Hasil untuk "Neoplasms. Tumors. Oncology. Including cancer and carcinogens"

J. Fruehauf, F. Meyskens

Jingxing Zhong, Qingtao Pan, Xuchang Zhou et al.

Breast cancer is one of the most common causes of death among women worldwide, with millions of fatalities annually. Magnetic Resonance Imaging (MRI) can provide various sequences for characterizing tumor morphology and internal patterns, and becomes an effective tool for detection and diagnosis of breast tumors. However, previous deep-learning based tumor segmentation methods have limitations in accurately locating tumor contours due to the challenge of low contrast between cancer and normal areas and blurred boundaries. Leveraging text prompt information holds promise in ameliorating tumor segmentation effect by delineating segmentation regions. Inspired by this, we propose text-guided Breast Tumor Segmentation model (TextBCS) with stage-divided vision-language interaction and evidential learning. Specifically, the proposed stage-divided vision-language interaction facilitates information mutual between visual and text features at each stage of down-sampling, further exerting the advantages of text prompts to assist in locating lesion areas in low contrast scenarios. Moreover, the evidential learning is adopted to quantify the segmentation uncertainty of the model for blurred boundary. It utilizes the variational Dirichlet to characterize the distribution of the segmentation probabilities, addressing the segmentation uncertainties of the boundaries. Extensive experiments validate the superiority of our TextBCS over other segmentation networks, showcasing the best breast tumor segmentation performance on publicly available datasets.

Daeyoung Kim

Due to silence in early stages, lung cancer has been one of the most leading causes of mortality in cancer patients world-wide. Moreover, major symptoms of lung cancer are hard to differentiate with other respiratory disease symptoms such as COPD, further leading patients to overlook cancer progression in early stages. Thus, to enhance survival rates in lung cancer, early detection from consistent proactive respiratory system monitoring becomes crucial. One of the most prevalent and effective methods for lung cancer monitoring would be low-dose computed tomography(LDCT) chest scans, which led to remarkable enhancements in lung cancer detection or tumor classification tasks under rapid advancements and applications of computer vision based AI models such as EfficientNet or ResNet in image processing. However, though advanced CNN models under transfer learning or ViT based models led to high performing lung cancer detections, due to its intrinsic limitations in terms of correlation dependence and low interpretability due to complexity, expansions of deep learning models to lung cancer treatment analysis or causal intervention analysis simulations are still limited. Therefore, this research introduced LungCRCT: a latent causal representation learning based lung cancer analysis framework that retrieves causal representations of factors within the physical causal mechanism of lung cancer progression. With the use of advanced graph autoencoder based causal discovery algorithms with distance Correlation disentanglement and entropy-based image reconstruction refinement, LungCRCT not only enables causal intervention analysis for lung cancer treatments, but also leads to robust, yet extremely light downstream models in malignant tumor classification tasks with an AUC score of 93.91%.

Sadegh Rajabi, Akram Shahhosseini, Mahboubeh Irani et al.

The metastasis process plays an important role in the outcome of all cancers, including breast cancer, a leading cause of cancer mortality in women. This study assessed the effects of gaillardin on the metastatic activity of two different breast cancer cell lines. The MTT assay was used to obtain the IC50 concentrations. Migration or metastatic capability of MCF7 and MDA-MB231 cell lines was assayed using the wound scratch assay. The real-time PCR was utilized to quantify the gene expression of epithelial-mesenchymal transition (EMT) markers CDH1, CDH2, VIM, and FN1, along with angiogenesis-related markers VEGFA and THBS1. Western blotting was conducted to estimate the protein expression of E-cadherin, N-cadherin, vimentin, fibronectin 1, VEGFA, and thrombospondin 1. Treatment of the MCF7 cell line with different concentrations of gaillardin revealed no significant effect on the metastatic capacity of these cancer cells compared with the controls. However, the migratory activity and aggressiveness of MDA-MB231 cells were significantly hindered compared to the control cells. The results of gene expression data revealed the upregulating effect of gaillardin on the expression of CDH1 and THBS1 genes. Conversely, this phytochemical significantly downregulated CDH2, VIM, FN1, and VEGFA transcripts. Western blotting results showed a similar effect of gaillardin on the expression levels of the above-mentioned markers. The present data highlight the anti-metastatic activity of gaillardin in breast cancer in a receptor-independent manner. These results also indicate gaillardin as a potential anti-metastatic natural compound against triple-negative breast cancer cells, via two mechanisms that act by suppressing EMT and angiogenesis.

