Pathological Invasion Research Articles

Clinical, pathological, and computed tomography morphological features of lung cancer with spread through air spaces.

Spread through air spaces (STAS) is significantly associated with decreased overall survival (OS) and reduced recurrence-free survival. However, there are no reliable methods to confirm the presence of STAS before surgery. The sensitivity and specificity of the intraoperative frozen section diagnosis of STAS are not satisfactory. This study sought to determine the clinical, pathological, and computed tomography (CT) features of lung cancer with STAS before surgery to guide treatment decisions. The data of 121 patients who were positive for STAS and 121 who were negative for STAS as confirmed by surgery and pathology were collected at Jiangsu Cancer Hospital from January 2020 to December 2022. The differences between the two groups in terms of the clinical, pathological, and CT characteristics were compared. STAS occurred not only in lung adenocarcinoma (LUAD) (106 of 121, 87.6%), but also in other pathological types of lung cancer (15 of 121, 12.4%). STAS was significantly correlated with pathological invasiveness [pathological differentiation, tumor, node, metastasis (TNM) staging, vascular invasion, and pleural invasion; all P<0.05]. STAS was most common in solid tumors (95 of 121, 78.51%). The receiver operating characteristic (ROC) curve showed that the optimal cut-off value for diagnosing STAS based on diameter is 1.55 cm with a sensitivity of 73.3% and a specificity of 47.9%. The percentage of solid components (PSC) is an independent influencing factor of lung cancer with STAS [odds ratio (OR) =111.27; P<0.05] with an optimal cut-off value of 63%, a sensitivity of 92.5%, and a specificity of 72.7%. In the part-solid nodules, the occurrence rate of STAS increased as the PSC increased. STAS was only observed in part-solid nodules with a PSC greater than 25%. Among the CT morphological features, lobulation was an independent influencing factor of lung cancer with STAS (OR =3.513; P<0.05), and persistent indistinct margin ground-glass opacity around the primary lesion of lung cancer (21 of 121, 17.36%) and satellite foci (9 of 121, 7.44%) strongly indicated the existence of STAS. The clinical, pathological and CT features of STAS may guide clinicians to develop appropriate strategies and improve the survival rate of patients.

P37-1 A diagnostic nomogram for pathological invasiveness in early LUAD: integration of autoantibody and radiomics features

P37-1 A diagnostic nomogram for pathological invasiveness in early LUAD: integration of autoantibody and radiomics features

Adaptively learning visual model of surgical resection images via coarse-to-fine–grained strategy for pathological invasiveness prediction in indeterminate stage IA lung adenocarcinoma.

1563 Background: Indeterminate nodules with high risk of malignancy are suggested to receive video-assisted thoracoscopy biopsy. Frozen section assists surgeons to decide surgical strategies for stage IA lung adenocarcinoma (LUAD) intraoperatively, which is time-consuming and may misdiagnosis due to limited sampling and poor tissue quality. Methods: We prospectively enrolled stage IA LUAD patients underwent complete resection between June 2020 and September 2023 in Guangdong Provincial People's Hospital (GDPH), Affiliated Hospital of Guangdong Medical University, Meizhou People's Hospital. All the resected lung nodules were finally diagnosed as pre-invasive lesion (PIL), minimally invasive adenocarcinoma (MIA) or invasive lung adenocarcinoma (IAC) by FFPE pathological diagnosis. Images of the whole section of the lung nodules were taken by smartphones under natural lighting condition in operating theaters without shadowless surgical lights. Patients received preoperative anti-cancer therapy and with low-quality tumor section images were excluded. Images of nodules section, FS reports, FFPE diagnosis and clinical information were prospectively collected. Predictive artificial intelligence (AI) model was developed by a three-step process, which first predict the IAC and non-IAC region at coarse level, and identify fine level features through the high-risk region. The coarse and fine labels were then coordinated through risk ranking loss to reach a final predictive result. Results: We prospectively enrolled 1516 patients with 1638 indetermined lung nodules from preoperative chest CT following the inclusion and exclusion criteria, with 2438 images acquired from intraoperative nodule sections. The included patients have median age of 57 years old and 38.6% male patients. The pathological diagnosis for included lung nodules are 122 PIL nodules, 502 MIA nodules and 1014 stage IA LUAD. A multi-task artificial intelligence based on Coarse-to-Fine-Grained Strategy has been established to classify the indetermined lung nodules during the surgery. For binary classification, AI model reach an AUC of 0.86 in differentiation between IAC or non-IAC. For 3-classification level, AI model reach an AUC of 0.87 in differentiation between PIL, MIA or IAC. We further defined the IAC nodules into G1, G2 and G3 according to IASLC lung adenocarcinoma grading system. For 5-classification level, AI model reach an AUC of 0.86 in differentiation between PIL, MIA, IAC-G1, IAC-G2 and IAC-G3. Conclusions: Our AI models based on images of intraoperative surgical resection could effectively classify indetermined lung nodules, which can assist thoracic surgeons diagnose the nodules rapidly during the surging and decide the following surgical strategies. Clinical trial information: ChiCTR2300075999 .

