Nutritional status and growth performance of Fijian non-descript local chickens and their crosses with broilers under different production systems.

The study compared nutrient intake and growth performance of local chickens to that of local x broiler crossbreds under scavenging and indoor conventional systems. A total of 48 male and 48 female chickens for each of the two chicken types were allocated to four outdoor free-range pens. The chickens were allowed to scavenge whilst being supplemented with sorghum plus kitchen waste and broiler growers from week 5 to week 13 of age. The same design was repeated using the indoor conventional system. Local chickens and their crosses with broilers had higher growth rates under the scavenging system than the indoor production system (P < 0.05). Local chickens and their crosses with broilers had the same growth rates when fed the same diet (P > 0.05). Crop and gizzard contents from local chickens had the same crude protein as their crosses with broilers under both systems (P > 0.05). The crude protein values of crop and gizzard contents ranged from 25.4 to 30.4%. Crop and gizzard contents from scavenging chickens had energy content ranging from 16.2 to 17.1 MJ/Kg which was lower (P < 0.05) than that from chickens under the indoor conventional system (20.3 to 25.8 kJ/Kg). Iron content ranged from 655.7 to 1619.4 mg/Kg in scavenging chickens and 156.1 to 621.4 mg/Kg in enclosed chickens. Chickens of the same type had higher iron content in their crop and gizzard contents under the scavenging system than the conventional system (P < 0.05). Crossbreds between local chickens and broilers matches the scavenging abilities of the local chickens but have lower growth rates under the scavenging system.

Deep learning for dual detection of microsatellite instability and POLE mutations in colorectal cancer histopathology.

In the spectrum of colorectal tumors, microsatellite-stable (MSS) tumors with DNA polymerase ε (POLE) mutations exhibit a hypermutated profile, holding the potential to respond to immunotherapy similarly to their microsatellite-instable (MSI) counterparts. Yet, due to their rarity and the associated testing costs, systematic screening for these mutations is not commonly pursued. Notably, the histopathological phenotype resulting from POLE mutations is theorized to resemble that of MSI. This resemblance not only could facilitate their detection by a transformer-based Deep Learning (DL) system trained on MSI pathology slides, but also indicates the possibility for MSS patients with POLE mutations to access enhanced treatment options, which might otherwise be overlooked. To harness this potential, we trained a Deep Learning classifier on a large dataset with the ground truth for microsatellite status and subsequently validated its capabilities for MSI and POLE detection across three external cohorts. Our model accurately identified MSI status in both the internal and external resection cohorts using pathology images alone. Notably, with a classification threshold of 0.5, over 75% of POLE driver mutant patients in the external resection cohorts were flagged as "positive" by a DL system trained on MSI status. In a clinical setting, deploying this DL model as a preliminary screening tool could facilitate the efficient identification of clinically relevant MSI and POLE mutations in colorectal tumors, in one go.

A photoaging smartphone application to promote sun safety behaviors among youth in late childhood and adolescence.

BACKGROUND: Ultraviolet (UV)-exposure behaviors can directly impact an individual's skin cancer risk, with many habits formed during childhood and adolescence. We explored the utility of a photoaging smartphone application to motivate youth to improve sun safety practices. METHODS: Participants completed a preintervention survey to gather baseline sun safety perceptions and behaviors. Participants then used a photoaging mobile application to view the projected effects of chronic UV exposure on participants' self-face image over time, followed by a postintervention survey to assess motivation to engage in future sun safety practices. RESULTS: The study sample included 87 participants (median [interquartile (IQR)] age, 14 [11-16] years). Most participants were White (50.6%) and reported skin type that burns a little and tans easily (42.5%). Preintervention sun exposure behaviors among participants revealed that 33 (37.9%) mostly or always used sunscreen on a sunny day, 48 (55.2%) experienced at least one sunburn over the past year, 26 (30.6%) engaged in outdoor sunbathing at least once during the past year, and zero (0%) used indoor tanning beds. Non-skin of color (18 [41.9%], p = .02) and older (24 [41.4%], p = .007) participants more often agreed they felt better with a tan. Most participants agreed the intervention increased their motivation to practice sun-protective behaviors (wear sunscreen, 74 [85.1%]; wear hats, 64 [74.4%]; avoid indoor tanning, 73 [83.9%]; avoid outdoor tanning, 68 [79%]). CONCLUSION: The findings of this cross-sectional study suggest that a photoaging smartphone application may serve as a useful tool to promote sun safety behaviors from a young age.

