GhVIM28, a negative regulator identified from VIM family genes, positively responds to salt stress in cotton.

The VIM (belonged to E3 ubiquitin ligase) gene family is crucial for plant growth, development, and stress responses, yet their role in salt stress remains unclear. We analyzed phylogenetic relationships, chromosomal localization, conserved motifs, gene structure, cis-acting elements, and gene expression patterns of the VIM gene family in four cotton varieties. Our findings reveal 29, 29, 17, and 14 members in Gossypium hirsutum (G.hirsutum), Gossypium barbadense (G.barbadense), Gossypium arboreum (G.arboreum), and Gossypium raimondii (G. raimondii), respectively, indicating the maturity and evolution of this gene family. motifs among GhVIMs genes were observed, along with the presence of stress-responsive, hormone-responsive, and growth-related elements in their promoter regions. Gene expression analysis showed varying patterns and tissue specificity of GhVIMs genes under abiotic stress. Silencing GhVIM28 via virus-induced gene silencing revealed its role as a salt-tolerant negative regulator. This work reveals a mechanism by which the VIM gene family in response to salt stress in cotton, identifying a potential negative regulator, GhVIM28, which could be targeted for enhancing salt tolerance in cotton. The objective of this study was to explore the evolutionary relationship of the VIM gene family and its potential function in salt stress tolerance, and provide important genetic resources for salt tolerance breeding of cotton.

Real-time breast lesion classification combining diffuse optical tomography frequency domain data and BI-RADS assessment.

Ultrasound (US)-guided diffuse optical tomography (DOT) has demonstrated potential for breast cancer diagnosis, in which real-time or near real-time diagnosis with high accuracy is desired. However, DOT's relatively slow data processing and image reconstruction speeds have hindered real-time diagnosis. Here, we propose a real-time classification scheme that combines US breast imaging reporting and data system (BI-RADS) readings and DOT frequency domain measurements. A convolutional neural network is trained to generate malignancy probability scores from DOT measurements. Subsequently, these scores are integrated with BI-RADS assessments using a support vector machine classifier, which then provides the final diagnostic output. An area under the receiver operating characteristic curve of 0.978 is achieved in distinguishing between benign and malignant breast lesions in patient data without image reconstruction.

Shelterin Dysfunction Promotes CD4+ T Cell Senescence in Behçet's Disease.

OBJECTIVES: To investigate the potential role of shelterin dysfunction in naïve CD4+ T cells in the pathogenesis of Behçet's disease (BD). METHODS: Naïve CD4+ T cells were isolated from 40 BD patients and 40 sex- and age-matched healthy controls (HC). Senescent profiles, shelterin subunits expression, telomere length, telomerase activity, and critical DNA damage response (DDR) was evaluated. TRF2 silencing was conducted for further validation. RESULTS: Compared to HC, BD patients had significantly decreased naïve CD4+ T cells, increased cell apoptosis, senescence, and productions of TNF-α and IFN-γ upon activation. Notably, BD naïve CD4+ T cells had shortened telomere, impaired telomerase activity, and expressed lower levels of shelterin subunits TRF2, TIN2, and RAP1. Furthermore, BD naïve CD4+ T cells exhibited significantly increased DDR, evidenced by elevated phosphorylated ataxia telangiectasia (AT) mutated (pATM), pp53, and p21. Finally, TRF2-silencing markedly upregulated DDR, apoptosis, and proinflammatory cytokines production in HC naïve CD4+ T cells. CONCLUSION: Our study demonstrated that TRF2 deficiency in BD naïve CD4+ T cells promoted cell apoptosis and senescence, leading to proinflammatory cytokines overproduction. Therefore, restoring TRF2 might be a promising therapeutic strategy for BD.

Automated pipeline for breast cancer diagnosis using US assisted diffuse optical tomography.

Ultrasound (US)-guided diffuse optical tomography (DOT) is a portable and non-invasive imaging modality for breast cancer diagnosis and treatment response monitoring. However, DOT data pre-processing and imaging reconstruction often require labor intensive manual processing which hampers real-time diagnosis. In this study, we aim at providing an automated US-assisted DOT pre-processing, imaging and diagnosis pipeline to achieve near real-time diagnosis. We have developed an automated DOT pre-processing method including motion detection, mismatch classification using deep-learning approach, and outlier removal. US-lesion information needed for DOT reconstruction was extracted by a semi-automated lesion segmentation approach combined with a US reading algorithm. A deep learning model was used to evaluate the quality of the reconstructed DOT images and a two-step deep-learning model developed earlier is implemented to provide final diagnosis based on US imaging features and DOT measurements and imaging results. The presented US-assisted DOT pipeline accurately processed the DOT measurements and reconstruction and reduced the procedure time to 2 to 3 minutes while maintained a comparable classification result with manually processed dataset.

