FedDUS: Lung tumor segmentation on CT images through federated semi-supervised with dynamic update strategy.

BACKGROUND AND OBJECTIVE: Lung tumor annotation is a key upstream task for further diagnosis and prognosis. Although deep learning techniques have promoted automation of lung tumor segmentation, there remain challenges impeding its application in clinical practice, such as a lack of prior annotation for model training and data-sharing among centers. METHODS: In this paper, we use data from six centers to design a novel federated semi-supervised learning (FSSL) framework with dynamic model aggregation and improve segmentation performance for lung tumors. To be specific, we propose a dynamically updated algorithm to deal with model parameter aggregation in FSSL, which takes advantage of both the quality and quantity of client data. Moreover, to increase the accessibility of data in the federated learning (FL) network, we explore the FAIR data principle while the previous federated methods never involve. RESULT: The experimental results show that the segmentation performance of our model in six centers is 0.9348, 0.8436, 0.8328, 0.7776, 0.8870 and 0.8460 respectively, which is superior to traditional deep learning methods and recent federated semi-supervised learning methods. CONCLUSION: The experimental results demonstrate that our method is superior to the existing FSSL methods. In addition, our proposed dynamic update strategy effectively utilizes the quality and quantity information of client data and shows efficiency in lung tumor segmentation. The source code is released on (https://github.com/GDPHMediaLab/FedDUS).

A novel stratification scheme combined with internal arteries in CT imaging for guiding postoperative adjuvant transarterial chemoembolization in hepatocellular carcinoma: a retrospective cohort study.

BACKGROUND: Although postoperative adjuvant transarterial chemoembolization (PA-TACE) improves survival outcomes in a subset of patients with resected hepatocellular carcinoma (HCC), the lack of reliable biomarkers for patient selection remains a significant challenge. The present study aimed to evaluate whether computed tomography imaging can provide more value for predicting benefits from PA-TACE and to establish a new scheme for guiding PA-TACE benefits. METHODS: In this retrospective study, patients with HCC who had undergone preoperative contrast-enhanced computed tomography and curative hepatectomy were evaluated. Inverse probability of treatment weight was performed to balance the difference of baseline characteristics. Cox models were used to test the interaction among PA-TACE, imaging features, and pathological indicators. An HCC imaging and pathological classification (HIPC) scheme incorporating these imaging and pathological indicators was established. RESULTS: This study included 1488 patients [median age, 52 years (IQR, 45-61 years); 1309 male]. Microvascular invasion (MVI) positive, and diameter >5 cm tumors achieved a higher recurrence-free survival (RFS), and overall survival (OS) benefit, respectively, from PA-TACE than MVI negative, and diameter ≤5 cm tumors. Patients with internal arteries (IA) positive benefited more than those with IA-negative in terms of RFS ( P =0.016) and OS ( P =0.018). PA-TACE achieved significant RFS and OS improvements in HIPC3 (IA present and diameter >5 cm, or two or three tumors) patients but not in HIPC1 (diameter ≤5 cm, MVI negative) and HIPC2 (other single tumor) patients. Our scheme may decrease the number of patients receiving PA-TACE by ~36.5% compared to the previous suggestion. CONCLUSIONS: IA can provide more value for predicting the benefit of PA-TACE treatment. The proposed HIPC scheme can be used to stratify patients with and without survival benefits from PA-TACE.

Development of a machine learning-based radiomics signature for estimating breast cancer TME phenotypes and predicting anti-PD-1/PD-L1 immunotherapy response.