Multi-domain stain normalization for digital pathology: A cycle-consistent adversarial network for whole slide images.

The variation in histologic staining between different medical centers is one of the most profound challenges in the field of computer-aided diagnosis. The appearance disparity of pathological whole slide images causes algorithms to become less reliable, which in turn impedes the wide-spread applicability of downstream tasks like cancer diagnosis. Furthermore, different stainings lead to biases in the training which in case of domain shifts negatively affect the test performance. Therefore, in this paper we propose MultiStain-CycleGAN, a multi-domain approach to stain normalization based on CycleGAN. Our modifications to CycleGAN allow us to normalize images of different origins without retraining or using different models. We perform an extensive evaluation of our method using various metrics and compare it to commonly used methods that are multi-domain capable. First, we evaluate how well our method fools a domain classifier that tries to assign a medical center to an image. Then, we test our normalization on the tumor classification performance of a downstream classifier. Furthermore, we evaluate the image quality of the normalized images using the Structural similarity index and the ability to reduce the domain shift using the Fréchet inception distance. We show that our method proves to be multi-domain capable, provides a very high image quality among the compared methods, and can most reliably fool the domain classifier while keeping the tumor classifier performance high. By reducing the domain influence, biases in the data can be removed on the one hand and the origin of the whole slide image can be disguised on the other, thus enhancing patient data privacy.

3-Dimensional Reconstruction From Histopathological Sections: A Systematic Review.

Although pathological tissue analysis is typically performed on single 2-dimensional (2D) histologic reference slides, 3-dimensional (3D) reconstruction from a sequence of histologic sections could provide novel opportunities for spatial analysis of the extracted tissue. In this review, we analyze recent works published after 2018 and report information on the extracted tissue types, the section thickness, and the number of sections used for reconstruction. By analyzing the technological requirements for 3D reconstruction, we observe that software tools exist, both free and commercial, which include the functionality to perform 3D reconstruction from a sequence of histologic images. Through the analysis of the most recent works, we provide an overview of the workflows and tools that are currently used for 3D reconstruction from histologic sections and address points for future work, such as a missing common file format or computer-aided analysis of the reconstructed model.

Distinct functional constraints driving conservation of the cofilin N-terminal regulatory tail.

Cofilin family proteins have essential roles in remodeling the cytoskeleton through filamentous actin depolymerization and severing. The short, unstructured N-terminal region of cofilin is critical for actin binding and harbors the major site of inhibitory phosphorylation. Atypically for a disordered sequence, the N-terminal region is highly conserved, but specific aspects driving this conservation are unclear. Here, we screen a library of 16,000 human cofilin N-terminal sequence variants for their capacity to support growth in S. cerevisiae in the presence or absence of the upstream regulator LIM kinase. Results from the screen and biochemical analysis of individual variants reveal distinct sequence requirements for actin binding and regulation by LIM kinase. LIM kinase recognition only partly explains sequence constraints on phosphoregulation, which are instead driven to a large extent by the capacity for phosphorylation to inactivate cofilin. We find loose sequence requirements for actin binding and phosphoinhibition, but collectively they restrict the N-terminus to sequences found in natural cofilins. Our results illustrate how a phosphorylation site can balance potentially competing sequence requirements for function and regulation.

Automated curation of large-scale cancer histopathology image datasets using deep learning.

