Pectoral muscle removal in mammogram images: A novel approach for improved accuracy and efficiency.

PURPOSE: Accurate pectoral muscle removal is critical in mammographic breast density estimation and many other computer-aided algorithms. We propose a novel approach to remove pectoral muscles form mediolateral oblique (MLO) view mammograms and compare accuracy and computational efficiency with existing method (Libra). METHODS: A pectoral muscle identification pipeline was developed. The image is first binarized to enhance contrast and then the Canny algorithm was applied for edge detection. Robust interpolation is used to smooth out the pectoral muscle region. Accuracy and computational speed of pectoral muscle identification was assessed using 951 women (1,902 MLO mammograms) from the Joanne Knight Breast Health Cohort at Washington University School of Medicine. RESULTS: Our proposed algorithm exhibits lower mean error of 12.22% in comparison to Libra's estimated error of 20.44%. This 40% gain in accuracy was statistically significant (p < 0.001). The computational time for the proposed algorithm is 5.4 times faster when compared to Libra (5.1 s for proposed vs. 27.7 s for Libra per mammogram). CONCLUSION: We present a novel approach for pectoral muscle removal in mammogram images that demonstrates significant improvement in accuracy and efficiency compared to existing method. Our findings have important implications for the development of computer-aided systems and other automated tools in this field.

Comparison between two packages for pectoral muscle removal on mammographic images.

BACKGROUND: Pectoral muscle removal is a fundamental preliminary step in computer-aided diagnosis systems for full-field digital mammography (FFDM). Currently, two open-source publicly available packages (LIBRA and OpenBreast) provide algorithms for pectoral muscle removal within Matlab environment. PURPOSE: To compare performance of the two packages on a single database of FFDM images. METHODS: Only mediolateral oblique (MLO) FFDM was considered because of large presence of pectoral muscle on this type of projection. For obtaining ground truth, pectoral muscle has been manually segmented by two radiologists in consensus. Both LIBRA's and OpenBreast's removal performance with respect to ground truth were compared using Dice similarity coefficient and Cohen-kappa reliability coefficient; Wilcoxon signed-rank test has been used for assessing differences in performances; Kruskal-Wallis test has been used to verify possible dependence of the performance from the breast density or image laterality. RESULTS: FFDMs from 168 consecutive women at our institution have been included in the study. Both LIBRA's Dice-index and Cohen-kappa were significantly higher than OpenBreast (Wilcoxon signed-rank test P < 0.05). No dependence on breast density or laterality has been found (Kruskal-Wallis test P > 0.05). CONCLUSION: Libra has a better performance than OpenBreast in pectoral muscle delineation so that, although our study has not a direct clinical application, these results are useful in the choice of packages for the development of complex systems for computer-aided breast evaluation.

Breast Augmentation in Athletic Women: A Retrospective Survey Assessing Pectoral Muscle Function and Implant Aesthetics Post-Augmentation.

BACKGROUND: Breast augmentation is the most common cosmetic, surgical procedure (1). Implant insertion planes include subglandular or submuscular. Submuscular augmentation is often preferred in women with less soft tissue coverage; requiring pectoralis major dissection (2). However, loss of functional muscle fibres is undesirable in athletic women who actively train the pectoral region. OBJECTIVES: 1. Assessment of pectoralis function and strength after breast augmentation in athletic women. 2. Augmentation aesthetical satisfaction at rest and whilst training. METHODS: A retrospective survey was sent to female, fitness competitors with breast implants via social media over a six-month period. The survey assessed baseline demographics, pectoral strength (bench press, push-ups, pectoral fly), aesthetical satisfaction and issues during training including pain, rippling, firmness and implant movement. RESULTS: Eighty-one participants were surveyed. The mean age of augmentation was 29.7 (±8.41), and mean age of survey completion was 37.6 (±7.22) years. Submuscular augmentation was performed in 72.8% of participants. Recovery post-operative and time spent training was synonymous. The majority of participants' pectoral strength was unaffected or positively affected by breast augmentation. Assessment of post-operative performance and training issues of pain, rippling and firmness yielded no statistically significant difference between groups. Implant movement during pectoral exercises was 2.5 times more likely with submuscular augmentations, p= 0.038. Overall, the majority of the population were very satisfied or satisfied with their breast aesthetic at rest (92.6%) and during training (79.0%). CONCLUSIONS: Breast augmentation in athletic women has a high satisfaction rate with the majority maintaining or improving the strength of the pectoral region regardless of augmentation plane. LEVEL OF EVIDENCE IV: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors https://www.springer.com/journal/00266 .