GMILT: A Novel Transformer Network That Can Noninvasively Predict EGFR Mutation Status.

Noninvasively and accurately predicting the epidermal growth factor receptor (EGFR) mutation status is a clinically vital problem. Moreover, further identifying the most suspicious area related to the EGFR mutation status can guide the biopsy to avoid false negatives. Deep learning methods based on computed tomography (CT) images may improve the noninvasive prediction of EGFR mutation status and potentially help clinicians guide biopsies by visual methods. Inspired by the potential inherent links between EGFR mutation status and invasiveness information, we hypothesized that the predictive performance of a deep learning network can be improved through extra utilization of the invasiveness information. Here, we created a novel explainable transformer network for EGFR classification named gated multiple instance learning transformer (GMILT) by integrating multi-instance learning and discriminative weakly supervised feature learning. Pathological invasiveness information was first introduced into the multitask model as embeddings. GMILT was trained and validated on a total of 512 patients with adenocarcinoma and tested on three datasets (the internal test dataset, the external test dataset, and The Cancer Imaging Archive (TCIA) public dataset). The performance (area under the curve (AUC) =0.772 on the internal test dataset) of GMILT exceeded that of previously published methods and radiomics-based methods (i.e., random forest and support vector machine) and attained a preferable generalization ability (AUC =0.856 in the TCIA test dataset and AUC =0.756 in the external dataset). A diameter-based subgroup analysis further verified the efficiency of our model (most of the AUCs exceeded 0.772) to noninvasively predict EGFR mutation status from computed tomography (CT) images. In addition, because our method also identified the "core area" of the most suspicious area related to the EGFR mutation status, it has the potential ability to guide biopsies.

Implementing preventive healthcare strategies in early intervention

In recent years, efforts to promote early intervention for children with developmental delays have been made to prevent further pathological invasion in children. Early rehabilitation through early screening not only enhances treatment effectiveness but also significantly reduces the pain and damage caused by diseases to families. In the concept of preventive healthcare strategies, it can be divided into three stages and five levels: (1) Primary prevention: can be divided into two levels, health promotion, and specific protection. (2) Secondary prevention: providing early treatment through early screening. (3) Tertiary prevention: mainly aimed at restoring the maximum function of disabilities caused by diseases, only causing minimal restrictions on personal function, and can be divided into two levels, limitation of disability, and rehabilitation treatment. In this article, besides exploring the causes of early childhood developmental disorders, the author combines preventive healthcare strategies to propose the differentiated application of early intervention in the three stages of preventive healthcare. This article reviews the current situation and challenges in Taiwan, and proposes possible responses based on scholars' views and personal opinions, aiming to enhance the quality of early intervention services provided by interdisciplinary teams.

Prognostic significance of ground-glass areas within tumours in non-small-cell lung cancer.

