A retrieval-based computer-aided diagnosis system for the characterization of liver lesions in CT scans

Precision diagnosis of hepatocellular carcinoma

ABSTRACT

Hepatocellular carcinoma (HCC) is the most common type of primary hepatocellular carcinoma (PHC). Early diagnosis of HCC remains the key to improve the prognosis. In recent years, with the promotion of the concept of precision medicine and more in-depth analysis of the biological mechanism underlying HCC, new diagnostic methods, including emerging serum markers, liquid biopsies, molecular diagnosis, and advances in imaging (novel contrast agents and radiomics), have emerged one after another. Herein, we reviewed and analyzed scientific advances in the early diagnosis of HCC and discussed their application and shortcomings. This review aimed to provide a reference for scientific research and clinical practice of HCC.

Evaluation of a Novel Content-Based Image Retrieval System for the Differentiation of Interstitial Lung Diseases in CT Examinations

To evaluate the reader's diagnostic performance against the ground truth with and without the help of a novel content-based image retrieval system (CBIR) that retrieves images with similar CT patterns from a database of 79 different interstitial lung diseases. We evaluated three novice readers' and three resident physicians' (with at least three years of experience) diagnostic performance evaluating 50 different CTs featuring 10 different patterns (e.g., honeycombing, tree-in bud, ground glass, bronchiectasis, etc.) and 24 different diseases (sarcoidosis, UIP, NSIP, Aspergillosis, COVID-19 pneumonia etc.). The participants read the cases first without assistance (and without feedback regarding correctness), and with a 2-month interval in a random order with the assistance of the novel CBIR. To invoke the CBIR, a ROI is placed into the pathologic pattern by the reader and the system retrieves diseases with similar patterns. To further narrow the differential diagnosis, the readers can consult an integrated textbook and have the possibility of selecting high-level semantic features representing clinical information (chronic, infectious, smoking status, etc.). We analyzed readers' accuracy without and with CBIR assistance and further tested the hypothesis that the CBIR would help to improve diagnostic performance utilizing Wilcoxon signed rank test. The novice readers demonstrated an unassisted accuracy of 18/28/44%, and an assisted accuracy of 84/82/90%, respectively. The resident physicians demonstrated an unassisted accuracy of 56/56/70%, and an assisted accuracy of 94/90/96%, respectively. For each reader, as well as overall, Sign test demonstrated statistically significant (p < 0.01) difference between the unassisted and the assisted reads. For students and physicians, Chi²-test and Mann-Whitney-U test demonstrated statistically significant (p < 0.01) difference for unassisted reads and statistically insignificant (p > 0.01) difference for assisted reads. The evaluated CBIR relying on pattern analysis and featuring the option to filter the results of the CBIR by predominant characteristics of the diseases via selecting high-level semantic features helped to drastically improve novices' and resident physicians' accuracy in diagnosing interstitial lung diseases in CT.

Systematic review: radiomics for the diagnosis and prognosis of hepatocellular carcinoma

BACKGROUND

Advances in imaging technology have the potential to transform the early diagnosis and treatment of hepatocellular carcinoma (HCC) through quantitative image analysis. Computational "radiomic" techniques extract biomarker information from images which can be used to improve diagnosis and predict tumour biology.

AIMS

To perform a systematic review on radiomic features in HCC diagnosis and prognosis, with a focus on reporting metrics and methodologic standardisation.

METHODS

We performed a systematic review of all full-text articles published from inception through December 1, 2019. Standardised data extraction and quality assessment metrics were applied to all studies.

RESULTS

A total of 54 studies were included for analysis. Radiomic features demonstrated good discriminatory performance to differentiate HCC from other solid lesions (c-statistics 0.66-0.95), and to predict microvascular invasion (c-statistic 0.76-0.92), early recurrence after hepatectomy (c-statistics 0.71-0.86), and prognosis after locoregional or systemic therapies (c-statistics 0.74-0.81). Common stratifying features for diagnostic and prognostic radiomic tools included analyses of imaging skewness, analysis of the peritumoural region, and feature extraction from the arterial imaging phase. The overall quality of the included studies was low, with common deficiencies in both internal and external validation, standardised imaging segmentation, and lack of comparison to a gold standard.