Safety of an Intravenous Formulation of Voriconazole as an Intramuscular Injection in Pigeons (Columba livia f. domestica).

Aspergillosis is a common disease in birds. Currently, avian aspergillosis is treated with voriconazole administered orally, although intramuscular (IM) administration increases bioavailability and is more effective in treating generalized aspergillosis. The objective of this study was to evaluate the safety of the intravenous formulation of voriconazole as an IM injection in the pectoral muscles of pigeons (Columba livia f. domestica) as a model for other avian species. Sixteen healthy pigeons received IM injections of voriconazole (12.5 mg/kg) and sterile saline in the right and left pectoral muscles, respectively, twice a day for 7 days. Additionally, 4 birds acted as controls (no injections). Eight birds in the treatment group and 2 of the control pigeons were humanely euthanized 1 day (group 1) and 14 days (group 2) after the final injection. Hematologic and plasma biochemistry panels were performed prior to the birds being euthanized. Gross and histopathological evaluations of the pectoral muscles were completed postmortem. Statistical analysis revealed significant differences in multiple parameters, including aspartate aminotransferase and lactate dehydrogenase, but all biochemical analytes remained within the reference intervals for the species. The group 1 birds had advanced gross and histopathological pectoral muscle lesions associated with the voriconazole injections compared with the contralateral side, the group 2 birds, and the negative controls. After 14 days, the pectoral muscles did not reveal any gross or histopathological changes associated with the voriconazole or sterile saline injections. These results indicate that the intravenous formulation is safe for IM use twice per day for 1 week in pigeons. Further investigation is needed to extrapolate these findings to other avian species and to evaluate the roles of longer treatment periods and higher doses of voriconazole.

Small RNA sequencing of pectoral muscle tissue reveals microRNA-mediated gene modulation in chicken muscle growth.

Sichuan mountainous black-bone (SMB) chicken is a small-sized black-feathered chicken breed with low amount of meat, while Dahen (DH) chicken has a larger body size and a faster growth rate. MicroRNAs (miRNAs) are involved in various physiological processes, but their role in chicken muscle growth remains unclear. We aimed to investigate the miRNAs and pathways participating in the muscle growth of chicken. MiRNA profiles of four SMB chickens and four DH chickens were detected by small RNA sequencing. A total of 994 known miRNAs were identified, among which gga-miR-1a-3p, gga-miR-148-3p and gga-miR-133a-3p exhibited the highest enrichment in both breeds of chickens. Thirty-two miRNAs were differently expressed between SMB and DH chickens. The differently expressed miRNAs were mainly associated with fatty acid metabolism, immunity and MAPK activation-related processes. Kyoto encyclopaedia of genes and genomes (KEGG) analysis showed that miRNAs were involved in the immunity-related and MAPK signalling pathways. Moreover, miR-204 was downregulated in DH chicken compared with SMB chicken, and significantly inhibited the expression of MAP3K13, which is involved in the MAPK pathway. It was confirmed through luciferase reporter assays that miR-204 specifically inhibited the activity of MAP3K13. Our results helped demonstrate the potential molecular mechanisms of muscle growth in chickens and provide valuable information for chicken breeding.

Vacuum-assisted closure therapy combined with bi-pectoral muscle flap for the treatment of deep sternal wound infections.