To validate or refute the hypothesis that non-small-cell lung cancers (NSCLC) with ground-glass areas (GGA+) within the tumour on high-resolution computed tomography are associated with a more favourable prognosis than those without GGA (GGA-). We analysed data from a multicentre observational cohort study in Japan including 5005 patients with completely resected pathological stage I NSCLC, who were excluded from the Japan Clinical Oncology Group (JCOG) 0707 trial on oral adjuvant treatment during the enrolment period. The patients' medical and pathological records were assessed retrospectively by physicians and re-staged according to the 8th tumour, node, metastasis edition. Of the 5005 patients, 2388 (48%) were ineligible for the JCOG0707 trial and 2617 (52%) were eligible but were not enrolled. A total of 958 patients (19.1%) died. Patients with GGA+ NSCLC and pathological invasion ≤3 cm showed significantly better overall survival than others. In patients with tumours with an invasive portion ≤4 cm, GGA+ was associated with better survival. The prognoses of patients with GGA+ T2a and GGA- T1c tumours were similar (5-year overall survival: 84.6% vs 83.1%, respectively). The survival with T2b or more tumours appeared unaffected by GGA, and GGA was not prognostic in these larger tumours. Patients with GGA+ NSCLC on high-resolution computed tomography and ≤4 cm invasion size may have a better prognosis than patients with solid GGA- tumours of the same T-stage. However, the presence or absence of radiological GGA has little impact on the prognosis of patients with NSCLC with greater (>4 cm) pathological invasion.

Radiologic Parameters Predicting the Histologic Invasiveness of Pure Ground-Glass Nodules

BackgroundThis study aimed to investigate the diagnostic performance of combined computed tomography (CT) and fluorine-18 fluorodeoxyglucose (FDG) positron emission tomography (PET) for predicting histologic invasiveness of pure ground-glass nodules (pGGNs). MethodsThe study analyzed 91 patients who underwent resection of pGGNs and examined the correlation of pathologic invasiveness with preoperative CT and FDG PET findings. ResultsOverall, 24, 36, and 31 patients had adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAD), respectively. Compared with AIS and MIA, IAD was significantly correlated with larger CT size (P = .001), maximum CT value (P = .026), and high maximum standardized uptake value (SUVmax; P < .001). Multivariable logistic analyses revealed that CT size (odds ratio [OR], 3.848; P = .019) and SUVmax (OR, 4.968; P = .009) were independent predictors of histologic invasiveness. Receiver operating characteristic curve analysis revealed that a cutoff CT size value of 18 mm predicted histologic invasiveness with a sensitivity and specificity of 65% and 80%, respectively; similarly, a cutoff SUVmax value of 1.5 predicted histologic invasiveness with a sensitivity and specificity of 61% and 90%, respectively. Of 20 lesions with CT size ≥18 mm and SUVmax ≥1.5, 16 (80%) were IAD. Of 54 lesions with CT size <18 mm and SUVmax <1.5, 46 (85%) were non-IAD lesions. Furthermore, all pGGNs with SUVmax ≥2.5 were IAD. ConclusionsCT size and SUVmax were significantly correlated with the histologic invasiveness of pGGNs. These factors may aid in determining optimal surgical procedures.

EGFR mutation impacts recurrence in high-risk early-stage lung adenocarcinoma in the IASLC grading system.

The developments of perioperative treatments for patients with high-risk early-stage lung cancer are ongoing, however, real-world data and evidence of clinical significance of genetic aberration are lacking in this population. This study aimed to identify patients with early-stage lung adenocarcinoma at high risk for recurrence based on pathological indicators of poor prognosis, including the International Association for the Study of Lung Cancer (IASLC) grade, and elucidate the prognostic impact of epidermal growth factor receptor mutation (EGFRm) status. This retrospective study included 494 consecutive patients who underwent complete resection for pathological stage I lung adenocarcinoma between 2011 and 2016. The patients were evaluated for EGFRm and IASLC grade. Multivariable analysis was used to identify pathological factors for poor prognosis associated with recurrence-free survival (RFS) and overall survival (OS). Patients with any one of these factors were classified into the high-risk group. The prognostic impact of EGFRm was evaluated using RFS, OS, and cumulative recurrence proportion. Multivariable analysis for RFS and OS revealed that IASLC grade 3, pathological invasion size>2 cm, and presence of lymphovascular invasion were indicators of poor prognosis. EGFRm-positive patients had a higher incidence of all types of recurrence, including central nervous system (CNS) metastasis and distant metastasis in high-risk group, but not in low-risk group. This study provides evidence that patients with EGFRm-positive stage I lung adenocarcinoma in the high-risk group have an increased risk of recurrence, including CNS metastasis. These findings highlight the need for development of adjuvant treatment in this population.

