Lung Cancer Diagnosis on Virtual Histologically Stained Tissue Using Weakly Supervised Learning.

Lung adenocarcinoma (LUAD) is the most common primary lung cancer and accounts for 40% of all lung cancer cases. The current gold standard for lung cancer analysis is based on the pathologists' interpretation of hematoxylin and eosin (H&E)-stained tissue slices viewed under a brightfield microscope or a digital slide scanner. Computational pathology using deep learning has been proposed to detect lung cancer on histology images. However, the histological staining workflow to acquire the H&E-stained images and the subsequent cancer diagnosis procedures are labor-intensive and time-consuming with tedious sample preparation steps and repetitive manual interpretation, respectively. In this work, we propose a weakly supervised learning method for LUAD classification on label-free tissue slices with virtual histological staining. The autofluorescence images of label-free tissue with histopathological information can be converted into virtual H&E-stained images by a weakly supervised deep generative model. For the downstream LUAD classification task, we trained the attention-based multiple-instance learning model with different settings on the open-source LUAD H&E-stained whole-slide images (WSIs) dataset from the Cancer Genome Atlas (TCGA). The model was validated on the 150 H&E-stained WSIs collected from patients in Queen Mary Hospital and Prince of Wales Hospital with an average area under the curve (AUC) of 0.961. The model also achieved an average AUC of 0.973 on 58 virtual H&E-stained WSIs, comparable to the results on 58 standard H&E-stained WSIs with an average AUC of 0.977. The attention heatmaps of virtual H&E-stained WSIs and ground-truth H&E-stained WSIs can indicate tumor regions of LUAD tissue slices. In conclusion, the proposed diagnostic workflow on virtual H&E-stained WSIs of label-free tissue is a rapid, cost effective, and interpretable approach to assist clinicians in postoperative pathological examinations. The method could serve as a blueprint for other label-free imaging modalities and disease contexts.

Exceeding the limit for microscopic image translation with a deep learning-based unified framework.

Deep learning algorithms have been widely used in microscopic image translation. The corresponding data-driven models can be trained by supervised or unsupervised learning depending on the availability of paired data. However, general cases are where the data are only roughly paired such that supervised learning could be invalid due to data unalignment, and unsupervised learning would be less ideal as the roughly paired information is not utilized. In this work, we propose a unified framework (U-Frame) that unifies supervised and unsupervised learning by introducing a tolerance size that can be adjusted automatically according to the degree of data misalignment. Together with the implementation of a global sampling rule, we demonstrate that U-Frame consistently outperforms both supervised and unsupervised learning in all levels of data misalignments (even for perfectly aligned image pairs) in a myriad of image translation applications, including pseudo-optical sectioning, virtual histological staining (with clinical evaluations for cancer diagnosis), improvement of signal-to-noise ratio or resolution, and prediction of fluorescent labels, potentially serving as new standard for image translation.

A comprehensive overview of the molecular features and therapeutic targets in BRAFV600E-mutant colorectal cancer.

As one of the most prevalent digestive system tumours, colorectal cancer (CRC) poses a significant threat to global human health. With the emergence of immunotherapy and target therapy, the prognosis for the majority of CRC patients has notably improved. However, the subset of patients with BRAF exon 15 p.V600E mutation (BRAFV600E) has not experienced remarkable benefits from these therapeutic advancements. Hence, researchers have undertaken foundational investigations into the molecular pathology of this specific subtype and clinical effectiveness of diverse therapeutic drug combinations. This review comprehensively summarised the distinctive molecular features and recent clinical research advancements in BRAF-mutant CRC. To explore potential therapeutic targets, this article conducted a systematic review of ongoing clinical trials involving patients with BRAFV600E-mutant CRC.

Deep learning-assisted low-cost autofluorescence microscopy for rapid slide-free imaging with virtual histological staining.

Slide-free imaging techniques have shown great promise in improving the histological workflow. For example, computational high-throughput autofluorescence microscopy by pattern illumination (CHAMP) has achieved high resolution with a long depth of field, which, however, requires a costly ultraviolet laser. Here, simply using a low-cost light-emitting diode (LED), we propose a deep learning-assisted framework of enhanced widefield microscopy, termed EW-LED, to generate results similar to CHAMP (the learning target). Comparing EW-LED and CHAMP, EW-LED reduces the cost by 85×, shortening the image acquisition time and computation time by 36× and 17×, respectively. This framework can be applied to other imaging modalities, enhancing widefield images for better virtual histology.

Effects of T2DM on postoperative outcome of patients with colorectal cancer: a study on the relationship between blood glucose control and survival rate.

To investigate the impact of type 2 diabetes (T2DM) on the prognosis of colorectal cancer (CRC). The data of 312 patients with CRC treated in the First Affiliated Hospital of Huzhou University from 2012 to 2018 were analyzed retrospectively. The patients were divided into a comorbidity group (n = 62) and a non-comorbidity group (n = 250) according to the presence of T2DM. The baseline data of the two groups were balanced by 1:2 propensity score matching (PSM). Kaplan-Meier analysis and Log-rank test were employed to compare the 5-year overall survival (OS) rates of patients. Cox regression model and inverse probability of treatment weighting (IPTW) were utilized to assess the influence of T2DM on 5-year OS of patients. Based on the results of Cox regression, a nomogram model of T2DM on 5-year OS of patients was constructed. A total of 62 patients in the comorbidity group and 124 patients in the non-comorbidity group were matched using PSM. The 5-year OS rate was lower in the comorbidity group than in the non-comorbidity group (82.23% VS 90.32%, P = 0.038). Subgroup analysis showed that the 5-year overall survival rate was higher in the good blood glucose control group than in the poor blood glucose control group (97.14% VS 62.96%, P<0.01). Multivariate Cox regression showed that the 5-year mortality risk in the comorbidity group was 2.641 times higher than that in the non-comorbidity group (P = 0.026). IPTW analysis showed that the 5-year risk of death in the comorbidity group was 2.458 times that of the non-comorbidity group (P = 0.019). The results showed that poor blood glucose control, BMI≥25 kg/m2, low differentiation, III/IV stage, and postoperative infection were independent factors affecting the 5-year overall survival rate of CRC patients (P<0.05). The ROC curve showed that the AUCs of the constructed model in predicting the 5-year OS in the training set and the testing set were 0.784 and 0.776, respectively. T2DM is identified as a risk factor for reduced 5-year survival among CRC patients, necessitating increased attention for this subgroup, particularly those with poor blood glucose control.