Oral cavity cancers are the 15th most common cancer with more than 350,000 new cases and ~178,000 deaths each year. Among them, squamous cell carcinoma (SCC) accounts for more than 90% of tumors located in the oral cavity and on oropharynx. For the oral cavity SCC, the surgical resection remains the primary course of treatment. Generally, surgical margins are defined intraoperatively using visual and tactile elements. However, in 15–30% of cases, positive margins are found after histopathological examination several days postsurgery. Technologies based on mass spectrometry (MS) were recently developed to help guide surgical resection. The SpiderMass technology is designed for in-vivo real-time analysis under minimally invasive conditions. This instrument achieves tissue microsampling and real-time molecular analysis with the combination of a laser microprobe and a mass spectrometer. It ultimately acts as a tool to support histopathological decision-making and diagnosis. This pilot study included 14 patients treated for tongue SCC (T1 to T4) with the surgical resection as the first line of treatment. Samples were first analyzed by a pathologist to macroscopically delineate the tumor, dysplasia, and peritumoral areas. The retrospective and prospective samples were sectioned into three consecutive sections and thaw-mounted on slides for H&E staining (7 μm), SpiderMass analysis (20 μm), and matrix-assisted laser desorption ionization (MALDI) MS imaging (12 μm). The SpiderMass microprobe collected lipidometabolic profiles of the dysplasia, tumor, and peritumoral regions annotated by the pathologist. The MS spectra were then subjected to the multivariate statistical analysis. The preliminary data demonstrate that the lipidometabolic molecular profiles collected with the SpiderMass are significantly different between the tumor and peritumoral regions enabling molecular classification to be established by linear discriminant analysis (LDA). MALDI images of the different samples were submitted to segmentation for cross instrument validation and revealed additional molecular discrimination within the tumor and nontumor regions. These very promising preliminary results show the applicability of the SpiderMass to SCC of the tongue and demonstrate its interest in the surgical treatment of head and neck cancers.

In recent years, cannabis and hemp-based products have become increasingly popular for recreational use, edibles, beverages, health care products, and medicines. The rapid detection and differentiation of phytocannabinoids is, therefore, essential to assess the potency and the therapeutic and nutritional values of cannabis cultivars. Here, we implemented SpiderMass technology for in vivo detection of cannabidiolic acid (CBDA) and ∆⁹-tetrahydrocannabinolicacid (∆⁹-THCA), and other endogenous organic plant compounds, to access distribution gradients within the plants and differentiate between cultivars. The SpiderMass system is composed of an IR-laser handheld microsampling probe connected to a mass spectrometer through a transfer tube. The analysis was performed on different plant organs from freshly cultivated cannabis plants in only a few seconds. SpiderMass analysis easily discriminated the two acid phytocannabinoid isomers via MS/MS, and the built statistical models differentiated between four cannabis cultivars. Different abundancies of the two acid phytocannabinoids were found along the plant as well as between different cultivars. Overall, these results introduce direct analysis by SpiderMass as a compelling analytical alternative for rapid hemp analysis.

Rapid and accurate clinical diagnosis of pathological conditions remains highly challenging. A very important component of diagnosis tool development is the design of effective classification models with Mass spectrometry (MS) data. Some popular Machine Learning (ML) approaches have been investigated for this purpose but these ML models require time-consuming preprocessing steps such as baseline correction, denoising, and spectrum alignment to remove non-sample-related data artifacts. They also depend on the tedious extraction of handcrafted features, making them unsuitable for rapid analysis. Convolutional Neural Networks (CNNs) have been found to perform well under such circumstances since they can learn efficient representations from raw data without the need for costly preprocessing. However, their effectiveness drastically decreases when the number of available training samples is small, which is a common situation in medical applications. Transfer learning strategies extend an accurate representation model learnt usually on a large dataset containing many categories, to a smaller dataset with far fewer categories. In this study, we first investigate transfer learning on a 1D-CNN we have designed to classify MS data, then we develop a new representation learning method when transfer learning is not powerful enough, as in cases of low-resolution or data heterogeneity. What we propose is to train the same model through several classification tasks over various small datasets in order to accumulate generic knowledge of what MS data are, in the resulting representation. By using rat brain data as the initial training dataset, a representation learning approach can have a classification accuracy exceeding 98% for canine sarcoma cancer cells, human ovarian cancer serums, and pathogenic microorganism biotypes in 1D clinical datasets. We show for the first time the use of cumulative representation learning using datasets generated in different biological contexts, on different organisms, in different mass ranges, with different MS ionization sources, and acquired by different instruments at different resolutions. Our approach thus proposes a promising strategy for improving MS data classification accuracy when only small numbers of samples are available as a prospective cohort. The principles demonstrated in this work could even be beneficial to other domains (astronomy, archaeology…) where training samples are scarce.