Clinical implication of the geometric location (fundal end versus cystic ductal end) of gallbladder cancer.

Management of early-stage gallbladder cancer is becoming more important as the rate of early detection is increasing. Although there have been many studies about the clinical implication of the invasion depth or peritoneal/hepatic location of gallbladder cancers, there is no study on the clinical implication of the geometric location of cancer along the longitudinal length of the gallbladder. The location of gallbladder cancer was defined as the geometric center of the primary site of a tumour, which lies on the longitudinal diameter of the surgical specimens. We compared the oncologic outcomes following surgery between gallbladder cancers located on the fundal end and those located on the cystic ductal end. We also analysed patients with stage 1 gallbladder cancer who recurred after surgery. A total of 575 patients with gallbladder cancer were included in this study. Patients with gallbladder cancer on the cystic ductal end had significantly lower rates of recurrence-free survival (P = 0.016) and overall survival (P = 0.023) compared to those with gallbladder cancer on the fundal end. Among 90 patients with stage 1 gallbladder cancer, three patients had a recurrence, all of whom had cystic ductal end gallbladder cancer and showed cystic duct invasion or concomitant xanthogranulomatous cholecystitis in permanent pathology. Gallbladder cancers on the cystic ductal end had worse postoperative oncologic outcomes compared with those on the fundal end.

Uniportal thoracoscopic mediastinal lymphadenectomy using appropriate surgical steps.

Although lymphadenectomies play an important role in the surgical treatment of patients with non-small cell lung cancer (NSCLC), the quality of lymphadenectomies via a uniportal approach has only been evaluated in a few studies. We describe the surgical steps for a mediastinal lymphadenectomy via uniportal video-assisted thoracoscopic surgery (uVATS) and compare the quality of mediastinal lymphadenectomies using uVATS versus multiportal video-assisted thoracoscopic surgery (mVATS). Between April 2017 and January 2023, we analyzed data from 304 patients with NSCLC who underwent (bi-)lobectomy with nodal dissection (ND)2a-1 or greater lymphadenectomy via uVATS or mVATS. We compared patient characteristics and perioperative results, including the number of harvested lymph nodes (LNs), between the two approaches. In addition, the factors associated with N-upstage were identified. No significant differences in the total number of harvested LNs were detected between the two approaches. Significantly more LN#2R/4R zone LNs were harvested in the uVATS group compared with the number harvested in the mVATS group [uVATS group: 8.5, interquartile range (IQR), 5-12.3; mVATS group: 7, IQR, 5-9, P=0.0177], while no significant differences in total nodes or nodes harvested in other zones were detected. Multivariable analysis revealed that pathologic invasion size [odds ratio: 1.0200, 95% confidence interval (CI): 1.0100-1.0400, P=0.0050], but not approach (uVATS, odds ratio: 0.6240, 95% CI: 0.3160-1.2300, P=0.1750), significantly contributed to N factor upstages. The use of appropriate surgical steps enabled us to achieve similar quality lymphadenectomies via mVATS or uVATS.

Predicting the pathological invasiveness in patients with a solitary pulmonary nodule via Shapley additive explanations interpretation of a tree-based machine learning radiomics model: a multicenter study.