BACKGROUND: Artificial intelligence (AI) has numerous applications in pathology, supporting diagnosis and prognostication in cancer. However, most AI models are trained on highly selected data, typically one tissue slide per patient. In reality, especially for large surgical resection specimens, dozens of slides can be available for each patient. Manually sorting and labelling whole-slide images (WSIs) is a very time-consuming process, hindering the direct application of AI on the collected tissue samples from large cohorts. In this study we addressed this issue by developing a deep-learning (DL)-based method for automatic curation of large pathology datasets with several slides per patient. METHODS: We collected multiple large multicentric datasets of colorectal cancer histopathological slides from the United Kingdom (FOXTROT, N = 21,384 slides; CR07, N = 7985 slides) and Germany (DACHS, N = 3606 slides). These datasets contained multiple types of tissue slides, including bowel resection specimens, endoscopic biopsies, lymph node resections, immunohistochemistry-stained slides, and tissue microarrays. We developed, trained, and tested a deep convolutional neural network model to predict the type of slide from the slide overview (thumbnail) image. The primary statistical endpoint was the macro-averaged area under the receiver operating curve (AUROCs) for detection of the type of slide. RESULTS: In the primary dataset (FOXTROT), with an AUROC of 0.995 [95% confidence interval [CI]: 0.994-0.996] the algorithm achieved a high classification performance and was able to accurately predict the type of slide from the thumbnail image alone. In the two external test cohorts (CR07, DACHS) AUROCs of 0.982 [95% CI: 0.979-0.985] and 0.875 [95% CI: 0.864-0.887] were observed, which indicates the generalizability of the trained model on unseen datasets. With a confidence threshold of 0.95, the model reached an accuracy of 94.6% (7331 classified cases) in CR07 and 85.1% (2752 classified cases) for the DACHS cohort. CONCLUSION: Our findings show that using the low-resolution thumbnail image is sufficient to accurately classify the type of slide in digital pathology. This can support researchers to make the vast resource of existing pathology archives accessible to modern AI models with only minimal manual annotations.

Federated Learning for Decentralized Artificial Intelligence in Melanoma Diagnostics.

Importance: The development of artificial intelligence (AI)-based melanoma classifiers typically calls for large, centralized datasets, requiring hospitals to give away their patient data, which raises serious privacy concerns. To address this concern, decentralized federated learning has been proposed, where classifier development is distributed across hospitals. Objective: To investigate whether a more privacy-preserving federated learning approach can achieve comparable diagnostic performance to a classical centralized (ie, single-model) and ensemble learning approach for AI-based melanoma diagnostics. Design, Setting, and Participants: This multicentric, single-arm diagnostic study developed a federated model for melanoma-nevus classification using histopathological whole-slide images prospectively acquired at 6 German university hospitals between April 2021 and February 2023 and benchmarked it using both a holdout and an external test dataset. Data analysis was performed from February to April 2023. Exposures: All whole-slide images were retrospectively analyzed by an AI-based classifier without influencing routine clinical care. Main Outcomes and Measures: The area under the receiver operating characteristic curve (AUROC) served as the primary end point for evaluating the diagnostic performance. Secondary end points included balanced accuracy, sensitivity, and specificity. Results: The study included 1025 whole-slide images of clinically melanoma-suspicious skin lesions from 923 patients, consisting of 388 histopathologically confirmed invasive melanomas and 637 nevi. The median (range) age at diagnosis was 58 (18-95) years for the training set, 57 (18-93) years for the holdout test dataset, and 61 (18-95) years for the external test dataset; the median (range) Breslow thickness was 0.70 (0.10-34.00) mm, 0.70 (0.20-14.40) mm, and 0.80 (0.30-20.00) mm, respectively. The federated approach (0.8579; 95% CI, 0.7693-0.9299) performed significantly worse than the classical centralized approach (0.9024; 95% CI, 0.8379-0.9565) in terms of AUROC on a holdout test dataset (pairwise Wilcoxon signed-rank, P < .001) but performed significantly better (0.9126; 95% CI, 0.8810-0.9412) than the classical centralized approach (0.9045; 95% CI, 0.8701-0.9331) on an external test dataset (pairwise Wilcoxon signed-rank, P < .001). Notably, the federated approach performed significantly worse than the ensemble approach on both the holdout (0.8867; 95% CI, 0.8103-0.9481) and external test dataset (0.9227; 95% CI, 0.8941-0.9479). Conclusions and Relevance: The findings of this diagnostic study suggest that federated learning is a viable approach for the binary classification of invasive melanomas and nevi on a clinically representative distributed dataset. Federated learning can improve privacy protection in AI-based melanoma diagnostics while simultaneously promoting collaboration across institutions and countries. Moreover, it may have the potential to be extended to other image classification tasks in digital cancer histopathology and beyond.

