Time-Series MR Images Identifying Complete Response to Neoadjuvant Chemotherapy in Breast Cancer Using a Deep Learning Approach.

BACKGROUND: Pathological complete response (pCR) is an essential criterion for adjusting follow-up treatment plans for patients with breast cancer (BC). The value of the visual geometry group and long short-term memory (VGG-LSTM) network using time-series dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) for pCR identification in BC is unclear. PURPOSE: To identify pCR to neoadjuvant chemotherapy (NAC) using deep learning (DL) models based on the VGG-LSTM network. STUDY TYPE: Retrospective. POPULATION: Center A: 235 patients (47.7 ± 10.0 years) were divided 7:3 into training (n = 164) and validation set (n = 71). Center B: 150 patients (48.5 ± 10.4 years) were used as test set. FIELD STRENGTH/SEQUENCE: 3-T, T2-weighted spin-echo sequence imaging, and gradient echo DCE sequence imaging. ASSESSMENT: Patients underwent MRI examinations at three sequential time points: pretreatment, after three cycles of treatment, and prior to surgery, with tumor regions of interest manually delineated. Histopathology was the gold standard. We used VGG-LSTM network to establish seven DL models using time-series DCE-MR images: pre-NAC images (t0 model), early NAC images (t1 model), post-NAC images (t2 model), pre-NAC and early NAC images (t0 + t1 model), pre-NAC and post-NAC images (t0 + t2 model), pre-NAC, early NAC and post-NAC images (t0 + t1 + t2 model), and the optimal model combined with the clinical features and imaging features (combined model). The models were trained and optimized on the training and validation set, and tested on the test set. STATISTICAL TESTS: The DeLong, Student's t-test, Mann-Whitney U, Chi-squared, Fisher's exact, Hosmer-Lemeshow tests, decision curve analysis, and receiver operating characteristics analysis were performed. P < 0.05 was considered significant. RESULTS: Compared with the other six models, the combined model achieved the best performance in the test set yielding an AUC of 0.927. DATA CONCLUSION: The combined model that used time-series DCE-MR images, clinical features and imaging features shows promise for identifying pCR in BC. TECHNICAL EFFICACY: Stage 4.

High Expression of CLDN 18.2 is Associated with Poor Disease-Free Survival of HER-2 Positive Gastric Cancer.

Background: Anti-claudin (CLDN) 18.2 therapy has been proven to be effective in treating advanced gastric cancer with negative human epidermal growth factor receptor 2 (HER-2). This study purposed to investigate the relationship of CLDN 18.2 expression with prognosis of HER-2-positive gastric cancer patients. Objective: To investigate the expression of claudin (CLDN) 18.2 in Human epidermal growth factor receptor 2 (HER-2) positive gastric cancer patients after radical resection and its relationship with gastric cancer prognosis. Methods: A total of 55 postoperative HER-2-positive gastric cancer patients were included in this study. CLDN 18.2 protein was detected by immunohistochemistry, and detailed clinical and pathological information was collected. Factors considered potentially important in the univariate analysis were included in the multivariate analysis, which involved COX regression to find the independent prognostic factors affecting disease-free survival (DFS). Results: Immunohistochemistry showed that different levels of CLDN 18.2 protein were expressed in HER-2 positive gastric cancer tissues, and the Chi-square analysis showed that the expression level of CLDN 18.2 was significantly correlated with the lymph node stage. Higher expression levels of CLDN 18.2 were found in patients with lymph node positivity and were associated with poor prognosis in HER-2-positive gastric cancer patients. Gastric cancer patients with low and high expressions of CLDN 18.2 had postoperative median DFS of 38.5 months (95% confidence interval (CI) 28.8-48.2 months) and 12.1 months (95% CI, 11.7-41.0 months), respectively. Conclusion: High expression of CLDN 18.2 in HER-2 positive gastric cancer is associated with poor prognosis, and the optimal treatment mode for this population is worth exploring after the approval of anti-CLDN 18.2 drugs.

5-Fluorouracil resistant CRC cells derived exosomes promote cancer-associated fibroblasts secreting more CXCL12.