L. Di Gianfrancesco, F. Marino, D. De Marchi et al.

Tomasz Marjański, Julia Niedzielska, Andrii Bilyk et al.

Lung cancer treatment has evolved into a complex multidisciplinary challenge, offering patients across all stagesaccess to diverse local and systemic therapies. The introduction of effective neoadjuvant, adjuvant, and peri-adjuvantprotocols has significantly improved treatment outcomes. While surgery was once the primary treatment, it is nowoften complemented by additional therapies that enhance overall survival from pathological stage IB to IIIB. Theseadvancements necessitate changes in resectability definitions, staging, preoperative workup, surgical safety, and the roleof multidisciplinary assessment. Despite these improvements, numerous controversies persist. Identifying optimalcandidates for perioperative chemoimmunotherapy remains challenging. Patients with squamous cell histology,high PD-L1 expression, EGFR/ALK wild-type tumors, and those who are smokers with good pulmonary function testsand initially resectable to the extent of lobectomy are most likely to benefit. Tailoring treatment to these characteristicsmay enhance outcomes and maximize benefits.

Vinil Polepalli

Pan-cancer classification using transcriptomic (RNA-Seq) data can inform tumor subtyping and therapy selection, but is challenging due to extremely high dimensionality and limited sample sizes. In this study, we propose a novel deep learning framework that uses a class-conditional variational autoencoder (cVAE) to augment training data for pan-cancer gene expression classification. Using 801 tumor RNA-Seq samples spanning 5 cancer types from The Cancer Genome Atlas (TCGA), we first perform feature selection to reduce 20,531 gene expression features to the 500 most variably expressed genes. A cVAE is then trained on this data to learn a latent representation of gene expression conditioned on cancer type, enabling the generation of synthetic gene expression samples for each tumor class. We augment the training set with these cVAE-generated samples (doubling the dataset size) to mitigate overfitting and class imbalance. A two-layer multilayer perceptron (MLP) classifier is subsequently trained on the augmented dataset to predict tumor type. The augmented framework achieves high classification accuracy (~98%) on a held-out test set, substantially outperforming a classifier trained on the original data alone. We present detailed experimental results, including VAE training curves, classifier performance metrics (ROC curves and confusion matrix), and architecture diagrams to illustrate the approach. The results demonstrate that cVAE-based synthetic augmentation can significantly improve pan-cancer prediction performance, especially for underrepresented cancer classes.

Tiziano Barbui, Arianna Ghirardi, Alessandra Carobbio et al.

Jinghan Song, Xiong Ye, Qianqian Peng et al.

Petra Ilenič, Ajda Herman, Erik Langerholc et al.

Background: As compared to endocrine responsive breast cancer bone is less frequent site of distant recurrence in triple-negative breast cancer (TNBC). A biomarker which predicts bone recurrence would allow a more personalized treatment approach with adjuvant bisphosphonates in TNBC. Here we hypothesised that tumour expression of androgen receptor (AR) is associated with bone recurrence in TNBC. Materials and methods: Patients with operable TNBC who were treated at the Institute of Oncology Ljubljana between 2005 and 2015 and developed distant recurrence were included into our study. Nuclear expression of AR in the tissue of primary tumours was determined immunohistochemically by using the Androgen Receptor (SP107) Rabbit Monoclonal Antibody. We applied a logistic regression model to test the association between expression of AR and development of bone metastases. The model was adjusted for selected known prognostic factors and possible confounders in TNBC, including the level of the stromal tumour-infiltrating lymphocytes (sTILs). Results: At recurrence 45 (45 %) out of 100 patients presented with bone metastases. Additionally, seven (7 %) developed bone metastases metachronously. AR was expressed in primary tumours of 35 (35 %) women and 19 (54.3 %) developed bone recurrence. In 25 (25 %) patients sTILs were absent. Neither the proportion of AR positive cancer cells (OR = 1.00; 95 % CI 0.96–1.03; p = 1.00) nor the intensity of AR positive reaction (OR = 0.71; 95 % CI 0.02–21.4; p = 1.00) were significantly associated with bone recurrence. However, women with at least mild level of the sTILs were at significantly lower risk for bone recurrence as compared to those without any sTILs (OR = 0.01; 95 % CI < 0.01–0.08; p = 0.01). Conclusions: Expression of AR is not significantly associated with the development of bone metastases in TNBC. However, patients with absent sTILs in their primary tumours are highly susceptible for recurrence in the bone and might particularly benefit from adjuvant bisphosphonates.

