Imaging segmentation mechanism for rectal tumors using improved U-Net.

OBJECTIVE: In radiation therapy, cancerous region segmentation in magnetic resonance images (MRI) is a critical step. For rectal cancer, the automatic segmentation of rectal tumors from an MRI is a great challenge. There are two main shortcomings in existing deep learning-based methods that lead to incorrect segmentation: 1) there are many organs surrounding the rectum, and the shape of some organs is similar to that of rectal tumors; 2) high-level features extracted by conventional neural networks often do not contain enough high-resolution information. Therefore, an improved U-Net segmentation network based on attention mechanisms is proposed to replace the traditional U-Net network. METHODS: The overall framework of the proposed method is based on traditional U-Net. A ResNeSt module was added to extract the overall features, and a shape module was added after the encoder layer. We then combined the outputs of the shape module and the decoder to obtain the results. Moreover, the model used different types of attention mechanisms, so that the network learned information to improve segmentation accuracy. RESULTS: We validated the effectiveness of the proposed method using 3773 2D MRI datasets from 304 patients. The results showed that the proposed method achieved 0.987, 0.946, 0.897, and 0.899 for Dice, MPA, MioU, and FWIoU, respectively; these values are significantly better than those of other existing methods. CONCLUSION: Due to time savings, the proposed method can help radiologists segment rectal tumors effectively and enable them to focus on patients whose cancerous regions are difficult for the network to segment. SIGNIFICANCE: The proposed method can help doctors segment rectal tumors, thereby ensuring good diagnostic quality and accuracy.

A medical image segmentation method for rectal tumors based on multi-scale feature retention and multiple attention mechanisms.

BACKGROUND: With the continuous development of deep learning algorithms in the field of medical images, models for medical image processing based on convolutional neural networks have made great progress. Since medical images of rectal tumors are characterized by specific morphological features and complex edges that differ from natural images, achieving good segmentation results often requires a higher level of enrichment through the utilization of semantic features. PURPOSE: The efficiency of feature extraction and utilization has been improved to some extent through enhanced hardware arithmetic and deeper networks in most models. However, problems still exist with detail loss and difficulty in feature extraction, arising from the extraction of high-level semantic features in deep networks. METHODS: In this work, a novel medical image segmentation model has been proposed for Magnetic Resonance Imaging (MRI) image segmentation of rectal tumors. The model constructs a backbone architecture based on the idea of jump-connected feature fusion and solves the problems of detail feature loss and low segmentation accuracy using three novel modules: Multi-scale Feature Retention (MFR), Multi-branch Cross-channel Attention (MCA), and Coordinate Attention (CA). RESULTS: Compared with existing methods, our proposed model is able to segment the tumor region more effectively, achieving 97.4% and 94.9% in Dice and mIoU metrics, respectively, exhibiting excellent segmentation performance and computational speed. CONCLUSIONS: Our proposed model has improved the accuracy of both lesion region and tumor edge segmentation. In particular, the determination of the lesion region can help doctors identify the tumor location in clinical diagnosis, and the accurate segmentation of the tumor edge can assist doctors in judging the necessity and feasibility of surgery.

Unveiling Anti-Diabetic Potential of Baicalin and Baicalein from Baikal Skullcap: LC-MS, In Silico, and In Vitro Studies.

Type 2 diabetes mellitus (T2DM) is marked by persistent hyperglycemia, insulin resistance, and pancreatic ß-cell dysfunction, imposing substantial health burdens and elevating the risk of systemic complications and cardiovascular diseases. While the pathogenesis of diabetes remains elusive, a cyclical relationship between insulin resistance and inflammation is acknowledged, wherein inflammation exacerbates insulin resistance, perpetuating a deleterious cycle. Consequently, anti-inflammatory interventions offer a therapeutic avenue for T2DM management. In this study, a herb called Baikal skullcap, renowned for its repertoire of bioactive compounds with anti-inflammatory potential, is posited as a promising source for novel T2DM therapeutic strategies. Our study probed the anti-diabetic properties of compounds from Baikal skullcap via network pharmacology, molecular docking, and cellular assays, concentrating on their dual modulatory effects on diabetes through Protein Tyrosine Phosphatase 1B (PTP1B) enzyme inhibition and anti-inflammatory actions. We identified the major compounds in Baikal skullcap using liquid chromatography-mass spectrometry (LC-MS), highlighting six flavonoids, including the well-studied baicalein, as potent inhibitors of PTP1B. Furthermore, cellular experiments revealed that baicalin and baicalein exhibited enhanced anti-inflammatory responses compared to the active constituents of licorice, a known anti-inflammatory agent in TCM. Our findings confirmed that baicalin and baicalein mitigate diabetes via two distinct pathways: PTP1B inhibition and anti-inflammatory effects. Additionally, we have identified six flavonoid molecules with substantial potential for drug development, thereby augmenting the T2DM pharmacotherapeutic arsenal and promoting the integration of herb-derived treatments into modern pharmacology.