BACKGROUNDS: Since breast cancer patients respond diversely to immunotherapy, there is an urgent need to explore novel biomarkers to precisely predict clinical responses and enhance therapeutic efficacy. The purpose of our present research was to construct and independently validate a biomarker of tumor microenvironment (TME) phenotypes via a machine learning-based radiomics way. The interrelationship between the biomarker, TME phenotypes and recipients' clinical response was also revealed. METHODS: In this retrospective multi-cohort investigation, five separate cohorts of breast cancer patients were recruited to measure breast cancer TME phenotypes via a radiomics signature, which was constructed and validated by integrating RNA-seq data with DCE-MRI images for predicting immunotherapy response. Initially, we constructed TME phenotypes using RNA-seq of 1089 breast cancer patients in the TCGA database. Then, parallel DCE-MRI images and RNA-seq of 94 breast cancer patients obtained from TCIA were applied to develop a radiomics-based TME phenotypes signature using random forest in machine learning. The repeatability of the radiomics signature was then validated in an internal validation set. Two additional independent external validation sets were analyzed to reassess this signature. The Immune phenotype cohort (n = 158) was divided based on CD8 cell infiltration into immune-inflamed and immune-desert phenotypes; these data were utilized to examine the relationship between the immune phenotypes and this signature. Finally, we utilized an Immunotherapy-treated cohort with 77 cases who received anti-PD-1/PD-L1 treatment to evaluate the predictive efficiency of this signature in terms of clinical outcomes. RESULTS: The TME phenotypes of breast cancer were separated into two heterogeneous clusters: Cluster A, an "immune-inflamed" cluster, containing substantial innate and adaptive immune cell infiltration, and Cluster B, an "immune-desert" cluster, with modest TME cell infiltration. We constructed a radiomics signature for the TME phenotypes ([AUC] = 0.855; 95% CI 0.777-0.932; p < 0.05) and verified it in an internal validation set (0.844; 0.606-1; p < 0.05). In the known immune phenotypes cohort, the signature can identify either immune-inflamed or immune-desert tumor (0.814; 0.717-0.911; p < 0.05). In the Immunotherapy-treated cohort, patients with objective response had higher baseline radiomics scores than those with stable or progressing disease (p < 0.05); moreover, the radiomics signature achieved an AUC of 0.784 (0.643-0.926; p < 0.05) for predicting immunotherapy response. CONCLUSIONS: Our imaging biomarker, a practicable radiomics signature, is beneficial for predicting the TME phenotypes and clinical response in anti-PD-1/PD-L1-treated breast cancer patients. It is particularly effective in identifying the "immune-desert" phenotype and may aid in its transformation into an "immune-inflamed" phenotype.

Sonographic and clinicopathologic features of metaplastic breast carcinoma and infiltrating ductal carcinoma: a comparative single-center cohort study.

Background: The rarity of metaplastic breast carcinoma (MBC) has resulted in limited sonographic data. Given the inferior prognosis of MBC compared to invasive ductal carcinoma (IDC), accurate preoperative differentiation between the two is imperative for effective treatment planning and prognostic prediction. The objective of this study was to assess the diagnostic accuracy of MBC and differentiate it from IDC by analyzing sonographic and clinicopathologic features. Methods: In this retrospective cohort study, 197 women comprising 200 IDC lesions were enrolled between January 2012 and December 2021 and 20 women comprising 20 pure MBC lesions were enrolled between January 2019 and December 2019. A comparison was made between the sonographic and clinicopathologic characteristics of MBC and IDC. Results: The results indicated that patients with MBC had a higher proportion of tumor grade 3 (95.0% vs. 32.5%; P<0.001), high Ki-67 expression (100.0% vs. 75.0%; P<0.001), and the triple-negative subtype (90.0% vs. 13.0%; P<0.001) as compared to those with IDC. On ultrasound (US) findings, MBC lesions tended to have a larger size (≥5 cm: 45.0% vs. 1.5%; P<0.001), regular shape (45.0% vs. 1.5%, P<0.001), circumscribed margin (40.0% vs. 0.5%, P<0.001), a complex cystic and solid echo pattern (50.0% vs. 3.5%; P<0.001), and posterior acoustic enhancement (95.0% vs. 14.5%; P<0.001). Additionally, MBC was more likely to be misinterpreted as a benign lesion by sonographers than was IDC (30.0% vs. 4.5%; P<0.001). Multilayer perceptron analysis revealed posterior acoustic enhancement, circumscribed margins, and size as distinguishing factors between these two tumor types. The estimated rates of local recurrence, distant metastasis, and 5-year overall survival in 19 cases with MBC were found to be 10.5%, 31.6%, and 65.0%, respectively. Conclusions: MBC typically presents as a large breast mass with more benign US features in older women, findings which may facilitate its accurate diagnosis and differentiation from other breast masses.