Fatma Zahra Abdeldjouad, Menaouer Brahami, Mohammed Sabri

Adverse drug reactions considerably impact patient outcomes and healthcare costs in cancer therapy. Using artificial intelligence to predict adverse drug reactions in real time could revolutionize oncology treatment. This study aims to assess the performance of artificial intelligence models in predicting adverse drug reactions in patients with cancer. This is the first systematic review and meta-analysis. Scopus, PubMed, IEEE Xplore, and ACM Digital Library databases were searched for studies in English, French, and Arabic from January 1, 2018, to August 20, 2023. The inclusion criteria were: (1) peer-reviewed research articles; (2) use of artificial intelligence algorithms (machine learning, deep learning, knowledge graphs); (3) study aimed to predict adverse drug reactions (cardiotoxicity, neutropenia, nephrotoxicity, hepatotoxicity); (4) study was on cancer patients. The data were extracted and evaluated by three reviewers for study quality. Of the 332 screened articles, 17 studies (5%) involving 93,248 oncology patients from 17 countries were included in the systematic review, of which ten studies synthesized the meta-analysis. A random-effects model was created to pool the sensitivity, specificity, and AUC of the included studies. The pooled results were 0.82 (95% CI:0.69, 0.9), 0.84 (95% CI:0.75, 0.9), and 0.83 (95% CI:0.77, 0.87) for sensitivity, specificity, and AUC, respectively, of ADR predictive models. Biomarkers proved their effectiveness in predicting ADRs, yet they were adopted by only half of the reviewed studies. The use of AI in cancer treatment shows great potential, with models demonstrating high specificity and sensitivity in predicting ADRs. However, standardized research and multicenter studies are needed to improve the quality of evidence. AI can enhance cancer patient care by bridging the gap between data-driven insights and clinical expertise.

Tianshu Feng, Rohan Gnanaolivu, Abolfazl Safikhani et al.

Human cancers present a significant public health challenge and require the discovery of novel drugs through translational research. Transcriptomics profiling data that describes molecular activities in tumors and cancer cell lines are widely utilized for predicting anti-cancer drug responses. However, existing AI models face challenges due to noise in transcriptomics data and lack of biological interpretability. To overcome these limitations, we introduce VETE (Variational and Explanatory Transcriptomics Encoder), a novel neural network framework that incorporates a variational component to mitigate noise effects and integrates traceable gene ontology into the neural network architecture for encoding cancer transcriptomics data. Key innovations include a local interpretability-guided method for identifying ontology paths, a visualization tool to elucidate biological mechanisms of drug responses, and the application of centralized large scale hyperparameter optimization. VETE demonstrated robust accuracy in cancer cell line classification and drug response prediction. Additionally, it provided traceable biological explanations for both tasks and offers insights into the mechanisms underlying its predictions. VETE bridges the gap between AI-driven predictions and biologically meaningful insights in cancer research, which represents a promising advancement in the field.

Mathilde Faanes, Ragnhild Holden Helland, Ole Solheim et al.