Mulberry Leaf Compounds and Gut Microbiota in Alzheimer's Disease and Diabetes: A Study Using Network Pharmacology, Molecular Dynamics Simulation, and Cellular Assays.

Recently, studies have reported a correlation that individuals with diabetes show an increased risk of developing Alzheimer's disease (AD). Mulberry leaves, serving as both a traditional medicinal herb and a food source, exhibit significant hypoglycemic and antioxidative properties. The flavonoid compounds in mulberry leaf offer therapeutic effects for relieving diabetic symptoms and providing neuroprotection. However, the mechanisms of this effect have not been fully elucidated. This investigation aimed to investigate the combined effects of specific mulberry leaf flavonoids (kaempferol, quercetin, rhamnocitrin, tetramethoxyluteolin, and norartocarpetin) on both type 2 diabetes mellitus (T2DM) and AD. Additionally, the role of the gut microbiota in these two diseases' treatment was studied. Using network pharmacology, we investigated the potential mechanisms of flavonoids in mulberry leaves, combined with gut microbiota, in combating AD and T2DM. In addition, we identified protein tyrosine phosphatase 1B (PTP1B) as a key target for kaempferol in these two diseases. Molecular docking and molecular dynamics simulations showed that kaempferol has the potential to inhibit PTP1B for indirect treatment of AD, which was proven by measuring the IC50 of kaempferol (279.23 µM). The cell experiment also confirmed the dose-dependent effect of kaempferol on the phosphorylation of total cellular protein in HepG2 cells. This research supports the concept of food-medicine homology and broadens the range of medical treatments for diabetes and AD, highlighting the prospect of integrating traditional herbal remedies with modern medical research.

Design, synthesis, and antiviral activity of 1-aryl-4-arylmethylpiperazine derivatives as Zika virus inhibitors with broad antiviral spectrum.

Zika virus (ZIKV) disease has been given attention due to the risk of congenital microcephaly and neurodevelopmental disorders after ZIKV infection in pregnancy, but no vaccine or antiviral drug is available. Based on a previously reported ZIKV inhibitor ZK22, a series of novel 1-aryl-4-arylmethylpiperazine derivatives was designed, synthesized, and investigated for antiviral activity by quantify cellular ZIKV RNA amount using RT-qPCR method in ZIKV-infected human venous endothelial cells (HUVECs) assay. Structure-activity relationship (SAR) analysis demonstrated that anti-ZIKV activity of 1-aryl-4-arylmethylpiperazine derivatives is not correlated with molecular hydrophobicity, multiple new derivatives with pyridine group to replace the benzonitrile moiety of ZK22 showed stronger antiviral activity, higher ligand lipophilicity efficiency as well as lower cytotoxicity. Two active compounds 13 and 33 were further identified as novel ZIKV entry inhibitors with the potential of oral available. Moreover, both ZK22 and newly active derivatives also possess of obvious inhibition on the viral replication of coronavirus and influenza A virus at low micromolar level. In summary, this work provided better candidates of ZIKV inhibitor for preclinical study and revealed the promise of 1-aryl-4-arylmethylpiperazine chemotype in the development of broad-spectrum antiviral agents.

Multicenter Evaluation of a Weakly Supervised Deep Learning Model for Lymph Node Diagnosis in Rectal Cancer at MRI.

