Intelligent Diagnosis of Thyroid Ultrasound Imaging Using an Ensemble of Deep Learning Methods.

Background and Objectives: At present, thyroid disorders have a great incidence in the worldwide population, so the development of alternative methods for improving the diagnosis process is necessary. Materials and Methods: For this purpose, we developed an ensemble method that fused two deep learning models, one based on convolutional neural network and the other based on transfer learning. For the first model, called 5-CNN, we developed an efficient end-to-end trained model with five convolutional layers, while for the second model, the pre-trained VGG-19 architecture was repurposed, optimized and trained. We trained and validated our models using a dataset of ultrasound images consisting of four types of thyroidal images: autoimmune, nodular, micro-nodular, and normal. Results: Excellent results were obtained by the ensemble CNN-VGG method, which outperformed the 5-CNN and VGG-19 models: 97.35% for the overall test accuracy with an overall specificity of 98.43%, sensitivity of 95.75%, positive and negative predictive value of 95.41%, and 98.05%. The micro average areas under each receiver operating characteristic curves was 0.96. The results were also validated by two physicians: an endocrinologist and a pediatrician. Conclusions: We proposed a new deep learning study for classifying ultrasound thyroidal images to assist physicians in the diagnosis process.

Feasibility of a lung airway navigation system using fiber-Bragg shape sensing and artificial intelligence for early diagnosis of lung cancer.

Currently early diagnosis of malignant lesions at the periphery of lung parenchyma requires guidance of the biopsy needle catheter from the bronchoscope into the smaller peripheral airways via harmful X-ray radiation. Previously, we developed an image-guided system, iMTECH which uses electromagnetic tracking and although it increases the precision of biopsy collection and minimizes the use of harmful X-ray radiation during the interventional procedures, it only traces the tip of the biopsy catheter leaving the remaining catheter untraceable in real time and therefore increasing image registration error. To address this issue, we developed a shape sensing guidance system containing a fiber-Bragg grating (FBG) catheter and an artificial intelligence (AI) software, AIrShape to track and guide the entire biopsy instrument inside the lung airways, without radiation or electromagnetic navigation. We used a FBG fiber with one central and three peripheral cores positioned at 120° from each other, an array of 25 draw tower gratings with 1cm/3nm spacing, 2 mm grating length, Ormocer-T coating, and a total outer diameter of 0.2 mm. The FBG fiber was placed in the working channel of a custom made three-lumen catheter with a tip bending mechanism (FBG catheter). The AIrShape software determines the position of the FBG catheter by superimposing its position to the lung airway center lines using an AI algorithm. The feasibility of the FBG system was tested in an anatomically accurate lung airway model and validated visually and with the iMTECH platform. The results prove a viable shape-sensing hardware and software navigation solution for flexible medical instruments to reach the peripheral airways. During future studies, the feasibility of FBG catheter will be tested in pre-clinical animal models.

Deep Learning Algorithm for the Confirmation of Mucosal Healing in Crohn's Disease, Based on Confocal Laser Endomicroscopy Images.