SwinHR: Hemodynamic-powered hierarchical vision transformer for breast tumor segmentation.

Accurate and automated segmentation of breast tumors in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) plays a critical role in computer-aided diagnosis and treatment of breast cancer. However, this task is challenging, due to random variation in tumor sizes, shapes, appearances, and blurred boundaries of tumors caused by inherent heterogeneity of breast cancer. Moreover, the presence of ill-posed artifacts in DCE-MRI further complicate the process of tumor region annotation. To address the challenges above, we propose a scheme (named SwinHR) integrating prior DCE-MRI knowledge and temporal-spatial information of breast tumors. The prior DCE-MRI knowledge refers to hemodynamic information extracted from multiple DCE-MRI phases, which can provide pharmacokinetics information to describe metabolic changes of the tumor cells over the scanning time. The Swin Transformer with hierarchical re-parameterization large kernel architecture (H-RLK) can capture long-range dependencies within DCE-MRI while maintaining computational efficiency by a shifted window-based self-attention mechanism. The use of H-RLK can extract high-level features with a wider receptive field, which can make the model capture contextual information at different levels of abstraction. Extensive experiments are conducted in large-scale datasets to validate the effectiveness of our proposed SwinHR scheme, demonstrating its superiority over recent state-of-the-art segmentation methods. Also, a subgroup analysis split by MRI scanners, field strength, and tumor size is conducted to verify its generalization. The source code is released on (https://github.com/GDPHMediaLab/SwinHR).

Decoding tumor stage by peritumoral and intratumoral radiomics in resectable esophageal squamous cell carcinoma.

PURPOSE: To evaluate the potential application of radiomics in predicting Tumor-Node-Metastasis (TNM) stage in patients with resectable esophageal squamous cell carcinoma (ESCC). METHODS: This retrospective study included 122 consecutive patients (mean age, 57 years; 27 women). Corresponding tumor of interest was identified on axial arterial-phase CT images with manual annotation. Radiomics features were extracted from intra- and peritumoral regions. Features were pruned to train LASSO regression model with 93 patients to construct a radiomics signature, whose performance was validated in a test set of 29 patients. Prognostic value of radiomics-predicted TNM stage was estimated by survival analysis in the entire cohort. RESULTS: The radiomics signature incorporating one intratumoral and four peritumoral features was significantly associated with TNM stage. This signature discriminated tumor stage with an area under curve (AUC) of 0.823 in the training set, with similar performance in the test set (AUC 0.813). Recurrence-free survival (RFS) was significantly different between different radiomics-predicted TNM stage groups (Low-risk vs high-risk, log-rank P = 0.004). Univariate and multivariate Cox regression analyses revealed that radiomics-predicted TNM stage was an independent preoperative factor for RFS. CONCLUSIONS: The proposed radiomics signature combing intratumoral and peritumoral features was predictive of TNM stage and associated with prognostication in ESCC.

In vivo visualization of tumor-associated macrophages re-education by photoacoustic/fluorescence dual-modal imaging with a metal-organic frames-based caspase-1 nanoreporter.

Tumor-associated macrophages (TAMs) are vital in the tumor microenvironment, contributing to immunosuppression and therapy tolerance. Despite their importance, the precise re-education of TAMs in vivo continues to present a formidable challenge. Moreover, the lack of real-time and efficient methods to comprehend the spatiotemporal kinetics of TAMs repolarization remains a significant hurdle, severely hampering the accurate assessment of treatment efficacy and prognosis. Herein, we designed a metal-organic frameworks (MOFs) based Caspase-1 nanoreporter (MCNR) that can deliver a TLR7/8 agonist to the TAMs and track time-sensitive Caspase-1 activity as a direct method to monitor the initiation of immune reprogramming. This nanosystem exhibits excellent TAMs targeting ability, enhanced tumor accumulation, and stimuli-responsive behavior. By inducing the reprogramming of TAMs, they were able to enhance T-cell infiltration in tumor tissue, resulting in inhibited tumor growth and improved survival in mice model. Moreover, MCNR also serves as an activatable photoacoustic and fluorescent dual-mode imaging agent through Caspase-1-mediated specific enzyme digestion. This feature enables non-invasive and real-time antitumor immune activation monitoring. Overall, our findings indicate that MCNR has the potential to be a valuable tool for tumor immune microenvironment remodeling and noninvasive quantitative detection and real-time monitoring of TAMs repolarization to immunotherapy in the early stage.