Purpose To develop a Weakly supervISed model DevelOpment fraMework (WISDOM) model to construct a lymph node (LN) diagnosis model for patients with rectal cancer (RC) that uses preoperative MRI data coupled with postoperative patient-level pathologic information. Materials and Methods In this retrospective study, the WISDOM model was built using MRI (T2-weighted and diffusion-weighted imaging) and patient-level pathologic information (the number of postoperatively confirmed metastatic LNs and resected LNs) based on the data of patients with RC between January 2016 and November 2017. The incremental value of the model in assisting radiologists was investigated. The performances in binary and ternary N staging were evaluated using area under the receiver operating characteristic curve (AUC) and the concordance index (C index), respectively. Results A total of 1014 patients (median age, 62 years; IQR, 54-68 years; 590 male) were analyzed, including the training cohort (n = 589) and internal test cohort (n = 146) from center 1 and two external test cohorts (cohort 1: 117; cohort 2: 162) from centers 2 and 3. The WISDOM model yielded an overall AUC of 0.81 and C index of 0.765, significantly outperforming junior radiologists (AUC = 0.69, P < .001; C index = 0.689, P < .001) and performing comparably with senior radiologists (AUC = 0.79, P = .21; C index = 0.788, P = .22). Moreover, the model significantly improved the performance of junior radiologists (AUC = 0.80, P < .001; C index = 0.798, P < .001) and senior radiologists (AUC = 0.88, P < .001; C index = 0.869, P < .001). Conclusion This study demonstrates the potential of WISDOM as a useful LN diagnosis method using routine rectal MRI data. The improved radiologist performance observed with model assistance highlights the potential clinical utility of WISDOM in practice. Keywords: MR Imaging, Abdomen/GI, Rectum, Computer Applications-Detection/Diagnosis Supplemental material is available for this article. Published under a CC BY 4.0 license.

A CT-based multitask deep learning model for predicting tumor stroma ratio and treatment outcomes in patients with colorectal cancer: a multicenter cohort study.

BACKGROUND: Tumor-stroma interactions, as indicated by tumor-stroma ratio (TSR), offer valuable prognostic stratification information. Current histological assessment of TSR is limited by tissue accessibility and spatial heterogeneity. We aimed to develop a multitask deep learning (MDL) model to noninvasively predict TSR and prognosis in colorectal cancer (CRC). MATERIALS AND METHODS: In this retrospective study including 2268 patients with resected CRC recruited from four centers, we developed an MDL model using preoperative CT images for the simultaneous prediction of TSR and overall survival. Patients in the training cohort (n=956) and internal validation cohort (IVC, n=240) were randomly selected from center I. Patients in the external validation cohort1(EVC1, n=509), EVC2 (n=203), and EVC3 (n=360) were recruited from other three centers. Model performance was evaluated with respect to discrimination and calibration. Furthermore, we evaluated whether the model could predict the benefit from adjuvant chemotherapy. RESULTS: The MDL model demonstrated strong TSR discrimination, yielding areas under the receiver operating curves (AUCs) of 0.855 (95%CI, 0.800-0.910), 0.838(95% CI, 0.802-0.874), and 0.857(95% CI, 0.804-0.909) in the three validation cohorts, respectively. The MDL model was also able to predict overall survival and disease-free survival across all cohorts. In multivariable Cox analysis, the MDL score (MDLS) remained an independent prognostic factor after adjusting for clinicopathological variables (all P<0.05). For stage II and stage III disease, patients with a high MDLS benefited from adjuvant chemotherapy (hazard ratio [HR] 0.391 [95%CI, 0.230-0.666], P=0.0003; HR=0.467[95%CI, 0.331-0.659], P<0.0001, respectively), whereas those with a low MDLS did not. CONCLUSION: The multitask DL model based on preoperative CT images effectively predicted TSR status and survival in CRC patients, offering valuable guidance for personalized treatment. Prospective studies are needed to confirm its potential to select patients who might benefit from chemotherapy.

Network Pharmacology Combined with Machine Learning to Reveal the Action Mechanism of Licochalcone Intervention in Liver Cancer.

There are reports indicating that licochalcones can inhibit the proliferation, migration, and invasion of cancer cells by promoting the expression of autophagy-related proteins, inhibiting the expression of cell cycle proteins and angiogenic factors, and regulating autophagy and apoptosis. This study aims to reveal the potential mechanisms of licochalcone A (LCA), licochalcone B (LCB), licochalcone C (LCC), licochalcone D (LCD), licochalcone E (LCE), licochalcone F (LCF), and licochalcone G (LCG) inhibition in liver cancer through computer-aided screening strategies. By using machine learning clustering analysis to search for other structurally similar components in licorice, quantitative calculations were conducted to collect the structural commonalities of these components related to liver cancer and to identify key residues involved in the interactions between small molecules and key target proteins. Our research results show that the seven licochalcones molecules interfere with the cancer signaling pathway via the NF-κB signaling pathway, PDL1 expression and PD1 checkpoint pathway in cancer, and others. Glypallichalcone, Echinatin, and 3,4,3',4'-Tetrahydroxy-2-methoxychalcone in licorice also have similar structures to the seven licochalcones, which may indicate their similar effects. We also identified the key residues (including ASN364, GLY365, TRP366, and TYR485) involved in the interactions between ten flavonoids and the key target protein (nitric oxide synthase 2). In summary, we provide valuable insights into the molecular mechanisms of the anticancer effects of licorice flavonoids, providing new ideas for the design of small molecules for liver cancer drugs.