Background: Chemoresistance is a key reason for treatment failure in colorectal cancer (CRC) patients. The tumor microenvironment of chemoresistant CRC is distinctly immunosuppressive, although the underlying mechanisms are unclear. Methods: The CRC data sets GSE69657 and GSE62080 were downloaded from the GEO database, and the correlation between TRPC5 and FAP expression was analyzed by Pearson method. The in-situ expression of transient receptor potential channel 5 (TRPC5) and fibroblast activation protein (FAP) in the CRC tissues was examined by immunohistochemistry. TRPC5 expression levels in the HCT8 and HCT116 cell lines and the corresponding 5-fluorouracil (5-FU)-resistant cell lines (HCT8R and HCT116R) were analyzed by western blotting and RT-PCR. Exosomes were isolated from the HCT8R and HCT116R cells and incubated with colorectal normal fibroblasts (NFs), and cancer-associated fibroblasts (CAFs)markers were detected. NFs were also incubated with exosomes isolated from TRPC5-knockdown HCT8R cells, and the changes in intracellular Ca2+ levels and C-X-C motif chemokine ligand 12 (CXCL12) secretion were analyzed. Results: TRPC5 and FAP expression showed positive correlation in the datasets. Immunostaining of CRC tissue specimens further revealed that high TRPC5 and FAP expressions were significantly associated with worse tumor regression. Furthermore, chemoresistant CRC cells expressed higher levels of TRPC5 compared to the chemosensitive cells, and knocking down TRPC5 reversed chemoresistance. Exosomes derived from CRC cells induced the transformation of NFs to CAFs. However, TRPC5-exosomes derived from chemoresistant CRC cells can promote CAFs to secrete more CXCL12. Conclusion: Chemoresistant CRC cells can induce CAFs activation and promote CXCL12 secretion through exosomal TRPC5.

Anaerostipes hadrus, a butyrate-producing bacterium capable of metabolizing 5-fluorouracil.

Anaerostipes hadrus (A. hadrus) is a dominant species in the human gut microbiota and considered a beneficial bacterium for producing probiotic butyrate. However, recent studies have suggested that A. hadrus may negatively affect the host through synthesizing fatty acid and metabolizing the anticancer drug 5-fluorouracil, indicating that the impact of A. hadrus is complex and unclear. Therefore, comprehensive genomic studies on A. hadrus need to be performed. We integrated 527 high-quality public A. hadrus genomes and five distinct metagenomic cohorts. We analyzed these data using the approaches of comparative genomics, metagenomics, and protein structure prediction. We also performed validations with culture-based in vitro assays. We constructed the first large-scale pan-genome of A. hadrus (n = 527) and identified 5-fluorouracil metabolism genes as ubiquitous in A. hadrus genomes as butyrate-producing genes. Metagenomic analysis revealed the wide and stable distribution of A. hadrus in healthy individuals, patients with inflammatory bowel disease, and patients with colorectal cancer, with healthy individuals carrying more A. hadrus. The predicted high-quality protein structure indicated that A. hadrus might metabolize 5-fluorouracil by producing bacterial dihydropyrimidine dehydrogenase (encoded by the preTA operon). Through in vitro assays, we validated the short-chain fatty acid production and 5-fluorouracil metabolism abilities of A. hadrus. We observed for the first time that A. hadrus can convert 5-fluorouracil to α-fluoro-ß-ureidopropionic acid, which may result from the combined action of the preTA operon and adjacent hydA (encoding bacterial dihydropyrimidinase). Our results offer novel understandings of A. hadrus, exceptionally functional features, and potential applications. IMPORTANCE: This work provides new insights into the evolutionary relationships, functional characteristics, prevalence, and potential applications of Anaerostipes hadrus.

Breast masses with rim enhancement on contrast-enhanced mammography: morphological and enhancement features for diagnosis and differentiation of benign and malignant.

OBJECTIVES: To investigate the imaging characteristics and clinicopathological features of rim enhancement of breast masses demonstrated on contrast-enhanced mammography (CEM). METHODS: 67 cases of breast lesions confirmed by pathology and showing rim enhancement on CEM examinations were analyzed. The lesions were divided into benign and malignant groups, and the morphological and enhanced features were described. Sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were calculated separately for each morphology descriptor to evaluate the diagnostic ability of each indicator. RESULTS: There were 35 (52.2%) malignant and 32 (47.8%) benign lesions. There are significant differences in the morphological and enhanced features between benign and malignant lesions. 29/35 (82.9%) malignant lesions exhibited irregular shapes, and 31/35 (88.6%) showed indistinct margins. 28/35 (80%) malignant lesions displayed strong enhancement on CEM, while 12/32 (37.5%) benign lesions exhibited weak enhancement (P = 0.001). Malignant lesions showed a higher incidence of unsmooth inner walls than benign lesions (28/35 vs 7/32; P <.001). Lesion margins showed high sensitivity of 88.57% and NPV of 81.8%. The presence of suspicious calcifications had the highest specificity of 100% and PPV of 100%. The diagnostic sensitivity, specificity, PPV, and NPV of the combined parameters were 97.14%, 93.15%, 94.44%, and 96.77%, respectively. CONCLUSIONS: The assessment of morphological and enhanced features of breast lesions exhibiting rim enhancement on CEM can improve the differentiation between benign and malignant breast lesions. ADVANCES IN KNOWLEDGE: This article provides a reference for the differential diagnosis of ring enhanced lesions on CEM.