Multimodal Imaging Features and Prognosis of Metaplastic Breast Carcinoma.

RATIONALE AND OBJECTIVES: Metaplastic breast carcinoma (MBC) is an infrequent malignancy with an unfavorable prognosis, and there is a paucity of research on the multimodal imaging features of MBC. This study aimed to provide a comprehensive analysis of the multimodal imaging features, clinicopathological characteristics, and prognosis of MBC. MATERIALS AND METHODS: A total of 36 patients with histologically confirmed MBC from 2012 to 2021 were included in the study. We analyzed the pre-treatment multimodal imaging features, including mammography, ultrasonography (US), and magnetic resonance imaging (MRI), as well as clinicopathology and prognosis of MBC. Follow-up data included local recurrence, distant metastasis, and overall survival (OS) rate. RESULTS: MBC patients had a median age of 51 years at diagnosis. The most common histologic subtype was squamous cell carcinoma, with 86.1% of MBC being histological grade 3 and triple negative. The most common mammographic findings were irregular shape, non-calcification, and high density. The predominant US findings included irregular shape, parallel orientation, posterior acoustic enhancement, and hypoecho. On MRI, most masses exhibited irregular shape, spiculate margin, heterogeneous enhancement, Type II time intensity curve, and diffusion restriction on diffusion weighted images determined by apparent diffusion coefficient. According to breast imaging reporting and data system, mammography suggested malignancy in 50% of cases, US indicated a moderate to high suspicion of malignancy in 77.8% of cases, MRI revealed malignancy in all cases. At a median follow-up time of 48 months (range, 8-122 months) for 35 MBC patients, the local recurrence, distant metastasis, and OS rates were 11.4%, 28.6%, and 67.4%, respectively. CONCLUSION: The benign features of MBC on mammography and US may cause misinterpretation. However, the inclusion of malignant features observed on MRI can improve diagnostic accuracy.

Using the non-distortion IVIM to reduce the need for contrast agents in nasopharyngeal MRI.

BACKGROUND: Patients with nasopharyngeal carcinoma (NPC) who undergo longitudinal follow-up contrast-enhanced MRI are at risk of developing gadolinium deposition in their neural tissue, which may potentially harm them. Therefore, for these patients, a non-contrast-enhanced method is potentially beneficial as an alternative approach to predict enhancement in T1-weighted imaging (CE-T1WI). The traditional intravoxel incoherent motion (IVIM) is one of the non-contrast-enhanced methods; however, the severe distortion and signal loss limit its application in patients with NPC. The present study aimed to investigate whether non-distortion IVIM could reduce the need of CE-T1WI in the follow-up of patients with NPC. METHODS: The patients with NPC underwent Turbo Spin-echo MVXD diffusion-weighted imaging-based IVIM (non-distortion IVIM) from November 2021 to May 2022. Firstly, thirty patients with NPC were underwent both non-distortion IVIM and traditional IVIM. The distortion rate (DR) of the non-distortion IVIM was compared with the traditional IVIM. Then, twenty-one NPC patients with tumors (areas >50mm2) were included and correlation coefficient analysis was used to assess the relationship between their non-distortion IVIM and CE-T1WI. Linear regression analysis was performed to determine whether non-distortion IVIM predictors could predict CE-T1WI. RESULTS: The correlation was observed between the parameter f of the non-distortion IVIM and the enhancement ratio of CE-T1WI (r = 0.543, P = 0.011). Moreover, the linear regression analysis revealed that f was an independent IVIM predictor of CE-T1WI in patients with NPC (P = 0.011). The DR of the non-distortion IVIM was significantly smaller than that of the traditional IVIM (0.12 ± 0.05 vs 0.48 ± 0.16, P < 0.001). CONCLUSIONS: In patients with NPC, non-distortion IVIM showed potential clinical benefits to reduce the need for contrast agents, and it can independently predict the enhancement ratio.

