(1) Background: Early diagnosis and treatment are essential to reduce the mortality rate of bladder cancer (BLCA). We aimed to develop deep learning (DL)-based weakly supervised models for the diagnosis of BLCA and prediction of overall survival (OS) in muscle-invasive bladder cancer (MIBC) patients using whole slide digitized histological images (WSIs). (2) Methods: Diagnostic and prognostic models were developed using 926 WSIs of 412 BLCA patients from The Cancer Genome Atlas cohort. We collected 250 WSIs of 150 BLCA patients from the Renmin Hospital of Wuhan University cohort for external validation of the models. Two DL models were developed: a BLCA diagnostic model (named BlcaMIL) and an MIBC prognostic model (named MibcMLP). (3) Results: The BlcaMIL model identified BLCA with accuracy 0.987 in the external validation set, comparable to that of expert uropathologists and outperforming a junior pathologist. The C-index values for the MibcMLP model on the internal and external validation sets were 0.631 and 0.622, respectively. The risk score predicted by MibcMLP was a strong predictor independent of existing clinical or histopathologic indicators, as demonstrated by univariate Cox (HR = 2.390, p < 0.0001) and multivariate Cox (HR = 2.414, p < 0.0001) analyses. The interpretability of DL models can help in the analysis of critical regions associated with tumors to enrich the information obtained from WSIs. Furthermore, the expression of six genes (ANAPC7, MAPKAPK5, COX19, LINC01106, AL161431.1 and MYO16-AS1) was significantly associated with MibcMLP-predicted risk scores, revealing possible potential biological correlations. (4) Conclusions: Our study developed DL models for accurately diagnosing BLCA and predicting OS in MIBC patients, which will help promote the precise pathological diagnosis of BLCA and risk stratification of MIBC to improve clinical treatment decisions.

Although the tumor-stroma ratio (TSR) has prognostic value in many cancers, the traditional semi-quantitative visual assessment method has inter-observer variability, making it impossible for clinical practice. We aimed to develop a machine learning (ML) algorithm for accurately quantifying TSR in hematoxylin-and-eosin (H&E)-stained whole slide images (WSI) and further investigate its prognostic effect in patients with muscle-invasive bladder cancer (MIBC). We used an optimal cell classifier previously built based on QuPath open-source software and ML algorithm for quantitative calculation of TSR. We retrospectively analyzed data from two independent cohorts to verify the prognostic significance of ML-based TSR in MIBC patients. WSIs from 133 MIBC patients were used as the discovery set to identify the optimal association of TSR with patient survival outcomes. Furthermore, we performed validation in an independent external cohort consisting of 261 MIBC patients. We demonstrated a significant prognostic association of ML-based TSR with survival outcomes in MIBC patients (p < 0.001 for all comparisons), with higher TSR associated with better prognosis. Uni- and multivariate Cox regression analyses showed that TSR was independently associated with overall survival (p < 0.001 for all analyses) after adjusting for clinicopathological factors including age, gender, and pathologic stage. TSR was found to be a strong prognostic factor that was not redundant with the existing staging system in different subgroup analyses (p < 0.05 for all analyses). Finally, the expression of six genes (DACH1, DEEND2A, NOTCH4, DTWD1, TAF6L, and MARCHF5) were significantly associated with TSR, revealing possible potential biological relevance. In conclusion, we developed an ML algorithm based on WSIs of MIBC patients to accurately quantify TSR and demonstrated its prognostic validity for MIBC patients in two independent cohorts. This objective quantitative method allows application in clinical practice while reducing the workload of pathologists. Thus, it might be of significant aid in promoting precise pathology services in MIBC.

(1) Background: The Fuhrman grading (FG) system is widely used in the management of clear cell renal cell carcinoma (ccRCC). However, it is affected by observer variability and irreproducibility in clinical practice. We aimed to use a deep learning multi-class model called SSL-CLAM to assist in diagnosing the FG status of ccRCC patients using digitized whole slide images (WSIs). (2) Methods: We recruited 504 eligible ccRCC patients from The Cancer Genome Atlas (TCGA) cohort and obtained 708 hematoxylin and eosin-stained WSIs for the development and internal validation of the SSL-CLAM model. Additionally, we obtained 445 WSIs from 188 ccRCC eligible patients in the Clinical Proteomic Tumor Analysis Consortium (CPTAC) cohort as an independent external validation set. A human–machine fusion approach was used to validate the added value of the SSL-CLAM model for pathologists. (3) Results: The SSL-CLAM model successfully diagnosed the five FG statuses (Grade-0, 1, 2, 3, and 4) of ccRCC, and achieved AUCs of 0.917 and 0.887 on the internal and external validation sets, respectively, outperforming a junior pathologist. For the normal/tumor classification (Grade-0, Grade-1/2/3/4) task, the SSL-CLAM model yielded AUCs close to 1 on both the internal and external validation sets. The SSL-CLAM model achieved a better performance for the two-tiered FG (Grade-0, Grade-1/2, and Grade-3/4) task, with AUCs of 0.936 and 0.915 on the internal and external validation sets, respectively. The human–machine diagnostic performance was superior to that of the SSL-CLAM model, showing promising prospects. In addition, the high-attention regions of the SSL-CLAM model showed that with an increasing FG status, the cell nuclei in the tumor region become larger, with irregular contours and increased cellular pleomorphism. (4) Conclusions: Our findings support the feasibility of using deep learning and human–machine fusion methods for FG classification on WSIs from ccRCC patients, which may assist pathologists in making diagnostic decisions.