CONCLUSIONS

Quantitative image analysis demonstrates promise as a non-invasive biomarker to improve HCC diagnosis and management. However, standardisation of protocols and outcome measurement, sharing of algorithms and analytic methods, and external validation are necessary prior to widespread application of radiomics to HCC diagnosis and prognosis in clinical practice.

Classification of focal liver lesions in CT images using convolutional neural networks with lesion information augmented patches and synthetic data augmentation

PURPOSE

We propose a deep learning method that classifies focal liver lesions (FLLs) into cysts, hemangiomas, and metastases from portal phase abdominal CT images. We propose a synthetic data augmentation process to alleviate the class imbalance and the Lesion INformation Augmented (LINA) patch to improve the learning efficiency.

METHODS

A dataset of 502 portal phase CT scans of 1,290 FLLs was used. First, to alleviate the class imbalance and to diversify the training data patterns, we suggest synthetic training data augmentation using DCGAN-based lesion mask synthesis and pix2pix-based mask-to-image translation. Second, to improve the learning efficiency of convolutional neural networks (CNNs) for the small lesions, we propose a novel type of input patch termed the LINA patch to emphasize the lesion texture information while also maintaining the lesion boundary information in the patches. Third, we construct a multi-scale CNN through a model ensemble of ResNet-18 CNNs trained on LINA patches of various mini-patch sizes.

RESULTS

The experiments demonstrate that (a) synthetic data augmentation method shows characteristics different but complementary to those in conventional real data augmentation in augmenting data distributions, (b) the proposed LINA patches improve classification performance compared to those by existing types of CNN input patches due to the enhanced texture and boundary information in the small lesions, and (c) through an ensemble of LINA patch-trained CNNs with different mini-patch sizes, the multi-scale CNN further improves overall classification performance. As a result, the proposed method achieved an accuracy of 87.30%, showing improvements of 10.81%p and 15.0%p compared to the conventional image patch-trained CNN and texture feature-trained SVM, respectively.

CONCLUSIONS

The proposed synthetic data augmentation method shows promising results in improving the data diversity and class imbalance, and the proposed LINA patches enhance the learning efficiency compared to the existing input image patches.

Radiomics analysis of contrast-enhanced CT for classification of hepatic focal lesions in colorectal cancer patients: its limitations compared to radiologists

OBJECTIVE

To evaluate diagnostic performance of a radiomics model for classifying hepatic cyst, hemangioma, and metastasis in patients with colorectal cancer (CRC) from portal-phase abdominopelvic CT images.

METHODS

This retrospective study included 502 CRC patients who underwent contrast-enhanced CT and contrast-enhanced liver MRI between January 2005 and December 2010. Portal-phase CT images of training (n = 386) and validation (n = 116) cohorts were used to develop a radiomics model for differentiating three classes of liver lesions. Among multiple handcrafted features, the feature selection was performed using ReliefF method, and random forest classifiers were used to train the selected features. Diagnostic performance of the developed model was compared with that of four radiologists. A subgroup analysis was conducted based on lesion size.

RESULTS

The radiomics model demonstrated significantly lower overall and hemangioma- and metastasis-specific polytomous discrimination index (PDI) (overall, 0.8037; hemangioma-specific, 0.6653; metastasis-specific, 0.8027) than the radiologists (overall, 0.9622-0.9680; hemangioma-specific, 0.9452-0.9630; metastasis-specific, 0.9511-0.9869). For subgroup analysis, the PDI of the radiomics model was different according to the lesion size (< 10 mm, 0.6486; ≥ 10 mm, 0.8264) while that of the radiologists was relatively maintained. For classifying metastasis from benign lesions, the radiomics model showed excellent diagnostic performance, with an accuracy of 84.36% and an AUC of 0.9426.