Guidelines for the Diagnosis and Treatment of Primary Liver Cancer (2022 Edition).

Background: Primary liver cancer, of which around 75-85% is hepatocellular carcinoma in China, is the fourth most common malignancy and the second leading cause of tumor-related death, thereby posing a significant threat to the life and health of the Chinese people. Summary: Since the publication of Guidelines for Diagnosis and Treatment of Primary Liver Cancer in China in June 2017, which were updated by the National Health Commission in December 2019, additional high-quality evidence has emerged from researchers worldwide regarding the diagnosis, staging, and treatment of liver cancer, that requires the guidelines to be updated again. The new edition (2022 Edition) was written by more than 100 experts in the field of liver cancer in China, which not only reflects the real-world situation in China but also may reshape the nationwide diagnosis and treatment of liver cancer. Key Messages: The new guideline aims to encourage the implementation of evidence-based practice and improve the national average 5-year survival rate for patients with liver cancer, as proposed in the "Health China 2030 Blueprint."

Value of mammographic microcalcifications and MRI-enhanced lesions in the evaluation of residual disease after neoadjuvant therapy for breast cancer.

Background: Microcalcifications persist even if a patient with breast cancer achieves pathologic complete response (pCR) as confirmed by surgery after neoadjuvant treatment (NAT). In practice, surgeons tend to remove all the microcalcifications. This study aimed to explore the correlation between changes in the extent of microcalcification after NAT and pathological tumor response and compare the accuracy of mammography (MG) and magnetic resonance imaging (MRI) in predicting the size of residual tumors. Methods: This was a retrospective study which included a consecutive series of patients in Guangdong Provincial People's Hospital. Between January 2010 and January 2020, 127 patients with breast cancer and Breast Imaging Reporting and Data System (BI-RADS) 4-5 microcalcifications were included in this study. The maximum diameter of the microcalcifications on MG and lesion enhancement on MRI pre- and post-NAT were measured. The correlations between the changes in residual microcalcifications on MG and pCR were analyzed. Intraclass correlation coefficients (ICCs) were computed between the extent of the residual microcalcifications, residual enhancement, and residual tumor size. Results: There were no statistically significant differences in the changes in microcalcifications after NAT according to the RECIST criteria on MRI (P=0.09) and Miller-Payne grade (P=0.14). MRI showed a higher agreement than did residual microcalcifications on MG in predicting residual tumor size (ICC: 0.771 vs. 0.097). Conclusions: MRI is more accurate for evaluating residual tumor size in breast cancer. In our study, the extent of microcalcifications on MG after NAT had nearly no correlation with the pathological size of the residual tumor. Therefore, residual tumors with microcalcifications may not necessarily be a contraindication to breast-conserving surgery.

MRI-based Quantification of Intratumoral Heterogeneity for Predicting Treatment Response to Neoadjuvant Chemotherapy in Breast Cancer.