Gut resistome profiling reveals high diversity and fluctuations in pancreatic cancer cohorts.

Background: Pancreatic cancer is one of the deadliest cancer, with a 5-year overall survival rate of 11%. Unfortunately, most patients are diagnosed with advanced stage by the time they present with symptoms. In the past decade, microbiome studies have explored the association of pancreatic cancer with the human oral and gut microbiomes. However, the gut microbial antibiotic resistance genes profiling of pancreatic cancer patients was never reported compared to that of the healthy cohort. Results: In this study, we addressed the gut microbial antibiotic resistance genes profile using the metagenomic data from two online public pancreatic cancer cohorts. We found a high degree of data concordance between the two cohorts, which can therefore be used for cross-sectional comparisons. Meanwhile, we used two strategies to predict antibiotic resistance genes and compared the advantages and disadvantages of these two approaches. We also constructed microbe-antibiotic resistance gene networks and found that most of the hub nodes in the networks were antibiotic resistance genes. Conclusions: In summary, we describe the panorama of antibiotic resistance genes in the gut microbes of patients with pancreatic cancer. We hope that our study will provide new perspectives on treatment options for the disease.

Atypical architectural distortion detection in digital breast tomosynthesis: a multi-view computer-aided detection model with ipsilateral learning.

Objective.Breast architectural distortion (AD), a common imaging symptom of breast cancer, is associated with a particularly high rate of missed clinical detection. In clinical practice, atypical ADs that lack an obvious radiating appearance constitute most cases, and detection models based on single-view images often exhibit poor performance in detecting such ADs. Existing multi-view deep learning methods have overlooked the correspondence between anatomical structures across different views.Approach.To develop a computer-aided detection (CADe) model for AD detection that effectively utilizes the craniocaudal (CC) and mediolateral oblique (MLO) views of digital breast tomosynthesis (DBT) images, we proposed an anatomic-structure-based multi-view information fusion approach by leveraging the related anatomical structure information between these ipsilateral views. To obtain a representation that can effectively capture the similarity between ADs in images from ipsilateral views, our approach utilizes a Siamese network architecture to extract and compare information from both views. Additionally, we employed a triplet module that utilizes the anatomical structural relationship between the ipsilateral views as supervision information.Main results.Our method achieved a mean true positive fraction (MTPF) of 0.05-2.0, false positives (FPs) per volume of 64.40%, and a number of FPs at 80% sensitivity (FPs@0.8) of 3.5754; this indicates a 6% improvement in MPTF and 16% reduction in FPs@0.8 compared to the state-of-the-art baseline model.Significance.From our experimental results, it can be observed that the anatomic-structure-based fusion of ipsilateral view information contributes significantly to the improvement of CADe model performance for atypical AD detection based on DBT. The proposed approach has the potential to lead to earlier diagnosis and better patient outcomes.

Comparative genomic analysis of Fusobacterium nucleatum reveals high intra-species diversity and cgmlst marker construction.

BACKGROUND: Fusobacterium nucleatum is a one of the most important anaerobic opportunistic pathogens in the oral and intestinal tracts of human and animals. It can cause various diseases such as infections, Lemierre's syndrome, oral cancer and colorectal cancer. The comparative genomic studies on the population genome level, have not been reported. RESULTS: We analyzed all publicly available Fusobacterium nucleatums' genomic data for a comparative genomic study, focusing on the pan-genomic features, virulence genes, plasmid genomes and developed cgmlst molecular markers. We found the pan-genome shows a clear open tendency and most of plasmids in Fusobacterium nucleatum are mainly transmitted intraspecifically. CONCLUSIONS: Our comparative analysis of Fusobacterium nucleatum systematically revealed the open pan-genomic features and phylogenetic tree based on cgmlst molecular markers. What's more, we also identified common plasmid typing among genomes. We hope that our study will provide a theoretical basis for subsequent functional studies.

The N6-methyladenosine METTL3 regulates tumorigenesis and glycolysis by mediating m6A methylation of the tumor suppressor LATS1 in breast cancer.

