-
Investigative Ophthalmology & Visual... Jul 2023There is great promise in use of machine learning (ML) for the diagnosis, prognosis, and treatment of various medical conditions in ophthalmology and beyond.... (Review)
Review
PURPOSE
There is great promise in use of machine learning (ML) for the diagnosis, prognosis, and treatment of various medical conditions in ophthalmology and beyond. Applications of ML for ocular neoplasms are in early development and this review synthesizes the current state of ML in ocular oncology.
METHODS
We queried PubMed and Web of Science and evaluated 804 publications, excluding nonhuman studies. Metrics on ML algorithm performance were collected and the Prediction model study Risk Of Bias ASsessment Tool was used to evaluate bias. We report the results of 63 unique studies.
RESULTS
Research regarding ML applications to intraocular cancers has leveraged multiple algorithms and data sources. Convolutional neural networks (CNNs) were one of the most commonly used ML algorithms and most work has focused on uveal melanoma and retinoblastoma. The majority of ML models discussed here were developed for diagnosis and prognosis. Algorithms for diagnosis primarily leveraged imaging (e.g., optical coherence tomography) as inputs, whereas those for prognosis leveraged combinations of gene expression, tumor characteristics, and patient demographics.
CONCLUSIONS
ML has the potential to improve the management of intraocular cancers. Published ML models perform well, but were occasionally limited by small sample sizes owing to the low prevalence of intraocular cancers. This could be overcome with synthetic data enhancement and low-shot ML techniques. CNNs can be integrated into existing diagnostic workflows, while non-neural networks perform well in determining prognosis.
Topics: Humans; Machine Learning; Neural Networks, Computer; Melanoma; Algorithms; Retinal Neoplasms
PubMed: 37477930
DOI: 10.1167/iovs.64.10.29 -
BMC Cancer Nov 2023The pathological diagnosis and prognosis prediction of hepatocellular carcinoma (HCC) is challenging due to the lack of specific biomarkers. This study aimed to validate...
PURPOSE
The pathological diagnosis and prognosis prediction of hepatocellular carcinoma (HCC) is challenging due to the lack of specific biomarkers. This study aimed to validate the diagnostic and prognostic efficiency of Kidney-type glutaminase (GLS1) for HCC in prospective cohorts with a large sample size.
METHODS
A total of 1140 HCC patients were enrolled in our prospective clinical trials. Control cases included 114 nontumour tissues. The registered clinical trial (ChiCTR-DDT-14,005,102, chictr.org.cn) was referred to for the exact protocol. GLS1 immunohistochemistry was performed on the whole tumour section. The diagnostic and prognostic performances of GLS1 was evaluated by the receiver operating characteristic curve and Cox regression model.
RESULTS
The sensitivity, specificity, positive predictive value, negative predictive value, Youden index, and area under the curve of GLS1 for the diagnosis of HCC were 0.746, 0.842, 0.979, 0.249, 0.588, and 0.814, respectively, which could be increased to 0.846, 0.886, 0.987,0.366, 0.732, and 0.921 when combined with glypican 3 (GPC3) and alpha-fetoprotein (AFP), indicating better diagnostic performance. Further, we developed a nomogram with GPC3 and GLS1 for identifying HCC which showed good discrimination and calibration. GLS1 expression was also related with age, T stage, TNM stage, Edmondson-Steiner grade, microvascular invasion, Ki67, VEGFR2, GPC3, and AFP expression in HCC. GLS1 expression was negatively correlated with disease-free survival (P < 0.001) probability of patients with HCC.
CONCLUSIONS
It was validated that GLS1 was a sensitive and specific biomarker for pathological diagnosis of HCC and had prognostic value, thus having practical value for clinical application.
Topics: Humans; Carcinoma, Hepatocellular; alpha-Fetoproteins; Prospective Studies; Liver Neoplasms; Glutaminase; Biomarkers, Tumor; Prognosis; Kidney; Glypicans
PubMed: 37946141
DOI: 10.1186/s12885-023-11601-y -
Open Veterinary Journal Oct 2023Only 27 cases of equine conjunctival haemangiosarcoma have been reported in the literature over the past 37 years. Out of these, 22% of cases were lost to follow-up, 52%...
