Dataset Information

Development of a Deep Learning Model to Assist With Diagnosis of Hepatocellular Carcinoma.

ABSTRACT:

Background

An accurate pathological diagnosis of hepatocellular carcinoma (HCC), one of the malignant tumors with the highest mortality rate, is time-consuming and heavily reliant on the experience of a pathologist. In this report, we proposed a deep learning model that required minimal noise reduction or manual annotation by an experienced pathologist for HCC diagnosis and classification.

Methods

We collected a whole-slide image of hematoxylin and eosin-stained pathological slides from 592 HCC patients at the First Affiliated Hospital, College of Medicine, Zhejiang University between 2015 and 2020. We propose a noise-specific deep learning model. The model was trained initially with 137 cases cropped into multiple-scaled datasets. Patch screening and dynamic label smoothing strategies are adopted to handle the histopathological liver image with noise annotation from the perspective of input and output. The model was then tested in an independent cohort of 455 cases with comparable tumor types and differentiations.

Results

Exhaustive experiments demonstrated that our two-step method achieved 87.81% pixel-level accuracy and 98.77% slide-level accuracy in the test dataset. Furthermore, the generalization performance of our model was also verified using The Cancer Genome Atlas dataset, which contains 157 HCC pathological slides, and achieved an accuracy of 87.90%.

Conclusions

The noise-specific histopathological classification model of HCC based on deep learning is effective for the dataset with noisy annotation, and it significantly improved the pixel-level accuracy of the regular convolutional neural network (CNN) model. Moreover, the model also has an advantage in detecting well-differentiated HCC and microvascular invasion.

SUBMITTER: Feng S

PROVIDER: S-EPMC8671137 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundAccurate assessment of the percentage total body surface area (%TBSA) of burn wounds is crucial in the management of burn patients. The resuscitation fluid and nutritional needs of burn patients, their need for intensive unit care, and probability of mortality are all directly related to %TBSA. It is difficult to estimate a burn area of irregular shape by inspection. Many articles have reported discrepancies in estimating %TBSA by different doctors.ObjectiveWe propose a method, based on deep learning, for burn wound detection, segmentation, and calculation of %TBSA on a pixel-to-pixel basis.MethodsA 2-step procedure was used to convert burn wound diagnosis into %TBSA. In the first step, images of burn wounds were collected from medical records and labeled by burn surgeons, and the data set was then input into 2 deep learning architectures, U-Net and Mask R-CNN, each configured with 2 different backbones, to segment the burn wounds. In the second step, we collected and labeled images of hands to create another data set, which was also input into U-Net and Mask R-CNN to segment the hands. The %TBSA of burn wounds was then calculated by comparing the pixels of mask areas on images of the burn wound and hand of the same patient according to the rule of hand, which states that one's hand accounts for 0.8% of TBSA.ResultsA total of 2591 images of burn wounds were collected and labeled to form the burn wound data set. The data set was randomly split into training, validation, and testing sets in a ratio of 8:1:1. Four hundred images of volar hands were collected and labeled to form the hand data set, which was also split into 3 sets using the same method. For the images of burn wounds, Mask R-CNN with ResNet101 had the best segmentation result with a Dice coefficient (DC) of 0.9496, while U-Net with ResNet101 had a DC of 0.8545. For the hand images, U-Net and Mask R-CNN had similar performance with DC values of 0.9920 and 0.9910, respectively. Lastly, we conducted a test diagnosis in a burn patient. Mask R-CNN with ResNet101 had on average less deviation (0.115% TBSA) from the ground truth than burn surgeons.ConclusionsThis is one of the first studies to diagnose all depths of burn wounds and convert the segmentation results into %TBSA using different deep learning models. We aimed to assist medical staff in estimating burn size more accurately, thereby helping to provide precise care to burn victims.

Project description:ImportanceDeep learning, a family of machine learning models that use artificial neural networks, has achieved great success at predicting outcomes in nonmedical domains.ObjectiveTo examine whether deep learning recurrent neural network (RNN) models that use raw longitudinal data extracted directly from electronic health records outperform conventional regression models in predicting the risk of developing hepatocellular carcinoma (HCC).Design, setting, and participantsThis prognostic study included 48 151 patients with hepatitis C virus (HCV)-related cirrhosis in the national Veterans Health Administration who had at least 3 years of follow-up after the diagnosis of cirrhosis. Patients were identified by having at least 1 positive HCV RNA test between January 1, 2000, to January 1, 2016, and were followed up from the diagnosis of cirrhosis to January 1, 2019, for the development of incident HCC. A total of 3 models predicting HCC during a 3-year period were developed and compared, as follows: (1) logistic regression (LR) with cross-sectional inputs (cross-sectional LR); (2) LR with longitudinal inputs (longitudinal LR); and (3) RNN with longitudinal inputs. Data analysis was conducted from April 2018 to August 2020.ExposuresDevelopment of HCC.Main outcomes and measuresArea under the receiver operating characteristic curve, area under the precision-recall curve, and Brier score.ResultsDuring a mean (SD) follow-up of 11.6 (5.0) years, 10 741 of 48 151 patients (22.3%) developed HCC (annual incidence, 3.1%), and a total of 52 983 samples (51 948 [98.0%] from men) were collected. Patients who developed HCC within 3 years were older than patients who did not (mean [SD] age, 58.2 [6.6] years vs 56.9 [6.9] years). RNN models had superior mean (SD) area under the receiver operating characteristic curve (0.759 [0.009]) and mean (SD) Brier score (0.136 [0.003]) than cross-sectional LR (0.689 [0.009] and 0.149 [0.003], respectively) and longitudinal LR (0.682 [0.007] and 0.150 [0.003], respectively) models. Using the RNN model, the samples with the mean (SD) highest 51% (1.5%) of HCC risk, in which 80% of all HCCs occurred, or the mean (SD) highest 66% (1.2%) of HCC risk, in which 90% of all HCCs occurred, could potentially be targeted. Among samples from patients who achieved sustained virologic response, the performance of the RNN models was even better (mean [SD] area under receiver operating characteristic curve, 0.806 [0.025]; mean [SD] Brier score, 0.117 [0.007]).Conclusions and relevanceIn this study, deep learning RNN models outperformed conventional LR models, suggesting that RNN models could be used to identify patients with HCV-related cirrhosis with a high risk of developing HCC for risk-based HCC outreach and surveillance strategies.