Growth performance, carcass characteristics and meat sensory evaluation of broiler chickens fed diets with fermented cassava leaves.

OBJECTIVE: The objective of the study was to determine the effects of feeding fermented cassava leaf meal (FCLM) on growth performance, carcass characteristics and meat sensory evaluation of broiler chickens. METHODS: A total of 160 Cobb-500 chickens were used during the phases of growing (21 days of age; initial weight 0.39±0.025 kg/bird) and finishing (35 days of age; initial weight 1.023±0.164 kg/bird). The whole experiment lasted for four weeks. The FCLM was included in starter and finishing diets at 0, 50, 100, and 150 g/kg inclusion levels. Total feed intake (TFI), weight gain (WG), feed conversion ratio, and nutrient digestibility were recorded. Sensory evaluation of breast meat was used to determine the eating quality of the meat prepared using roasting and boiling methods. RESULTS: The TFI and WG decreased (p<0.05) with increasing inclusion levels of FCLM in the diets of growing chickens. Crude protein digestibility for chickens fed 0 and 50 g/kg FCLM was higher (p<0.05) than for chickens subjected to a diet with 150 g/kg FCLM. During the finishing phase, TFI increased linearly (p<0.05) with increasing inclusion level of FCLM in chicken diets, while WG decreased (p<0.05) with inclusion level of FCLM. Treatment diets had no effect (p>0.05) on the eating qualities of breast meat. However, juiciness was significant (p<0.05) for the cooking method and treatment interaction. At 50 g/kg inclusion level, boiled meat had a higher (p<0.05) juiciness score than roasted meat. Tenderness, on the other hand, was significant (p<0.05) for the interaction of gender and treatment. Females considered the boiled meat to be more tender than the males at 150 g/kg inclusion level. Using principal component analysis, a positive correlation was observed between teeth adhesion and fibrousness, flavour and juiciness, and springiness and tenderness. CONCLUSION: From the study, it can be concluded that FCLM can be used as an ingredient in the diets of broiler chickens. Inclusion level of 50 g/kg can be used in chicken diets during the growing phase, whereas in the finishing phase, inclusion level of 150 g/kg FCLM can be used. The FCLM did not affect the eating quality of breast meat.

Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma.

Artificial intelligence (AI) systems have been shown to help dermatologists diagnose melanoma more accurately, however they lack transparency, hindering user acceptance. Explainable AI (XAI) methods can help to increase transparency, yet often lack precise, domain-specific explanations. Moreover, the impact of XAI methods on dermatologists' decisions has not yet been evaluated. Building upon previous research, we introduce an XAI system that provides precise and domain-specific explanations alongside its differential diagnoses of melanomas and nevi. Through a three-phase study, we assess its impact on dermatologists' diagnostic accuracy, diagnostic confidence, and trust in the XAI-support. Our results show strong alignment between XAI and dermatologist explanations. We also show that dermatologists' confidence in their diagnoses, and their trust in the support system significantly increase with XAI compared to conventional AI. This study highlights dermatologists' willingness to adopt such XAI systems, promoting future use in the clinic.

Evaluating deep learning-based melanoma classification using immunohistochemistry and routine histology: A three center study.

Pathologists routinely use immunohistochemical (IHC)-stained tissue slides against MelanA in addition to hematoxylin and eosin (H&E)-stained slides to improve their accuracy in diagnosing melanomas. The use of diagnostic Deep Learning (DL)-based support systems for automated examination of tissue morphology and cellular composition has been well studied in standard H&E-stained tissue slides. In contrast, there are few studies that analyze IHC slides using DL. Therefore, we investigated the separate and joint performance of ResNets trained on MelanA and corresponding H&E-stained slides. The MelanA classifier achieved an area under receiver operating characteristics curve (AUROC) of 0.82 and 0.74 on out of distribution (OOD)-datasets, similar to the H&E-based benchmark classification of 0.81 and 0.75, respectively. A combined classifier using MelanA and H&E achieved AUROCs of 0.85 and 0.81 on the OOD datasets. DL MelanA-based assistance systems show the same performance as the benchmark H&E classification and may be improved by multi stain classification to assist pathologists in their clinical routine.