Automatic segmentation of brain tumors in intra-operative ultrasound (iUS) images could facilitate localization of tumor tissue during resection surgery. The lack of large annotated datasets limits the current models performances. In this paper, we investigated the use of tumor annotations in magnetic resonance imaging (MRI) scans, which are more accessible than annotations in iUS images, for training of deep learning models for iUS brain tumor segmentation. We used 180 annotated MRI scans with corresponding unannotated iUS images, and 29 annotated iUS images. Image registration was performed to transfer the MRI annotations to the corresponding iUS images before training the nnU-Net model with different configurations of the data and label origins. The results showed no significant difference in Dice score for a model trained with only MRI annotated tumors compared to models trained with only iUS annotations and both, and to expert annotations, indicating that MRI tumor annotations can be used as a substitute for iUS tumor annotations to train a deep learning model for automatic brain tumor segmentation in iUS images. The best model obtained an average Dice score of $0.62\pm0.31$, compared to $0.67\pm0.25$ for an expert neurosurgeon, where the performance on larger tumors were similar, but lower for the models on smaller tumors. In addition, the results showed that removing smaller tumors from the training sets improved the results. The main models are available here: https://github.com/mathildefaanes/us_brain_tumor_segmentation/tree/main

Eleonora Beatrice Rossi, Eleonora Lopez, Danilo Comminiello

The application of deep learning in medical imaging has significantly advanced diagnostic capabilities, enhancing both accuracy and efficiency. Despite these benefits, the lack of transparency in these AI models, often termed "black boxes," raises concerns about their reliability in clinical settings. Explainable AI (XAI) aims to mitigate these concerns by developing methods that make AI decisions understandable and trustworthy. In this study, we propose Tumor Aware Counterfactual Explanations (TACE), a framework designed to generate reliable counterfactual explanations for medical images. Unlike existing methods, TACE focuses on modifying tumor-specific features without altering the overall organ structure, ensuring the faithfulness of the counterfactuals. We achieve this by including an additional step in the generation process which allows to modify only the region of interest (ROI), thus yielding more reliable counterfactuals as the rest of the organ remains unchanged. We evaluate our method on mammography images and brain MRI. We find that our method far exceeds existing state-of-the-art techniques in quality, faithfulness, and generation speed of counterfactuals. Indeed, more faithful explanations lead to a significant improvement in classification success rates, with a 10.69% increase for breast cancer and a 98.02% increase for brain tumors. The code of our work is available at https://github.com/ispamm/TACE.

Zhuxian Guo, Amine Marzouki, Jean-François Emile et al.

Lymphoid infiltration at tumor margins is a key prognostic marker in solid tumors, playing a crucial role in guiding immunotherapy decisions. Current assessment methods, heavily reliant on immunohistochemistry (IHC), face challenges in tumor margin delineation and are affected by tissue preservation conditions. In contrast, we propose a Hematoxylin and Eosin (H&E) staining-based approach, underpinned by an advanced lymphocyte segmentation model trained on a public dataset for the precise detection of CD3+ and CD20+ lymphocytes. In our colorectal cancer study, we demonstrate that our H&E-based method offers a compelling alternative to traditional IHC, achieving comparable results in many cases. Our method's validity is further explored through a Turing test, involving blinded assessments by a pathologist of anonymized curves from H&E and IHC slides. This approach invites the medical community to consider Turing tests as a standard for evaluating medical applications involving expert human evaluation, thereby opening new avenues for enhancing cancer management and immunotherapy planning.

Bo Li, Lili Duan, Xiali Li et al.

ObjectivesTumor-induced osteomalacia (TIO) is a rare acquired paraneoplastic disorder characterized by hypophosphatemia resulting from tumor-secreted fibroblast growth factor-23 (FGF23). Surgical resection of the culprit TIO is the first choice of treatment. However, TIO is difficult to detect with conventional diagnostic tools due to its small size and variable location in the body. Somatostatin receptor scintigraphy (SSR) has recently emerged as a functional molecular imaging choice for TIO detection and localization. This research was undertaken to evaluate the efficacy of 99mTc-labeled hydrazinonicotinyl-Tyr3-octreotide (99mTc-HYNIC-TOC) SPECT/CT in detecting TIO.Methods99mTc-HYNIC-TOC SPECT/CT and the available clinical data of 25 patients with suspected TIO were analyzed retrospectively. The 99mTc-HYNIC-TOC SPECT/CT findings were compared with the post-surgical pathology diagnosis and clinical follow-up results.ResultsUsing 99mTc-HYNIC-TOC SPECT/CT, suspicious tumors were found in 18 of the 25 patients, and 15 of them underwent surgical resection. The post-operative pathology confirmed a TIO in those 13 patients whose symptoms and biochemical anomalies gradually resolved after the surgery. The remaining five patients were finally considered false positives. Moreover, the 99mTc-HYNIC-TOC SPECT/CT results were negative in seven patients, with six patients being true negative (4 patients were diagnosed with acquired Fanconi syndrome and 2 patients responded well to conservative therapy) and one being false negative. Therefore, the sensitivity and specificity values of 99mTc-HYNIC-TOC SPECT/CT in the evaluation of TIO were 92.9% (13/14) and 54.5% (6/11), respectively. The overall accuracy of 99mTc-HYNIC-TOC SPECT/CT for detecting TIO was 76.0% (19/25).ConclusionsThe 99mTc-HYNIC-TOC SPECT/CT is an accurate imaging modality for locating culprit tumors in TIO.