CONCLUSION

Albeit inferior to the radiologists, the radiomics model achieved substantial diagnostic performance when differentiating hepatic lesions from portal-phase CT images of CRC patients. This model was limited particularly to classifying hemangiomas and subcentimeter lesions.

KEY POINTS

• Albeit inferior to the radiologists, the radiomics model could differentiate cyst, hemangioma, and metastasis with substantial diagnostic performance using portal-phase CT images of colorectal cancer patients. • The radiomics model demonstrated limitations especially in classifying hemangiomas and subcentimeter liver lesions.

Convolutional neural networks versus radiologists in characterization of small hypoattenuating hepatic nodules on CT: a critical diagnostic challenge in staging of colorectal carcinoma

Our objective was to compare the diagnostic performance and diagnostic confidence of convolutional neural networks (CNN) to radiologists in characterizing small hypoattenuating hepatic nodules (SHHN) in colorectal carcinoma (CRC) on CT scans. Retrospective review of CRC CT scans over 6-years yielded 199 patients (550 SHHN) defined as < 1 cm in diameter. The reference standard was established through 1-year stability/MRI for benign or nodule evolution for malignant nodules. Five CNNs underwent supervised training on 150 patients (412 SHHN). The remaining 49 patients (138 SHHN) were used as testing-set to compare performance of 3 radiologists to CNN, measured through ROC AUC analysis of confidence rating assigned to each nodule by the radiologists. Multivariable modeling was used to compensate for radiologist bias from visible findings other than SHHN. In characterizing SHHN as benign or malignant, the radiologists’ mean AUC ROC (0.96) was significantly higher than CNN (0.84, p = 0.0004) but equivalent to CNN adjusted through multivariable modeling for presence of synchronous ≥ 1 cm liver metastases (0.95, p = 0.9). The diagnostic confidence of radiologists and CNN were analyzed. There were significantly lower number of nodules rated with low confidence by CNN (19.6%) and CNN with liver metastatic status (18.1%) than two (38.4%, 44.2%, p < 0.0001) but not a third radiologist (11.1%, p = 0.09). We conclude that in CRC, CNN in combination with liver metastatic status equaled expert radiologists in characterizing SHHN but with better diagnostic confidence.

Overview on subjective similarity of images for content-based medical image retrieval

Computer-aided diagnosis systems for assisting the classification of various diseases have the potential to improve radiologists' diagnostic accuracy and efficiency, as reported in several studies. Conventional systems generally provide the probabilities of disease types in terms of numerical values, a method that may not be efficient for radiologists who are trained by reading a large number of images. Presentation of reference images similar to those of a new case being diagnosed can supplement the probability outputs based on computerized analysis as an intuitive guide, and it can assist radiologists in their diagnosis, reporting, and treatment planning. Many studies on content-based medical image retrievals have been reported on. For retrieval of perceptually similar and diagnostically relevant images, incorporation of perceptual similarity data by radiologists has been suggested. In this paper, studies on image retrieval methods are reviewed with a special focus on quantification, utilization, and the evaluation of subjective similarities between pairs of images.

A fully automatic end-to-end method for content-based image retrieval of CT scans with similar liver lesion annotations

PURPOSE

The goal of medical content-based image retrieval (M-CBIR) is to assist radiologists in the decision-making process by retrieving medical cases similar to a given image. One of the key interests of radiologists is lesions and their annotations, since the patient treatment depends on the lesion diagnosis. Therefore, a key feature of M-CBIR systems is the retrieval of scans with the most similar lesion annotations. To be of value, M-CBIR systems should be fully automatic to handle large case databases.