RTAU-Net: A novel 3D rectal tumor segmentation model based on dual path fusion and attentional guidance.

BACKGROUND AND OBJECTIVE: According to the Global Cancer Statistics 2020, colorectal cancer has the third-highest diagnosis rate (10.0 %) and the second-highest mortality rate (9.4 %) among the 36 types. Rectal cancer accounts for a large proportion of colorectal cancer. The size and shape of the rectal tumor can directly affect the diagnosis and treatment by doctors. The existing rectal tumor segmentation methods are based on two-dimensional slices, which cannot analyze a patient's tumor as a whole and lose the correlation between slices of MRI image, so the practical application value is not high. METHODS: In this paper, a three-dimensional rectal tumor segmentation model is proposed. Firstly, image preprocessing is performed to reduce the effect caused by the unbalanced proportion of background region and target region, and improve the quality of the image. Secondly, a dual-path fusion network is designed to extract both global features and local detail features of rectal tumors. The network includes two encoders, a residual encoder for enhancing the spatial detail information and feature representation of the tumor and a transformer encoder for extracting global contour information of the tumor. In the decoding stage, we merge the information extracted from the dual paths and decode them. In addition, for the problem of the complex morphology and different sizes of rectal tumors, a multi-scale fusion channel attention mechanism is designed, which can capture important contextual information of different scales. Finally, visualize the 3D rectal tumor segmentation results. RESULTS: The RTAU-Net is evaluated on the data set provided by Shanxi Provincial Cancer Hospital and Xinhua Hospital. The experimental results showed that the Dice of tumor segmentation reached 0.7978 and 0.6792, respectively, which improved by 2.78 % and 7.02 % compared with suboptimal model. CONCLUSIONS: Although the morphology of rectal tumors varies, RTAU-Net can precisely localize rectal tumors and learn the contour and details of tumors, which can relieve physicians' workload and improve diagnostic accuracy.

Molecular Dynamics Simulations Combined with Markov Model to Explore the Effect of Allosteric Inhibitor Binding on Bromodomain-Containing Protein 4.

Bromodomain-Containing Protein 4 (BRD4) can play an important role in gene transcriptional regulation of tumor development and survival by participating in histone modification epigenetic mechanism. Although it has been reported that novel allosteric inhibitors such as ZL0590 have a high affinity with target protein BRD4 and good efficacy, their inhibitory mechanism has not been studied further. The aim of this study was to reveal the inhibition mechanism of allosteric inhibitor ZL0590 on Free-BRD4 and BRD4 binding MS436 (orthosteric inhibitor) by molecular dynamics simulation combined with a Markov model. Our results showed that BRD4-ZL0590 led to α-helices formation of 100-105 compared with Free-BRD4; the combination of MS436 caused residues 30-40 and 95-105 to form α-helices, while the combination of allosteric inhibitors untangled the α-helices formed by the MS436. The results of Markov flux analysis showed that the binding process of inhibitors mainly involved changes in the degree of α-helices at ZA loop. The binding of ZL0590 reduced the distance between ZA loop and BC loop, blocked the conformation at the active site, and inhibited the binding of MS436. After the allosteric inhibitor binding, the MS436 that could normally penetrate into the interior of the pocket was floating on the edge of the active pocket and did not continue to penetrate into the active pocket as expected. In summary, we provide a theoretical basis for the inhibition mechanism of ZL0590 against BRD4, which can be used as a reference for improving the development of drug targets for cancer therapy.

Automatic segmentation of rectal tumors from MRI using multiscale densely connected convolutional neural network based on attention mechanism.