Ecologically different earthworm species are the driving force of microbial hotspots influencing Pb uptake by the leafy vegetable Brassica campestris.

Food chain contamination by soil lead (Pb), beginning with Pb uptake by leafy vegetables, is a threat to food safety and poses a potential risk to human health. This study highlights the importance of two ecologically different earthworm species (the anecic species Amynthas aspergillum and the epigeic species Eisenia fetida) as the driving force of microbial hotspots to enhance Pb accumulation in the leafy vegetable Brassica campestris at different Pb contamination levels (0, 100, 500, and 1,000 mg·kg-1). The fingerprints of phospholipid fatty acids (PLFAs) were employed to reveal the microbial mechanism of Pb accumulation involving earthworm-plant interaction, as PLFAs provide a general profile of soil microbial biomass and community structure. The results showed that Gram-positive (G+) bacteria dominated the microbial community. At 0 mg·kg-1 Pb, the presence of earthworms significantly reduced the total PLFAs. The maximum total of PLFAs was found at 100 mg·kg-1 Pb with E. fetida inoculation. A significant shift in the bacterial community was observed in the treatments with E. fetida inoculation at 500 and 1,000 mg·kg-1 Pb, where the G+/G- bacteria ratio was significantly decreased compared to no earthworm inoculation. Principal component analysis (PCA) showed that E. fetida had a greater effect on soil microbial hotspots than A. aspergillum, thus having a greater effect on the Pb uptake by B. campestris. Redundancy analysis (RDA) showed that soil microbial biomass and structure explained 43.0% (R2 = 0.53) of the total variation in Pb uptake by B. campestris, compared to 9.51% of microbial activity. G- bacteria explained 23.2% of the total variation in the Pb uptake by B. campestris, significantly higher than the other microbes. The Mantel test showed that microbial properties significantly influenced Pb uptake by B. campestris under the driving force of earthworms. E. fetida inoculation was favorable for the G- bacterial community, whereas A. aspergillum inoculation was favorable for the fungal community. Both microbial communities facilitated the entry of Pb into the vegetable food chain system. This study delivers novel evidence and meaningful insights into how earthworms prime the microbial mechanism of Pb uptake by leafy vegetables by influencing soil microbial biomass and community composition. Comprehensive metagenomics analysis can be employed in future studies to identify the microbial strains promoting Pb migration and develop effective strategies to mitigate Pb contamination in food chains.

GhCYS2 governs the tolerance against cadmium stress by regulating cell viability and photosynthesis in cotton.

Cysteine, an early sulfur-containing compound in plants, is of significant importance in sulfur metabolism. CYS encodes cysteine synthetase that further catalyzes cysteine synthesis. In this investigation, CYS genes, identified from genome-wide analysis of Gossypium hirsutum bioinformatically, led to the discovery of GhCYS2 as the pivotal gene responsible for Cd2+ response. The silencing of GhCYS2 through virus-induced gene silencing (VIGS) rendered plants highly susceptible to Cd2+ stress. Silencing GhCYS2 in plants resulted in diminished levels of cysteine and glutathione while leading to the accumulation of MDA and ROS within cells, thereby impeding the regular process of photosynthesis. Consequently, the stomatal aperture of leaves decreased, epidermal cells underwent distortion and deformation, intercellular connections are dramatically disrupted, and fissures manifested between cells. Ultimately, these detrimental effected culminating in plant wilting and a substantial reduction in biomass. The association established between Cd2+ and cysteine in this investigation offered a valuable reference point for further inquiry into the functional and regulatory mechanisms of cysteine synthesis genes.

Two-stage classification strategy for breast cancer diagnosis using ultrasound-guided diffuse optical tomography and deep learning.