BACKGROUND AND AIMS: Mucosal healing (MH) is associated with a stable course of Crohn's disease (CD) which can be assessed by confocal laser endomicroscopy (CLE). To minimize the operator's errors and automate assessment of CLE images, we used a deep learning (DL) model for image analysis. We hypothesized that DL combined with convolutional neural networks (CNNs) and long short-term memory (LSTM) can distinguish between normal and inflamed colonic mucosa from CLE images. METHODS: The study included 54 patients, 32 with known active CD, and 22 control patients (18 CD patients with MH and four normal mucosa patients with no history of inflammatory bowel diseases). We designed and trained a deep convolutional neural network to detect active CD using 6,205 endomicroscopy images classified as active CD inflammation (3,672 images) and control mucosal healing or no inflammation (2,533 images). CLE imaging was performed on four colorectal areas and the terminal ileum. Gold standard was represented by the histopathological evaluation. The dataset was randomly split in two distinct training and testing datasets: 80% data from each patient were used for training and the remaining 20% for testing. The training dataset consists of 2,892 images with inflammation and 2,189 control images. The testing dataset consists of 780 images with inflammation and 344 control images of the colon. We used a CNN-LSTM model with four convolution layers and one LSTM layer for automatic detection of MH and CD diagnosis from CLE images. RESULTS: CLE investigation reveals normal colonic mucosa with round crypts and inflamed mucosa with irregular crypts and tortuous and dilated blood vessels. Our method obtained a 95.3% test accuracy with a specificity of 92.78% and a sensitivity of 94.6%, with an area under each receiver operating characteristic curves of 0.98. CONCLUSIONS: Using machine learning algorithms on CLE images can successfully differentiate between inflammation and normal ileocolonic mucosa and can be used as a computer aided diagnosis for CD. Future clinical studies with a larger patient spectrum will validate our results and improve the CNN-SSTM model.

Assessment of Deep Learning Methods for Differentiating Autoimmune Disorders in Ultrasound Images.

At present, deep learning becomes an important tool in medical image analysis, with good performance in diagnosing, pattern detection, and segmentation. Ultrasound imaging offers an easy and rapid method to detect and diagnose thyroid disorders. With the help of a computer-aided diagnosis (CAD) system based on deep learning, we have the possibility of real-time and non-invasive diagnosing of thyroidal US images. This paper proposed a study based on deep learning with transfer learning for differentiating the thyroidal ultrasound images using image pixels and diagnosis labels as inputs. We trained, assessed, and compared two pre-trained models (VGG-19 and Inception v3) using a dataset of ultrasound images consisting of 2 types of thyroid ultrasound images: autoimmune and normal. The training dataset consisted of 615 thyroid ultrasound images, from which 415 images were diagnosed as autoimmune, and 200 images as normal. The models were assessed using a dataset of 120 images, from which 80 images were diagnosed as autoimmune, and 40 images diagnosed as normal. The two deep learning models obtained very good results, as follows: the pre-trained VGG-19 model obtained 98.60% for the overall test accuracy with an overall specificity of 98.94% and overall sensitivity of 97.97%, while the Inception v3 model obtained 96.4% for the overall test accuracy with an overall specificity of 95.58% and overall sensitivity of 95.58.

Transfer learning with pre-trained deep convolutional neural networks for the automatic assessment of liver steatosis in ultrasound images.

AIM: In this paper we proposed different architectures of convolutional neural network (CNN) to classify fatty liver disease in images using only pixels and diagnosis labels as input. We trained and validated our models using a dataset of 629 images consisting of 2 types of liver images, normal and liver steatosis. MATERIAL AND METHODS: We assessed two pre-trained models of convolutional neural networks, Inception-v3 and VGG-16 using fine-tuning. Both models were pre-trained on ImageNet dataset to extract features from B-mode ultrasound liver images. The results obtained through these methods were compared for selecting the predictive model with the best performance metrics. We trained the two models using a dataset of 262 images of liver steatosis and 234 images of normal liver. We assessed the models using a dataset of 70 liver steatosis im-ages and 63 normal liver images. RESULTS: The proposed model that used Inception v3 obtained a 93.23% test accuracy with a sensitivity of 89.9%% and a precision of 96.6%, and areas under each receiver operating characteristic curves (ROC AUC) of 0.93. The other proposed model that used VGG-16, obtained a 90.77% test accuracy with a sensitivity of 88.9% and a precision of 92.85%, and areas under each receiver operating characteristic curves (ROC AUC) of 0.91. CONCLUSION: The deep learning algorithms that we proposed to detect steatosis and classify the images in normal and fatty liver images, yields an excellent test performance of over 90%. However, future larger studies are required in order to establish how these algorithms can be implemented in a clinical setting.