End-to-end prognostication in colorectal cancer by deep learning: a retrospective, multicentre study.

BACKGROUND: Precise prognosis prediction in patients with colorectal cancer (ie, forecasting survival) is pivotal for individualised treatment and care. Histopathological tissue slides of colorectal cancer specimens contain rich prognostically relevant information. However, existing studies do not have multicentre external validation with real-world sample processing protocols, and algorithms are not yet widely used in clinical routine. METHODS: In this retrospective, multicentre study, we collected tissue samples from four groups of patients with resected colorectal cancer from Australia, Germany, and the USA. We developed and externally validated a deep learning-based prognostic-stratification system for automatic prediction of overall and cancer-specific survival in patients with resected colorectal cancer. We used the model-predicted risk scores to stratify patients into different risk groups and compared survival outcomes between these groups. Additionally, we evaluated the prognostic value of these risk groups after adjusting for established prognostic variables. FINDINGS: We trained and validated our model on a total of 4428 patients. We found that patients could be divided into high-risk and low-risk groups on the basis of the deep learning-based risk score. On the internal test set, the group with a high-risk score had a worse prognosis than the group with a low-risk score, as reflected by a hazard ratio (HR) of 4·50 (95% CI 3·33-6·09) for overall survival and 8·35 (5·06-13·78) for disease-specific survival (DSS). We found consistent performance across three large external test sets. In a test set of 1395 patients, the high-risk group had a lower DSS than the low-risk group, with an HR of 3·08 (2·44-3·89). In two additional test sets, the HRs for DSS were 2·23 (1·23-4·04) and 3·07 (1·78-5·3). We showed that the prognostic value of the deep learning-based risk score is independent of established clinical risk factors. INTERPRETATION: Our findings indicate that attention-based self-supervised deep learning can robustly offer a prognosis on clinical outcomes in patients with colorectal cancer, generalising across different populations and serving as a potentially new prognostic tool in clinical decision making for colorectal cancer management. We release all source codes and trained models under an open-source licence, allowing other researchers to reuse and build upon our work. FUNDING: The German Federal Ministry of Health, the Max-Eder-Programme of German Cancer Aid, the German Federal Ministry of Education and Research, the German Academic Exchange Service, and the EU.

Autoregulation of the LIM kinases by their PDZ domain.

LIM domain kinases (LIMK) are important regulators of actin cytoskeletal remodeling. These protein kinases phosphorylate the actin depolymerizing factor cofilin to suppress filament severing, and are key nodes between Rho GTPase cascades and actin. The two mammalian LIMKs, LIMK1 and LIMK2, contain consecutive LIM domains and a PDZ domain upstream of the C-terminal kinase domain. The roles of the N-terminal regions are not fully understood, and the function of the PDZ domain remains elusive. Here, we determine the 2.0 Å crystal structure of the PDZ domain of LIMK2 and reveal features not previously observed in PDZ domains including a core-facing arginine residue located at the second position of the 'x-Φ-G-Φ' motif, and that the expected peptide binding cleft is shallow and poorly conserved. We find a distal extended surface to be highly conserved, and when LIMK1 was ectopically expressed in yeast we find targeted mutagenesis of this surface decreases growth, implying increased LIMK activity. PDZ domain LIMK1 mutants expressed in yeast are hyperphosphorylated and show elevated activity in vitro. This surface in both LIMK1 and LIMK2 is critical for autoregulation independent of activation loop phosphorylation. Overall, our study demonstrates the functional importance of the PDZ domain to autoregulation of LIMKs.

Lactobacillus buchneri and molasses can alter the physicochemical properties of cassava leaf silage.