BACKGROUND: Posttranscriptional modification of tumor-associated factors plays a pivotal role in breast cancer progression. However, the underlying mechanism remains unknown. M6A modifications in cancer cells are dynamic and reversible and have been found to impact tumor initiation and progression through various mechanisms. In this study, we explored the regulatory mechanism of breast cancer cell proliferation and metabolism through m6A methylation in the Hippo pathway.  METHODS: A combination of MeRIP-seq, RNA-seq and metabolomics-seq was utilized to reveal a map of m6A modifications in breast cancer tissues and cells. We conducted RNA pull-down assays, RIP-qPCR, MeRIP-qPCR, and RNA stability analysis to identify the relationship between m6A proteins and LATS1 in m6A regulation in breast cancer cells. The expression and biological functions of m6A proteins were confirmed in breast cancer cells in vitro and in vivo. Furthermore, we investigated the phosphorylation levels and localization of YAP/TAZ to reveal that the activity of the Hippo pathway was affected by m6A regulation of LATS1 in breast cancer cells.  RESULTS: We demonstrated that m6A regulation plays an important role in proliferation and glycolytic metabolism in breast cancer through the Hippo pathway factor, LATS1. METTL3 was identified as the m6A writer, with YTHDF2 as the reader protein of LATS1 mRNA, which plays a positive role in promoting both tumorigenesis and glycolysis in breast cancer. High levels of m6A modification were induced by METTL3 in LATS1 mRNA. YTHDF2 identified m6A sites in LATS1 mRNA and reduced its stability. Knockout of the protein expression of METTL3 or YTHDF2 increased the expression of LATS1 mRNA and suppressed breast cancer tumorigenesis by activating YAP/TAZ in the Hippo pathway. CONCLUSIONS: In summary, we discovered that the METTL3-LATS1-YTHDF2 pathway plays an important role in the progression of breast cancer by activating YAP/TAZ in the Hippo pathway.

Atypical architectural distortion detection in digital breast tomosynthesis: a computer-aided detection model with adaptive receptive field.

Objective. In digital breast tomosynthesis (DBT), architectural distortion (AD) is a breast lesion that is difficult to detect. Compared with typical ADs, which have radial patterns, identifying a typical ADs is more difficult. Most existing computer-aided detection (CADe) models focus on the detection of typical ADs. This study focuses on atypical ADs and develops a deep learning-based CADe model with an adaptive receptive field in DBT.Approach. Our proposed model uses a Gabor filter and convergence measure to depict the distribution of fibroglandular tissues in DBT slices. Subsequently, two-dimensional (2D) detection is implemented using a deformable-convolution-based deep learning framework, in which an adaptive receptive field is introduced to extract global features in slices. Finally, 2D candidates are aggregated to form the three-dimensional AD detection results. The model is trained on 99 positive cases with ADs and evaluated on 120 AD-positive cases and 100 AD-negative cases.Main results. A convergence-measure-based model and deep-learning model without an adaptive receptive field are reproduced as controls. Their mean true positive fractions (MTPF) ranging from 0.05 to 4 false positives per volume are 0.3846 ± 0.0352 and 0.6501 ± 0.0380, respectively. Our proposed model achieves an MTPF of 0.7148 ± 0.0322, which is a significant improvement (p< 0.05) compared with the other two methods. In particular, our model detects more atypical ADs, primarily contributing to the performance improvement.Significance. The adaptive receptive field helps the model improve the atypical AD detection performance. It can help radiologists identify more ADs in breast cancer screening.

Multi-scale cascaded networks for synthesis of mammogram to decrease intensity distortion and increase model-based perceptual similarity.

