Computer-aided Detection Scheme Research Articles

Predicting muscle invasion in bladder cancer based on MRI: A comparison of radiomics, and single-task and multi-task deep learning

Background and objectivesRadiomics and deep learning are two popular technologies used to develop computer-aided detection and diagnosis schemes for analysing medical images. This study aimed to compare the effectiveness of radiomics, single-task deep learning (DL) and multi-task DL methods in predicting muscle-invasive bladder cancer (MIBC) status based on T2-weighted imaging (T2WI). MethodsA total of 121 tumours (93 for training, from Centre 1; 28 for testing, from Centre 2) were included. MIBC was confirmed with pathological examination. A radiomics model, a single-task model, and a multi-task model based on T2WI were constructed in the training cohort with five-fold cross-validation, and validation was conducted in the external test cohort. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic performance of each model. DeLong's test and a permutation test were used to compare the performance of the models. ResultsThe area under the ROC curve (AUC) values of the radiomics, single-task and multi-task models in the training cohort were: 0.920, 0.933 and 0.932, respectively; and were 0.844, 0.884 and 0.932, respectively, in the test cohort. The multi-task model achieved better performance in the test cohort than did the other models. No statistically significant differences in AUC values and Kappa coefficients were observed between pairwise models, in either the training or test cohorts. According to the Grad-CAM feature visualization results, the multi-task model focused more on the diseased tissue area in some samples of the test cohort compared with the single-task model. ConclusionsThe T2WI-based radiomics, single-task, and multi-task models all exhibited good diagnostic performance in preoperatively predicting MIBC, in which the multi-task model had the best diagnostic performance. Compared with the radiomics method, our multi-task DL method had the advantage of saving time and effort. Compared with the single-task DL method, our multi-task DL method had the advantage of being more lesion-focused and more reliable for clinical reference.

Optimized hyperbolic tangent function-based contrast-enhanced mammograms for breast mass detection

Breast cancer is a grave concern among women due to its high mortality rate in women as compared to that in men. Mass, an early symptom of breast cancer, is difficult to detect due to its subtle nature. Mammography, an effective and most preferred screening technique, generally uses low-contrast images where identification of some of the mass lesions from surrounding normal tissues is a difficult task even for skilled radiologists. Therefore, to alleviate the issue, this paper introduces an effective computer-aided detection scheme based on a novel contrast enhancement scheme for mammograms to automate the localization procedure of mass cases. Hyperbolic tangent function, a simple yet effective method, is introduced as an enhancement transfer function whose adjustable parameter is optimized by the Tunicate swarm algorithm, a nature-inspired optimization algorithm, via fitness function. To minimize the false positives generated after the detection, the median robust extended local binary pattern, a texture-based descriptor, is introduced, which possesses the ability to capture both micro- and macro-structure information from an image patch. The analysis includes four classifiers: Fisher linear discriminant analysis, K-nearest neighbor, support vector machine, and an ensemble classifier in the feature-based classification for false positive reduction (FPR). The proposed approach of automatic detection of masses when verified using two standard databases, mini-MIAS and Digital Database for Screening Mammography, comprised 68 and 550 mammograms, respectively, achieved sensitivities of 95.3% and 94.1% with 0.36 and 0.40 false positives per image after false positive reduction.

Applying artificial intelligence technology to assist with breast cancer diagnosis and prognosis prediction

Breast cancer remains the most diagnosed cancer in women. Advances in medical imaging modalities and technologies have greatly aided in the early detection of breast cancer and the decline of patient mortality rates. However, reading and interpreting breast images remains difficult due to the high heterogeneity of breast tumors and fibro-glandular tissue, which results in lower cancer detection sensitivity and specificity and large inter-reader variability. In order to help overcome these clinical challenges, researchers have made great efforts to develop computer-aided detection and/or diagnosis (CAD) schemes of breast images to provide radiologists with decision-making support tools. Recent rapid advances in high throughput data analysis methods and artificial intelligence (AI) technologies, particularly radiomics and deep learning techniques, have led to an exponential increase in the development of new AI-based models of breast images that cover a broad range of application topics. In this review paper, we focus on reviewing recent advances in better understanding the association between radiomics features and tumor microenvironment and the progress in developing new AI-based quantitative image feature analysis models in three realms of breast cancer: predicting breast cancer risk, the likelihood of tumor malignancy, and tumor response to treatment. The outlook and three major challenges of applying new AI-based models of breast images to clinical practice are also discussed. Through this review we conclude that although developing new AI-based models of breast images has achieved significant progress and promising results, several obstacles to applying these new AI-based models to clinical practice remain. Therefore, more research effort is needed in future studies.