Deep sternal wound infection (DSWI) is a fatal complication after median sternotomy. This study was to assess the effect of vacuum-assisted closure (VAC) combined with bi-pectoral muscle advancement flap therapy on rehabilitation for the treatment of DSWI. Fifty-two patients with DSWI underwent treatment of VAC and bi-pectoral muscle flap. These patients were followed-up 12 months postoperation. The patient characteristics, duration of VAC therapy, the mean hospital stay, and postoperative complications were retrospectively analysed. All patients underwent 1 to 3 VAC treatment sessions before closure. Fifty-one of 52 DSWI patients were cured to discharge; the mean hospital stay was 26.5 days. The drainage tube continued to drain a large amount of bloody fluid in three patients after the wound was closed. Respiratory failure occurred in one patient with severe mediastinal and pulmonary infections and died eventually in hospital. One patient died of acute cerebral haemorrhage during the12-month follow-up. VAC therapy combined with bi-pectoral muscle flap is a simple and effective treatment for DSWIs with short hospital stays and few complications. However, this is a retrospective case series presentation with no comparison group; further large-scale controlled studies are needed.

Removal of pectoral muscle based on topographic map and shape-shifting silhouette.

BACKGROUND: In digital mammography, finding accurate breast profile segmentation of women's mammogram is considered a challenging task. The existence of the pectoral muscle may mislead the diagnosis of cancer due to its high-level similarity to breast body. In addition, some other challenges due to manifestation of the breast body pectoral muscle in the mammogram data include inaccurate estimation of the density level and assessment of the cancer cell. The discrete differentiation operator has been proven to eliminate the pectoral muscle before the analysis processing. METHODS: We propose a novel approach to remove the pectoral muscle in terms of the mediolateral-oblique observation of a mammogram using a discrete differentiation operator. This is used to detect the edges boundaries and to approximate the gradient value of the intensity function. Further refinement is achieved using a convex hull technique. This method is implemented on dataset provided by MIAS and 20 contrast enhanced digital mammographic images. RESULTS: To assess the performance of the proposed method, visual inspections by radiologist as well as calculation based on well-known metrics are observed. For calculation of performance metrics, the given pixels in pectoral muscle region of the input scans are calculated as ground truth. CONCLUSIONS: Our approach tolerates an extensive variety of the pectoral muscle geometries with minimum risk of bias in breast profile than existing techniques.

Automatic Pectoral Muscle Region Segmentation in Mammograms Using Genetic Algorithm and Morphological Selection.

In computer-aided diagnosis systems for breast mammography, the pectoral muscle region can easily cause a high false positive rate and misdiagnosis due to its similar texture and low contrast with breast parenchyma. Pectoral muscle region segmentation is a crucial pre-processing step to identify lesions, and accurate segmentation in poor-contrast mammograms is still a challenging task. In order to tackle this problem, a novel method is proposed to automatically segment pectoral muscle region in this paper. The proposed method combines genetic algorithm and morphological selection algorithm, incorporating four steps: pre-processing, genetic algorithm, morphological selection, and polynomial curve fitting. For the evaluation results on different databases, the proposed method achieves average FP rate and FN rate of 2.03 and 6.90% (mini MIAS), 1.60 and 4.03% (DDSM), and 2.42 and 13.61% (INBreast), respectively. The results can be comparable performance in various metrics over the state-of-the-art methods.

Detection and Segmentation of Pectoral Muscle on MLO-View Mammogram Using Enhancement Filter.

The presence of predominant density region of the pectoral muscle in Medio-Lateral Oblique (MLO) view of the mammograms can affect or bias the results of mammograms processing for breast cancer detection using intensity based methods. Therefore, to improve the diagnostic performance of breast cancer detection using computer-aided system, identification and segmentation of pectoral muscle is an important task. This paper presents, an intensity based approach to identify the pectoral region in mammograms. In the presented approach enhancement mask and threshold technique is used to enhance and select the pectoral region and boundary points respectively, to find the boundary of pectoral muscle. Then curve fitting by Least Square Error (LSE) method is used to refine the rough initial boundaries. The proposed approach was applied on 320 mammograms from mini-Mammographic Image Analysis Society (mini-MIAS) database of 322 mammograms, with acceptable rate of 96.56% from radiologist experts. The performance evaluation for pectoral muscle segmentation, based on Hausdorff distance (H d ), False Positive (FP) and False Negative (FN) rate, shows the usefulness and effectiveness of the proposed approach.

INTRAOPERATIVE FAT GRAFTING INTO THE PECTORALIS AND LATISSIMUS DORSI MUSCLES-NOVEL MODIFICATION OF AUTOLOGOUS BREAST RECONSTRUCTION WITH EXTENDED LATISSIMUS DORSI FLAP.

