Artificial Intelligence Algorithms for Benign vs. Malignant Dermoscopic Skin Lesion Image Classification.

In recent decades, the incidence of melanoma has grown rapidly. Hence, early diagnosis is crucial to improving clinical outcomes. Here, we propose and compare a classical image analysis-based machine learning method with a deep learning one to automatically classify benign vs. malignant dermoscopic skin lesion images. The same dataset of 25,122 publicly available dermoscopic images was used to train both models, while a disjointed test set of 200 images was used for the evaluation phase. The training dataset was randomly divided into 10 datasets of 19,932 images to obtain an equal distribution between the two classes. By testing both models on the disjoint set, the deep learning-based method returned accuracy of 85.4 ± 3.2% and specificity of 75.5 ± 7.6%, while the machine learning one showed accuracy and specificity of 73.8 ± 1.1% and 44.5 ± 4.7%, respectively. Although both approaches performed well in the validation phase, the convolutional neural network outperformed the ensemble boosted tree classifier on the disjoint test set, showing better generalization ability. The integration of new melanoma detection algorithms with digital dermoscopic devices could enable a faster screening of the population, improve patient management, and achieve better survival rates.

Tumor-Infiltrating Lymphocyte Recognition in Primary Melanoma by Deep Learning Convolutional Neural Network.

The presence of tumor-infiltrating lymphocytes (TILs) is associated with a favorable prognosis of primary melanoma (PM). Recently, artificial intelligence (AI)-based approach in digital pathology was proposed for the standardized assessment of TILs on hematoxylin and eosin-stained whole slide images (WSIs). Herein, the study applied a new convolution neural network (CNN) analysis of PM WSIs to automatically assess the infiltration of TILs and extract a TIL score. A CNN was trained and validated in a retrospective cohort of 307 PMs including a training set (237 WSIs, 57,758 patches) and an independent testing set (70 WSIs, 29,533 patches). An AI-based TIL density index (AI-TIL) was identified after the classification of tumor patches by the presence or absence of TILs. The proposed CNN showed high performance in recognizing TILs in PM WSIs, showing 100% specificity and sensitivity on the testing set. The AI-based TIL index correlated with conventional TIL evaluation and clinical outcome. The AI-TIL index was an independent prognostic marker associated directly with a favorable prognosis. A fully automated and standardized AI-TIL appeared to be superior to conventional methods at differentiating the PM clinical outcome. Further studies are required to develop an easy-to-use tool to assist pathologists to assess TILs in the clinical evaluation of solid tumors.

Artificial Intelligence Application to Screen Abdominal Aortic Aneurysm Using Computed tomography Angiography.

The aim of our study is to validate a totally automated deep learning (DL)-based segmentation pipeline to screen abdominal aortic aneurysms (AAA) in computed tomography angiography (CTA) scans. We retrospectively evaluated 73 thoraco-abdominal CTAs (48 AAA and 25 control CTA) by means of a DL-based segmentation pipeline built on a 2.5D convolutional neural network (CNN) architecture to segment lumen and thrombus of the aorta. The maximum aortic diameter of the abdominal tract was compared using a threshold value (30 mm). Blinded manual measurements from a radiologist were done in order to create a true comparison. The screening pipeline was tested on 48 patients with aneurysm and 25 without aneurysm. The average diameter manually measured was 51.1 ± 14.4 mm for patients with aneurysms and 21.7 ± 3.6 mm for patients without aneurysms. The pipeline correctly classified 47 AAA out of 48 and 24 control patients out of 25 with 97% accuracy, 98% sensitivity, and 96% specificity. The automated pipeline of aneurysm measurements in the abdominal tract reported a median error with regard to the maximum abdominal diameter measurement of 1.3 mm. Our approach allowed for the maximum diameter of 51.2 ± 14.3 mm in patients with aneurysm and 22.0 ± 4.0 mm in patients without an aneurysm. The DL-based screening for AAA is a feasible and accurate method, calling for further validation using a larger pool of diagnostic images towards its clinical use.

An Innovative Sensorized Face Mask for Early Detection of Physiological Changes Associated with Viral Infection.

A sensorized face mask could be a useful tool in the case of a viral pandemic event, as well as the Covid-19 emergency. In the context of the proposed project "RESPIRE", we have developed a "Smart-Mask" able to collect the signal patterns of body temperature, respiration, and symptoms such as cough, through a set of textile sensors. The signals have been analyzed by Artificial Intelligence algorithms in order to compare them with gold standard measurements, and to recognize the physiological changes associated with a viral infection. This low-cost prototype of a smart face mask is a reliable tool for the estimation of the individual physiological parameters. Moreover, it enables both personal protection and the early and rapid identification and tracking of potentially infected individuals.

Deep Learning to Automatically Segment and Analyze Abdominal Aortic Aneurysm from Computed Tomography Angiography.

PURPOSE: Although segmentation of Abdominal Aortic Aneurysms (AAA) thrombus is a crucial step for both the planning of endovascular treatment and the monitoring of the intervention's outcome, it is still performed manually implying time consuming operations as well as operator dependency. The present paper proposes a fully automatic pipeline to segment the intraluminal thrombus in AAA from contrast-enhanced Computed Tomography Angiography (CTA) images and to subsequently analyze AAA geometry. METHODS: A deep-learning-based pipeline is developed to localize and segment the thrombus from the CTA scans. The thrombus is first identified in the whole sub-sampled CTA, then multi-view U-Nets are combined together to segment the thrombus from the identified region of interest. Polygonal models are generated for the thrombus and the lumen. The lumen centerline is automatically extracted from the lumen mesh and used to compute the aneurysm and lumen diameters. RESULTS: The proposed multi-view integration approach returns an improvement in thrombus segmentation with respect to the single-view prediction. The thrombus segmentation model is trained over a training set of 63 CTA and a validation set of 8 CTA scans. By comparing the thrombus segmentation predicted by the model with the ground truth data, a Dice Similarity Coefficient (DSC) of 0.89 ± 0.04 is achieved. The AAA geometry analysis provided an Intraclass Correlation Coefficient (ICC) of 0.92 and a mean-absolute difference of 3.2 ± 2.4 mm, for the measurements of the total diameter of the aneurysm. Validation of both thrombus segmentation and aneurysm geometry analysis is performed over a test set of 14 CTA scans. CONCLUSION: The developed deep learning models can effectively segment the thrombus from patients affected by AAA. Moreover, the diameters automatically extracted from the AAA show high correlation with those manually measured by experts.