Significance: Ultrasound (US)-guided diffuse optical tomography (DOT) has demonstrated great potential for breast cancer diagnosis in which real-time or near real-time diagnosis with high accuracy is desired. Aim: We aim to use US-guided DOT to achieve an automated, fast, and accurate classification of breast lesions. Approach: We propose a two-stage classification strategy with deep learning. In the first stage, US images and histograms created from DOT perturbation measurements are combined to predict benign lesions. Then the non-benign suspicious lesions are passed through to the second stage, which combine US image features, DOT histogram features, and 3D DOT reconstructed images for final diagnosis. Results: The first stage alone identified 73.0% of benign cases without image reconstruction. In distinguishing between benign and malignant breast lesions in patient data, the two-stage classification approach achieved an area under the receiver operating characteristic curve of 0.946, outperforming the diagnoses of all single-modality models and of a single-stage classification model that combines all US images, DOT histogram, and imaging features. Conclusions: The proposed two-stage classification strategy achieves better classification accuracy than single-modality-only models and a single-stage classification model that combines all features. It can potentially distinguish breast cancers from benign lesions in near real-time.

Characterization and gene expression patterns analysis implies BSK family genes respond to salinity stress in cotton.

Identification, evolution, and expression patterns of BSK (BR signaling kinase) family genes revealed that BSKs participated in the response of cotton to abiotic stress and maintained the growth of cotton in extreme environment. The steroidal hormone brassinosteroids (BR) play important roles in different plant biological processes. This study focused on BSK which were downstream regulatory element of BR, in order to help to decipher the functions of BSKs genes from cotton on growth development and responses to abiotic stresses and lean the evolutionary relationship of cotton BSKs. BSKs are a class of plant-specific receptor-like cytoplasmic kinases involved in BR signal transduction. In this study, bioinformatics methods were used to identify the cotton BSKs gene family at the cotton genome level, and the gene structure, promoter elements, protein structure and properties, gene expression patterns and candidate interacting proteins were analyzed. In the present study, a total of 152 BSKs were identified by a genome-wide search in four cotton species and other 11 plant species, and phylogenetic analysis revealed three evolutionary clades. It was identified that BSKs contain typical PKc and TPR domains, the N-terminus is composed of extended chains and helical structures. Cotton BSKs genes show different expression patterns in different tissues and organs. The gene promoter contains numerous cis-acting elements induced by hormones and abiotic stress, the hormone ABA and Cold-inducing related elements have the highest count, indicating that cotton BSK genes may be regulated by various hormones at different growth stages and involved in the response regulation of cotton to various stresses. The expression analysis of BSKs in cotton showed that the expression levels of GhBSK06, GhBSK10, GhBSK21 and GhBSK24 were significantly increased with salt-inducing. This study is helpful to analyze the function of cotton BSKs genes in growth and development and in response to stress.

Fusion deep learning approach combining diffuse optical tomography and ultrasound for improving breast cancer classification.

Diffuse optical tomography (DOT) is a promising technique that provides functional information related to tumor angiogenesis. However, reconstructing the DOT function map of a breast lesion is an ill-posed and underdetermined inverse process. A co-registered ultrasound (US) system that provides structural information about the breast lesion can improve the localization and accuracy of DOT reconstruction. Additionally, the well-known US characteristics of benign and malignant breast lesions can further improve cancer diagnosis based on DOT alone. Inspired by a fusion model deep learning approach, we combined US features extracted by a modified VGG-11 network with images reconstructed from a DOT deep learning auto-encoder-based model to form a new neural network for breast cancer diagnosis. The combined neural network model was trained with simulation data and fine-tuned with clinical data: it achieved an AUC of 0.931 (95% CI: 0.919-0.943), superior to those achieved using US images alone (0.860) or DOT images alone (0.842).

Baricitinib for the treatment of intestinal Behçet's disease: A pilot study.

OBJECTIVES: The pilot study aims to explore the efficacy and safety of baricitinib in treating refractory intestinal Behçet's disease (BD). METHODS: We consecutively enrolled patients with refractory intestinal BD from October 2020 to September 2022. They were treated with baricitinib 2-4 mg daily, with background glucocorticoids and immunosuppressants. Efficacy assessment included the global gastrointestinal symptom scores, the endoscopy scores, the Disease activity index for intestinal Behçet's disease (DAIBD), and the inflammatory parameters. Side effects were recorded. RESULTS: The thirteen patients (six males and seven females) had a median follow-up of eleven months, 76.92% (10/13) patients achieved complete remission of global gastrointestinal symptom scores, and 66.7% (6/9) had mucosal healing on endoscopy. The DAIBD scores decreased significantly, as well as the C-reactive protein level. Baricitinib showed a glucocorticoid-sparing effect, and the safety profile is favorable. CONCLUSION: Baricitinib might be a potential choice in treating refractory intestinal BD.