Real-time computer-aided diagnosis of focal pancreatic masses from endoscopic ultrasound imaging based on a hybrid convolutional and long short-term memory neural network model.

Differential diagnosis of focal pancreatic masses is based on endoscopic ultrasound (EUS) guided fine needle aspiration biopsy (EUS-FNA/FNB). Several imaging techniques (i.e. gray-scale, color Doppler, contrast-enhancement and elastography) are used for differential diagnosis. However, diagnosis remains highly operator dependent. To address this problem, machine learning algorithms (MLA) can generate an automatic computer-aided diagnosis (CAD) by analyzing a large number of clinical images in real-time. We aimed to develop a MLA to characterize focal pancreatic masses during the EUS procedure. The study included 65 patients with focal pancreatic masses, with 20 EUS images selected from each patient (grayscale, color Doppler, arterial and venous phase contrast-enhancement and elastography). Images were classified based on cytopathology exam as: chronic pseudotumoral pancreatitis (CPP), neuroendocrine tumor (PNET) and ductal adenocarcinoma (PDAC). The MLA is based on a deep learning method which combines convolutional (CNN) and long short-term memory (LSTM) neural networks. 2688 images were used for training and 672 images for testing the deep learning models. The CNN was developed to identify the discriminative features of images, while a LSTM neural network was used to extract the dependencies between images. The model predicted the clinical diagnosis with an area under curve index of 0.98 and an overall accuracy of 98.26%. The negative (NPV) and positive (PPV) predictive values and the corresponding 95% confidential intervals (CI) are 96.7%, [94.5, 98.9] and 98.1%, [96.81, 99.4] for PDAC, 96.5%, [94.1, 98.8], and 99.7%, [99.3, 100] for CPP, and 98.9%, [97.5, 100] and 98.3%, [97.1, 99.4] for PNET. Following further validation on a independent test cohort, this method could become an efficient CAD tool to differentiate focal pancreatic masses in real-time.

Finite Element Analysis of a Novel Aortic Valve Stent.

Worldwide, one of the leading causes of death for patients with cardiovascular disease is aortic valve failure or insufficiency as a result of calcification and cardiovascular disease. The surgical treatment consists of repair or total replacement of the aortic valve. Artificial aortic valve implantation via a percutaneous or endovascular procedure is the minimally invasive alternative to open chest surgery, and the only option for high-risk or older patients. Due to the complex anatomical location between the left ventricle and the aorta, there are still engineering design optimization challenges which influence the long-term durability of the valve. In this study we developed a computer model and performed a numerical analysis of an original self-expanding stent for transcatheter aortic valve in order to optimize its design and materials. The study demonstrates the current valve design could be a good alternative to the existing commercially available valve devices.

Skin Diseases Classification Using Deep Leaning Methods.

Due to the high incidence of skin tumors, the development of computer aided-diagnosis methods will become a very powerful diagnosis tool for dermatologists. The skin diseases are initially diagnosed visually, through clinical screening and followed in some cases by dermoscopic analysis, biopsy and histopathological examination. Automatic classification of dermatoscopic images is a challenge due to fine-grained variations in lesions. The convolutional neural network (CNN), one of the most powerful deep learning techniques proved to be superior to traditional algorithms. These networks provide the flexibility of extracting discriminatory features from images that preserve the spatial structure and could be developed for region recognition and medical image classification. In this paper we proposed an architecture of CNN to classify skin lesions using only image pixels and diagnosis labels as inputs. We trained and validated the CNN model using a public dataset of 10015 images consisting of 7 types of skin lesions: actinic keratoses and intraepithelial carcinoma/Bowen disease (akiec), basal cell carcinoma (bcc), benign lesions of the keratosis type (solar lentigine/seborrheic keratoses and lichen-planus like keratosis, bkl), dermatofibroma (df), melanoma (mel), melanocytic nevi (nv) and vascular lesions (angiomas, angiokeratomas, pyogenic granulomas and hemorrhages, vasc).