BACKGROUND
Only 27 cases of equine conjunctival haemangiosarcoma have been reported in the literature over the past 37 years. Out of these, 22% of cases were lost to follow-up, 52% were euthanized, and 26% survived. A scarcity of cases and information is available for this rarely seen conjunctival tumour.
AIM
To describe the clinical features, management, and outcome of conjunctival hemangiosarcoma in seven horses in the UK.
METHODS
Optivet medical records were reviewed for equine cases seen or advised on with a histopathological diagnosis of conjunctival haemangiosarcoma between January 2013 and March 2023. Medical records were accessed for details of signalment, history, management, and follow-up. Histopathology was used to confirm the diagnosis of haemangiosarcoma and assess the surgical margins. Immunohistochemistry was performed in a minority of cases with poorly differentiated solid tumours to support vascular lineage.
RESULTS
Seven eyes from seven horses (five geldings and two mares) with a mean age of 16 years and median of 18 years (range 10-21 years) met the criteria. Serosanguinous discharge was seen in six eyes. All eyes were managed surgically; 4 by exenteration and 3 by conjunctivectomy/keratectomy. Adjunctive cryotherapy was performed in two eyes. Metastatic disease in the ipsilateral parotid salivary gland, confirmed with histopathology, was seen in one horse. Surgical margins were clear in all but one eye. Solar elastosis was noted in five eyes. All horses were healthy at the last follow-up (0.2-5 years, mean 2.9 years, and median 2 years).
CONCLUSION
Equine conjunctival haemangiosarcoma is rare. Serosanguinous ocular discharge is a common clinical sign. Early surgical excision is highly effective. Solar elastosis is a common histopathological feature, suggesting a role for UV-light in the pathogenesis.
Topics: Horses; Animals; Male; Female; Hemangiosarcoma; Margins of Excision; United Kingdom; Horse Diseases
PubMed: 38027397
DOI: 10.5455/OVJ.2023.v13.i10.17 -
The Veterinary Quarterly Dec 2023Hyperthyroidism is considered the most common endocrinopathy in middle-aged and old cats. The increased level of thyroid hormones influences many organs, including the...
Hyperthyroidism is considered the most common endocrinopathy in middle-aged and old cats. The increased level of thyroid hormones influences many organs, including the heart. Cardiac functional and structural abnormalities in cats with hyperthyroidism have indeed been previously described. Nonetheless, myocardial vasculature has not been subjected to analysis. Also, no comparison with hypertrophic cardiomyopathy has been previously described. Although it has been shown that clinical alterations resolve after the treatment of hyperthyroidism, no detailed data have been published on the cardiac pathological or histopathological image of field cases of hyperthyroid cats that received pharmacological treatment. The aim of this study was to evaluate the cardiac pathological changes in feline hyperthyroidism and to compare them to alterations present in cardiac hypertrophy due to hypertrophic cardiomyopathy in cats. The study was conducted on 40 feline hearts divided into three groups: 17 hearts from cats suffering from hyperthyroidism, 13 hearts from cats suffering from idiopathic hypertrophic cardiomyopathy and 10 hearts from cats without cardiac or thyroid disease. A detailed pathological and histopathological examination was performed. Cats with hyperthyroidism showed no ventricular wall hypertrophy in contrast to cats with hypertrophic cardiomyopathy. Nonetheless, histological alterations were similarly advanced in both diseases. Moreover, in hyperthyroid cats more prominent vascular alterations were noted. In contrast to hypertrophic cardiomyopathy, the histological changes in hyperthyroid cats involved all ventricular walls and not mainly the left ventricle. Our study showed that despite normal cardiac wall thickness, cats with hyperthyroidism show severe structural changes in the myocardium.
Topics: Cats; Animals; Cardiomyopathy, Hypertrophic; Myocardium; Hyperthyroidism; Cat Diseases
PubMed: 37427551
DOI: 10.1080/01652176.2023.2234436 -
European Journal of Cancer (Oxford,... Sep 2023Intra-tumour heterogeneity (ITH) causes diagnostic challenges and increases the risk for disease recurrence. Quantification of ITH is challenging and has not been...