A Comparison of Computer-Aided Diagnosis Schemes Optimized Using Radiomics and Deep Transfer Learning Methods.

Objective: Radiomics and deep transfer learning are two popular technologies used to develop computer-aided detection and diagnosis (CAD) schemes of medical images. This study aims to investigate and to compare the advantages and the potential limitations of applying these two technologies in developing CAD schemes. Methods: A relatively large and diverse retrospective dataset including 3000 digital mammograms was assembled in which 1496 images depicted malignant lesions and 1504 images depicted benign lesions. Two CAD schemes were developed to classify breast lesions. The first scheme was developed using four steps namely, applying an adaptive multi-layer topographic region growing algorithm to segment lesions, computing initial radiomics features, applying a principal component algorithm to generate an optimal feature vector, and building a support vector machine classifier. The second CAD scheme was built based on a pre-trained residual net architecture (ResNet50) as a transfer learning model to classify breast lesions. Both CAD schemes were trained and tested using a 10-fold cross-validation method. Several score fusion methods were also investigated to classify breast lesions. CAD performances were evaluated and compared by the areas under the ROC curve (AUC). Results: The ResNet50 model-based CAD scheme yielded AUC = 0.85 ± 0.02, which was significantly higher than the radiomics feature-based CAD scheme with AUC = 0.77 ± 0.02 (p < 0.01). Additionally, the fusion of classification scores generated by the two CAD schemes did not further improve classification performance. Conclusion: This study demonstrates that using deep transfer learning is more efficient to develop CAD schemes and it enables a higher lesion classification performance than CAD schemes developed using radiomics-based technology.

Ensemble of weighted deep concatenated features for the skin disease classification model using modified long short term memory

Skin diseases are considered to be a common disease in human, which have many invisible dangers that may reduce the self-confidence and causes certain psychological depression and in-depth, these skin diseases may also results in skin cancer. These skin diseases needs to be diagnosed with the medical experts but it requires high-level instruments for diagnosing as they suffer from the visual resolution problem while analyzing the skin disease images. Hence, it is important to implement a computer-aided detection scheme for automatically diagnosing the skin disorder. Hence, this work plans to implement an effective skin disease classification method with the help of novel deep learning methodology. Initially, the dataset is gathered and pre-processed by the contrast enhancement technique through “histogram equalization”. After pre-processing, the segmentation of the images is done by the Fuzzy C Means segmentation (FCM). Further the segmented images assigned as a input for the deep feature extraction using Resnet50, VGG16, and Deeplabv3. The features are attained from the final layer of these three techniques and are concatenated. These concatenated features are provided to the feature transformation phase through the weighted feature extraction, which is performed by Hybrid Squirrel Butterfly Search Optimization (HSBSO). The transformed features are given to Modified Long Short Term Memory (MLSTM), where the architecture optimization is done by the same HSBSO for producing the final classified output. The analysis results confirms that the better effectiveness of the introduced method when observing the accuracy of the implemented skin disease classification than the conventional approaches.

Developing new quantitative CT image markers to predict prognosis of acute ischemic stroke patients.

Endovascular mechanical thrombectomy (EMT) is an effective method to treat acute ischemic stroke (AIS) patients due to large vessel occlusion (LVO). However, stratifying AIS patients who can and cannot benefit from EMT remains a clinical challenge. To develop a new quantitative image marker computed from pre-intervention computed tomography perfusion (CTP) images and evaluate its feasibility to predict clinical outcome among AIS patients undergoing EMT after diagnosis of LVO. A retrospective dataset of 31 AIS patients with pre-intervention CTP images is assembled. A computer-aided detection (CAD) scheme is developed to pre-process CTP images of different scanning series for each study case, perform image segmentation, quantify contrast-enhanced blood volumes in bilateral cerebral hemispheres, and compute features related to asymmetrical cerebral blood flow patterns based on the cumulative cerebral blood flow curves of two hemispheres. Next, image markers based on a single optimal feature and machine learning (ML) models fused with multi-features are developed and tested to classify AIS cases into two classes of good and poor prognosis based on the Modified Rankin Scale. Performance of image markers is evaluated using the area under the ROC curve (AUC) and accuracy computed from the confusion matrix. The ML model using the neuroimaging features computed from the slopes of the subtracted cumulative blood flow curves between two cerebral hemispheres yields classification performance of AUC = 0.878±0.077 with an overall accuracy of 90.3%. This study demonstrates feasibility of developing a new quantitative imaging method and marker to predict AIS patients' prognosis in the hyperacute stage, which can help clinicians optimally treat and manage AIS patients.

