particular surgeon's practice.

Deep learning on reflectance confocal microscopy improves Raman spectral diagnosis of basal cell carcinoma.

SIGNIFICANCE: Raman spectroscopy (RS) provides an automated approach for assisting Mohs micrographic surgery for skin cancer diagnosis; however, the specificity of RS is limited by the high spectral similarity between tumors and normal tissues structures. Reflectance confocal microscopy (RCM) provides morphological and cytological details by which many features of epidermis and hair follicles can be readily identified. Combining RS with deep-learning-aided RCM has the potential to improve the diagnostic accuracy of RS in an automated fashion, without requiring additional input from the clinician. AIM: The aim of this study is to improve the specificity of RS for detecting basal cell carcinoma (BCC) using an artificial neural network trained on RCM images to identify false positive normal skin structures (hair follicles and epidermis). APPROACH: Our approach was to build a two-step classification model. In the first step, a Raman biophysical model that was used in prior work classified BCC tumors from normal tissue structures with high sensitivity. In the second step, 191 RCM images were collected from the same site as the Raman data and served as inputs for two ResNet50 networks. The networks selected the hair structure and epidermis images, respectively, within all images corresponding to the positive predictions of the Raman biophysical model with high specificity. The specificity of the BCC biophysical model was improved by moving the Raman spectra corresponding to these selected images from false positive to true negative. RESULTS: Deep-learning trained on RCM images removed 52% of false positive predictions from the Raman biophysical model result while maintaining a sensitivity of 100%. The specificity was improved from 84.2% using Raman spectra alone to 92.4% by integrating Raman spectra with RCM images. CONCLUSIONS: Combining RS with deep-learning-aided RCM imaging is a promising tool for guiding tumor resection surgery.

BMEntored: Enhancing the First-Year Experience in a BME Doctoral Program.

We describe our experiences with the first offering of a new program, BMEntored, for supporting first-year doctoral students in Biomedical Engineering (BME) during their first semester. The goal of BMEntored was to enhance the first-semester experience of first-year doctoral students in BME with an emphasis on guiding students in selecting a research supervisor and promoting cross-cohort, cross-lab social connections.

What Does "Dr. Google" Show Patients Searching for Breast Reconstruction Outcomes Photographs?

Many women with breast cancer search the internet for photographs of their potential reconstruction outcomes, but little is known about the quality, variety, and relevance of images patients are viewing. Methods: Breast reconstruction outcome photographs identified by a Google Images search were assessed based on the American Society of Plastic Surgeons/Plastic Surgery Foundation photographic guidelines. Information such as source metadata, breast reconstruction procedure information, and subject demographics was collected from the photographs. Additional analyses were conducted to assess whether nipple reconstruction or tattooing occurred and was disclosed, whether a symmetry procedure was performed and disclosed, and whether donor site scarring is visible in abdominal flap photographs. Results: We acquired and analyzed 114 photograph sets. Although a variety of images were readily available, the majority of photograph sets did not follow photographic guidelines or provide sufficient information. Most photograph sets (60%) indicated symmetry procedures when a symmetry procedure was evident, but only 40% of photograph sets disclosed a nipple procedure when a nipple procedure was evident. Only 40% of abdominal flap photographs showed donor site scarring. Subject demographics were largely missing: 50% of photograph sets included subject age, 3% included race or ethnicity, and 12% included weight or BMI. Conclusions: Although breast reconstruction outcome photographs shown by "Dr. Google" represent a variety of reconstruction types, they typically lack information that a patient needs to assess self-applicability. Patients may benefit from discussion with their healthcare team about the strengths and limitations of breast reconstruction outcome photographs available on the internet.

The role of psychosocial factors in patients' recollections of breast reconstruction options discussed with their surgeons.

A patient's comprehension and memory of conversations with their providers plays an important role in their healthcare. Adult breast cancer patients whose legal sex was female and who underwent treatment at the Center for Reconstructive Surgery at The University of Texas MD Anderson Cancer Center were asked to indicate which breast reconstruction procedures they discussed with their surgeon. We focused on the three most frequent responses: (a) participants who remembered discussing implant-based, tissue-based, and combination procedures; (b) participants who remembered only an implant-based option being discussed; and (c) participants who remember only a tissue-based option being discussed. We used multinomial logistic regression models to explore the psychosocial factors associated with patients' recollections of their breast reconstruction options after discussions with their reconstructive surgeons, controlling for medical factors that impact surgical decision-making. Our analyses identified body mass index, body image investment, and body image as statistically significantly associated with the reconstructive options that a participant recalls discussing with their surgeon. Our findings highlight body image investment and body image as important psychological factors that may influence what patients remember from consultations about breast reconstruction options.

Healthcare Fraud Data Mining Methods: A Look Back and Look Ahead.

Healthcare fraud is an expensive, white-collar crime in the United States, and it is not a victimless crime. Costs associated with fraud are passed on to the population in the form of increased premiums or serious harm to beneficiaries. There is an intense need for digital healthcare fraud detection systems to evolve in combating this societal threat. Due to the complex, heterogenic data systems and varied health models across the US, implementing digital advancements in healthcare is difficult. The end goal of healthcare fraud detection is to provide leads to the investigators that can then be inspected more closely with the possibility of recoupments, recoveries, or referrals to the appropriate authorities or agencies. In this article, healthcare fraud detection systems and methods found in the literature are described and summarized. A tabulated list of peer-reviewed articles in this research domain listing the main objectives, conclusions, and data characteristics is provided. The potential gaps identified in the implementation of such systems to real-world healthcare data will be discussed. The authors propose several research topics to fill these gaps for future researchers in this domain.

On the Three-Dimensional Mechanical Behavior of Human Breast Tissue.