(1) Purpose: Although assessment of tumor-infiltrating lymphocytes (TILs) has been acknowledged to have important predictive prognostic value in muscle-invasive bladder cancer (MIBC), it is limited by inter- and intra-observer variability, hampering widespread clinical application. We aimed to evaluate the prognostic value of quantitative TILs score based on a machine learning (ML) algorithm to identify MIBC patients who might benefit from immunotherapy or the de-escalation of therapy. (2) Methods: We constructed an artificial neural network classifier for tumor cells, lymphocytes, stromal cells, and “ignore” cells from hematoxylin-and-eosin-stained slide images using the QuPath open source software. We defined four unique TILs variables based on ML to analyze TILs measurements. Pathological slide images from 133 MIBC patients were retrospectively collected as the discovery set to determine the optimal association of ML-read TILs variables with patient survival outcomes. For validation, we evaluated an independent external validation set consisting of 247 MIBC patients. (3) Results: We found that all four TILs variables had significant prognostic associations with survival outcomes in MIBC patients (p < 0.001 for all comparisons), with higher TILs score being associated with better prognosis. Univariate and multivariate Cox regression analyses demonstrated that electronic TILs (eTILs) variables were independently associated with overall survival after adjustment for clinicopathological factors including age, sex, and pathological stage (p < 0.001 for all analyses). Results analyzed in different subgroups showed that the eTILs variable was a strong prognostic factor that was not redundant with pre-existing clinicopathological features (p < 0.05 for all analyses). (4) Conclusion: ML-driven cell classifier-defined TILs variables were robust and independent prognostic factors in two independent cohorts of MIBC patients. eTILs have the potential to identify a subset of high-risk stage II or stage III-IV MIBC patients who might benefit from adjuvant immunotherapy.

Background: Accurate prediction of lymph node metastasis (LNM) status in patients with muscle-invasive bladder cancer (MIBC) before radical cystectomy can guide the use of neoadjuvant chemotherapy and the extent of pelvic lymph node dissection. We aimed to develop and validate a weakly-supervised deep learning model to predict LNM status from digitized histopathological slides in MIBC. Methods: We trained a multiple instance learning model with an attention mechanism (namely SBLNP) from a cohort of 323 patients in the TCGA cohort. In parallel, we collected corresponding clinical information to construct a logistic regression model. Subsequently, the score predicted by the SBLNP was incorporated into the logistic regression model. In total, 417 WSIs from 139 patients in the RHWU cohort and 230 WSIs from 78 patients in the PHHC cohort were used as independent external validation sets. Results: In the TCGA cohort, the SBLNP achieved an AUROC of 0.811 (95% confidence interval [CI], 0.771–0.855), the clinical classifier achieved an AUROC of 0.697 (95% CI, 0.661–0.728) and the combined classifier yielded an improvement to 0.864 (95% CI, 0.827–0.906). Encouragingly, the SBLNP still maintained high performance in the RHWU cohort and PHHC cohort, with an AUROC of 0.762 (95% CI, 0.725–0.801) and 0.746 (95% CI, 0.687–0.799), respectively. Moreover, the interpretability of SBLNP identified stroma with lymphocytic inflammation as a key feature of predicting LNM presence. Conclusions: Our proposed weakly-supervised deep learning model can predict the LNM status of MIBC patients from routine WSIs, demonstrating decent generalization performance and holding promise for clinical implementation.

Background: The assessment of the International Society of Urological Pathology (ISUP) nuclear grade is crucial for the management and treatment of clear cell renal cell carcinoma (ccRCC). This study aimed to explore the value of using integrated multimodal information for ISUP grading and prognostic stratification in ccRCC patients, to guide postoperative adjuvant therapy. Methods: This retrospective study analyzed a total of 729 patients from three cohorts, utilizing whole slide i-mages and computed tomography (CT) images. Artificial intelligence algorithms were used to extract morphological and textural features from whole slide images and CT images separately, creating single-modality predictive models for ISUP grading. By combining the CT and pathology single-modality predictive features, a multimodal predictive signature (MPS) was developed. The prognostic performance of the MPS model was further validated in two independent cohorts. Results: The single-modality predictive models for CT and pathology performed well in predicting ISUP grade for ccRCC. The MPS model achieved higher area under the curve values of 0.95, 0.93, and 0.95 across three independent patient cohorts. Additionally, the MPS model was able to distinguish patients with poorer overall survival. In the external validation cohort, uni- and multivariate analyses showed hazard ratios of 2.542 (95% confidence interval [CI]: 1.363–4.741, P < 0.0001) and 1.723 (95% CI: 0.888–3.357, P = 0.003), respectively. The C-index values for the two cohorts were 0.75 and 0.71. Furthermore, the MPS outperformed single-modality models, providing a complementary tool for current risk stratification in ccRCC adjuvant therapy. Conclusion: Our novel MPS model demonstrated high accuracy in ISUP grading for ccRCC patients. With further validation across multiple centers, the MPS model could be used for precise detection of nuclear grading in ccRCC, serving as an effective tool for assisting clinical decision-making.