METHODS

We present a fully automatic end-to-end method for the retrieval of CT scans with similar liver lesion annotations. The input is a database of abdominal CT scans labeled with liver lesions, a query CT scan, and optionally one radiologist-specified lesion annotation of interest. The output is an ordered list of the database CT scans with the most similar liver lesion annotations. The method starts by automatically segmenting the liver in the scan. It then extracts a histogram-based features vector from the segmented region, learns the features' relative importance, and ranks the database scans according to the relative importance measure. The main advantages of our method are that it fully automates the end-to-end querying process, that it uses simple and efficient techniques that are scalable to large datasets, and that it produces quality retrieval results using an unannotated CT scan.

RESULTS

Our experimental results on 9 CT queries on a dataset of 41 volumetric CT scans from the 2014 Image CLEF Liver Annotation Task yield an average retrieval accuracy (Normalized Discounted Cumulative Gain index) of 0.77 and 0.84 without/with annotation, respectively.

CONCLUSIONS

Fully automatic end-to-end retrieval of similar cases based on image information alone, rather that on disease diagnosis, may help radiologists to better diagnose liver lesions.

Application of Machine Learning Algorithms to a Well Defined Clinical Problem: Liver Disease

Liver diseases represent a major health burden worldwide. Machine learning (ML) algorithms have been extensively used to diagnose liver disease. This study accordingly aims to employ various individual and integrated ML algorithms on distinct liver disease datasets for evaluating the diagnostic performances, to integrate dimensionality reduction method with the ML algorithms for analyzing variation in results, to find the best classification model and to analyze the merits and demerits of these algorithms. KNN and PCA-KNN emerged to be the top individual and integrated models. The study also concluded that one specific algorithm can't show best results for all types of datasets and integrated models not always perform better than the individuals. It is observed that no algorithm is perfect and performance of an algorithm totally depends on the dataset type and structure, its number of observations, its dimensions and the decision boundary.

Computer-aided diagnosis program for classifying the risk of hepatocellular carcinoma on MR images following liver imaging reporting and data system (LI-RADS)

PURPOSE

To develop and evaluate a computer-aided diagnosis (CAD) program for liver lesions on magnetic resonance (MR) images for classification of the risk of hepatocellular carcinoma (HCC) following the liver imaging reporting and data system (LI-RADS).

MATERIALS AND METHODS

Liver MR images from 41 patients with hyperenhancing liver lesions categorized as LR 3, 4, and 5 were evaluated by two radiologists. The major LI-RADS features of each index liver lesion were recorded, including size (maximum transverse diameter), presence of hyperenhancement, washout appearance, and capsule appearance. A CAD program was implemented to register MR images at different contrast-enhancement phases, segment liver lesions, extract lesion features, and classify lesions according to LI-RADS. The LI-RADS features quantified by CAD were compared with those assessed by radiologists using the intraclass correlation coefficient (ICC) and receiver operator curve (ROC) analyses. The LI-RADS categorization between CAD and radiologists was evaluated using the weighted Cohen's kappa coefficient.

RESULTS

The mean and standard deviation of the lesion diameters were 21 ± 11 mm (range, 7-70 mm) by radiologists and 22 ± 11 mm (range, 8-72 mm) by CAD (ICC, 0.96-0.97). The area under the curve (AUC) for the washout assessment by CAD was 0.79-0.93 with sensitivity 0.69-0.82 and specificity 0.79-1. The AUC for the capsule assessment by CAD was 0.79-0.9 with sensitivity 0.75-0.9 and specificity 0.82-0.96. The classifications by the radiologists and CAD coincided in 76-83% lesions (k = 0.57-0.71), while the agreements between radiologists were in 78% lesions (k = 0.59).

CONCLUSION

We developed a CAD program for liver lesions on MR images and showed a substantial agreement in the LI-RADS-based classification of the risk of HCCs between the CAD and radiologists.

LEVEL OF EVIDENCE

1 Technical Efficacy: Stage 1 J. Magn. Reson. Imaging 2018;47:710-722.