Radiomics models could help assess the benign and malignant invasiveness and prognosis of pulmonary nodules. However, the lack of interpretability limits application of these models. We thus aimed to construct and validate an interpretable and generalized computed tomography (CT) radiomics model to evaluate the pathological invasiveness in patients with a solitary pulmonary nodule in order to improve the management of these patients. We retrospectively enrolled 248 patients with CT-diagnosed solitary pulmonary nodules. Radiomic features were extracted from nodular region and perinodular regions of 3 and 5 mm. After coarse-to-fine feature selection, the radiomics score (radscore) was calculated using the least absolute shrinkage and selection operator logistic method. Univariate and multivariate logistic regression analyses were performed to determine the invasiveness-related clinicoradiological factors. The clinical-radiomics model was then constructed using the logistic and extreme gradient boosting (XGBoost) algorithms. The Shapley additive explanations (SHAP) method was then used to explain the contributions of the features. After removing batch effects with the ComBat algorithm, we assessed the generalization of the explainable clinical-radiomics model in two independent external validation cohorts (n=147 and n=149). The clinical-radiomic XGBoost model integrating the radscore, CT value, nodule length, and crescent sign demonstrated better predictive performance than did the clinical-radiomics logistic model in assessing pulmonary nodule invasiveness, with an area under the receiver operating characteristic (ROC) curve (AUC) of 0.889 [95% confidence interval (CI), 0.848-0.927] in the training cohort. The SHAP algorithm illustrates the contribution of each feature in the final model. The specific model decision process was visualized using a tree-based decision heatmap. Satisfactory generalization performance was shown with AUCs of 0.889 (95% CI, 0.823-0.942) and 0.915 (95% CI, 0.851-0.963) in the two external validation cohorts. An interpretable and generalized clinical-radiomics model for predicting pulmonary nodule invasibility was constructed to help clinicians determine the invasiveness of pulmonary nodules and devise assessment strategies in an easily understandable manner.

Lack of incremental value of three-dimensional measurement in assessing invasiveness for lung cancer.

The aim of this study was to evaluate the performance of consolidation-to-tumour ratio (CTR) and the radiomic models in two- and three-dimensional modalities for assessing radiological invasiveness in early-stage lung adenocarcinoma. A retrospective analysis was conducted on patients with early-stage lung adenocarcinoma from Guangdong Provincial People's Hospital and Shenzhen People's Hospital. Manual delineation of pulmonary nodules along the boundary was performed on cross-sectional images to extract radiomic features. Clinicopathological characteristics and radiomic signatures were identified in both cohorts. CTR and radiomic score for every patient were calculated. The performance of CTR and radiomic models were tested and validated in the respective cohorts. A total of 818 patients from Guangdong Provincial People's Hospital were included in the primary cohort, while 474 patients from Shenzhen People's Hospital constituted an independent validation cohort. Both CTR and radiomic score were identified as independent factors for predicting pathological invasiveness. CTR in two- and three-dimensional modalities exhibited comparable results with areas under the receiver operating characteristic curves and were demonstrated in the validation cohort (area under the curve: 0.807 vs 0.826, P = 0.059) Furthermore, both CTR in two- and three-dimensional modalities was able to stratify patients with significant relapse-free survival (P < 0.000 vs P < 0.000) and overall survival (P = 0.003 vs P = 0.001). The radiomic models in two- and three-dimensional modalities demonstrated favourable discrimination and calibration in independent cohorts (P = 0.189). Three-dimensional measurement provides no additional clinical benefit compared to two-dimensional.

Deep learning-based solid component measuring enabled interpretable prediction of tumor invasiveness for lung adenocarcinoma

BackgroundThe nature of the solid component of subsolid nodules (SSNs) can indicate tumor pathological invasiveness. However, preoperative solid component assessment still lacks a reference standard. MethodsIn this retrospective study, an AI algorithm was proposed for measuring the solid components ratio in SSNs, which was used to assess the diameter ratio (1D), area ratio (2D), and volume ratio (3D). The radiologist measured each SSN's consolidation to tumor ratio (CTR) twice, four weeks apart. The area under the receiver-operating characteristic (ROC) curve (AUC) was calculated for each method used to discriminate an Invasive Adenocarcinoma (IA) from a non-IA. The AUC and the time cost of each measurement were compared. Furthermore, we examined the consistency of measurements made by the radiologist on two separate occasions. ResultsA total of 379 patients (the primary dataset n = 278, the validation dataset n = 101) were included. In the primary dataset, compared to the manual approach (AUC: 0.697), the AI algorithm (AUC: 0.811) had better predictive performance (P =.0027) in measuring solid components ratio in 3D. Algorithm measurement in 3D had an AUC no inferior to 1D (AUC: 0.806) and 2D (AUC: 0.796). In the validation dataset, the AI 3D method also achieved superior diagnostic performance compared to the radiologist (AUC: 0.803 vs 0.682, P =.046). The two measurements of the CTR in the primary dataset, taken 4 weeks apart, have 7.9 % cases in poor consistency. The measurement time cost by the radiologist is about 60 times that of the AI algorithm (P <.001). ConclusionThe 3D measurement of solid components using AI, is an effective and objective approach to predict the pathological invasiveness of SSNs. It can be a preoperative interpretable indicator of pathological invasiveness in patients with lung adenocarcinoma.

