Chien‐Hung Liao

Fakai Wang, Chi-Tung Cheng, Chien-Wei Peng et al.

Liver cancer has high morbidity and mortality rates in the world. Multi-phase CT is a main medical imaging modality for detecting/identifying and diagnosing liver tumors. Automatically detecting and classifying liver lesions in CT images have the potential to improve the clinical workflow. This task remains challenging due to liver lesions' large variations in size, appearance, image contrast, and the complexities of tumor types or subtypes. In this work, we customize a multi-object labeling tool for multi-phase CT images, which is used to curate a large-scale dataset containing 1,631 patients with four-phase CT images, multi-organ masks, and multi-lesion (six major types of liver lesions confirmed by pathology) masks. We develop a two-stage liver lesion detection pipeline, where the high-sensitivity detecting algorithms in the first stage discover as many lesion proposals as possible, and the lesion-reclassification algorithms in the second stage remove as many false alarms as possible. The multi-sensitivity lesion detection algorithm maximizes the information utilization of the individual probability maps of segmentation, and the lesion-shuffle augmentation effectively explores the texture contrast between lesions and the liver. Independently tested on 331 patient cases, the proposed model achieves high sensitivity and specificity for malignancy classification in the multi-phase contrast-enhanced CT (99.2%, 97.1%, diagnosis setting) and in the noncontrast CT (97.3%, 95.7%, screening setting).

Chi-Tung Cheng, Jinzheng Cai, Wei Teng et al.

Hepatocellular carcinoma (HCC) can be potentially discovered from abdominal computed tomography (CT) studies under varied clinical scenarios, e.g., fully dynamic contrast enhanced (DCE) studies, non-contrast (NC) plus venous phase (VP) abdominal studies, or NC-only studies. We develop a flexible three-dimensional deep algorithm, called hetero-phase volumetric detection (HPVD), that can accept any combination of contrast-phase inputs and with adjustable sensitivity depending on the clinical purpose. We trained HPVD on 771 DCE CT scans to detect HCCs and tested on external 164 positives and 206 controls, respectively. We compare performance against six clinical readers, including two radiologists, two hepato-pancreatico-biliary (HPB) surgeons, and two hepatologists. The area under curve (AUC) of the localization receiver operating characteristic (LROC) for NC-only, NC plus VP, and full DCE CT yielded 0.71, 0.81, 0.89 respectively. At a high sensitivity operating point of 80% on DCE CT, HPVD achieved 97% specificity, which is comparable to measured physician performance. We also demonstrate performance improvements over more typical and less flexible non hetero-phase detectors. Thus, we demonstrate that a single deep learning algorithm can be effectively applied to diverse HCC detection clinical scenarios.

Feng-Yu Liu, Chih-Chi Chen, Shann-Ching Chen et al.

Purpose Automated detection of region of interest (ROI) is a critical step for many medical image applications such as heart ROIs detection in perfusion MRI images, lung boundary detection in chest X-rays, and femoral head detection in pelvic radiographs. Thus, we proposed a practical framework of ROIs detection in medical images, with a case study for hip detection in anteroposterior (AP) pelvic radiographs. Materials and Methods: We conducted a retrospective study which analyzed hip joints seen on 7,399 AP pelvic radiographs from three diverse sources, including 4,290 high resolution radiographs from Chang Gung Memorial Hospital Osteoarthritis, 3,008 low to medium resolution radiographs from Osteoarthritis Initiative, and 101 heterogeneous radiographs from Google image search engine. We presented a deep learning-based ROI detection framework utilizing single-shot multi-box detector (SSD) with ResNet-101 backbone and customized head structure based on the characteristics of the obtained datasets, whose ground truths were labeled by non-medical annotators in a simple graphical interface. Results: Our method achieved average intersection over union (IoU)=0.8115, average confidence=0.9812, and average precision with threshold IoU=0.5 (AP50)=0.9901 in the independent test set, suggesting that the detected hip regions have appropriately covered main features of the hip joints. Conclusion: The proposed approach featured on low-cost labeling, data-driven model design, and heterogeneous data testing. We have demonstrated the feasibility of training a robust hip region detector for AP pelvic radiographs. This practical framework has a promising potential for a wide range of medical image applications.

Yirui Wang, Kang Zheng, Chi-Tung Chang et al.