Project description:Background & aimsPersonalised risk prediction of the development of hepatocellular carcinoma (HCC) among patients with liver cirrhosis on potent antiviral therapy is important for targeted screening and individualised intervention. This study aimed to develop and validate a new model for risk prediction of HCC development based on deep learning, and to compare it with previously reported risk models.MethodsA novel deep-learning-based model was developed from a cohort of 424 patients with HBV-related cirrhosis on entecavir therapy with 2 residual blocks, including 7 layers of a neural network, and it was validated using an independent external cohort (n = 316). The deep-learning-based model was compared to 6 previously reported models (platelet, age, and gender-hepatitis B score [PAGE-B], Chinese University HCC score [CU-HCC], HCC-Risk Estimating Score in CHB patients Under Entecavir [HCC-RESCUE], age, diabetes, race, etiology of cirrhosis, sex, and severity HCC score [ADRESS-HCC], modified PAGE-B score [mPAGE], and Toronto HCC risk index [THRI]) using Harrell's concordance (c)-index.ResultsDuring a median 5.2 yr of follow-up (inter-quartile range 2.8-6.9 yr), 86 patients (20.3%) developed HCC. The deep-learning-based model had a Harrell's c-index of 0.719 in the derivation cohort and 0.782 in the validation cohort. Goodness of fit was confirmed by the Hosmer-Lemeshow test (p >0.05). Moreover, this model in the validation cohort had the highest c-index among the 6 previously reported models: PAGE-B (0.570), CU-HCC (0.548), HCC-RESCUE (0.577), ADRESS-HCC (0.551), mPAGE (0.598), and THRI (0.587) (all p <0.001). The misclassification rate of this model was 23.7% (model accuracy: 76.3%) in the validation group.ConclusionsThe deep-learning-based model had better performance than the previous models for predicting the HCC risk in patients with HBV-related cirrhosis on potent antivirals.Lay summaryFor early detection of hepatocellular carcinoma, it is important to maintain regular surveillance. However, there is currently no standard prediction model for risk stratification that can be used to establish a personalised surveillance strategy. We develop and validate a deep-learning-based model that showed better performance than previous models.

Project description:BackgroundGastric cancer is a highly prevalent and fatal disease. Accurate differentiation between early gastric cancer (EGC) and advanced gastric cancer (AGC) is essential for personalized treatment. Currently, the diagnostic accuracy of computerized tomography (CT) for gastric cancer staging is insufficient to meet clinical requirements. Many studies rely on manual marking of lesion areas, which is not suitable for clinical diagnosis.MethodsIn this study, we retrospectively collected data from 341 patients with gastric cancer at the First Affiliated Hospital of Wenzhou Medical University. The dataset was randomly divided into a training set (n=273) and a validation set (n=68) using an 8:2 ratio. We developed a two-stage deep learning model that enables fully automated EGC screening based on CT images. In the first stage, an unsupervised domain adaptive segmentation model was employed to automatically segment the stomach on unlabeled portal phase CT images. Subsequently, based on the results of the stomach segmentation model, the image was cropped out of the stomach area and scaled to a uniform size, and then the EGC and AGC classification models were built based on these images. The segmentation accuracy of the model was evaluated using the dice index, while the classification performance was assessed using metrics such as the area under the curve (AUC) of the receiver operating characteristic (ROC), accuracy, sensitivity, specificity, and F1 score.ResultsThe segmentation model achieved an average dice accuracy of 0.94 on the hand-segmented validation set. On the training set, the EGC screening model demonstrated an AUC, accuracy, sensitivity, specificity, and F1 score of 0.98, 0.93, 0.92, 0.92, and 0.93, respectively. On the validation set, these metrics were 0.96, 0.92, 0.90, 0.89, and 0.93, respectively. After three rounds of data regrouping, the model consistently achieved an AUC above 0.9 on both the validation set and the validation set.ConclusionThe results of this study demonstrate that the proposed method can effectively screen for EGC in portal venous CT images. Furthermore, the model exhibits stability and holds promise for future clinical applications.