Rectal cancer is one of the most common malignancies in the gastrointestinal tract. Currently, magnetic resonance imaging has become a vital tool in diagnosing and treating patients with rectal cancer. Notably, early diagnosis of rectal cancer can help improve patient survival rate; however, the clinical expertize of physicians is a limiting factor. Therefore, we propose an attention-based multiscale densely connected convolutional neural network based on an attention mechanism to improve the accuracy of diagnosis by automatically segmenting rectal tumors from two-dimensional (2D) magnetic resonance images (MRI) using computer-aided diagnostic techniques. First, to address the inability of U-Net (a classical segmentation network for medical images) and extract rich semantic features and the inconsistent shape and size of tumors between different patients, we replace the conventional convolutional blocks in the U-Net network with multiscale densely connected convolutional blocks. Second, to make the network focus better on global contextual information, we add central blocks with atrous convolution in the final coding layer or the last coding layer. Finally, we add a hybrid attention mechanism to each decoder module to help the model focus on the features of the rectal tumor region. We validated the effectiveness of the proposed method using 3773 2D MRI datasets from 572 patients. The sensitivity, specificity, Dice correlation coefficient, and Hausdorff distance of MRI rectal tumor segmentation were 85.47%, 86.35%, 94.71%, and 7.88 mm, respectively. The results showed that the proposed method outperforms conventional approaches. Moreover, the proposed method has better segmentation results in the rectal tumor segmentation task and can provide physicians with the second-most important clinical diagnostic opinion.

The maximal contrast-enhanced range of CT for differentiating the WHO pathological subtypes and risk subgroups of thymic epithelial tumors.

OBJECTIVE: To explore the value of maximal contrast-enhanced (CEmax) range using contrast-enhanced CT (CECT) imaging in differentiating the pathological subtypes and risk subgroups of thymic epithelial tumors (TETs). METHODS: The pre-treatment-CECT images of 319 TET patients from May 2012 to November 2021 were analyzed retrospectively. The CEmax was defined as the maximum difference between the CT value of the solid tumor on pre-contrast and contrast-enhanced images. The mean CEmax value was calculated at three different tumor levels. RESULTS: There was a significant difference in the CEmax among the eight main pathological subtypes [types A, AB, B1, B2, and B3 thymoma, thymic carcinoma (TC), low-grade neuroendocrine tumor (NET) and high-grade NET] (p < 0.001). Among the eight subtypes, the CEmax values of types A, AB, and low-risk NET were higher than those of the other subtypes (all p < 0.001), and there was no difference among types B1-B3 and high-risk NET (all p > 0.05). There was no difference for CEmax values between NET and TC (p = 0.491). For the risk subgroups, the CEmax of TC (including NET) was 35.35 ± 11.41 HU, which was lower than that of low-risk thymoma (A and AB) (57.73±21.24 HU) (P < 0.001) and was higher than that of high-risk thymoma (B1-B3) (27.37±8.27 HU) (P < 0.001). The CEmax cut-off values were 38.5 HU and 30.5 HU respectively (AUC: 0.829 and 0.712; accuracy, 72.4% and 67.7%). CONCLUSION: The tumor CEmax on CECT helps differentiate the pathological subtypes and risk subgroups of TETs. ADVANCES IN KNOWLEDGE: In this study, an improved simplified risk grouping method was proposed based on the traditional (2004 edition) simplified risk grouping method for TETs. If Type B1 thymoma is classified as high-risk, radiologists using this improved method may improve the accuracy in differentiating risk level of TETs compared with the traditional method.

Dual parallel net: A novel deep learning model for rectal tumor segmentation via CNN and transformer with Gaussian Mixture prior.

Segmentation of rectal cancerous regions from Magnetic Resonance (MR) images can help doctor define the extent of the rectal cancer and judge the severity of rectal cancer, so rectal tumor segmentation is crucial to improve the accuracy of rectal cancer diagnosis. However, accurate segmentation of rectal cancerous regions remains a challenging task due to the shape of rectal tumor has significant variations and the tumor and surrounding tissue are indistinguishable. In addition, in the early research on rectal tumor segmentation, most deep learning methods were based on convolutional neural networks (CNNs), and traditional CNN have small receptive field, which can only capture local information while ignoring the global information of the image. Nevertheless, the global information plays a crucial role in rectal tumor segmentation, so traditional CNN-based methods usually cannot achieve satisfactory segmentation results. In this paper, we propose an encoder-decoder network named Dual Parallel Net (DuPNet), which fuses transformer and classical CNN for capturing both global and local information. Meanwhile, as for capture features at different scales as well as to avoid accuracy loss and parameters reduction, we design a feature adaptive block (FAB) in skip connection between encoder and decoder. Furthermore, in order to utilize the apriori information of rectal tumor shape effectively, we design a Gaussian Mixture prior and embed it in self-attention mechanism of the transformer, leading to robust feature representation and accurate segmentation results. We have performed extensive ablation experiments to verify the effectiveness of our proposed dual parallel encoder, FAB and Gaussian Mixture prior on the dataset from the Shanxi Cancer Hospital. In the experimental comparison with the state-of-the-art methods, our method achieved a Mean Intersection over Union (MIoU) of 89.34% on the test set. In addition to that, we evaluated the generalizability of our method on the dataset from Xinhua Hospital, the promising results verify the superiority of our method.