In developing countries where feed resources are scarce, cassava leaves can be used as feed for animals. However, the use of cassava leaves is limited mainly because of their high fibre content and overall acceptability by animals. The resolution to this problem is to process the cassava leaves by ensiling and using additives. Therefore, the objective of the study was to determine the effects of including different inclusion levels of molasses and bacteria concentration on the physicochemical properties of cassava leaf silage. Molasses was added at inclusion levels of 0, 3, 5 and 7 g/100g of the chopped cassava leaves, and Lactobacillus buchneri was mixed with chopped cassava leaves at different concentrations of 0, 3.1 × 106 cfu/ml, 3.1 × 108 cfu/ml and 3.1 × 1010 cfu/ml. The effects of inclusion level of molasses on the colour, smell and texture of cassava leaf silage were significant (P < 0.05). Inclusion of bacteria concentration also influenced the smell of silage (P < 0.05). Effects of the inclusion level of molasses and bacteria concentration resulted in decreased pH, crude protein and crude fibre of silage (P < 0.05). There was a quadratic relationship between Ca and K with inclusion level of molasses in cassava leaf silage (P < 0.05). A positive linear relationship was observed between Mg and molasses inclusion levels in cassava leaf silage (P < 0.05). Using principal component analysis (PCA), molasses had a strong positive correlation with PCA 1, whereas crude fibre, pH and crude protein had a positive correlation with PCA 2. The inclusion level of bacterial concentration was negatively correlated to Ca, CP, P and CF. From the study, the use of molasses and L. buchneri can greatly improve the physicochemical qualities of cassava leaf silage.

Deep learning to predict breast cancer sentinel lymph node status on INSEMA histological images.

BACKGROUND: Sentinel lymph node (SLN) status is a clinically important prognostic biomarker in breast cancer and is used to guide therapy, especially for hormone receptor-positive, HER2-negative cases. However, invasive lymph node staging is increasingly omitted before therapy, and studies such as the randomised Intergroup Sentinel Mamma (INSEMA) trial address the potential for further de-escalation of axillary surgery. Therefore, it would be helpful to accurately predict the pretherapeutic sentinel status using medical images. METHODS: Using a ResNet 50 architecture pretrained on ImageNet and a previously successful strategy, we trained deep learning (DL)-based image analysis algorithms to predict sentinel status on hematoxylin/eosin-stained images of predominantly luminal, primary breast tumours from the INSEMA trial and three additional, independent cohorts (The Cancer Genome Atlas (TCGA) and cohorts from the University hospitals of Mannheim and Regensburg), and compared their performance with that of a logistic regression using clinical data only. Performance on an INSEMA hold-out set was investigated in a blinded manner. RESULTS: None of the generated image analysis algorithms yielded significantly better than random areas under the receiver operating characteristic curves on the test sets, including the hold-out test set from INSEMA. In contrast, the logistic regression fitted on the Mannheim cohort retained a better than random performance on INSEMA and Regensburg. Including the image analysis model output in the logistic regression did not improve performance further on INSEMA. CONCLUSIONS: Employing DL-based image analysis on histological slides, we could not predict SLN status for unseen cases in the INSEMA trial and other predominantly luminal cohorts.

Structure Determination of SH2-Phosphopeptide Complexes by X-Ray Crystallography: The Example of p120RasGAP.

The p120RasGAP protein contains two Src homology 2 (SH2) domains, each with phosphotyrosine-binding activity. We describe the crystallization of the isolated and purified p120RasGAP SH2 domains with phosphopeptides derived from a binding partner protein, p190RhoGAP. Purified recombinant SH2 domain protein is mixed with synthetic phosphopeptide at a stoichiometric ratio to form the complex in vitro. Crystallization is then achieved by the hanging drop vapor diffusion method over specific reservoir solutions that yield single macromolecular co-crystals containing SH2 domain protein and phosphopeptide. This protocol yields suitable crystals for X-ray diffraction studies, and our recent X-ray crystallography studies of the two SH2 domains of p120RasGAP demonstrate that the N-terminal SH2 domain binds phosphopeptide in a canonical interaction. In contrast, the C-terminal SH2 domain binds phosphopeptide via a unique atypical binding mode. The crystallographic studies for p120RasGAP illustrate that although the three-dimensional structure of SH2 domains and the molecular details of their binding to phosphotyrosine peptides are well defined, careful structural analysis can continue to yield new molecular-level insights.