BACKGROUND: The latissimus dorsi flap is a reliable and one of the most commonly used methods of both immediate and delayed breast reconstruction. Its disadvantage is the limited volume of transferred tissue. The authors present their experience with the use of extended latissimus dorsi flap associated with immediate fat grafting into the pectoralis and latissimus dorsi muscles for secondary breast reconstruction. METHODS: From 2013 to 2016, 14 patients underwent secondary unilateral total breast reconstruction with extended latissimus dorsi flap associated with primary fat grafting into the pectoralis major and latissimus dorsi muscles. Fat was injected under visual control between muscle fibers. Fat injected into the pectoralis muscle formed an apparent bulging - autoprosthesis. RESULTS: Mean patient age was 48.2 years (range, 34 to 64 years). Mean injected fat volume was 86.4 ml (range, 50 to 160 ml) and majority of this volume was injected into the pectoralis muscle. All flaps healed uneventfully and no fat grafting-related complications were observed. The most common complication was donor site seroma, which occurred in 57.1%. Results of postoperative ultrasound examination were evaluated. Incidence and the size of oil cysts and fat necroses were significantly lower in muscular layer in comparison with the subcutaneous layer of the reconstructed breast. CONCLUSIONS: Immediate fat transfer into the pectoralis and latissimus dorsi muscle increases the breast volume during the reconstruction with extended latissimus dorsi flap avoiding implant-related complications when abdominal tissue is not available. Pectoralis and latissimus dorsi muscles were shown as reliable and safe recipients for fat grafting.

Avian energetics: The passerine/non-passerine dichotomy.

Whether passerines collectively have a higher mean mass-independent basal rate of metabolism than the mean of other birds has been controversial. The conclusion that no difference exists was based on phylogenetic analyses. Higher basal rates, however, have been repeatedly seen in passerines and demonstrated by ANCOVA analyses. Several studies indicated that the mean mass-independent basal rate of passerines is >30% higher than the collective mean of other birds. Yet, at least three non-passerine orders of 25 have mean mass-independent basal rates equal to that of passerines. They are Anseriformes, Charadriiformes, and Procellariiformes, all characterized by an active lifestyle, including migratory and pelagic habits. In contrast, sedentary ducks endemic to islands have low basal rates. The high basal rates in temperate passerines correlate with migratory habits and life in cool to cold environments, the absence of these factors being partly responsible for the lower basal rates in most tropical passerines. The principal difference in energetics among non-passerines, between passerines and most non-passerines, and among passerines reflects the frequency of habits associated with high or low mass-independent energy expenditures, the habits correlating with body composition. The mean mass-independent basal rate in tropical passerines is slightly lower than in temperate passerines which implies that the collective mean in passerines would be somewhat lower if tropical passerines were included in proportion to their diversity. However, their inclusion will not eliminate the difference presently seen between passerines and other birds because the difference between tropical and temperate passerines is less than that between passerines and other birds.

Robust Automatic Pectoral Muscle Segmentation from Mammograms Using Texture Gradient and Euclidean Distance Regression.

In computer-aided diagnosis (CAD) of mediolateral oblique (MLO) view of mammogram, the accuracy of tissue segmentation highly depends on the exclusion of pectoral muscle. Robust methods for such exclusions are essential as the normal presence of pectoral muscle can bias the decision of CAD. In this paper, a novel texture gradient-based approach for automatic segmentation of pectoral muscle is proposed. The pectoral edge is initially approximated to a straight line by applying Hough transform on Probable Texture Gradient (PTG) map of the mammogram followed by block averaging with the aid of approximated line. Furthermore, a smooth pectoral muscle curve is achieved with proposed Euclidean Distance Regression (EDR) technique and polynomial modeling. The algorithm is robust to texture and overlapping fibro glandular tissues. The method is validated with 340 MLO views from three databases-including 200 randomly selected scanned film images from miniMIAS, 100 computed radiography images and 40 full-field digital mammogram images. Qualitatively, 96.75 % of the pectoral muscles are segmented with an acceptable pectoral score index. The proposed method not only outperforms state-of-the-art approaches but also accurately quantifies the pectoral edge. Thus, its high accuracy and relatively quick processing time clearly justify its suitability for CAD.

