Self-supervised learning-based cervical cytology for the triage of HPV-positive women in resource-limited settings and low-data regime.

Screening Papanicolaou test samples has proven to be highly effective in reducing cervical cancer-related mortality. However, the lack of trained cytopathologists hinders its widespread implementation in low-resource settings. Deep learning-assisted telecytology diagnosis emerges as an appealing alternative, but it requires the collection of large annotated training datasets, which is costly and time-consuming. In this paper, we demonstrate that the abundance of unlabeled images that can be extracted from Pap smear test whole slide images presents a fertile ground for self-supervised learning methods, yielding performance improvements compared to off-the-shelf pre-trained models for various downstream tasks. In particular, we propose Cervical Cell Copy-Pasting (C3P) as an effective augmentation method, which enables knowledge transfer from public and labeled single-cell datasets to unlabeled tiles. Not only does C3P outperforms naive transfer from single-cell images, but we also demonstrate its advantageous integration into multiple instance learning methods. Importantly, all our experiments are conducted on our introduced in-house dataset comprising liquid-based cytology Pap smear images obtained using low-cost technologies. This aligns with our long-term objective of deep learning-assisted telecytology for diagnosis in low-resource settings.

Pathologist Computer-Aided Diagnostic Scoring of Tumor Cell Fraction: A Swiss National Study.

Tumor cell fraction (TCF) estimation is a common clinical task with well-established large interobserver variability. It thus provides an ideal test bed to evaluate potential impacts of employing a tumor cell fraction computer-aided diagnostic (TCFCAD) tool to support pathologists' evaluation. During a National Slide Seminar event, pathologists (n = 69) were asked to visually estimate TCF in 10 regions of interest (ROIs) from hematoxylin and eosin colorectal cancer images intentionally curated for diverse tissue compositions, cellularity, and stain intensities. Next, they re-evaluated the same ROIs while being provided a TCFCAD-created overlay highlighting predicted tumor vs nontumor cells, together with the corresponding TCF percentage. Participants also reported confidence levels in their assessments using a 5-tier scale, indicating no confidence to high confidence, respectively. The TCF ground truth (GT) was defined by manual cell-counting by experts. When assisted, interobserver variability significantly decreased, showing estimates converging to the GT. This improvement remained even when TCFCAD predictions deviated slightly from the GT. The standard deviation (SD) of the estimated TCF to the GT across ROIs was 9.9% vs 5.8% with TCFCAD (P < .0001). The intraclass correlation coefficient increased from 0.8 to 0.93 (95% CI, 0.65-0.93 vs 0.86-0.98), and pathologists stated feeling more confident when aided (3.67 ± 0.81 vs 4.17 ± 0.82 with the computer-aided diagnostic [CAD] tool). TCFCAD estimation support demonstrated improved scoring accuracy, interpathologist agreement, and scoring confidence. Interestingly, pathologists also expressed more willingness to use such a CAD tool at the end of the survey, highlighting the importance of training/education to increase adoption of CAD systems.

Impact of scanner variability on lymph node segmentation in computational pathology.

Computer-aided diagnostics in histopathology are based on the digitization of glass slides. However, heterogeneity between the images generated by different slide scanners can unfavorably affect the performance of computational algorithms. Here, we evaluate the impact of scanner variability on lymph node segmentation due to its clinical importance in colorectal cancer diagnosis. 100 slides containing 276 lymph nodes were digitized using 4 different slide scanners, and 50 of the lymph nodes containing metastatic cancer cells. These 400 scans were subsequently annotated by 2 experienced pathologists to precisely label lymph node boundary. Three different segmentation methods were then applied and compared: Hematoxylin-channel-based thresholding (HCT), Hematoxylin-based active contours (HAC), and a convolution neural network (U-Net). Evaluation of U-Net trained from both a single scanner and an ensemble of all scanners was completed. Mosaic images based on representative tiles from a scanner were used as a reference image to normalize the new data from different test scanners to evaluate the performance of a pre-trained model. Fine-tuning was carried out by using weights of a model trained on one scanner to initialize model weights for other scanners. To evaluate the domain generalization, domain adversarial learning and stain mix-up augmentation were also implemented. Results show that fine-tuning and domain adversarial learning decreased the impact of scanner variability and greatly improved segmentation across scanners. Overall, U-Net with stain mix-up (Matthews correlation coefficient (MCC) = 0.87), domain adversarial learning (MCC = 0.86), and HAC (MCC = 0.87) were shown to outperform HCT (MCC = 0.81) for segmentation of lymph nodes when compared against the ground truth. The findings of this study should be considered for future algorithms applied in diagnostic routines.

Self-rule to multi-adapt: Generalized multi-source feature learning using unsupervised domain adaptation for colorectal cancer tissue detection.

Supervised learning is constrained by the availability of labeled data, which are especially expensive to acquire in the field of digital pathology. Making use of open-source data for pre-training or using domain adaptation can be a way to overcome this issue. However, pre-trained networks often fail to generalize to new test domains that are not distributed identically due to tissue stainings, types, and textures variations. Additionally, current domain adaptation methods mainly rely on fully-labeled source datasets. In this work, we propose Self-Rule to Multi-Adapt (SRMA), which takes advantage of self-supervised learning to perform domain adaptation, and removes the necessity of fully-labeled source datasets. SRMA can effectively transfer the discriminative knowledge obtained from a few labeled source domain's data to a new target domain without requiring additional tissue annotations. Our method harnesses both domains' structures by capturing visual similarity with intra-domain and cross-domain self-supervision. Moreover, we present a generalized formulation of our approach that allows the framework to learn from multiple source domains. We show that our proposed method outperforms baselines for domain adaptation of colorectal tissue type classification in single and multi-source settings, and further validate our approach on an in-house clinical cohort. The code and trained models are available open-source: https://github.com/christianabbet/SRA.