Population genetic structure analysis and identification of backfat thickness loci of Chinese synthetic Yunan pigs.

Yunan is a crossed lean meat pig breed in China. Backfat thickness is the gold standard for carcass quality grading. However, over 14 years after breed registration, the backfat of Yunan thickened and the consistency of backfat thickness decreased. Meanwhile, no genetic study has been ever performed on Yunan population. So, in this study we collected all the 120 nucleus individuals of Yunan and recorded six backfat traits of them, carried out population genetic structure analysis, selection signals analysis and genome-wide association study of Yunan pigs with the help of their founder population Duroc and Chinese native Huainan pigs, to determine the genomic loci on backfat of Yunan. Genetic diversity indexes suggested Yunan pigs had no inbreeding risk while population genetic structure showed they had few molecular pedigrees and were stratified. A total of 71 common selection signals affecting growth and fat deposition were detected by F ST and XP-CLR methods. 34 significant loci associated with six backfat traits were detected, among which a 1.40 Mb region on SSC4 (20.03-21.43 Mb) were outstanding as the strong region underlying backfat. This region was common with the results of selection signature analysis, former reported QTLs for backfat and was common for different kinds of backfat traits at different development stage. ENPP2, EXT1 and SLC30A8 genes around were fat deposition related genes and were of Huainan pig's origin, among which Type 2 diabetes related gene SLC30A8 was the most reasonable for being in a 193.21 Kb haplotype block of the 1.40 Mb region. Our results had application value for conservation, mating and breeding improvement of backfat thickness of Yunan pigs and provided evidence for a human function gene might be reproduced in pigs.

Transcriptional analysis of neutrophils from patients with Behçet's disease reveals activation and chemotaxis of neutrophils.

Behçet's disease (BD) is a systemic vasculitis characterized by neutrophil activation with unclear pathogenesis. This study aimed to explore the transcriptional profiles of BD neutrophils and identify specific gene signatures. We performed RNA sequencing on neutrophils from treatment-naive active BD patients and healthy controls, then analyzed differentially expressed genes (DEGs), Kyoto Encyclopedia of Genes and Genomes pathways (KEGG) and transcription regulatory network. Quantitative real-time PCR and Western Blot were used to validate chemotaxis-related DEGs expression. We detected 567 DEGs, including 520 upregulated genes and 47 downregulated genes. 9 KEGG pathways were enriched, dominated by the NF-κB pathway and chemotaxis. The transcription regulatory network suggests ETS1 regulated the enhanced chemotaxis of BD neutrophils. Validation experiments demonstrated the overexpression of ETS1, CCR6 and CCL5 in BD neutrophils compared with HC, and ETS1 was significantly increased in vascular BD compared with other BD subgroups. Our study revealed increased activation and chemotaxis of BD neutrophils characterized by the overexpression of CCL5, CCR6 and ETS1.

Comprehensive analysis of mitogenome of native Henan pig breeds with 58 worldwide pig breeds.

Mitochondria follow non-Mendelian maternal inheritance, and thus can be used to compare genetic diversity and infer the expansion and migration between animal populations. Based on the mitochondrial DNA sequences of 58 pig breeds from Asia, Europe, Oceania, and America, we observed a distinct division of Eurasian pig species into two main Haplogroups (A and B), with the exception of the Berkshire and Yorkshire breeds. Oceanian pigs were much more similar to European and American pigs in Haplogroup A. Additionally, native Chinese pigs exhibited the most abundant genetic polymorphisms and occupied the centre of Haplogroup B. Miyazaki (Japan) and Siberia (Russia) are two distant and disconnected regions; however, most pigs from these regions were clustered into a subcluster, while native pigs from Korea clustered into a second subcluster. This study is the first to report that pigs from Thailand and Vietnam had haplotypes similar to those of Henan, where the earliest evidence of domestic pigs was found from the Yellow River Basin of North China. Local Henan pig breeds are related to many Asian breeds while still having their own mutation identity, such as g.314 delins T>AC/AT/C of the 12S rRNA gene in Yuxi. Some pigs from Palawan, Itbayat, and Batan Islands of the Philippines and Lanyu Island of China were distinct from other Asian pigs and clustered together into Haplogroup C. These findings show that the complexity of domestication of worldwide pig breeds and mitochondria could reflect genetic communication between pig breeds due to geographical proximity and human activities.

Difference imaging from single measurements in diffuse optical tomography: a deep learning approach.