PURPOSE: Synthetic digital mammogram (SDM) is a 2D image generated from digital breast tomosynthesis (DBT) and used as a substitute for a full-field digital mammogram (FFDM) to reduce the radiation dose for breast cancer screening. The previous deep learning-based method used FFDM images as the ground truth, and trained a single neural network to directly generate SDM images with similar appearances (e.g., intensity distribution, textures) to the FFDM images. However, the FFDM image has a different texture pattern from DBT. The difference in texture pattern might make the training of the neural network unstable and result in high-intensity distortion, which makes it hard to decrease intensity distortion and increase perceptual similarity (e.g., generate similar textures) at the same time. Clinically, radiologists want to have a 2D synthesized image that feels like an FFDM image in vision and preserves local structures such as both mass and microcalcifications (MCs) in DBT because radiologists have been trained on reading FFDM images for a long time, while local structures are important for diagnosis. In this study, we proposed to use a deep convolutional neural network to learn the transformation to generate SDM from DBT. METHOD: To decrease intensity distortion and increase perceptual similarity, a multi-scale cascaded network (MSCN) is proposed to generate low-frequency structures (e.g., intensity distribution) and high-frequency structures (e.g., textures) separately. The MSCN consist of two cascaded sub-networks: the first sub-network is used to predict the low-frequency part of the FFDM image; the second sub-network is used to generate a full SDM image with textures similar to the FFDM image based on the prediction of the first sub-network. The mean-squared error (MSE) objective function is used to train the first sub-network, termed low-frequency network, to generate a low-frequency SDM image. The gradient-guided generative adversarial network's objective function is to train the second sub-network, termed high-frequency network, to generate a full SDM image with textures similar to the FFDM image. RESULTS: 1646 cases with FFDM and DBT were retrospectively collected from the Hologic Selenia system for training and validation dataset, and 145 cases with masses or MC clusters were independently collected from the Hologic Selenia system for testing dataset. For comparison, the baseline network has the same architecture as the high-frequency network and directly generates a full SDM image. Compared to the baseline method, the proposed MSCN improves the peak-to-noise ratio from 25.3 to 27.9 dB and improves the structural similarity from 0.703 to 0.724, and significantly increases the perceptual similarity. CONCLUSIONS: The proposed method can stabilize the training and generate SDM images with lower intensity distortion and higher perceptual similarity.

Predicting futile recanalization, malignant cerebral edema, and cerebral herniation using intelligible ensemble machine learning following mechanical thrombectomy for acute ischemic stroke.

Purpose: To establish an ensemble machine learning (ML) model for predicting the risk of futile recanalization, malignant cerebral edema (MCE), and cerebral herniation (CH) in patients with acute ischemic stroke (AIS) who underwent mechanical thrombectomy (MT) and recanalization. Methods: This prospective study included 110 patients with premorbid mRS ≤ 2 who met the inclusion criteria. Futile recanalization was defined as a 90-day modified Rankin Scale score >2. Clinical and imaging data were used to construct five ML models that were fused into a logistic regression algorithm using the stacking method (LR-Stacking). We added the Shapley Additive Explanation method to display crucial factors and explain the decision process of models for each patient. Prediction performances were compared using area under the receiver operating characteristic curve (AUC), F1-score, and decision curve analysis (DCA). Results: A total of 61 patients (55.5%) experienced futile recanalization, and 34 (30.9%) and 22 (20.0%) patients developed MCE and CH, respectively. In test set, the AUCs for the LR-Stacking model were 0.949, 0.885, and 0.904 for the three outcomes mentioned above. The F1-scores were 0.882, 0.895, and 0.909, respectively. The DCA showed that the LR-Stacking model provided more net benefits for predicting MCE and CH. The most important factors were the hypodensity volume and proportion in the corresponding vascular supply area. Conclusion: Using the ensemble ML model to analyze the clinical and imaging data of AIS patients with successful recanalization at admission and within 24 h after MT allowed for accurately predicting the risks of futile recanalization, MCE, and CH.

Architectural distortion detection based on superior-inferior directional context and anatomic prior knowledge in digital breast tomosynthesis.

BACKGROUND: In 2020, breast cancer becomes the most leading diagnosed cancer all over the world. The burden is increasing in the prevention and treatment of breast cancer. Accurately detecting breast lesions in screening images is important for early detection of cancer. Architectural distortion (AD) is one of the breast lesions that need to be detected. PURPOSE: To develop a deep-learning-based computer-aided detection (CADe) model for AD in digital breast tomosynthesis (DBT). This model uses the superior-inferior directional context of DBT and anatomic prior knowledge to reduce false positive (FP). It can identify some negative samples that cannot be distinguished by deep learning features. METHODS: The proposed CADe model consists of three steps. In the first step, a deep learning detection network detects two-dimensional (2D) candidates of ADs in DBT slices with the inputs preprocessed by Gabor filters and convergence measure. In the second step, three-dimensional (3D) candidates are obtained by stacking 2D candidates along superior-inferior direction. In the last step, FP reduction for 3D candidates is implemented based on superior-inferior directional context and anatomic prior knowledge of breast. DBT data from 99 cases with AD were used as the training set to train the CADe model, and data from 208 cases were used as an independent test set (including 108 cases with AD and 100 cases without AD as the control group). The free-response receiver operating characteristic and mean true positive fraction (MTPF) in the range of 0.05-2.0 FPs per volume are used to evaluate the model. RESULTS: Compared with the baseline model based on convergence measure, our proposed method demonstrates significant improvement (MTPF: 0.2826 ± 0.0321 vs. 0.6640 ± 0.0399). Results of an ablation study show that our proposed context- and anatomy-based FP reduction methods improve the detection performance. The number of FPs per DBT volume reduces from 2.47 to 1.66 at 80% sensitivity after employing these two schemes. CONCLUSIONS: The deep learning model demonstrates practical value for AD detection. The results indicate that introducing superior-inferior directional context and anatomic prior knowledge into model can indeed reduce FPs and improve the performance of CADe model.