BACKGROUND
Intra-tumour heterogeneity (ITH) causes diagnostic challenges and increases the risk for disease recurrence. Quantification of ITH is challenging and has not been demonstrated in large studies. It has previously been shown that deep learning can enable spatially resolved prediction of molecular phenotypes from digital histopathology whole slide images (WSIs). Here we propose a novel method (Deep-ITH) to predict and measure ITH, and we evaluate its prognostic performance in breast cancer.
METHODS
Deep convolutional neural networks were used to spatially predict gene-expression (PAM50 set) from WSIs. For each predicted transcript, 12 measures of heterogeneity were extracted in the training data set (N = 931). A prognostic score to dichotomise patients into Deep-ITH low- and high-risk groups was established using an elastic-net regularised Cox proportional hazards model (recurrence-free survival). Prognostic performance was evaluated in two independent data sets: SöS-BC-1 (N = 1358) and SCAN-B-Lund (N = 1262).
RESULTS
We observed an increase in risk of recurrence in the high-risk group with hazard ratio (HR) 2.11 (95%CI:1.22-3.60; p = 0.007) using nested cross-validation. Subgroup analyses confirmed the prognostic performance in oestrogen receptor (ER)-positive, human epidermal growth factor receptor 2 (HER2)-negative, grade 3, and large tumour subgroups. The prognostic value was confirmed in the independent SöS-BC-1 cohort (HR=1.84; 95%CI:1.03-3.3; p = 3.99 ×10). In the other external cohort, significant HR was observed in the subgroup of histological grade 2 patients, as well as in the subgroup of patients with small tumours (<20 mm).
CONCLUSION
We developed a novel method for an automated, scalable, and cost-efficient measure of ITH from WSIs that provides independent prognostic value for breast cancer.
SIGNIFICANCE
Transcriptional ITH predicted by deep learning models enables prediction of patient survival from routine histopathology WSIs in breast cancer.
Topics: Humans; Female; Prognosis; Biomarkers, Tumor; Deep Learning; Neoplasm Recurrence, Local; Breast Neoplasms
PubMed: 37494846
DOI: 10.1016/j.ejca.2023.112953 -
Histopathology image classification: highlighting the gap between manual analysis and AI automation.Frontiers in Oncology 2023The field of histopathological image analysis has evolved significantly with the advent of digital pathology, leading to the development of automated models capable of...
The field of histopathological image analysis has evolved significantly with the advent of digital pathology, leading to the development of automated models capable of classifying tissues and structures within diverse pathological images. Artificial intelligence algorithms, such as convolutional neural networks, have shown remarkable capabilities in pathology image analysis tasks, including tumor identification, metastasis detection, and patient prognosis assessment. However, traditional manual analysis methods have generally shown low accuracy in diagnosing colorectal cancer using histopathological images. This study investigates the use of AI in image classification and image analytics using histopathological images using the histogram of oriented gradients method. The study develops an AI-based architecture for image classification using histopathological images, aiming to achieve high performance with less complexity through specific parameters and layers. In this study, we investigate the complicated state of histopathological image classification, explicitly focusing on categorizing nine distinct tissue types. Our research used open-source multi-centered image datasets that included records of 100.000 non-overlapping images from 86 patients for training and 7180 non-overlapping images from 50 patients for testing. The study compares two distinct approaches, training artificial intelligence-based algorithms and manual machine learning models, to automate tissue classification. This research comprises two primary classification tasks: binary classification, distinguishing between normal and tumor tissues, and multi-classification, encompassing nine tissue types, including adipose, background, debris, stroma, lymphocytes, mucus, smooth muscle, normal colon mucosa, and tumor. Our findings show that artificial intelligence-based systems can achieve 0.91 and 0.97 accuracy in binary and multi-class classifications. In comparison, the histogram of directed gradient features and the Random Forest classifier achieved accuracy rates of 0.75 and 0.44 in binary and multi-class classifications, respectively. Our artificial intelligence-based methods are generalizable, allowing them to be integrated into histopathology diagnostics procedures and improve diagnostic accuracy and efficiency. The CNN model outperforms existing machine learning techniques, demonstrating its potential to improve the precision and effectiveness of histopathology image analysis. This research emphasizes the importance of maintaining data consistency and applying normalization methods during the data preparation stage for analysis. It particularly highlights the potential of artificial intelligence to assess histopathological images.