Expression Changes in Programmed Death Ligand 1 from Precancerous Lesions to Invasive Adenocarcinoma in Subcentimeter Pulmonary Nodules: A Large Study of 2022 Cases in China.

This large-scale, multicenter, retrospective observational study aimed to evaluate the clinicopathological and molecular profiles associated with programmed death-ligand 1 (PD-L1) expression in precancerous lesions and invasive adenocarcinoma in subcentimeter pulmonary nodules. Patients with histologically confirmed atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (ADC) were included. PD-L1 expression was evaluated at each center using a PD-L1 immunohistochemistry 22C3 pharmDx kit (Agilent, Santa Clara, CA, USA). The tumor proportion score (TPS) cutoff values were set at ≥ 1% and ≥ 50%. A total of 2022 nodules from 1844 patients were analyzed. Of these, 9 (0.45%) nodules had PD-L1 TPS ≥ 50%, 187 (9.25%) had PD-L1 TPS 1-49%, and 1826 (90.30%) had PD-L1 TPS < 1%. A total of 378 (18.69%), 1016 (50.25%), and 628 (31.06%) nodules were diagnosed as AAH/AIS, MIA, and ADC, respectively, by pathology. A total of 1377 (68.10%), 591 (25.67%), and 54 (2.67%) nodules were diagnosed as pure ground-glass opacity (GGO), mixed GGO, and solid nodules, respectively, by computed tomography. There was a significant difference between PD-L1 expression and anaplastic lymphoma kinase (ALK) mutation status (P < 0.001). PD-L1 expression levels were significantly different from those determined using the International Association for the Study of Lung Cancer (IASLC) grading system (P < 0.001). PD-L1 expression was significantly associated with radiological and pathological invasiveness and driver mutation status in subcentimeter pulmonary nodules. The significance of PD-L1 expression in the evolution of early-stage lung adenocarcinoma requires further investigation.

Analysis of Risk Factors for Recurrence after Transurethral Resection of Bladder Tumor in Patients with Non-Muscle Invasive Bladder Cancer: 2-Year Follow-Up Outcomes.

The aim was to investigate the risk factors for recurrence after transurethral resection of bladder tumor (TURBT) in patients with non-muscle invasive bladder cancer (NMIBC) and to provide a basis for clinical prevention of recurrence of NMIBC. From January 2012 to December 2020, 592 patients with NMIBC who underwent TURBT attending the Second Affiliated Hospital of Xi'an Jiaotong University were retrospectively included in this study. Patients were divided into relapse and relapse-free groups according to whether relapse occurred within 2 years. Ultimately, 72 patients were included in the relapse group and 350 patients were included in the relapse-free group. Observation indicators included age, sex, smoking, underlying disease (hypertension, diabetes, coronary heart disease), two or more lesions, tumor size, hematuria, pathology grading (low, medium, high), staging (Ta, T1), muscular invasion in initial pathology, tumor base (sessile, pedunculated), use of intravesical drug (pirarubicin, bacillus Calmette-Guerin [BCG], mitomycin, hydroxycamptothecin, gemcitabine). In this study, the 2-year recurrence rate of NMIBC patients after TURBT was 17.06%. There were significant differences in comparison of pirarubicin, BCG, and mitomycin treatment between the two groups (p &lt; 0.05). To avoid missing risk factors for recurrence, factors with p &lt; 0.1 were analyzed. The results of univariate logistic regression analysis showed that NMIBC patients with BCG treatment (OR = 5.088, 95% CI = 1.444-17.73, p = 0.012), high pathology grading (OR = 0.415, 95% CI = 0.197-0.880, p = 0.023), T1 stage (OR = 2.097, 95% CI = 0.996-4.618, p = 0.059), mitomycin treatment (OR = 5.029, 95% CI = 1.149-21.77, p = 0.031), and pirarubicin treatment (OR = 1.794, 95% CI = 1.079-3.030, p = 0.024) had significantly higher risk of recurrence within 2 years after TURBT. The results of multivariate logistic regression analysis showed that NMIBC patients with high pathology grading (OR = 0.4030, 95% CI = 0.1702-0.8426, p = 0.0241), pirarubicin treatment (OR = 1.961, 95% CI = 1.159-3.348, p = 0.0125), and BCG treatment (OR = 6.201, 95% CI = 1.275-29.73, p = 0.0190) had significantly higher risk of recurrence within 2 years after TURBT. Our study highlights the importance of postoperative surveillance and individualized treatment for patients with NMIBC. Our findings show that high pathology grading, pirarubicin treatment, and BCG treatment are independent risk factors for recurrence after TURBT in patients with NMIBC. However, caution is warranted when interpreting our findings due to the small sample size and the need for further research to confirm the negative impact of mitomycin and BCG on recurrence rates.