Clinical and imaging features of 112 patients with irregular and flat bone osteosarcoma.

Background: This study evaluated the clinical characteristics and imaging findings of 112 patients with irregular and flat bone osteosarcoma (IFBO). Methods: The age, gender, location, tumor size, density and signal intensity, osteoid matrix, periosteal reaction, and histological subtypes were analyzed for 112 patients with IFBO. Results: A total of 112 patients with IFBO, including 64 males and 48 females, with a mean age of 34.8 years were enrolled in this study. Over half of the tumors (54.5%) were detected in the craniofacial region and the skull (24 in the maxilla bone, 17 in the mandible bone, 11 in the sphenoid bone, 7 in the temporal bone, 1 in the frontal bone, and 1 in the occipital bone). Other tumor locations included the pelvic region (20.5%; 20 in the ilium and 3 in the pubis), the chest (18.8%; 11 in the scapula, 7 in the ribs, and 3 in the clavicle), and the vertebrae (6.3%; 3 in the thoracic spine, 2 in the lumbar spine, 1 in the sacrum, and 1 in the cervical spine). Transarticular extension occurred in 11 of the 23 pelvic cases (47.8%), primarily involving the sacroiliac joint (90.9%; 10 of 11). Six cases (6/7; 85.7%) of vertebral osteosarcoma arose from the transverse process and the pedicle, and 1 (1/7; 14.3%) arose from the sacral tuberosity and the ala, with partial vertebral body involvement. Additionally, 27 patients (24.1%) presented with secondary osteosarcoma related to prior radiotherapy, and 2 (1.8%) were associated with osteoblastoma and fibrous dysplasia. Histological examination revealed high-grade tumors in 88 (78.6%) cases. The tumors presented as soft-tissue masses with a diameter of 7.5±3.2 cm. A total of 91 patients underwent X-ray examination and/or computed tomography (CT) examinations. The osteoid matrix was detected in 84 patients (84/91;92.3%). A periosteal reaction was detected in 56 cases (56/91; 61.5%), including a lamellar periosteal reaction in 10 patients (11.0%) and a spiculated periosteal reaction in 46 cases (50.5%). All 74 cases who underwent magnetic resonance imaging (MRI) examinations presented with heterogeneous masses in the surrounding soft tissue. Enhancement was homogenous in 12 cases (18.5%) and heterogeneous in 53 cases (81.5%). Peripheral rim enhancement was observed in 10 cases (13.5%). Conclusions: IFBO should be considered when diagnosing patients over 30 years of age who exhibit osteoid matrix in bone lesions. Maxillofacial osteosarcoma is commonly associated with a history of radiation exposure. Pelvic osteosarcoma is more likely to invade the sacroiliac joint. Vertebral osteosarcoma frequently arises in the transverse process and pedicle, with partial body involvement.

A deep learning-machine learning fusion approach for the classification of benign, malignant, and intermediate bone tumors.

OBJECTIVES: To build and validate deep learning and machine learning fusion models to classify benign, malignant, and intermediate bone tumors based on patient clinical characteristics and conventional radiographs of the lesion. METHODS: In this retrospective study, data were collected with pathologically confirmed diagnoses of bone tumors between 2012 and 2019. Deep learning and machine learning fusion models were built to classify tumors as benign, malignant, or intermediate using conventional radiographs of the lesion and potentially relevant clinical data. Five radiologists compared diagnostic performance with and without the model. Diagnostic performance was evaluated using the area under the curve (AUC). RESULTS: A total of 643 patients' (median age, 21 years; interquartile range, 12-38 years; 244 women) 982 radiographs were included. In the test set, the binary category classification task, the radiological model of classification for benign/not benign, malignant/nonmalignant, and intermediate/not intermediate had AUCs of 0.846, 0.827, and 0.820, respectively; the fusion models had an AUC of 0.898, 0.894, and 0.865, respectively. In the three-category classification task, the radiological model achieved a macro average AUC of 0.813, and the fusion model had a macro average AUC of 0.872. In the observation test, the mean macro average AUC of all radiologists was 0.819. With the three-category classification fusion model support, the macro AUC improved by 0.026. CONCLUSION: We built, validated, and tested deep learning and machine learning models that classified bone tumors at a level comparable with that of senior radiologists. Model assistance may somewhat help radiologists' differential diagnoses of bone tumors. KEY POINTS: • The deep learning model can be used to classify benign, malignant, and intermediate bone tumors. • The machine learning model fusing information from radiographs and clinical characteristics can improve the classification capacity for bone tumors. • The diagnostic performance of the fusion model is comparable with that of senior radiologists and is potentially useful as a complement to radiologists in a bone tumor differential diagnosis.