Exploiting available medical records to train high performance computer-aided diagnosis (CAD) models via the semi-supervised learning (SSL) setting is emerging to tackle the prohibitively high labor costs involved in large-scale medical image annotations. Despite the extensive attentions received on SSL, previous methods failed to 1) account for the low disease prevalence in medical records and 2) utilize the image-level diagnosis indicated from the medical records. Both issues are unique to SSL for CAD models. In this work, we propose a new knowledge distillation method that effectively exploits large-scale image-level labels extracted from the medical records, augmented with limited expert annotated region-level labels, to train a rib and clavicle fracture CAD model for chest X-ray (CXR). Our method leverages the teacher-student model paradigm and features a novel adaptive asymmetric label sharpening (AALS) algorithm to address the label imbalance problem that specially exists in medical domain. Our approach is extensively evaluated on all CXR (N = 65,845) from the trauma registry of anonymous hospital over a period of 9 years (2008-2016), on the most common rib and clavicle fractures. The experiment results demonstrate that our method achieves the state-of-the-art fracture detection performance, i.e., an area under receiver operating characteristic curve (AUROC) of 0.9318 and a free-response receiver operating characteristic (FROC) score of 0.8914 on the rib fractures, significantly outperforming previous approaches by an AUROC gap of 1.63% and an FROC improvement by 3.74%. Consistent performance gains are also observed for clavicle fracture detection.

Xinyu Zhang, Yirui Wang, Chi-Tung Cheng et al.

Object detection methods are widely adopted for computer-aided diagnosis using medical images. Anomalous findings are usually treated as objects that are described by bounding boxes. Yet, many pathological findings, e.g., bone fractures, cannot be clearly defined by bounding boxes, owing to considerable instance, shape and boundary ambiguities. This makes bounding box annotations, and their associated losses, highly ill-suited. In this work, we propose a new bone fracture detection method for X-ray images, based on a labor effective and flexible annotation scheme suitable for abnormal findings with no clear object-level spatial extents or boundaries. Our method employs a simple, intuitive, and informative point-based annotation protocol to mark localized pathology information. To address the uncertainty in the fracture scales annotated via point(s), we convert the annotations into pixel-wise supervision that uses lower and upper bounds with positive, negative, and uncertain regions. A novel Window Loss is subsequently proposed to only penalize the predictions outside of the uncertain regions. Our method has been extensively evaluated on 4410 pelvic X-ray images of unique patients. Experiments demonstrate that our method outperforms previous state-of-the-art image classification and object detection baselines by healthy margins, with an AUROC of 0.983 and FROC score of 89.6%.

Ashwin Raju, Zhanghexuan Ji, Chi Tung Cheng et al.

Mask-based annotation of medical images, especially for 3D data, is a bottleneck in developing reliable machine learning models. Using minimal-labor user interactions (UIs) to guide the annotation is promising, but challenges remain on best harmonizing the mask prediction with the UIs. To address this, we propose the user-guided domain adaptation (UGDA) framework, which uses prediction-based adversarial domain adaptation (PADA) to model the combined distribution of UIs and mask predictions. The UIs are then used as anchors to guide and align the mask prediction. Importantly, UGDA can both learn from unlabelled data and also model the high-level semantic meaning behind different UIs. We test UGDA on annotating pathological livers using a clinically comprehensive dataset of 927 patient studies. Using only extreme-point UIs, we achieve a mean (worst-case) performance of 96.1%(94.9%), compared to 93.0% (87.0%) for deep extreme points (DEXTR). Furthermore, we also show UGDA can retain this state-of-the-art performance even when only seeing a fraction of available UIs, demonstrating an ability for robust and reliable UI-guided segmentation with extremely minimal labor demands.

Jinzheng Cai, Ke Yan, Chi-Tung Cheng et al.

Identifying, measuring and reporting lesions accurately and comprehensively from patient CT scans are important yet time-consuming procedures for physicians. Computer-aided lesion/significant-findings detection techniques are at the core of medical imaging, which remain very challenging due to the tremendously large variability of lesion appearance, location and size distributions in 3D imaging. In this work, we propose a novel deep anchor-free one-stage VULD framework that incorporates (1) P3DC operators to recycle the architectural configurations and pre-trained weights from the off-the-shelf 2D networks, especially ones with large capacities to cope with data variance, and (2) a new SPR method to effectively regress the 3D lesion spatial extents by pinpointing their representative key points on lesion surfaces. Experimental validations are first conducted on the public large-scale NIH DeepLesion dataset where our proposed method delivers new state-of-the-art quantitative performance. We also test VULD on our in-house dataset for liver tumor detection. VULD generalizes well in both large-scale and small-sized tumor datasets in CT imaging.