Background Breast cancer is highly heterogeneous, resulting in different treatment responses to neoadjuvant chemotherapy (NAC) among patients. A noninvasive quantitative measure of intratumoral heterogeneity (ITH) may be valuable for predicting treatment response. Purpose To develop a quantitative measure of ITH on pretreatment MRI scans and test its performance for predicting pathologic complete response (pCR) after NAC in patients with breast cancer. Materials and Methods Pretreatment MRI scans were retrospectively acquired in patients with breast cancer who received NAC followed by surgery at multiple centers from January 2000 to September 2020. Conventional radiomics (hereafter, C-radiomics) and intratumoral ecological diversity features were extracted from the MRI scans, and output probabilities of imaging-based decision tree models were used to generate a C-radiomics score and ITH index. Multivariable logistic regression analysis was used to identify variables associated with pCR, and significant variables, including clinicopathologic variables, C-radiomics score, and ITH index, were combined into a predictive model for which performance was assessed using the area under the receiver operating characteristic curve (AUC). Results The training data set was comprised of 335 patients (median age, 48 years [IQR, 42-54 years]) from centers A and B, and 590, 280, and 384 patients (median age, 48 years [IQR, 41-55 years]) were included in the three external test data sets. Molecular subtype (odds ratio [OR] range, 4.76-8.39 [95% CI: 1.79, 24.21]; all P < .01), ITH index (OR, 30.05 [95% CI: 8.43, 122.64]; P < .001), and C-radiomics score (OR, 29.90 [95% CI: 12.04, 81.70]; P < .001) were independently associated with the odds of achieving pCR. The combined model showed good performance for predicting pCR to NAC in the training data set (AUC, 0.90) and external test data sets (AUC range, 0.83-0.87). Conclusion A model that combined an index created from pretreatment MRI-based imaging features quantitating ITH, C-radiomics score, and clinicopathologic variables showed good performance for predicting pCR to NAC in patients with breast cancer. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Rauch in this issue.

SMILE: Cost-sensitive multi-task learning for nuclear segmentation and classification with imbalanced annotations.

High throughput nuclear segmentation and classification of whole slide images (WSIs) is crucial to biological analysis, clinical diagnosis and precision medicine. With the advances of CNN algorithms and the continuously growing datasets, considerable progress has been made in nuclear segmentation and classification. However, few works consider how to reasonably deal with nuclear heterogeneity in the following two aspects: imbalanced data distribution and diversified morphology characteristics. The minority classes might be dominated by the majority classes due to the imbalanced data distribution and the diversified morphology characteristics may lead to fragile segmentation results. In this study, a cost-Sensitive MultI-task LEarning (SMILE) framework is conducted to tackle the data heterogeneity problem. Based on the most popular multi-task learning backbone in nuclei segmentation and classification, we propose a multi-task correlation attention (MTCA) to perform feature interaction of multiple high relevant tasks to learn better feature representation. A cost-sensitive learning strategy is proposed to solve the imbalanced data distribution by increasing the penalization for the error classification of the minority classes. Furthermore, we propose a novel post-processing step based on the coarse-to-fine marker-controlled watershed scheme to alleviate fragile segmentation when nuclei are with large size and unclear contour. Extensive experiments show that the proposed method achieves state-of-the-art performances on CoNSeP and MoNuSAC 2020 datasets. The code is available at: https://github.com/panxipeng/nuclear_segandcls.

Homogeneous-resolution photoacoustic microscopy for ultrawide field-of-view neurovascular imaging in Alzheimer's disease.

Neurovascular imaging is essential for investigating neurodegenerative diseases. However, the existing neurovascular imaging technology suffers from a trade-off between a field of view (FOV) and resolution in the whole brain, resulting in an inhomogeneous resolution and lack of information. Here, homogeneous-resolution arched-scanning photoacoustic microscopy (AS-PAM), which has an ultrawide FOV to cover the entire mouse cerebral cortex, was developed. Imaging of the neurovasculature was performed with a homogenous resolution of 6.9 µm from the superior sagittal sinus to the middle cerebral artery and caudal rhinal vein in an FOV of 12 × 12 mm2. Moreover, using AS-PAM, vascular features of the meninges and cortex were quantified in early Alzheimer's disease (AD) and wild-type (WT) mice. The results demonstrated high sensitivity to the pathological progression of AD on tortuosity and branch index. The high-fidelity imaging capability in large FOV enables AS-PAM to be a promising tool for precise brain neurovascular visualization and quantification.

Artificial intelligence-assisted analysis for tumor-immune interaction within the invasive margin of colorectal cancer.