Mass Detection in Mammographic Images Using Wavelet Processing and Adaptive Threshold Technique.

Detection of mass in mammogram for early diagnosis of breast cancer is a significant assignment in the reduction of the mortality rate. However, in some cases, screening of mass is difficult task for radiologist, due to variation in contrast, fuzzy edges and noisy mammograms. Masses and micro-calcifications are the distinctive signs for diagnosis of breast cancer. This paper presents, a method for mass enhancement using piecewise linear operator in combination with wavelet processing from mammographic images. The method includes, artifact suppression and pectoral muscle removal based on morphological operations. Finally, mass segmentation for detection using adaptive threshold technique is carried out to separate the mass from background. The proposed method has been tested on 130 (45 + 85) images with 90.9 and 91 % True Positive Fraction (TPF) at 2.35 and 2.1 average False Positive Per Image(FP/I) from two different databases, namely Mammographic Image Analysis Society (MIAS) and Digital Database for Screening Mammography (DDSM). The obtained results show that, the proposed technique gives improved diagnosis in the early breast cancer detection.

Shape-based Automatic Detection of Pectoral Muscle Boundary in Mammograms.

The detection of the pectoral muscle boundary in the medio-lateral oblique view of mammograms is essential to improving the computer-aided diagnosis of breast cancer. In this study, a shape-based detection method is proposed for accurately extracting the boundary of the pectoral muscle in mammograms. A shape-based enhancement mask is applied to the mammogram and the initial boundary is then defined using morphological operators. The seed point is then detected on the initial boundary and the pectoral boundary is evolved from candidate points produced using a shape-based growth strategy. A cubic polynomial fitting function is implemented to obtain the final pectoral muscle boundary. The proposed method was applied to 322 mammograms from the mini Mammographic Image Analysis Society database. A 97.2 % acceptable rate from expert radiologists and assessment results based on the false positive rate, false negative rate, and Hausdorff distance demonstrate the robustness and effectiveness of the proposed shape-based detection method.

Transcriptomic and epigenomic landscapes of muscle growth during the postnatal period of broilers.

BACKGROUND: Broilers stand out as one of the fastest-growing livestock globally, making a substantial contribution to animal meat production. However, the molecular and epigenetic mechanisms underlying the rapid growth and development of broiler chickens are still unclear. This study aims to explore muscle development patterns and regulatory networks during the postnatal rapid growth phase of fast-growing broilers. We measured the growth performance of Cornish (CC) and White Plymouth Rock (RR) over a 42-d period. Pectoral muscle samples from both CC and RR were randomly collected at day 21 after hatching (D21) and D42 for RNA-seq and ATAC-seq library construction. RESULTS: The consistent increase in body weight and pectoral muscle weight across both breeds was observed as they matured, with CC outpacing RR in terms of weight at each stage of development. Differential expression analysis identified 398 and 1,129 genes in the two dimensions of breeds and ages, respectively. A total of 75,149 ATAC-seq peaks were annotated in promoter, exon, intron and intergenic regions, with a higher number of peaks in the promoter and intronic regions. The age-biased genes and breed-biased genes of RNA-seq were combined with the ATAC-seq data for subsequent analysis. The results spotlighted the upregulation of ACTC1 and FDPS at D21, which were primarily associated with muscle structure development by gene cluster enrichment. Additionally, a noteworthy upregulation of MUSTN1, FOS and TGFB3 was spotted in broiler chickens at D42, which were involved in cell differentiation and muscle regeneration after injury, suggesting a regulatory role of muscle growth and repair. CONCLUSIONS: This work provided a regulatory network of postnatal broiler chickens and revealed ACTC1 and MUSTN1 as the key responsible for muscle development and regeneration. Our findings highlight that rapid growth in broiler chickens triggers ongoing muscle damage and subsequent regeneration. These findings provide a foundation for future research to investigate the functional aspects of muscle development.

Deep learning-based breast region segmentation in raw and processed digital mammograms: generalization across views and vendors.