Pure and Mixed Tubular Carcinoma of the Breast: Mammographic Features, Clinicopathological Characteristics and Prognostic Analysis.

Objective: To evaluate the mammographic features, clinicopathological characteristics, treatments, and prognosis of pure and mixed tubular carcinomas of the breast. Materials and methods: Twenty-five tubular carcinomas were pathologically confirmed at our hospital from January 2011 to May 2019. Twenty-one patients underwent preoperative mammography. A retrospective analysis of mammographic features, clinicopathological characteristics, treatment, and outcomes was performed. Results: Altogether, 95% of the pure tubular carcinomas (PTCs) and mixed tubular carcinomas (MTCs) showed the presence of a mass or structural distortions on mammography and the difference was not statistically significant (P = .373). MTCs exhibited a larger tumor size than PTCs (P = .033). Lymph node metastasis was more common (P = .005) in MTCs. Patients in our study showed high estrogen receptor and progesterone receptor positivity rates, but low human epidermal growth factor receptor 2 positivity rate. The overall survival rate was 100% in both PTC and MTC groups and the 5-year disease-free survival rates were 100% and 75%, respectively with no significant difference between the groups (P = .264). Conclusion: Tubular carcinoma of the breast is potentially malignant and has a favorable prognosis. Digital breast tomosynthesis may improve its detection. For patients with PTC, breast-conserving surgery and sentinel lymph node biopsy are recommended based on the low rate of lymph node metastasis and good prognosis. MTC has a relatively high rate of lymph node metastasis and a particular risk of metastasis. Axillary lymph node dissection should be performed for MTC even if the tumor is smaller than 2 cm.

Cost-Effectiveness of Short-Course Radiation Plus Temozolomide for the Treatment of Newly Diagnosed Glioblastoma Among Elderly Patients in China and the United States.

Background: Glioblastoma multiforme (GBM) is a fatal type of brain tumor with a high incidence among elderly people. Temozolomide (TMZ) has proven to be an effective chemotherapeutic agent with significant survival benefits. This study aimed to evaluate the economic outcomes of radiotherapy (RT) and TMZ for the treatment of newly diagnosed GBM in elderly people in the United States (US) and China. Methods: A partitioned survival model was constructed for RT plus TMZ and RT alone among patients with methylated and unmethylated tumor status. Base case calculations and one-way and probabilistic sensitivity analyses were performed. Life-years, quality-adjusted life-years (QALYs), costs (in 2021 US dollars [$] and Chinese Yuan Renminbi [¥]), and incremental cost-effectiveness ratios (ICERs) were calculated. Results: RT plus TMZ was found to be associated with significantly higher costs and QALYs in all groups. Only US patients with methylated status receiving RT plus TMZ had an ICER ($89358.51) less than the willingness-to-pay (WTP) threshold of $100000 per QALY gained when compared with receiving RT alone. When the WTP threshold ranged from $100000 to $150000 from the US perspective, the probability of RT plus TMZ being cost-effective increased from 80.5 to 99.8%. The cost of TMZ must be lower than ¥120 per 20 mg for RT plus TMZ to be cost-effective among patients with methylated tumor status in China. Conclusion: RT plus TMZ was not cost-effective in China, and a reduction in the TMZ price was justified. However, it is highly likely to be cost-effective for patients with methylated tumor status in the US.

Can the delayed phase of quantitative contrast-enhanced mammography improve the diagnostic performance on breast masses?