Applying Quantitative Radiographic Image Markers to Predict Clinical Complications After Aneurysmal Subarachnoid Hemorrhage: A Pilot Study.

Accurately predicting clinical outcome of aneurysmal subarachnoid hemorrhage (aSAH) patients is difficult. The purpose of this study was to develop and test a new fully-automated computer-aided detection (CAD) scheme of brain computed tomography (CT) images to predict prognosis of aSAH patients. A retrospective dataset of 59 aSAH patients was assembled. Each patient had 2 sets of CT images acquired at admission and prior-to-discharge. CAD scheme was applied to segment intracranial brain regions into four subregions, namely, cerebrospinal fluid (CSF), white matter (WM), gray matter (GM), and leaked extraparenchymal blood (EPB), respectively. CAD then detects sulci and computes 9 image features related to 5 volumes of the segmented sulci, EPB, CSF, WM, and GM and 4 volumetrical ratios to sulci. Subsequently, applying a leave-one-case-out cross-validation method embedded with a principal component analysis (PCA) algorithm to generate optimal feature vector, 16 support vector machine (SVM) models were built using CT images acquired either at admission or prior-to-discharge to predict each of eight clinically relevant parameters commonly used to assess patients' prognosis. Finally, a receiver operating characteristics (ROC) method was used to evaluate SVM model performance. Areas under ROC curves of 16 SVM models range from 0.62 ± 0.07 to 0.86 ± 0.07. In general, SVM models trained using CT images acquired at admission yielded higher accuracy to predict short-term clinical outcomes, while SVM models trained using CT images acquired prior-to-discharge demonstrated higher accuracy in predicting long-term clinical outcomes. This study demonstrates feasibility to predict prognosis of aSAH patients using new quantitative image markers generated by SVM models.

Applying a random projection algorithm to optimize machine learning model for predicting peritoneal metastasis in gastric cancer patients using CT images

Background and ObjectiveNon-invasively predicting the risk of cancer metastasis before surgery can play an essential role in determining which patients can benefit from neoadjuvant chemotherapy. This study aims to investigate and test the advantages of applying a random projection algorithm to develop and optimize a radiomics-based machine learning model to predict peritoneal metastasis in gastric cancer patients using a small and imbalanced computed tomography (CT) image dataset. MethodsA retrospective dataset involving CT images acquired from 159 patients is assembled, including 121 and 38 cases with and without peritoneal metastasis, respectively. A computer-aided detection scheme is first applied to segment primary gastric tumor volumes and initially compute 315 image features. Then, five gradients boosting machine (GBM) models embedded with five feature selection methods (including random projection algorithm, principal component analysis, least absolute shrinkage, and selection operator, maximum relevance and minimum redundancy, and recursive feature elimination) along with a synthetic minority oversampling technique, are built to predict the risk of peritoneal metastasis. All GBM models are trained and tested using a leave-one-case-out cross-validation method. ResultsResults show that the GBM model embedded with a random projection algorithm yields a significantly higher prediction accuracy (71.2%) than the other four GBM models (p<0.05). The precision, sensitivity, and specificity of this optimal GBM model are 65.78%, 43.10%, and 87.12%, respectively. ConclusionsThis study demonstrates that CT images of the primary gastric tumors contain discriminatory information to predict the risk of peritoneal metastasis, and a random projection algorithm is a promising method to generate optimal feature vector, improving the performance of machine learning based prediction models.