Computer-Aided Screening and Revealing Action Mechanism of Green Tea Polyphenols Intervention in Alzheimer's Disease.

The accumulation of cross-ß-sheet amyloid fibrils is a hallmark of the neurodegenerative process of Alzheimer's disease (AD). Although it has been reported that green tea substances such as epicatechin (EC), epicatechin-3-gallate (ECG), epigallocatechin (EGC) and epigallocatechin-3-gallate (EGCG) could alleviate the symptoms of AD and other neurodegenerative diseases, the pharmacological mechanism remains largely unexplored. This study aimed to reveal the underlying mechanism of EC, ECG, EGC and EGCG in AD using a computer-aided screening strategy. Our results showed that the four tea polyphenols interfered with the signaling pathways of AD via calcium signaling channels, neurodegeneration-multiple disease signal pathways and others. We also identified the key residues of the interaction between VEGFA and the four active components, which included Glu64 and Phe36. Overall, we have provided valuable insights into the molecular mechanism of tea polyphenols, which could be used as a reference to improve therapeutic strategies against AD.

Design, synthesis and biological evaluation of 2-((4-sulfamoylphenyl)amino)-pyrrolo[2,3-d]pyrimidine derivatives as CDK inhibitors.

To explore the potential use of CDK inhibitors in pancreatic ductal adenocarcinoma (PDAC) therapy, a series of novel 2-((4-sulfamoylphenyl)amino)-pyrrolo[2,3-d]pyrimidine derivatives was designed, synthesised, and investigated for inhibition on both CDK kinase activity and cellular proliferation of pancreatic cancer. Most of new sulphonamide-containing derivatives demonstrated strong inhibitory activity on CDK9 and obvious anti-proliferative activity in cell culture. Moreover, two new compounds suppressed cell proliferation of multiple human pancreatic cancer cell lines. The most potent compound 2g inhibited cancer cell proliferation by blocking Rb phosphorylation and induced apoptosis via downregulation of CDK9 downstream proteins Mcl-1 and c-Myc in MIA PaCa-2 cells. CDK9 knockdown experiment suggests its anti-proliferative activity is mainly mediated by CDK9. Additionally, 2g displayed moderate tumour inhibition effect in AsPC-1 derived xenograft mice model. Altogether, this study provided a new start for further optimisation to develop potential CDK inhibitor candidates for PDAC treatment by alone or combination use.

An integrated deep learning model for the prediction of pathological complete response to neoadjuvant chemotherapy with serial ultrasonography in breast cancer patients: a multicentre, retrospective study.

BACKGROUND: The biological phenotype of tumours evolves during neoadjuvant chemotherapy (NAC). Accurate prediction of pathological complete response (pCR) to NAC in the early-stage or posttreatment can optimize treatment strategies or improve the breast-conserving rate. This study aimed to develop and validate an autosegmentation-based serial ultrasonography assessment system (SUAS) that incorporated serial ultrasonographic features throughout the NAC of breast cancer to predict pCR. METHODS: A total of 801 patients with biopsy-proven breast cancer were retrospectively enrolled from three institutions and were split into a training cohort (242 patients), an internal validation cohort (197 patients), and two external test cohorts (212 and 150 patients). Three imaging signatures were constructed from the serial ultrasonographic features before (pretreatment signature), during the first-second cycle of (early-stage treatment signature), and after (posttreatment signature) NAC based on autosegmentation by U-net. The SUAS was constructed by subsequently integrating the pre, early-stage, and posttreatment signatures, and the incremental performance was analysed. RESULTS: The SUAS yielded a favourable performance in predicting pCR, with areas under the receiver operating characteristic curve (AUCs) of 0.927 [95% confidence interval (CI) 0.891-0.963] and 0.914 (95% CI 0.853-0.976), compared with those of the clinicopathological prediction model [0.734 (95% CI 0.665-0.804) and 0.610 (95% CI 0.504-0.716)], and radiologist interpretation [0.632 (95% CI 0.570-0.693) and 0.724 (95% CI 0.644-0.804)] in the external test cohorts. Furthermore, similar results were also observed in the early-stage treatment of NAC [AUC 0.874 (0.793-0.955)-0.897 (0.851-0.943) in the external test cohorts]. CONCLUSIONS: We demonstrate that autosegmentation-based SAUS integrating serial ultrasonographic features throughout NAC can predict pCR with favourable performance, which can facilitate individualized treatment strategies.