SIGNIFICANCE: "Difference imaging," which reconstructs target optical properties using measurements with and without target information, is often used in diffuse optical tomography (DOT) in vivo imaging. However, taking additional reference measurements is time consuming, and mismatches between the target medium and the reference medium can cause inaccurate reconstruction. AIM: We aim to streamline the data acquisition and mitigate the mismatch problems in DOT difference imaging using a deep learning-based approach to generate data from target measurements only. APPROACH: We train an artificial neural network to output data for difference imaging from target measurements only. The model is trained and validated on simulation data and tested with simulations, phantom experiments, and clinical data from 56 patients with breast lesions. RESULTS: The proposed method has comparable performance to the traditional approach using measurements without mismatch between the target side and the reference side, and it outperforms the traditional approach using measurements when there is a mismatch. It also improves the target-to-artifact ratio and lesion localization in patient data. CONCLUSIONS: The proposed method can simplify the data acquisition procedure, mitigate mismatch problems, and improve reconstructed image quality in DOT difference imaging.

Effectiveness and safety of low-dose interferon alpha-2a treatment in Behçet's Syndrome with refractory vascular or neurological involvement: a case series.

Objective: The aim of this study was to evaluate the effectiveness and safety of low-dose interferon alpha-2a (IFNα2a) in Behçet's syndrome (BS) patients with refractory vascular/cardiac or neurological involvement. Methods: In this retrospective cohort study, we consecutively included 25 BS patients with refractory vascular/cardiac (n = 16) or neurological involvement (n = 9) who received IFNα2a treatment in our center between June 2018 and September 2021. The low-dose IFNα2a (3 million IU, every other day) was used as an add-on treatment with the continuation of glucocorticoids (GCs) and immunosuppressants. Results: In total, 25 patients (20 males, 5 females) with a mean age of 31.92 ± 9.25 years were included. IFNα2a was administered for BS patients with refractory vascular/cardiac involvement (n = 16) and neurological involvement (n = 9). Before the initiation of IFNα2a, patients had insufficient response or intolerance to conventional therapies. After a median follow-up of 23 [interquartile range (IQR), 11-30] months, all patients achieved clinical improvement. The Behçet's disease Current Activity Form (BDCAF) score improved significantly (5 versus 0, median, p < 0.0001). BS Overall Damage Index (BODI) and vasculitis damage index (VDI) remain stable (p > 0.05). Decrease in erythrocyte sedimentation rate [ESR; 24 (IQR, 12-43.5) versus 5 (IQR, 2.75-10.5) mm/h, p = 0.0001] and C-reactive protein [CRP; 6.64 (IQR, 3.67-19.82) versus 1.24 (IQR, 0.24-3.12) mg/liter, p < 0.005] was achieved effectively. The median GCs dosage tapered from 26.25 (IQR, 11.88-41.25) to 10.00 (IQR, 7.50-10.63) mg/d, p < 0.0001. Immunosuppressants were also reduced in number (p < 0.005). No serious adverse events were observed during follow-up. Conclusion: Our study suggests that low-dose IFNα2a, combined with GCs and immunosuppressants, is well-tolerated and effective for BS patients with refractory vascular/cardiac or neurological involvement and has a steroid- and immunosuppressant-sparing effect.

The role of cyclophilins in viral infection and the immune response.

Cyclophilins (Cyps) are a subgroup of peptidyl-prolyl cis-trans isomerases (PPIases) that contain a highly conserved domain of PPIases. Sixteen Cyps have been identified in humans, among which the functions of five classical Cyp subtypes (CypA, B, C, D, and 40) have been studied in more detail. Cyps are widely expressed in almost all human tissues and are involved in several intracellular signaling pathways such as oxidative stress, mitochondrial dysfunction, cell migration, and apoptosis. Several studies have also demonstrated that Cyps play an important role in the development of cardiovascular diseases, neurodegeneration, cancer, and other diseases. However, as regulators of intercellular communication, Cyps have increasingly attracted attention as a result of their implications in viral infection. The specific motifs of Cyps can be targeted by viral proteins and thus promote either a viral infection or an antiviral response. This review highlights the present understanding of Cyps in viral infection and immune response. These effects will facilitate revealing the molecular mechanisms of several diseases induced by viruses and may provide novel insight into the development of corresponding drug-based treatment methods.

Single-cell analyses highlight the proinflammatory contribution of C1q-high monocytes to Behçet's disease.