The detection of lung cancer using massive artificial neural network based on soft tissue technique

BackgroundA proposed computer aided detection (CAD) scheme faces major issues during subtle nodule recognition. However, radiologists have not noticed subtle nodules in beginning stage of lung cancer while a proposed CAD scheme recognizes non subtle nodules using x-ray images.MethodSuch an issue has been resolved by creating MANN (Massive Artificial Neural Network) based soft tissue technique from the lung segmented x-ray image. A soft tissue image recognizes nodule candidate for feature extortion and classification. X-ray images are downloaded using Japanese society of radiological technology (JSRT) image set. This image set includes 233 images (140 nodule x-ray images and 93 normal x-ray images). A mean size for a nodule is 17.8 mm and it is validated with computed tomography (CT) image. Thirty percent (42/140) abnormal represents subtle nodules and it is split into five stages (tremendously subtle, very subtle, subtle, observable, relatively observable) by radiologists.ResultA proposed CAD scheme without soft tissue technique attained 66.42% (93/140) sensitivity and 66.76% accuracy having 2.5 false positives per image. Utilizing soft tissue technique, many nodules superimposed by ribs as well as clavicles have identified (sensitivity is 72.85% (102/140) and accuracy is 72.96% at one false positive rate).ConclusionIn particular, a proposed CAD system determine sensitivity and accuracy in support of subtle nodules (sensitivity is 14/42 = 33.33% and accuracy is 33.66%) is statistically higher than CAD (sensitivity is 13/42 = 30.95% and accuracy is 30.97%) scheme without soft tissue technique. A proposed CAD scheme attained tremendously minimum false positive rate and it is a promising technique in support of cancerous recognition due to improved sensitivity and specificity.

Detection of pulmonary nodules based on a multiscale feature 3D U-Net convolutional neural network of transfer learning.

A new computer-aided detection scheme is proposed, the 3D U-Net convolutional neural network, based on multiscale features of transfer learning to automatically detect pulmonary nodules from the thoracic region containing background and noise. The test results can be used as reference information for doctors to assist in the detection of early lung cancer. The proposed scheme is composed of three major steps: First, the pulmonary parenchyma area is segmented by various methods. Then, the 3D U-Net convolutional neural network model with a multiscale feature structure is built. The network model structure is subsequently fine-tuned by the transfer learning method based on weight, and the optimal parameters are selected in the network model. Finally, datasets are extracted to train the fine-tuned 3D U-Net network model to detect pulmonary nodules. The five-fold cross-validation method is used to obtain the experimental results for the LUNA16 and TIANCHI17 datasets. The experimental results show that the scheme not only has obvious advantages in the detection of medium and large-sized nodules but also has an accuracy rate of more than 70% for the detection of small-sized nodules. The scheme provides automatic and accurate detection of pulmonary nodules that reduces the overfitting rate and training time and improves the efficiency of the algorithm. It can assist doctors in the diagnosis of lung cancer and can be extended to other medical image detection and recognition fields.

Automatically discriminating and localizing COVID-19 from community-acquired pneumonia on chest X-rays

The COVID-19 outbreak continues to threaten the health and life of people worldwide. It is an immediate priority to develop and test a computer-aided detection (CAD) scheme based on deep learning (DL) to automatically localize and differentiate COVID-19 from community-acquired pneumonia (CAP) on chest X-rays. Therefore, this study aims to develop and test an efficient and accurate deep learning scheme that assists radiologists in automatically recognizing and localizing COVID-19. A retrospective chest X-ray image dataset was collected from open image data and the Xiangya Hospital, which was divided into a training group and a testing group. The proposed CAD framework is composed of two steps with DLs: the Discrimination-DL and the Localization-DL. The first DL was developed to extract lung features from chest X-ray radiographs for COVID-19 discrimination and trained using 3548 chest X-ray radiographs. The second DL was trained with 406-pixel patches and applied to the recognized X-ray radiographs to localize and assign them into the left lung, right lung or bipulmonary. X-ray radiographs of CAP and healthy controls were enrolled to evaluate the robustness of the model. Compared to the radiologists’ discrimination and localization results, the accuracy of COVID-19 discrimination using the Discrimination-DL yielded 98.71%, while the accuracy of localization using the Localization-DL was 93.03%. This work represents the feasibility of using a novel deep learning-based CAD scheme to efficiently and accurately distinguish COVID-19 from CAP and detect localization with high accuracy and agreement with radiologists.

Deep learning-based CAD schemes for the detection and classification of lung nodules from CT images: A survey.