Early prediction of treatment response to neoadjuvant chemotherapy based on longitudinal ultrasound images of HER2-positive breast cancer patients by Siamese multi-task network: A multicentre, retrospective cohort study.

Background: Early prediction of treatment response to neoadjuvant chemotherapy (NACT) in patients with human epidermal growth factor receptor 2 (HER2)-positive breast cancer can facilitate timely adjustment of treatment regimens. We aimed to develop and validate a Siamese multi-task network (SMTN) for predicting pathological complete response (pCR) based on longitudinal ultrasound images at the early stage of NACT. Methods: In this multicentre, retrospective cohort study, a total of 393 patients with biopsy-proven HER2-positive breast cancer were retrospectively enrolled from three hospitals in china between December 16, 2013 and March 05, 2021, and allocated into a training cohort and two external validation cohorts. Patients receiving full cycles of NACT and with surgical pathological results available were eligible for inclusion. The key exclusion criteria were missing ultrasound images and/or clinicopathological characteristics. The proposed SMTN consists of two subnetworks that could be joined at multiple layers, which allowed for the integration of multi-scale features and extraction of dynamic information from longitudinal ultrasound images before and after the first /second cycles of NACT. We constructed the clinical model as a baseline using multivariable logistic regression analysis. Then the performance of SMTN was evaluated and compared with the clinical model. Findings: The training cohort, comprising 215 patients, were selected from Yunnan Cancer Hospital. The two independent external validation cohorts, comprising 95 and 83 patients, were selected from Guangdong Provincial People's Hospital, and Shanxi Cancer Hospital, respectively. The SMTN yielded an area under the receiver operating characteristic curve (AUC) values of 0.986 (95% CI: 0.977-0.995), 0.902 (95%CI: 0.856-0.948), and 0.957 (95%CI: 0.924-0.990) in the training cohort and two external validation cohorts, respectively, which were significantly higher than that those of the clinical model (AUC: 0.524-0.588, P all < 0.05). The AUCs values of the SMTN within the anti-HER2 therapy subgroups were 0.833-0.972 in the two external validation cohorts. Moreover, 272 of 279 (97.5%) non-pCR patients (159 of 160 (99.4%), 53 of 54 (98.1%), and 60 of 65 (92.3%) in the training and two external validation cohorts, respectively) were successfully identified by the SMTN, suggesting that they could benefit from regime adjustment at the early-stage of NACT. Interpretation: The SMTN was able to predict pCR in the early-stage of NACT for HER2-positive breast cancer patients, which could guide clinicians in adjusting treatment regimes. Funding: Key-Area Research and Development Program of Guangdong Province (No.2021B0101420006); National Natural Science Foundation of China (No.82071892, 82171920); Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application (No.2022B1212010011); the National Science Foundation for Young Scientists of China (No.82102019, 82001986); Project Funded by China Postdoctoral Science Foundation (No.2020M682643); the Outstanding Youth Science Foundation of Yunnan Basic Research Project (202101AW070001); Scientific research fund project of Department of Education of Yunnan Province(2022J0249). Science and technology Projects in Guangzhou (202201020001;202201010513); High-level Hospital Construction Project (DFJH201805, DFJHBF202105).

Deep learning predicts resistance to neoadjuvant chemotherapy for locally advanced gastric cancer: a multicenter study.