Purpose: We developed a segmentation method suited for both raw (for processing) and processed (for presentation) digital mammograms (DMs) that is designed to generalize across images acquired with systems from different vendors and across the two standard screening views. Approach: A U-Net was trained to segment mammograms into background, breast, and pectoral muscle. Eight different datasets, including two previously published public sets and six sets of DMs from as many different vendors, were used, totaling 322 screen film mammograms (SFMs) and 4251 DMs (2821 raw/processed pairs and 1430 only processed) from 1077 different women. Three experiments were done: first training on all SFM and processed images, second also including all raw images in training, and finally testing vendor generalization by leaving one dataset out at a time. Results: The model trained on SFM and processed mammograms achieved a good overall performance regardless of projection and vendor, with a mean (±std. dev.) dice score of 0.96±0.06 for all datasets combined. When raw images were included in training, the mean (±std. dev.) dice score for the raw images was 0.95±0.05 and for the processed images was 0.96±0.04. Testing on a dataset with processed DMs from a vendor that was excluded from training resulted in a difference in mean dice varying between -0.23 to +0.02 from that of the fully trained model. Conclusions: The proposed segmentation method yields accurate overall segmentation results for both raw and processed mammograms independent of view and vendor. The code and model weights are made available.

Pectoral muscle mass is not a robust prognostic factor for survival after left ventricular assist device (LVAD) implantation.

BACKGROUND: Left ventricular assist devices (LVAD) are an established treatment for end-stage left ventricular heart failure. Parameters are needed to identify the most appropriate patients for LVADs. This study aimed to evaluate pectoral muscle mass and density as prognostic parameters. METHODS: This single-center study included all patients with LVAD implantation between January 2010 and October 2017 and a preoperative chest CT scan. Pectoral muscle mass was assessed using the Pectoralis Muscle Index (PMI, surface area indexed to height, cm2/m2) and pectoral muscle density by Hounsfield Units (HU). Overall mortality was analyzed with Kaplan-Meier survival analysis and 1-year and 3-year mortality with receiver operating characteristic (ROC) curves and Cox regression models. RESULTS: 57 patients (89.5% male, mean age 57.8 years) were included. 64.9% of patients had end-stage left ventricular failure due to ischemic heart disease and 35.1% due to dilated cardiomyopathy. 49.2% of patients had preoperative INTERMACS profile of 1 or 2 and 33.3% received mechanical circulatory support prior to LVAD implantation. Total mean PMI was 4.7 cm2/m2 (± 1.6), overall HU of the major pectoral muscle was 39.0 (± 14.9) and of the minor pectoral muscle 37.1 (± 16.6). Mean follow-up was 2.8 years (± 0.2). Mortality rates were 37.5% at 1 year and 48.0% at 3 years. Neither PMI nor HU were significantly associated with overall mortality at 1-year or 3-year. CONCLUSIONS: The results of our study do not confirm the association between higher pectoral muscle mass and better survival after LVAD implantation previously described in the literature.

Dietary macroalgae Chaetomorpha linum supplementation improves morphology of small intestine and pectoral muscle, growth performance, and meat quality of broilers.

Background and Aim: Over the last decades, the poultry industry has experienced steady growth. Although the industry is gradually expanding in Indonesia, poultry feed production has always been expensive. There is a need to study alternative ingredients to obtain affordable feed from natural resources. Chaetomorpha linum (CL) is an abundant macroalgae available throughout the year in Indonesia. This study aimed to determine the effect of CL on the histological structure of the small intestine, pectoralis muscle, growth performance, and meat quality of broilers. Materials and Methods: This study used 300-day-old chick (DOC) male broilers that were reared until they were 21 days old. This study used a completely randomized design with four treatment groups and five replications, and each replication group contained 15 DOC individuals. The treatment groups consisted of Control (CON), CON basal feed (BF), CL1 (0.75%/kg BF), CL2 (1.5%/kg BF), and CL3 (3%/kg BF) groups. The histological structure of the small intestine, pectoralis muscle, growth performance, and meat quality of the broiler was examined. Results: Small intestine and pectoral muscle histomorphology, growth performance, and meat quality were significantly improved in the CL2 (1.5%) and CL3 (3%) groups compared with the CL1 (0.75%) and CON groups. Conclusion: Dietary CL supplementation ameliorates small intestine and pectoral muscle histomorphology, growth performance, and meat quality of broilers.