Lung cancer is the most common cancer in the world. Computed tomography (CT) is the standard medical imaging modality for early lung nodule detection and diagnosis that improves patient's survival rate. Recently, deep learning algorithms, especially convolutional neural networks (CNNs), have become a preferred methodology for developing computer-aided detection and diagnosis (CAD) schemes of lung CT images. Several CNN-based research projects have been initiated to design robust and efficient CAD schemes for the detection and classification of lung nodules. This paper reviews the recent works in this area and gives an insight into technical progress. First, a brief overview of CNN models and their basic structures is presented in this investigation. Then, we provide an analytic comparison of the existing approaches to discover recent trend and upcoming challenges. We also introduce an objective description of both handcrafted and deep learning features, as well as the types of nodules, the medical imaging modalities, the widely used databases, and related works in the last three years. The articles presented in this work were selected from various databases. About 57% of reviewed articles published in the last year. Our analysis reveals that several methods achieved promising performance with high sensitivity rates ranging from 66% to 100% under the false-positive rates ranging from 1 to 15 per CT scan. It can be noted that CNN models have contributed to the accurate detection and early diagnosis of lung nodules. From the critical discussion and an outline for prospective directions, this survey provide researchers valuable information to master the deep learning concepts and to deepen their knowledge of the trend and latest techniques in developing CAD schemes of lung CT images.

A Study on Tuberculosis Classification in Chest X-ray Using Deep Residual Attention Networks.

The introduction of deep learning techniques for the computer-aided detection scheme has shed a light for real incorporation into the clinical workflow. In this work, we focus on the effect of attention in deep neural networks on the classification of tuberculosis x-ray images. We propose a Convolutional Block Attention Module (CBAM), a simple but effective attention module for feed-forward convolutional neural networks. Given an intermediate feature map, our module infers attention maps and multiplied it to the input feature map for adaptive feature refinement. It achieves high precision and recalls while localizing objects with its attention. We validate the performance of our approach on a standard-compliant data set, including a dataset of 4990 x-ray chest radiographs from three hospitals and show that our performance is better than the models used in previous work.

Pulmonary nodule detection on chest radiographs using balanced convolutional neural network and classic candidate detection.

Computer-aided detection (CADe) systems play a crucial role in pulmonary nodule detection via chest radiographs (CXRs). A two-stage CADe scheme usually includes nodule candidate detection and false positive reduction. A pure deep learning model, such as faster region convolutional neural network (faster R-CNN), has been successfully applied for nodule candidate detection via computed tomography (CT). The model is yet to achieve a satisfactory performance in CXR, because the size of the CXR is relatively large and the nodule in CXR has been obscured by structures such as ribs. In contrast, the CNN has proved effective for false positive reduction compared to the shallow method. In this paper, we developed a CADe scheme using the balanced CNN with classic candidate detection. First, the scheme applied a multi-segment active shape model to accurately segment pulmonary parenchyma. The grayscale morphological enhancement technique was then used to improve the conspicuity of the nodule structure. Based on the nodule enhancement image, 200 nodule candidates were selected and a region of interest (ROI) was cropped for each. Nodules in CXR exhibit a large variation in density, and rib crossing and vessel tissue usually present similar features to the nodule. Compared to the original ROI image, the nodule enhancement ROI image has potential discriminative features from false positive reduction. In this study, the nodule enhancement ROI image, corresponding segmentation result, and original ROI image were encoded into a red-green-blue (RGB) color image instead of the duplicated original ROI image as input of the CNN (GoogLeNet) for false positive reduction. With the Japanese Society of Radiological Technology database, the CADe scheme achieved high performance of the published literatures (a sensitivity of 91.4 % and 97.1 %, with 2.0 false positives per image (FPs/image) and 5.0 FPs/image, respectively) for nodule cases.

Region growing algorithm combined with morphology and skeleton analysis for segmenting airway tree in CT images.