A machine learning model based on MRI for the preoperative prediction of bladder cancer invasion depth.

To construct and validate a prediction model based on full-sequence MRI for preoperatively evaluating the invasion depth of bladder cancer. A total of 445 patients with bladder cancer were divided into a seven-to-three training set and test set for each group. The radiomic features of lesions were extracted automatically from the preoperative MRI images. Two feature selection methods were performed and compared, the key of which are the Least Absolute Shrinkage and Selection Operator (LASSO) and the Max Relevance Min Redundancy (mRMR). The classifier of the prediction model was selected from six advanced machine-learning techniques. The receiver operating characteristic (ROC) curves and the area under the curve (AUC) were applied to assess the efficiency of the models. The models with the best performance for pathological invasion prediction and muscular invasion prediction consisted of LASSO as the feature selection method and random forest as the classifier. In the training set, the AUC of the pathological invasion model and muscular invasion model were 0.808 and 0.828. Furthermore, with the mRMR as the feature selection method, the external invasion model based on random forest achieved excellent discrimination (AUC, 0.857). The full-sequence models demonstrated excellent accuracy for preoperatively predicting the bladder cancer invasion status. This study introduces a full-sequence MRI model for preoperative prediction of the depth of bladder cancer infiltration, which could help clinicians to recognise pathological features associated with tumour infiltration prior to invasive procedures. • Full-sequence MRI prediction model performed better than Vesicle Imaging-Reporting and Data System (VI-RADS) for preoperatively evaluating the invasion status of bladder cancer. • Machine learning methods can extract information from T1-weighted image (T1WI) sequences and benefit bladder cancer invasion prediction.

Development of a novel combined nomogram integrating deep-learning-assisted CT texture and clinical–radiological features to predict the invasiveness of clinical stage IA part-solid lung adenocarcinoma: a multicentre study

To develop a novel combined nomogram based on deep-learning-assisted computed tomography (CT) texture (DL-TA) and clinical-radiological features for the preoperative prediction of invasiveness in patients with clinical stage IA lung adenocarcinoma manifesting as part-solid nodules (PSNs). This study was conducted from January 2015 to October 2021 at three centres: 355 patients with 355 PSN lung adenocarcinomas who underwent surgical resection were included and classified into the training (n=222) and validation (n=133) cohorts. PSN segmentation on CT images was performed automatically with a commercial deep-learning algorithm, and CT texture features were extracted. The least absolute shrinkage and selection operator was used for feature selection and transformed into a DL-TA score. The combined nomogram that incorporated the DL-TA score and identified clinical-radiological features was developed for the prediction of pathological invasiveness of the PSNs and validated in terms of discrimination and calibration. The present study generated a combined nomogram for predicting the invasiveness of PSNs that included age, consolidation-to-tumour ratio, smoking status, and DL-TA score, with a C-index of 0.851 (95% confidence interval: 0.826-0.877) for the training cohort and 0.854 (95% confidence interval: 0.817-0.891) for the validation cohort, indicating good discrimination. Furthermore, the model had a Brier score of 0.153 for the training cohort and 0.135 for the validation cohort, indicating good calibration. The developed combined nomogram consisting of the DL-TA score and clinical-radiological features and has the potential to predict the individual risk for the invasiveness of stage IA PSN lung adenocarcinomas.