Roberto Alfonso Arcuri

O informe apresenta um panorama sobre o processo de reorganização do RNPT, órgão do Ministério da Saúde, Divisão Nacional de Doenças Crônico-Degenerativas e Campanha Nacional de Combate ao Câncer.

Jason Holmes, Zhengliang Liu, Lian Zhang et al.

We present the first study to investigate Large Language Models (LLMs) in answering radiation oncology physics questions. Because popular exams like AP Physics, LSAT, and GRE have large test-taker populations and ample test preparation resources in circulation, they may not allow for accurately assessing the true potential of LLMs. This paper proposes evaluating LLMs on a highly-specialized topic, radiation oncology physics, which may be more pertinent to scientific and medical communities in addition to being a valuable benchmark of LLMs. We developed an exam consisting of 100 radiation oncology physics questions based on our expertise at Mayo Clinic. Four LLMs, ChatGPT (GPT-3.5), ChatGPT (GPT-4), Bard (LaMDA), and BLOOMZ, were evaluated against medical physicists and non-experts. ChatGPT (GPT-4) outperformed all other LLMs as well as medical physicists, on average. The performance of ChatGPT (GPT-4) was further improved when prompted to explain first, then answer. ChatGPT (GPT-3.5 and GPT-4) showed a high level of consistency in its answer choices across a number of trials, whether correct or incorrect, a characteristic that was not observed in the human test groups. In evaluating ChatGPTs (GPT-4) deductive reasoning ability using a novel approach (substituting the correct answer with "None of the above choices is the correct answer."), ChatGPT (GPT-4) demonstrated surprising accuracy, suggesting the potential presence of an emergent ability. Finally, although ChatGPT (GPT-4) performed well overall, its intrinsic properties did not allow for further improvement when scoring based on a majority vote across trials. In contrast, a team of medical physicists were able to greatly outperform ChatGPT (GPT-4) using a majority vote. This study suggests a great potential for LLMs to work alongside radiation oncology experts as highly knowledgeable assistants.

Farzane Tajidini

To provide the reader with a historical perspective on cancer classification approaches, we first discuss the fundamentals of the area of cancer diagnosis in this article, including the processes of cancer diagnosis and the standard classification methods employed by clinicians. Current methods for cancer diagnosis are deemed ineffective, calling for new and more intelligent approaches.

Yujin Oh, Sangjoon Park, Hwa Kyung Byun et al.

Target volume contouring for radiation therapy is considered significantly more challenging than the normal organ segmentation tasks as it necessitates the utilization of both image and text-based clinical information. Inspired by the recent advancement of large language models (LLMs) that can facilitate the integration of the textural information and images, here we present a novel LLM-driven multimodal AI, namely LLMSeg, that utilizes the clinical text information and is applicable to the challenging task of target volume contouring for radiation therapy, and validate it within the context of breast cancer radiation therapy target volume contouring. Using external validation and data-insufficient environments, which attributes highly conducive to real-world applications, we demonstrate that the proposed model exhibits markedly improved performance compared to conventional unimodal AI models, particularly exhibiting robust generalization performance and data efficiency. To our best knowledge, this is the first LLM-driven multimodal AI model that integrates the clinical text information into target volume delineation for radiation oncology.