Can artificial intelligence detect type 2 diabetes in women by evaluating the pectoral muscle on tomosynthesis: diagnostic study.

OBJECTIVES: This retrospective single-center analysis aimed to evaluate whether artificial intelligence can detect type 2 diabetes mellitus by evaluating the pectoral muscle on digital breast tomosynthesis (DBT). MATERIAL METHOD: An analysis of 11,594 DBT images of 287 consecutive female patients (mean age 60, range 40-77 years) was conducted using convolutional neural networks (EfficientNetB5). The inclusion criterion was left-sided screening images with unsuspicious interpretation who also had a current glycosylated hemoglobin A1c (HBA1c) % value. The exclusion criteria were inadequate imaging, history of breast cancer, and/or diabetes mellitus. HbA1c values between 5.6 and 6.4% were categorized as prediabetic, and those with values ≥ 6.5% were categorized as diabetic. A recorded HbA1c ≤ 5.5% served as the control group. Each group was divided into 3 subgroups according to age. Images were subjected to pattern analysis parameters then cropped and resized in a format to contain only pectoral muscle. The dataset was split into 85% for training and 15% for testing the model's performance. The accuracy rate and F1-score were selected as performance indicators. RESULTS: The training process was concluded in the 15th epoch, each comprising 1000 steps, with an accuracy rate of 92% and a loss of only 0.22. The average specificity and sensitivity for all 3 groups were 95%. The F1-score was 0.95. AUC-ROC was 0.995. PPV was 94%, and NPV was 98%. CONCLUSION: Our study presented a pioneering approach, applying deep learning for the detection of diabetes mellitus status in women using pectoral muscle images and was found to function with an accuracy rate of 92%. CRITICAL RELEVANCE STATEMENT: AI can differentiate pathological changes within pectoral muscle tissue by assessing radiological images and maybe a potential diagnostic tool for detecting diabetes mellitus and other diseases that affect muscle tissues. KEY POINTS: • AI may have an opportunistic use as a screening exam for diabetes during digital breast tomosynthesis. • This technique allows for early and non-invasive detection of diabetes mellitus by AI. • AI may have broad applications in detecting pathological changes within muscle tissue.

Vertebral HU value and the pectoral muscle index based on chest CT can be used to opportunistically screen for osteoporosis.

BACKGROUND: Existing studies have shown that computed tomography (CT) attenuation and skeletal muscle tissue are strongly associated with osteoporosis; however, few studies have examined whether vertebral HU values and the pectoral muscle index (PMI) measured at the level of the 4th thoracic vertebra (T4) are strongly associated with bone mineral density (BMD). In this study, we demonstrate that vertebral HU values and the PMI based on chest CT can be used to opportunistically screen for osteoporosis and reduce fracture risk through prompt treatment. METHODS: We retrospectively evaluated 1000 patients who underwent chest CT and DXA scans from August 2020-2022. The T4 HU value and PMI were obtained using manual chest CT measurements. The participants were classified into normal, osteopenia, and osteoporosis groups based on the results of dual-energy X-ray (DXA) absorptiometry. We compared the clinical baseline data, T4 HU value, and PMI between the three groups of patients and analyzed the correlation between the T4 HU value, PMI, and BMD to further evaluate the diagnostic efficacy of the T4 HU value and PMI for patients with low BMD and osteoporosis. RESULTS: The study ultimately enrolled 469 participants. The T4 HU value and PMI had a high screening capacity for both low BMD and osteoporosis. The combined diagnostic model-incorporating sex, age, BMI, T4 HU value, and PMI-demonstrated the best diagnostic efficacy, with areas under the receiver operating characteristic curve (AUC) of 0.887 and 0.892 for identifying low BMD and osteoporosis, respectively. CONCLUSIONS: The measurement of T4 HU value and PMI on chest CT can be used as an opportunistic screening tool for osteoporosis with excellent diagnostic efficacy. This approach allows the early prevention of osteoporotic fractures via the timely screening of individuals at high risk of osteoporosis without requiring additional radiation.