Influence of training and expertise on deep neural network attention and human attention during a medical image classification task.

In many different domains, experts can make complex decisions after glancing very briefly at an image. However, the perceptual mechanisms underlying expert performance are still largely unknown. Recently, several machine learning algorithms have been shown to outperform human experts in specific tasks. But these algorithms often behave as black boxes and their information processing pipeline remains unknown. This lack of transparency and interpretability is highly problematic in applications involving human lives, such as health care. One way to "open the black box" is to compute an artificial attention map from the model, which highlights the pixels of the input image that contributed the most to the model decision. In this work, we directly compare human visual attention to machine visual attention when performing the same visual task. We have designed a medical diagnosis task involving the detection of lesions in small bowel endoscopic images. We collected eye movements from novices and gastroenterologist experts while they classified medical images according to their relevance for Crohn's disease diagnosis. We trained three state-of-the-art deep learning models on our carefully labeled dataset. Both humans and machine performed the same task. We extracted artificial attention with six different post hoc methods. We show that the model attention maps are significantly closer to human expert attention maps than to novices', especially for pathological images. As the model gets trained and its performance gets closer to the human experts, the similarity between model and human attention increases. Through the understanding of the similarities between the visual decision-making process of human experts and deep neural networks, we hope to inform both the training of new doctors and the architecture of new algorithms.

A time-lapse embryo dataset for morphokinetic parameter prediction.

One of the most common treatments for infertile couples is In Vitro Fertilization (IVF). It consists of controlled ovarian hyperstimulation, followed by ovum pickup, fertilization, and embryo culture for 2-6 days under controlled environmental conditions, leading to intrauterine transfer or freezing of embryos identified as having a good implantation potential by embryologists. To allow continuous monitoring of embryo development, Time-lapse imaging incubators (TLI) were first released in the IVF market around 2010. This time-lapse technology provides a dynamic overview of embryonic in vitro development by taking photographs of each embryo at regular intervals throughout its development. TLI appears to be the most promising solution to improve embryo quality assessment methods, and subsequently the clinical efficiency of IVF. In particular, the unprecedented high volume of high-quality images produced by TLI systems has already been leveraged using modern Artificial Intelligence (AI) methods, like deep learning (DL). An important limitation to the development of AI-based solutions for IVF is the absence of a public reference dataset to train and evaluate deep learning (DL) models. In this work, we describe a fully annotated dataset of 704 TLI videos of developing embryos with all 7 focal planes available, for a total of 2,4M images. Of note, we propose highly detailed annotations with 16 different development phases, including early cell division phases, but also late cell divisions, phases after morulation, and very early phases, which have never been used before. This is the first public dataset that will allow the community to evaluate morphokinetic models and the first step towards deep learning-powered IVF. We postulate that this dataset will help improve the overall performance of DL approaches on time-lapse videos of embryo development, ultimately benefiting infertile patients with improved clinical success rates.

Cytotoxic Effect In Vitro of Acalypha monostachya Extracts over Human Tumor Cell Lines.

Acalypha monostachya (A. monostachya) is a plant that is used in traditional medicine as a cancer treatment; however, its effect has not been validated. In this study, the potential cytotoxic effects and morphological changes of A. monostachya were evaluated in human tumor cell lines. The aqueous (AE), methanolic (ME), and hexane (HE) extracts were obtained, and flavonoid-type phenolic compounds were detected, which indicates an antineoplastic effect. We observed a time-dependent and concentration-selective toxicity in human tumor cells. Additionally, the ME and HE showed the greatest cytotoxic effect at minimum concentrations compared to the AE, which showed this effect at the highest concentrations. All extracts induced significant morphological changes in tumor cells. The HeLa (cervix carcinoma) cells were more sensitive compared to the MDA-MB-231 (triple-negative breast cancer) cells. In conclusion, we demonstrated a cytotoxic in vitro effect of A. monostachya extracts in tumoral human cell lines. These results show the potential antineoplastic effects of A. monostachya in vitro. Hereafter, our lab team will continue working to usefully isolate and obtain the specific compounds of A. monostachya extracts with cytotoxic effects on tumor cells to find more alternatives for cancer treatment.

Hyaluronate Functionalized Multi-Wall Carbon Nanotubes Loaded with Carboplatin Enhance Cytotoxicity on Human Cancer Cell Lines.

Cancer is a major global public health problem and conventional chemotherapy has several adverse effects and deficiencies. As a valuable option for chemotherapy, nanomedicine requires novel agents to increase the effects of antineoplastic drugs in multiple cancer models. Since its discovery, carbon nanotubes (CNTs) are intensively investigated for their use as carriers in drug delivery applications. This study shows the development of a nanovector generated with commercial carbon nanotubes (cCNTs) that were oxidized (oxCNTs) and chemically functionalized with hyaluronic acid (HA) and loaded with carboplatin (CPT). The nanovector, oxCNTs-HA-CPT, was used as a treatment against HeLa and MDA-MB-231 human tumor cell lines. The potential antineoplastic impact of the fabricated nanovector was evaluated in human cervical adenocarcinoma (HeLa) and mammary adenocarcinoma (MDA-MB-231). The oxCNTs-HA-CPT nanovector demonstrate to have a specific antitumor effect in vitro. The functionalization with HA allows that nanovector bio-directed towards tumor cells, while the toxicity effect is attributed mainly to CPT in a dose-dependent manner.