Automatic segmentation of pulmonary airway tree is a challenging task in many clinical applications, including developing computer-aided detection and diagnosis schemes of lung diseases. To segment the pulmonary airway tree from the computed tomography (CT) chest images using a novel automatic method proposed in this study. This method combines a two-pass region growing algorithm with gray-scale morphological reconstruction and leakage elimination. The first-pass region growing is implemented to obtain a rough airway tree. The second-pass region growing and gray-scale morphological reconstruction are used to detect the distal airways. Finally, leakage detection is performed to remove leakage and refine the airway tree. Our methods were compared with the gold standards. Forty-five clinical CT lung image scan cases were used in the experiments. Statistics on tree division order, branch number, and airway length were adopted for evaluation. The proposed method detected up to 12 generations of bronchi. On average, 148.85 branches were extracted with a false positive rate of 0.75%. The results show that our method is accurate for pulmonary airway tree segmentation. The strategy of separating the leakage detection from the segmenting process is feasible and promising for ensuring a high branch detected rate with a low leakage volume.

Multi-Scale deep learning framework for cochlea localization, segmentation and analysis on clinical ultra-high-resolution CT images

Background and objectivePerforming patient-specific, pre-operative cochlea CT-based measurements could be helpful to positively affect the outcome of cochlear surgery in terms of intracochlear trauma and loss of residual hearing. Therefore, we propose a method to automatically segment and measure the human cochlea in clinical ultra-high-resolution (UHR) CT images, and investigate differences in cochlea size for personalized implant planning. Methods123 temporal bone CT scans were acquired with two UHR-CT scanners, and used to develop and validate a deep learning-based system for automated cochlea segmentation and measurement. The segmentation algorithm is composed of two major steps (detection and pixel-wise classification) in cascade, and aims at combining the results of a multi-scale computer-aided detection scheme with a U-Net-like architecture for pixelwise classification. The segmentation results were used as an input to the measurement algorithm, which provides automatic cochlear measurements (volume, basal diameter, and cochlear duct length (CDL)) through the combined use of convolutional neural networks and thinning algorithms. Automatic segmentation was validated against manual annotation, by the means of Dice similarity, Boundary-F1 (BF) score, and maximum and average Hausdorff distances, while measurement errors were calculated between the automatic results and the corresponding manually obtained ground truth on a per-patient basis. Finally, the developed system was used to investigate the differences in cochlea size within our patient cohort, to relate the measurement errors to the actual variation in cochlear size across different patients. ResultsAutomatic segmentation resulted in a Dice of 0.90 ± 0.03, BF score of 0.95 ± 0.03, and maximum and average Hausdorff distance of 3.05 ± 0.39 and 0.32 ± 0.07 against manual annotation. Automatic cochlear measurements resulted in errors of 8.4% (volume), 5.5% (CDL), 7.8% (basal diameter). The cochlea size varied broadly, ranging between 0.10 and 0.28 ml (volume), 1.3 and 2.5 mm (basal diameter), and 27.7 and 40.1 mm (CDL). ConclusionsThe proposed algorithm could successfully segment and analyze the cochlea on UHR-CT images, resulting in accurate measurements of cochlear anatomy. Given the wide variation in cochlear size found in our patient cohort, it may find application as a pre-operative tool in cochlear implant surgery, potentially helping elaborate personalized treatment strategies based on patient-specific, image-based anatomical measurements.

Multiple Linear Discriminant Models for Extracting Salient Characteristic Patterns in Capsule Endoscopy Images for Multi-Disease Detection.

Background: Computer-aided disease detection schemes from wireless capsule endoscopy (WCE) videos have received great attention by the researchers for reducing physicians’ burden due to the time-consuming and risky manual review process. While single disease classification schemes are greatly dealt by the researchers in the past, developing a unified scheme which is capable of detecting multiple gastrointestinal (GI) diseases is very challenging due to the highly irregular behavior of diseased images in terms of color patterns. Method: In this paper, a computer-aided method is developed to detect multiple GI diseases from WCE videos utilizing linear discriminant analysis (LDA) based region of interest (ROI) separation scheme followed by a probabilistic model fitting approach. Commonly in training phase, as pixel-labeled images are available in small number, only the image-level annotations are used for detecting diseases in WCE images, whereas pixel-level knowledge, although a major source for learning the disease characteristics, is left unused. In view of learning the characteristic disease patterns from pixel-labeled images, a set of LDA models are trained which are later used to extract the salient ROI from WCE images both in training and testing stages. The intensity patterns of ROI are then modeled by a suitable probability distribution and the fitted parameters of the distribution are utilized as features in a supervised cascaded classification scheme. Results: For the purpose of validation of the proposed multi-disease detection scheme, a set of pixel-labeled images of bleeding, ulcer and tumor are used to extract the LDA models and then, a large WCE dataset is used for training and testing. A high level of accuracy is achieved even with a small number of pixel-labeled images. Conclusion: Therefore, the proposed scheme is expected to help physicians in reviewing a large number of WCE images to diagnose different GI diseases.