As the human breast undergoes complex, large-scale, fully three dimensional deformations in vivo, three-dimensional (3D) characterization of its mechanical behavior is fundamental to its diagnosis, treatment, and surgical modifications. Its anisotropic, heterogeneous fibrous structure results in complex behavior at both the tissue and organ levels. Mathematically modeling of this complex anisotropic behavior is thus critical to the proper simulation of the human breast. Yet, current breast tissue constitutive models do not account for these complexities, so that there is a pressing need for more detailed fully 3D analysis. To this end, we performed a full 3D kinematic mechanical evaluation of human fibroglandular and adipose breast tissues. We utilized our recently developed 3D kinematic numerical-experimental approach to acquire force-displacement data from both breast tissue subtypes. This was done by subjecting cuboidal test specimens, aligned to the anatomical axes,to both pure shear and simple compression loading paths. We then developed novel constitutive model that was able to simulate the unique anisotropic tension/compression behaviors observed. Constitutive model parameters were determined using a detailed finite element model of the experimental setup coupled to nonlinear optimization. We found that human breast tissues displayed complex anisotropic behavior, with strong, directionally dependent non-linearities. This was especially true for the fibroglandular tissue. The novel constitutive model was also able fully capture these behaviors, including states of combined tension and compression (i.e. in pure shear). The results of this study suggest that human breast tissue is complex in its mechanical response, exhibiting varying levels of anisotropy. Future studies will be required to link the observed anisotropy to the physical structure of the tissue, as well as mapping this heterogeneity and anisotropy across individuals.

Potential of Intraoperative 3D Photography and 3D Visualization in Breast Reconstruction.

Although pre- and postoperative three-dimensional (3D) photography are well-established in breast reconstruction, intraoperative 3D photography is not. We demonstrate the process of intraoperative acquisition and visualization of 3D photographs for breast reconstruction and present clinicians' opinions about intraoperative visualization tools. METHODS: Mastectomy specimens were scanned with a handheld 3D scanner during breast surgery. The 3D photographs were processed to compute morphological measurements of the specimen. Three visualization modalities (screen-based viewing, augmented reality viewing, and 3D printed models) were created to show different representations of the 3D photographs to plastic surgeons. We interviewed seven surgeons about the usefulness of the visualization methods. RESULTS: The average time for intraoperative acquisition of 3D photographs of the mastectomy specimen was 4 minutes, 8 seconds ± 44 seconds. The average time for image processing to compute morphological measurements of the specimen was 54.26 ± 40.39 seconds. All of the interviewed surgeons would be more inclined to use intraoperative visualization if it displayed information that they are currently missing (eg, the target shape of the reconstructed breast mound). Additionally, the surgeons preferred high-fidelity visualization tools (such as 3D printing) that are easy-to-use and have minimal disruption to their current workflow. CONCLUSIONS: This study demonstrates that 3D photographs can be collected intraoperatively within acceptable time limits, and quantitative measurements can be computed timely to be utilized within the same procedure. We also report surgeons' comments on usability of visualization methods and of measurements of the mastectomy specimen, which can be used to guide future surgical practice.

Goldilocks Principle: Preference for Change in Breast Size in Breast Cancer Reconstruction Patients.

Patients' preferences regarding changing or maintaining their breast size after mastectomy and reconstruction are important but understudied determinants of post-surgical satisfaction and quality of life. The goal of this study was to identify factors associated with preferences for changing or maintaining breast size for women undergoing breast reconstruction at The University of Texas MD Anderson Cancer Center in the United States from 2011 to 2014. The average age of participants was 45.7 ± 9.1 years. At baseline, mean average breast volumes were 755.7 ± 328.4 mL for all women (n = 48), 492.3 mL ± 209.3 for 13 women who preferred to be "bigger than now," 799.2 mL ± 320.9 for 25 women who preferred to remain "about the same," and 989.3 mL ± 253.1 for 10 women who preferred "smaller than now." Among the 23 women who preferred to change their breast size, 19 desired to shift toward the mean. Women with the smallest and largest 20% of baseline breast size were more likely to desire a change toward the mean (p = 0.006). Multinomial logistic regression models found average breast volume and satisfaction with breast size to be the most important factors associated with preferences for changing or maintaining breast size for women undergoing breast reconstruction. This study provides preliminary evidence for a "Goldilocks principle" in women's preferences for breast size change in the context of breast reconstruction, and identifies hypotheses for future studies of the associations among preference for change in breast size, preference achievement, and post-reconstruction body image.

Imaging sub-diffuse optical properties of cancerous and normal skin tissue using machine learning-aided spatial frequency domain imaging.

SIGNIFICANCE: Sub-diffuse optical properties may serve as useful cancer biomarkers, and wide-field heatmaps of these properties could aid physicians in identifying cancerous tissue. Sub-diffuse spatial frequency domain imaging (sd-SFDI) can reveal such wide-field maps, but the current time cost of experimentally validated methods for rendering these heatmaps precludes this technology from potential real-time applications. AIM: Our study renders heatmaps of sub-diffuse optical properties from experimental sd-SFDI images in real time and reports these properties for cancerous and normal skin tissue subtypes. APPROACH: A phase function sampling method was used to simulate sd-SFDI spectra over a wide range of optical properties. A machine learning model trained on these simulations and tested on tissue phantoms was used to render sub-diffuse optical property heatmaps from sd-SFDI images of cancerous and normal skin tissue. RESULTS: The model accurately rendered heatmaps from experimental sd-SFDI images in real time. In addition, heatmaps of a small number of tissue samples are presented to inform hypotheses on sub-diffuse optical property differences across skin tissue subtypes. CONCLUSION: These results bring the overall process of sd-SFDI a fundamental step closer to real-time speeds and set a foundation for future real-time medical applications of sd-SFDI such as image guided surgery.