BACKGROUND: Accurate pre-treatment prediction of neoadjuvant chemotherapy (NACT) resistance in patients with locally advanced gastric cancer (LAGC) is essential for timely surgeries and optimized treatments. We aim to evaluate the effectiveness of deep learning (DL) on computed tomography (CT) images in predicting NACT resistance in LAGC patients. METHODS: A total of 633 LAGC patients receiving NACT from three hospitals were included in this retrospective study. The training and internal validation cohorts were randomly selected from center 1, comprising 242 and 104 patients, respectively. The external validation cohort 1 comprised 128 patients from center 2, and the external validation cohort 2 comprised 159 patients from center 3. First, a DL model was developed using ResNet-50 to predict NACT resistance in LAGC patients, and the gradient-weighted class activation mapping (Grad-CAM) was assessed for visualization. Then, an integrated model was constructed by combing the DL signature and clinical characteristics. Finally, the performance was tested in internal and external validation cohorts using area under the receiver operating characteristic (ROC) curves (AUC). RESULTS: The DL model achieved AUCs of 0.808 (95% CI 0.724-0.893), 0.755 (95% CI 0.660-0.850), and 0.752 (95% CI 0.678-0.825) in validation cohorts, respectively, which were higher than those of the clinical model. Furthermore, the integrated model performed significantly better than the clinical model (P < 0.05). CONCLUSIONS: A CT-based model using DL showed promising performance for predicting NACT resistance in LAGC patients, which could provide valuable information in terms of individualized treatment.

CT-based radiomics analysis in the prediction of response to neoadjuvant chemotherapy in locally advanced gastric cancer: A dual-center study.

BACKGROUND: To investigate the ability of the CT-based radiomics models for pretreatment prediction of the response to neoadjuvant chemotherapy (NAC) in patients with locally advanced gastric cancer (LAGC). METHODS: This retrospective analysis included 279 consecutive LAGC patients from center I (training cohort, n = 196; internal validation cohort, n = 83) who were examined by contrast-enhanced CT before treatment and 211 consecutive patients from center II who were recruited as an external validation cohort. A total of 102 features were extracted from the portal venous phase CT images, and feature selection was further subjected to three-step procedures. Next, five classifications, including Logistic Regression (LR), Naive Bayes, Random forest (RF), Support Vector Machine (SVM), and Extreme Gradient Boosting (XGB) algorithms, were applied to construct radiomics models for predicting the good-responder (GR) to NAC in the training cohort. The prediction performances were evaluated using ROC and decision curve analysis (DCA). RESULTS: No statistically significant difference was detected for all clinicopathological characteristics. Additionally, allsix key features were significantly different between GR and poor-responder (PR). Compared to models from other classifiers, the model obtained with XGB showed promising prediction performance with the highest AUC of 0.790(95%CI: 0.700-0.880) in the training cohort. The corresponding AUCs were 0.784(95%CI, 0.659-0.908) and 0.803(95%CI, 0.717-0.888) in the internal and external validation cohorts, respectively. DCA confirmed the clinical utility. CONCLUSIONS: The proposed pretreatment CT-based radiomics models revealed good performances in predicting response to NAC and thus may be used to improve clinical treatment in LAGC patients.

Characteristics of Sunburn Browning Fruit and Rootstock-Dependent Damage-Free Yield of Ambrosia™ Apple after Sustained Summer Heat Events.

The 2021 summer heat waves experienced in the Pacific Northwest led to considerable fruit damage in many apple production zones. Sunburn browning (SB) was a particularly evident symptom. To understand the mechanism underlying the damage and to facilitate the early assessment of compromised fruit quality, we conducted a study on external characteristics and internal quality attributes of SB 'Ambrosia' apple (Malus domestica var. Ambrosia) and evaluated the fruit loss on five rootstocks. The cell integrity of the epidermal and hypodermal layers of fruit skins in the SB patch was compromised. Specifically, the number of chloroplasts and anthocyanin decreased in damaged cells, while autofluorescent stress-related compounds accumulated in dead cells. Consequently, the affected sun-exposed skin demonstrated a significant increase in differential absorbance between 670 nm and 720 nm, measured using a handheld apple DA meter, highlighting the potential of using this method as a non-destructive early indicator for sunburn damage. Sunburn browning eventually led to lower fruit weight, an increase in average dry matter content, soluble solids content, acidity, deteriorated weight retention, quicker loss of firmness, and accelerated ethylene emission during ripening. Significant inconsistency was found between the sun-exposed and shaded sides in SB apples regarding dry matter content, firmness, and tissue water potential, which implied preharvest water deficit in damaged tissues and the risk of quicker decline of postharvest quality. Geneva 935 (G.935), a large-dwarfing rootstock with more vigor and higher water transport capacity, led to a lower ratio of heat-damaged fruits and a higher yield of disorder-free fruits, suggesting rootstock selection as a long-term horticultural measure to mitigate summer heat stress.