A threshold-based method to predict thyroid nodules on scintigraphy scans

Nuclear Medicine imaging is an important modality to follow up abnormalities of thyroid function tests and to uncover and characterize thyroid nodules either de novo or as previously seen on other imaging modalities, namely ultrasound. In general, the hypofunctioning ‘cold’ nodules pose a higher malignancy potential than hyperfunctioning ‘hot’ nodules, for which the risk is <1%. Hot nodules are detected by the radiologist as a region of focal increased radiotracer uptake, which appears as a density of pixels that is higher than surrounding normal thyroid parenchyma. Similarly, cold nodules show decreased density of pixels, corresponding to their decreased uptake of radiotracer, and are photopenic. Partly because Nuclear Medicine images have poor resolution, these density variations can sometimes be subtle, and a second reader computer-aided detection (CAD) scheme that can highlight hot/cold nodules has the potential to reduce false negatives by bringing the radiologists’ attention to the occasional overlooked nodules. Our approach subdivides thyroid images into small regions and employs a set of pixel density cutoffs, marking regions that fulfill density criteria. Thresholding is a fundamental tool in image processing. In nuclear medicine, scroll bars to adjust standardized uptake value cutoffs are already in wide commercial use in PET/CT display systems. A similar system could be used for planar thyroid images, whereby the user varies threshold and highlights suspect regions after an initial reader survey of the images. We hypothesized that a thresholding approach would accurately detect both hot and cold thyroid nodules relative to expert readers. Analyzing 22 nodules, half of them hot and the other half cold, we found good agreement between highlighted candidate nodules and the consensus selections of two expert readers, with nonzero overlap between expert and CAD selections in all cases.

Developing global image feature analysis models to predict cancer risk and prognosis

In order to develop precision or personalized medicine, identifying new quantitative imaging markers and building machine learning models to predict cancer risk and prognosis has been attracting broad research interest recently. Most of these research approaches use the similar concepts of the conventional computer-aided detection schemes of medical images, which include steps in detecting and segmenting suspicious regions or tumors, followed by training machine learning models based on the fusion of multiple image features computed from the segmented regions or tumors. However, due to the heterogeneity and boundary fuzziness of the suspicious regions or tumors, segmenting subtle regions is often difficult and unreliable. Additionally, ignoring global and/or background parenchymal tissue characteristics may also be a limitation of the conventional approaches. In our recent studies, we investigated the feasibility of developing new computer-aided schemes implemented with the machine learning models that are trained by global image features to predict cancer risk and prognosis. We trained and tested several models using images obtained from full-field digital mammography, magnetic resonance imaging, and computed tomography of breast, lung, and ovarian cancers. Study results showed that many of these new models yielded higher performance than other approaches used in current clinical practice. Furthermore, the computed global image features also contain complementary information from the features computed from the segmented regions or tumors in predicting cancer prognosis. Therefore, the global image features can be used alone to develop new case-based prediction models or can be added to current tumor-based models to increase their discriminatory power.

Multi-resolution convolutional networks for chest X-ray radiograph based lung nodule detection.

Lung cancer is the leading cause of cancer death worldwide. Early detection of lung cancer is helpful to provide the best possible clinical treatment for patients. Due to the limited number of radiologist and the huge number of chest x-ray radiographs (CXR) available for observation, a computer-aided detection scheme should be developed to assist radiologists in decision-making. While deep learning showed state-of-the-art performance in several computer vision applications, it has not been used for lung nodule detection on CXR. In this paper, a deep learning-based lung nodule detection method was proposed. We employed patch-based multi-resolution convolutional networks to extract the features and employed four different fusion methods for classification. The proposed method shows much better performance and is much more robust than those previously reported researches. For publicly available Japanese Society of Radiological Technology (JSRT) database, more than 99% of lung nodules can be detected when the false positives per image (FPs/image) was 0.2. The FAUC and R-CPM of the proposed method were 0.982 and 0.987, respectively. The proposed approach has the potential of applications in clinical practice.