Haomin Chen, Yirui Wang, Kang Zheng et al.

Visual cues of enforcing bilaterally symmetric anatomies as normal findings are widely used in clinical practice to disambiguate subtle abnormalities from medical images. So far, inadequate research attention has been received on effectively emulating this practice in CAD methods. In this work, we exploit semantic anatomical symmetry or asymmetry analysis in a complex CAD scenario, i.e., anterior pelvic fracture detection in trauma PXRs, where semantically pathological (refer to as fracture) and non-pathological (e.g., pose) asymmetries both occur. Visually subtle yet pathologically critical fracture sites can be missed even by experienced clinicians, when limited diagnosis time is permitted in emergency care. We propose a novel fracture detection framework that builds upon a Siamese network enhanced with a spatial transformer layer to holistically analyze symmetric image features. Image features are spatially formatted to encode bilaterally symmetric anatomies. A new contrastive feature learning component in our Siamese network is designed to optimize the deep image features being more salient corresponding to the underlying semantic asymmetries (caused by pelvic fracture occurrences). Our proposed method have been extensively evaluated on 2,359 PXRs from unique patients (the largest study to-date), and report an area under ROC curve score of 0.9771. This is the highest among state-of-the-art fracture detection methods, with improved clinical indications.

Yuankai Huo, Jinzheng Cai, Chi-Tung Cheng et al.

Non-invasive radiological-based lesion characterization and identification, e.g., to differentiate cancer subtypes, has long been a major aim to enhance oncological diagnosis and treatment procedures. Here we study a specific population of human subjects, with the hope of reducing the need for invasive surgical biopsies of liver cancer patients, which can cause many harmful side-effects. To this end, we propose a fully-automated and multi-stage liver tumor characterization framework designed for dynamic contrast computed tomography (CT). Our system comprises four sequential processes of tumor proposal detection, tumor harvesting, primary tumor site selection, and deep texture-based tumor characterization. Our main contributions are that, (1) we propose a 3D non-isotropic anchor-free detection method for liver lesions; (2) we present and validate spatially adaptivedeep texture (SaDT) learning, which allows for more precise characterization of liver lesions; (3) using a semi-automatic process, we bootstrap off of 200 gold standard annotations to curate another 1001 patients. Experimental evaluations demonstrate that our new data curation strategy, combined with the SaDT deep dynamic texture analysis, can effectively improve the mean F1 scores by >8.6% compared with baselines, in differentiating four major liver lesion types. Our F1 score of (hepatocellular carcinoma versus remaining subclasses) is 0.763, which is higher than reported human observer performance using dynamic CT and comparable to an advanced magnetic resonance imagery protocol. Apart from demonstrating the benefits of our data curation approach and physician-inspired workflow, these results also indicate that analyzing texture features, instead of standard object-based analysis, is a promising strategy for lesion differentiation.

Bo Zhou, Adam P. Harrison, Jiawen Yao et al.

As the demand for more descriptive machine learning models grows within medical imaging, bottlenecks due to data paucity will exacerbate. Thus, collecting enough large-scale data will require automated tools to harvest data/label pairs from messy and real-world datasets, such as hospital PACS. This is the focus of our work, where we present a principled data curation tool to extract multi-phase CT liver studies and identify each scan's phase from a real-world and heterogenous hospital PACS dataset. Emulating a typical deployment scenario, we first obtain a set of noisy labels from our institutional partners that are text mined using simple rules from DICOM tags. We train a deep learning system, using a customized and streamlined 3D SE architecture, to identify non-contrast, arterial, venous, and delay phase dynamic CT liver scans, filtering out anything else, including other types of liver contrast studies. To exploit as much training data as possible, we also introduce an aggregated cross entropy loss that can learn from scans only identified as "contrast". Extensive experiments on a dataset of 43K scans of 7680 patient imaging studies demonstrate that our 3DSE architecture, armed with our aggregated loss, can achieve a mean F1 of 0.977 and can correctly harvest up to 92.7% of studies, which significantly outperforms the text-mined and standard-loss approach, and also outperforms other, and more complex, model architectures.