New Acylated Flavonol Glycosides and a Phenolic Profile of Pritzelago alpina, a Forgotten Edible Alpine Plant.

Thirteen acylated flavonoid glycosides, 1-13, including eleven new congeners, 3-13, were isolated from the aerial parts of Pritzelago alpina (Brassicaceae) by a combination of column chromatography on Sephadex LH-20, and preparative and semi-preparative HPLC. The structures were established by extensive NMR and MS experiments in combination with acid hydrolysis and sugar analysis by GC/MS. The new compounds were shown to be kaempferol and quercetin glycosides acylated for most of them by a branched short chain fatty acid or a hydroxycinnamic acid residue on the sugar portion. As shown by a HPLC-DAD analysis of a MeOH extract, these compounds are the main phenolic constituents in the aerial parts of the plant.

Comprehensive analysis of Cirsium spinosissimum Scop., a wild alpine food plant.

Plants which have been traditionally eaten by alpine populations may provide new opportunities of agricultural development for mountain regions. In this context we investigated the chemical composition of Cirsium spinosissimum (Asteraceae), a perennial thistle. Its receptacles were eaten by shepherds in Valais (Switzerland). Extracts of aerial parts were subjected to a comprehensive metabolite profiling, using a dereplication platform, combining HPLC-PDA-MS and offline microprobe NMR analysis. Twenty compounds, including various phenolic glycosides, a monoterpene lactone, a spermine derivative, and fatty acids, could be identified online, or after targeted isolation. The total phenolic content was determined, and the major flavonoids were quantitatively assessed in fresh receptacles by HPLC-PDA analysis. In addition, substances relevant for nutrition, such as ß-carotene, fatty acids, ascorbic acid, and minerals, were quantified. The ethanolic extract of the receptacles showed no sign of cytotoxicity when tested in Caco-2 cells.

Ethnobotanical survey on wild alpine food plants in Lower and Central Valais (Switzerland).

ETHNOPHARMACOLOGICAL RELEVANCE: Swiss Alps have an ancestral tradition with regard to the use of wild plants as medicines and food. However, this knowledge is falling into oblivion, and is nowadays confined to village areas. Aim of the study was to identify wild edible plants used today and during the last two centuries by the alpine population of Valais (Switzerland). MATERIAL AND METHODS: Data were collected by means of semi-directed interviews made in four different lateral valleys of Valais (Val d'Anniviers, Val d'Entremont, Val d'Hérens, and Val d'Illiez). Wild food plants were classified according to their uses (salads, cooked vegetables, spices, raw snacks, teas, alcoholic drinks, sirups, and jams). Books and reports written in the XIXth century were consulted to identify uses of wild plants which have fallen in oblivion meanwhile. RESULTS: A total of 98 edible wild plants, distributed into 38 botanical families, were identified during the interviews. Several plants were highly cited (e.g. Taraxacum officinale, Chenopodium bonus-henricus). The most frequent usage was as tea (18%), followed by uses as cooked vegetables (16%), jams (16%), and raw snacks (16%). A strong association was observed between food and medicinal uses of plants. Wild food plants were of critical importance in times of food scarcity. Meanwhile, they have lost their relevance as vital components of the diet and are nowadays rather perceived and appreciated as delicacies. CONCLUSIONS: This study provides for the first time comprehensive data on present day and historical uses of wild plants as food in Lower and Central Valais. Besides being of historical interest, this ethnobotanical information can be used to identify species which may provide interesting opportunities for diversification of mountain agriculture.

Comprehensive analysis of Phyteuma orbiculare L., a wild Alpine food plant.

Plants which have been traditionally eaten by the alpine population may provide new opportunities for agricultural development in mountain regions. In this context we have investigated the chemical composition of Phyteuma orbiculare (Campanulaceae), a perennial herb whose leaves have been eaten as salad by rural populations in Valais (Switzerland). Extracts of different polarities were subjected to comprehensive metabolite profiling using a dereplication platform combining HPLC-PDA-MS, and offline NMR analysis. Twenty-three compounds, including various phenolic glycosides, a new dimeric phenylpropanoid glucoside, saponins, and fatty acids were identified online, or after targeted isolation. Selected phenolic constituents were quantitatively assessed by HPLC-PDA analysis. In addition, substances relevant for nutrition, such as ß-carotene, fatty acids, ascorbic acid and minerals were quantified in leaves and flowers. The antioxidant capacity was determined with an ORAC assay, and total phenolic compounds were quantified. Finally, the phytochemical profile was compared to that of the related species P. spicatum, P. hemisphaericum and P. ovatum.

Phyteumosides A and B: new saponins with unique triterpenoid aglycons from Phyteuma orbiculare L.

Phyteumosides A (1) and B (2), two saponins with unprecedented triterpenoid aglycons, were isolated from the aerial parts of Phyteuma orbiculare (Campanulaceae). Their structures were elucidated by spectroscopic and chemical methods and corroborated by X-ray diffraction analyses of the aglycons obtained through enzymatic hydrolysis. The aglycon of 1 can be considered as an incompletely cyclized onoceroid or gammaceroid triterpene with two additional tetrahydropyran rings arising from oxygen bridges. Compound 2 possesses a new 17-polypodene aglycon.