BACKGROUND: Contrast-enhanced mammography (CEM) is an imaging tool for breast cancer detection. Most quantitative analyses of CEM involve two phases, and it is unknown whether an added delayed phase can improve its diagnostic performance compared to dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). This study aimed to evaluate whether the delayed phase improves the diagnostic performance of CEM in distinguishing malignant and benign masses. METHODS: This prospective study enrolled 111 women with 111 pathologically confirmed breast masses. CEM was performed after the injection of contrast agent between 2-3 minutes (T1, early phase), 4-5 minutes (T2, second phase), and 7-9 minutes (T3, delayed phase). The quantitative enhanced gray value of lesions (LGV) and the lesion to background grey value ratio (LBR) were measured within each phase's corresponding region of interest (ROI). Based on their changes, the kinetic enhancement pattern was assessed among the three phases, and the diagnostic performance was subsequently measured. RESULTS: The LGV and LBR of malignant masses were significantly greater than those of benign lesions. The diagnostic performance of LGV and LBR at the delayed phase was consistent with that of the second phase but poorer than that of the early phase. The sensitivity of LGVT1 + LGVT2 + LGVT3 was less than that of LGVT1 + LGVT2 (86.5% vs. 95.1%) with a similar area under the curve (AUC), specificity, positive-predictive value (PPV), negative-predictive value (NPV), and accuracy. The sensitivity of LBRT1 + LBRT2 + LBRT3 increased by 19.6%, and specificity decreased by 20.7% compared with LBRT1 + LBRT2. The LGVT1 + LGVT2 + LGVT3 + kinetic enhancement (T1-T3) had the lowest sensitivity (67.0%), but the highest specificity (75.8%), and the sensitivity of LBRT1 + LBRT2 + LBRT3 + kinetic enhancement (T1-T3) was higher than that of LBRT1 + LBRT2 + kinetic enhancement (T1-T2) (90.2% vs. 63.4%, respectively). CONCLUSIONS: The addition of a delayed CEM phase for breast cancer diagnosis yielded limited performance improvement. The quantitative analysis combined with enhancement patterns between the two consecutive phases has great potential to distinguish between malignant and benign lesions.

Using Machine Learning to Unravel the Value of Radiographic Features for the Classification of Bone Tumors.

OBJECTIVES: To build and validate random forest (RF) models for the classification of bone tumors based on the conventional radiographic features of the lesion and patients' clinical characteristics, and identify the most essential features for the classification of bone tumors. MATERIALS AND METHODS: In this retrospective study, 796 patients (benign bone tumors: 412 cases, malignant bone tumors: 215 cases, intermediate bone tumors: 169 cases) with pathologically confirmed bone tumors from Nanfang Hospital of Southern Medical University, Foshan Hospital of TCM, and University of Hong Kong-Shenzhen Hospital were enrolled. RF models were built to classify tumors as benign, malignant, or intermediate based on conventional radiographic features and potentially relevant clinical characteristics extracted by three musculoskeletal radiologists with ten years of experience. SHapley Additive exPlanations (SHAP) was used to identify the most essential features for the classification of bone tumors. The diagnostic performance of the RF models was quantified using receiver operating characteristic (ROC) curves. RESULTS: The features extracted by the three radiologists had a satisfactory agreement and the minimum intraclass correlation coefficient (ICC) was 0.761 (CI: 0.686-0.824, P < .001). The binary and tertiary models were built to classify tumors as benign, malignant, or intermediate based on the imaging and clinical features from 627 and 796 patients. The AUC of the binary (19 variables) and tertiary (22 variables) models were 0.97 and 0.94, respectively. The accuracy of binary and tertiary models were 94.71% and 82.77%, respectively. In descending order, the most important features influencing classification in the binary model were margin, cortex involvement, and the pattern of bone destruction, and the most important features in the tertiary model were margin, high-density components, and cortex involvement. CONCLUSIONS: This study developed interpretable models to classify bone tumors with great performance. These should allow radiographers to identify imaging features that are important for the classification of bone tumors in the clinical setting.

Synthesis of Mammogram From Digital Breast Tomosynthesis Using Deep Convolutional Neural Network With Gradient Guided cGANs.

Synthetic digital mammography (SDM), a 2D image generated from digital breast tomosynthesis (DBT), is used as a potential substitute for full-field digital mammography (FFDM) in clinic to reduce the radiation dose for breast cancer screening. Previous studies exploited projection geometry and fused projection data and DBT volume, with different post-processing techniques applied on re-projection data which may generate different image appearance compared to FFDM. To alleviate this issue, one possible solution to generate an SDM image is using a learning-based method to model the transformation from the DBT volume to the FFDM image using current DBT/FFDM combo images. In this study, we proposed to use a deep convolutional neural network (DCNN) to learn the transformation to generate SDM using current DBT/FFDM combo images. Gradient guided conditional generative adversarial networks (GGGAN) objective function was designed to preserve subtle MCs and the perceptual loss was exploited to improve the performance of the proposed DCNN on perceptual quality. We used various image quality criteria for evaluation, including preserving masses and MCs which are important in mammogram. Experiment results demonstrated progressive performance improvement of network using different objective functions in terms of those image quality criteria. The methodology we exploited in the SDM generation task to analyze and progressively improve image quality by designing objective functions may be helpful to other image generation tasks.