BACKGROUND: In colorectal cancer (CRC), both tumor invasion and immunological analysis at the tumor invasive margin (IM) are significantly associated with patient prognosis, but have traditionally been reported independently. We propose a new scoring system, the TGP-I score, to assess the association and interactions between tumor growth pattern (TGP) and tumor infiltrating lymphocytes at the IM and to predict its prognostic validity for CRC patient stratification. MATERIALS AND METHODS: The types of TGP were assessed in hematoxylin and eosin-stained whole-slide images. The CD3+ T-cells density at the IM was automatically quantified on immunohistochemical-stained slides using a deep learning method. A discovery (N = 347) and a validation (N = 132) cohorts were used to evaluate the prognostic value of the TGP-I score for overall survival. RESULTS: The TGP-I score3 (trichotomy) was an independent prognostic factor, with higher TGP-I score3 associated with worse prognosis in the discovery (unadjusted hazard ratio [HR] for high vs. low 3.62, 95% confidence interval [CI] 2.22-5.90; p < 0.001) and validation cohort (unadjusted HR for high vs. low 5.79, 95% CI 1.84-18.20; p = 0.003). The relative contribution of each parameter to predicting survival was analyzed. The TGP-I score3 had similar importance compared to tumor-node-metastasis staging (31.2% vs. 32.9%) and was stronger than other clinical parameters. CONCLUSIONS: This automated workflow and the proposed TGP-I score could further provide accurate prognostic stratification and have potential value for supporting the clinical decision-making of stage I-III CRC patients.Key messagesA new scoring system, the TGP-I score, was proposed to assess the association and interactions of TGP and TILs at the tumor invasive margin.TGP-I score could be an independent predictor of prognosis for CRC patients, with higher scores being associated with worse survival.TGP-I score had similar importance compared to tumor-node-metastasis staging and was stronger than other clinical parameters.

Necrosis score as a prognostic factor in stage I-III colorectal cancer: a retrospective multicenter study.

BACKGROUND: Tumor necrosis results from failure to meet the requirement for rapid proliferation of tumor, related to unfavorable prognosis in colorectal cancer (CRC). However, previous studies used traditional microscopes to evaluate necrosis on slides, lacking a simultaneous phase and panoramic view for assessment. Therefore, we proposed a whole-slide images (WSIs)-based method to develop a necrosis score and validated its prognostic value in multicenter cohorts. METHODS: Necrosis score was defined as the proportion of necrosis in the tumor area, semi-quantitatively classified into 3-level score groups by the cut-off of 10% and 30% on HE-stained WSIs. 768 patients from two centers were enrolled in this study, divided into a discovery (N = 445) and a validation (N = 323) cohort. The prognostic value of necrosis score was evaluated by Kaplan-Meier curves and the Cox model. RESULT: Necrosis score was associated with overall survival, with hazard ratio for high vs. low in discovery and validation cohorts being 2.62 (95% confidence interval 1.59-4.32) and 2.51 (1.39-4.52), respectively. The 3-year disease free survival rates of necrosis-low, middle, and high were 83.6%, 80.2%, and 59.8% in discovery cohort, and 86.5%, 84.2%, and 66.5% in validation cohort. In necrosis middle plus high subgroup, there was a trend but no significant difference in overall survival between surgery alone and adjuvant chemotherapy group in stage II CRC (P = .075). CONCLUSION: As a stable prognostic factor, high-level necrosis evaluated by the proposed method on WSIs was associated with unfavorable outcomes. Additionally, adjuvant chemotherapy provide survival benefits for patients with high necrosis in stage II CRC.

Development and validation of a scoring system incorporating tumor growth pattern and perineural invasion for risk stratification in colorectal cancer.