Behçet's disease (BD) is a chronic vasculitis characterized by systemic immune aberrations. However, a comprehensive understanding of immune disturbances in BD and how they contribute to BD pathogenesis is lacking. Here, we performed single-cell and bulk RNA sequencing to profile peripheral blood mononuclear cells (PBMCs) and isolated monocytes from BD patients and healthy donors. We observed prominent expansion and transcriptional changes in monocytes in PBMCs from BD patients. Deciphering the monocyte heterogeneity revealed the accumulation of C1q-high (C1qhi) monocytes in BD. Pseudotime inference indicated that BD monocytes markedly shifted their differentiation toward inflammation-accompanied and C1qhi monocyte-ended trajectory. Further experiments showed that C1qhi monocytes enhanced phagocytosis and proinflammatory cytokine secretion, and multiplatform analyses revealed the significant clinical relevance of this subtype. Mechanistically, C1qhi monocytes were induced by activated interferon-γ (IFN-γ) signaling in BD patients and were decreased by tofacitinib treatment. Our study illustrates the BD immune landscape and the unrecognized contribution of C1qhi monocytes to BD hyperinflammation, showing their potential as therapeutic targets and clinical assessment indexes.

Assessment of bioremediation potential of metal contaminated soils (Cu, Cd, Pb and Zn) by earthworms from their tolerance, accumulation and impact on metal activation and soil quality: A case study in South China.

This study was aimed to evaluate the potential of four earthworm species commonly found in South China for the bioremediation of soils contaminated by Cu, Cd, Pb and Zn. Survival rates and metal accumulation of Eisenia fetida, Amynthas morrisi, A. robustus and A. corticis and changes in soil physico-chemical properties were investigated in a 60-day incubation experiment with a metal-polluted soil. At the end of the experiment, the survival rates of E. fetida, A. morrisi and A. robustus were significantly higher than that of A. corticis. Principal component analysis showed that earthworm activity improved soil quality with the averaging soil quality index being 0.66, 0.64, 0.56, 0.53, and 0.12 for the A. corticis, A. morrisi, A. robustus, E. fetida, and control treatments, respectively. The highest total available Cd, Cu, and Pb in casts were found in the treatment with A. morrisi, and this species accumulated the smallest amount of metals. Results indicate that A. morrisi may be the best candidate for earthworm-assisted bioremediation of metal contaminated soils in South China.

Cyclophilin A regulates the apoptosis of A549 cells by stabilizing Twist1 protein.

Cyclophilin A (CypA, also known as PPIA) is an essential member of the immunophilin family. As an intracellular target of the immunosuppressive drug cyclosporin A (CsA) or a peptidyl-prolyl cis/trans isomerase (PPIase), it catalyzes the cis-trans isomerization of proline amidic peptide bonds, through which it regulates a variety of biological processes, such as intracellular signaling, transcription and apoptosis. In this study, we found that intracellular CypA enhanced Twist1 phosphorylation at Ser68 and inhibited apoptosis in A549 cells. Mechanistically, CypA could mediate the phosphorylation of Twist1 at Ser68 via p38 mitogen-activated protein kinase (also known as MAPK14), which inhibited its ubiquitylation-mediated degradation. In addition, CypA increased interaction between Twist1 and p65 (also known as RELA), as well as nuclear accumulation of the Twist1-p65 complex, which regulated Twist1-dependent expression of CDH1 and CDH2. Our findings collectively indicate the role of CypA in Twist1-mediated apoptosis of A549 cells through stabilizing Twist1 protein.

Deep learning-based method to accurately estimate breast tissue optical properties in the presence of the chest wall.

SIGNIFICANCE: In general, image reconstruction methods used in diffuse optical tomography (DOT) are based on diffusion approximation, and they consider the breast tissue as a homogenous, semi-infinite medium. However, the semi-infinite medium assumption used in DOT reconstruction is not valid when the chest wall is underneath the breast tissue. AIM: We aim to reduce the chest wall's effect on the estimated average optical properties of breast tissue and obtain accurate forward model for DOT reconstruction. APPROACH: We propose a deep learning-based neural network approach where a convolution neural network (CNN) is trained to simultaneously obtain accurate optical property values for both the breast tissue and the chest wall. RESULTS: The CNN model shows great promise in reducing errors in estimating the optical properties of the breast tissue in the presence of a shallow chest wall. For patient data, the CNN model predicted the breast tissue optical absorption coefficient, which was independent of chest wall depth. CONCLUSIONS: Our proposed method can be readily used in DOT and diffuse spectroscopy measurements to improve the accuracy of estimated tissue optical properties.