Prediction of melanoma Breslow thickness using deep transfer learning algorithms.

BACKGROUND: The distinction between in situ melanoma (MIS) and invasive melanoma is challenging even for expert dermatologists. The use of pretrained convolutional neural networks (CNNs) as ancillary decision systems needs further research. AIM: To develop, validate and compare three deep transfer learning (DTL) algorithms to predict MIS vs. invasive melanoma and melanoma with a Breslow thickness (BT) of < 0.8 mm vs. ≥ 0.8 mm. METHODS: A dataset of 1315 dermoscopic images of histopathologically confirmed melanomas was created from Virgen del Rocio University Hospital and open repositories of the International Skin Imaging Collaboration archive and Polesie S et al. (Dermatol Pract Concept 2021; 11:e2021079). The images were labelled as MIS or invasive melanoma and < 0.8 mm or ≥ 0.8 mm of BT. We conducted three trainings, and overall means for receiver operating characteristic (ROC) curves, sensitivity, specificity, positive and negative predictive value, and balanced diagnostic accuracy outcomes were evaluated on the test set with ResNetV2, EfficientNetB6 and InceptionV3. The results of 10 dermatologists were compared with the algorithms. Grad-CAM gradient maps were generated, highlighting relevant areas considered by the CNNs within the images. RESULTS: EfficientNetB6 achieved the highest diagnostic accuracy for the comparison between MIS vs. invasive melanoma (61%) and BT < 0.8 mm vs. ≥ 0.8 mm (75%). For the BT comparison, ResNetV2 with an area under the ROC curve of 0.76 and InceptionV3 with an area under the ROC curve of 0.75, outperformed the results obtained by the dermatologist group with an area under the ROC curve of 0.70. CONCLUSION: EfficientNetB6 recorded the best prediction results, outperforming the dermatologists for the comparison of 0.8 mm of BT. DTL could be an ancillary aid to support dermatologists' decisions in the near future.

Performance Evaluation of Deep Learning-Based Prostate Cancer Screening Methods in Histopathological Images: Measuring the Impact of the Model's Complexity on Its Processing Speed.

Prostate cancer (PCa) is the second most frequently diagnosed cancer among men worldwide, with almost 1.3 million new cases and 360,000 deaths in 2018. As it has been estimated, its mortality will double by 2040, mostly in countries with limited resources. These numbers suggest that recent trends in deep learning-based computer-aided diagnosis could play an important role, serving as screening methods for PCa detection. These algorithms have already been used with histopathological images in many works, in which authors tend to focus on achieving high accuracy results for classifying between malignant and normal cases. These results are commonly obtained by training very deep and complex convolutional neural networks, which require high computing power and resources not only in this process, but also in the inference step. As the number of cases rises in regions with limited resources, reducing prediction time becomes more important. In this work, we measured the performance of current state-of-the-art models for PCa detection with a novel benchmark and compared the results with PROMETEO, a custom architecture that we proposed. The results of the comprehensive comparison show that using dedicated models for specific applications could be of great importance in the future.

Wildlife Monitoring on the Edge: A Performance Evaluation of Embedded Neural Networks on Microcontrollers for Animal Behavior Classification.

Monitoring animals' behavior living in wild or semi-wild environments is a very interesting subject for biologists who work with them. The difficulty and cost of implanting electronic devices in this kind of animals suggest that these devices must be robust and have low power consumption to increase their battery life as much as possible. Designing a custom smart device that can detect multiple animal behaviors and that meets the mentioned restrictions presents a major challenge that is addressed in this work. We propose an edge-computing solution, which embeds an ANN in a microcontroller that collects data from an IMU sensor to detect three different horse gaits. All the computation is performed in the microcontroller to reduce the amount of data transmitted via wireless radio, since sending information is one of the most power-consuming tasks in this type of devices. Multiples ANNs were implemented and deployed in different microcontroller architectures in order to find the best balance between energy consumption and computing performance. The results show that the embedded networks obtain up to 97.96% ± 1.42% accuracy, achieving an energy efficiency of 450 Mops/s/watt.

A systematic comparison of deep learning methods for Gleason grading and scoring.

Prostate cancer is the second most frequent cancer in men worldwide after lung cancer. Its diagnosis is based on the identification of the Gleason score that evaluates the abnormality of cells in glands through the analysis of the different Gleason patterns within tissue samples. The recent advancements in computational pathology, a domain aiming at developing algorithms to automatically analyze digitized histopathology images, lead to a large variety and availability of datasets and algorithms for Gleason grading and scoring. However, there is no clear consensus on which methods are best suited for each problem in relation to the characteristics of data and labels. This paper provides a systematic comparison on nine datasets with state-of-the-art training approaches for deep neural networks (including fully-supervised learning, weakly-supervised learning, semi-supervised learning, Additive-MIL, Attention-Based MIL, Dual-Stream MIL, TransMIL and CLAM) applied to Gleason grading and scoring tasks. The nine datasets are collected from pathology institutes and openly accessible repositories. The results show that the best methods for Gleason grading and Gleason scoring tasks are fully supervised learning and CLAM, respectively, guiding researchers to the best practice to adopt depending on the task to solve and the labels that are available.

Data-driven color augmentation for H&E stained images in computational pathology.

Computational pathology targets the automatic analysis of Whole Slide Images (WSI). WSIs are high-resolution digitized histopathology images, stained with chemical reagents to highlight specific tissue structures and scanned via whole slide scanners. The application of different parameters during WSI acquisition may lead to stain color heterogeneity, especially considering samples collected from several medical centers. Dealing with stain color heterogeneity often limits the robustness of methods developed to analyze WSIs, in particular Convolutional Neural Networks (CNN), the state-of-the-art algorithm for most computational pathology tasks. Stain color heterogeneity is still an unsolved problem, although several methods have been developed to alleviate it, such as Hue-Saturation-Contrast (HSC) color augmentation and stain augmentation methods. The goal of this paper is to present Data-Driven Color Augmentation (DDCA), a method to improve the efficiency of color augmentation methods by increasing the reliability of the samples used for training computational pathology models. During CNN training, a database including over 2 million H&E color variations collected from private and public datasets is used as a reference to discard augmented data with color distributions that do not correspond to realistic data. DDCA is applied to HSC color augmentation, stain augmentation and H&E-adversarial networks in colon and prostate cancer classification tasks. DDCA is then compared with 11 state-of-the-art baseline methods to handle color heterogeneity, showing that it can substantially improve classification performance on unseen data including heterogeneous color variations.