Tumor growth pattern (TGP) and perineural invasion (PNI) at the invasive margin have been recognized as indicators of tumor invasiveness and prognostic events in colorectal cancer (CRC). This study aims to develop a scoring system incorporating TGP and PNI, and further investigate its prognostic significance for CRC risk stratification. A scoring system, termed tumor-invasion score, was established by summing TGP and PNI scores. The discovery cohort (N = 444) and the validation cohort (N = 339) were used to explore the prognostic significance of the tumor-invasion score. The endpoints of the event were disease-free survival (DFS) and overall survival (OS) which were analyzed by the Cox proportional hazard model. In the discovery cohort, Cox regression analysis showed that DFS and OS were inferior for score 4 group compared with score 1 group (DFS, hazard ratio (HR) 4.44, 95% confidence interval (CI) 2.49-7.92, p < 0.001; OS, 4.41, 2.37-8.19,p < 0.001). The validation cohort showed similar results (DFS, 4.73, 2.39-9.37, p < 0.001; OS, 5.52, 2.55-12.0, p < 0.001). The model combining tumor-invasion score and clinicopathologic information showed good discrimination performance than single predictors. TGP and PNI were associated with tumor invasiveness and survival in CRC. The tumor-invasion score generated by TGP and PNI scores served as an independent prognostic parameter of DFS and OS for CRC patients.

CKD-TransBTS: Clinical Knowledge-Driven Hybrid Transformer With Modality-Correlated Cross-Attention for Brain Tumor Segmentation.

Brain tumor segmentation (BTS) in magnetic resonance image (MRI) is crucial for brain tumor diagnosis, cancer management and research purposes. With the great success of the ten-year BraTS challenges as well as the advances of CNN and Transformer algorithms, a lot of outstanding BTS models have been proposed to tackle the difficulties of BTS in different technical aspects. However, existing studies hardly consider how to fuse the multi-modality images in a reasonable manner. In this paper, we leverage the clinical knowledge of how radiologists diagnose brain tumors from multiple MRI modalities and propose a clinical knowledge-driven brain tumor segmentation model, called CKD-TransBTS. Instead of directly concatenating all the modalities, we re-organize the input modalities by separating them into two groups according to the imaging principle of MRI. A dual-branch hybrid encoder with the proposed modality-correlated cross-attention block (MCCA) is designed to extract the multi-modality image features. The proposed model inherits the strengths from both Transformer and CNN with the local feature representation ability for precise lesion boundaries and long-range feature extraction for 3D volumetric images. To bridge the gap between Transformer and CNN features, we propose a Trans&CNN Feature Calibration block (TCFC) in the decoder. We compare the proposed model with six CNN-based models and six transformer-based models on the BraTS 2021 challenge dataset. Extensive experiments demonstrate that the proposed model achieves state-of-the-art brain tumor segmentation performance compared with all the competitors.

HoVer-Trans: Anatomy-Aware HoVer-Transformer for ROI-Free Breast Cancer Diagnosis in Ultrasound Images.

Ultrasonography is an important routine examination for breast cancer diagnosis, due to its non-invasive, radiation-free and low-cost properties. However, the diagnostic accuracy of breast cancer is still limited due to its inherent limitations. Then, a precise diagnose using breast ultrasound (BUS) image would be significant useful. Many learning-based computer-aided diagnostic methods have been proposed to achieve breast cancer diagnosis/lesion classification. However, most of them require a pre-define region of interest (ROI) and then classify the lesion inside the ROI. Conventional classification backbones, such as VGG16 and ResNet50, can achieve promising classification results with no ROI requirement. But these models lack interpretability, thus restricting their use in clinical practice. In this study, we propose a novel ROI-free model for breast cancer diagnosis in ultrasound images with interpretable feature representations. We leverage the anatomical prior knowledge that malignant and benign tumors have different spatial relationships between different tissue layers, and propose a HoVer-Transformer to formulate this prior knowledge. The proposed HoVer-Trans block extracts the inter- and intra-layer spatial information horizontally and vertically. We conduct and release an open dataset GDPH&SYSUCC for breast cancer diagnosis in BUS. The proposed model is evaluated in three datasets by comparing with four CNN-based models and three vision transformer models via five-fold cross validation. It achieves state-of-the-art classification performance (GDPH&SYSUCC AUC: 0.924, ACC: 0.893, Spec: 0.836, Sens: 0.926) with the best model interpretability. In the meanwhile, our proposed model outperforms two senior sonographers on the breast cancer diagnosis when only one BUS image is given (GDPH&SYSUCC-AUC ours: 0.924 vs. reader1: 0.825 vs. reader2: 0.820).