Immune-Mediated Necrotizing Myopathy(IMNM)

Immune-mediated necrotizing myopathy (IMNM) has recently been classified from polymyositis, and it clinically shows subacute progressive proximal dominant muscle weakness. Laboratory examinations show a great increase in serum creatine kinase and prominent necrotic muscle fibers without any pathological invasion of inflammatory cells. It is thought to be an autoimmune disease because SRP and HMGCR antibodies have been detected in many cases. These two antibodies affect the pathophysiology of IMNM. Immuno-modulating therapies have usually been induced. Moreover, intensive treatments are necessary in cases of corticosteroid resistant IMNM.

Survival analysis and prognostic factors of retroperitoneal liposarcoma curative surgery in a single centre. Analysis of adjacent organ invasion between imaging and definitive histopathology

IntroductionRetroperitoneal liposarcoma (RPL) is a rare primary mesenchymal tumour that develops in retroperitoneal adipose tissue. Unlike the majority of published series, this homogeneous cohort focuses on RPL. The main purpose of this study is to evaluate the overall and recurrence-free survival of RPLs who underwent excision surgery and the prognostic factors involved. Patients and methodsA total of 82 patients from a single centre, who underwent curative surgery for histologically confirmed retroperitoneal liposarcoma between 2008 and 2020, were analysed in the study. Compartmental surgical excision was advised as per the guidelines. The primary endpoints were 5 years of overall survival and recurrence-free survival. Predictable tumour invasion of adjacent organs, based on a pre-operative CT scan, was also investigated to test the correlation between pre-operative imaging and pathological data. ResultsMedian follow-up was 61.6 months. Five year overall survival was 71.9% [95% CI: 59.8; 80.9] and 5 year recurrence-free survival was 49% [95% CI: 36.4; 60.5]. Following multivariable analysis, the factors influencing overall survival were tumour rupture and onset of severe complications (Dindo-Clavien grade ≥3). Factors influencing recurrence-free survival were neoadjuvant radiotherapy and tumour rupture.A significant correlation (p < 0.05) was found between predicted invasion based on a CT scan of the colon, spleen, adrenal gland, posterior abdominal wall and diaphragm, and pathological invasion. ConclusionsCurative compartmental surgery remains the gold standard treatment for RPL. This study, highlights the fact that the quality of the surgical excision is a crucial factor in patient prognosis.

Lung adenocarcinoma associated with cystic airspaces: Predictive value of CT features in assessing pathologic invasiveness

ObjectivesLung adenocarcinoma associated with cystic airspaces (LACA) is a unique entity with limited understanding. Our aim was to evaluate the radiological characteristics of LACA and to study which criteria were predictive of invasiveness. MethodsA retrospective monocentric analysis of consecutive patients with pathologically confirmed LACA was performed. The diagnosed adenocarcinomas were classified into preinvasive (atypical adenomatous hyperplasia, adenocarcinoma in situ, or minimally invasive adenocarcinoma) and invasive adenocarcinomas. Eight clinical features and twelve CT features were evaluated. Univariable and multivariable analyses were performed to analyse the correlation between invasiveness, and CT and clinical features. The inter-observer agreement was evaluated using κ statistics and intraclass correlation coefficients. The predictive performance of the model was evaluated using the area under the receiver operating characteristic curve (AUC). ResultsA total of 252 patients with 265 lesions (128 men and 124 women; mean age, 58.0 ± 11.1 years) were enrolled. Multivariable logistic regression indicated that multiple cystic airspaces (OR, 5.599; 95 % CI, 1.865–16.802), irregular shape of cystic airspace (OR, 3.236; 95 % CI, 1.073–9.761), entire tumour size (OR, 1.281; 95 % CI, 1.075–1.526), and attenuation (OR, 1.007; 95 % CI, 1.005–1.010) were independent risk factors for invasive LACA. The AUC of the logistic regression model was 0.964 (95 % CI, 0.944–0.985). ConclusionMultiple cystic airspaces, irregular shape of cystic airspace, entire tumour size, and attenuation were identified as independent risk factors for invasive LACA. The prediction model gives a good predictive performance, providing additional diagnostic information.