PubMed: 38298445
DOI: 10.3389/fonc.2023.1325271 -
Clinical characteristics, radiologic features, and histopathology of biopsied lacrimal gland tumors.Scientific Reports Oct 2023Herein, we described the clinicopathologic and radiologic features of biopsied lacrimal gland tumors. A retrospective case series of 79 patients treated between 2004 and...
Herein, we described the clinicopathologic and radiologic features of biopsied lacrimal gland tumors. A retrospective case series of 79 patients treated between 2004 and 2021 was reviewed. The median age was 48.9 years (range 18.3-88.3 years), with 51.9% females. The histopathologic diagnoses were as follows: immunoglobulin G4-related disease (IgG4-RD) = 23, reactive lymphoid hyperplasia = 14, lymphoma = 14, nonspecific inflammation = 10, adenoid cystic carcinoma (ACC) = 9, and pleomorphic adenoma = 9. The proportion of histopathologic diagnoses did not differ significantly over the range of symptom durations (≤ 1 month, > 1-3 months, > 3 months). Patients with ACC had significantly shorter symptom duration and more frequent proptosis than those with pleomorphic adenoma (p = 0.040 and p = 0.009, respectively). Patients with IgG4-RD were older (median 54.3 years) than those with nonspecific inflammation (36.2 years; p = 0.046). Patients with ACC were more likely to present with diplopia than those with lymphoma (p < 0.001). The superior wedge sign increased the likelihood of ACC compared with that of non-epithelial non-malignant lacrimal gland tumors (relative risk ratio = 13.44, p = 0.002). The overall survival of patients with ACC and lymphoma did not differ significantly. Although these patients present with a short symptom duration, urgent orbital imaging, tissue biopsy, and prompt treatment should be performed in patients with lacrimal gland tumors.
Topics: Female; Humans; Adolescent; Young Adult; Adult; Middle Aged; Aged; Aged, 80 and over; Male; Lacrimal Apparatus; Adenoma, Pleomorphic; Retrospective Studies; Immunoglobulin G4-Related Disease; Lacrimal Apparatus Diseases; Eye Neoplasms; Carcinoma, Adenoid Cystic; Inflammation; Lymphoma; Biopsy
PubMed: 37789105
DOI: 10.1038/s41598-023-43817-0 -
Cancer Biomarkers : Section a of... 2024Breast cancer is one of the leading causes of death in women worldwide. Histopathology analysis of breast tissue is an essential tool for diagnosing and staging breast... (Review)
Review
BACKGROUND
Breast cancer is one of the leading causes of death in women worldwide. Histopathology analysis of breast tissue is an essential tool for diagnosing and staging breast cancer. In recent years, there has been a significant increase in research exploring the use of deep-learning approaches for breast cancer detection from histopathology images.
OBJECTIVE
To provide an overview of the current state-of-the-art technologies in automated breast cancer detection in histopathology images using deep learning techniques.
METHODS
This review focuses on the use of deep learning algorithms for the detection and classification of breast cancer from histopathology images. We provide an overview of publicly available histopathology image datasets for breast cancer detection. We also highlight the strengths and weaknesses of these architectures and their performance on different histopathology image datasets. Finally, we discuss the challenges associated with using deep learning techniques for breast cancer detection, including the need for large and diverse datasets and the interpretability of deep learning models.
RESULTS
Deep learning techniques have shown great promise in accurately detecting and classifying breast cancer from histopathology images. Although the accuracy levels vary depending on the specific data set, image pre-processing techniques, and deep learning architecture used, these results highlight the potential of deep learning algorithms in improving the accuracy and efficiency of breast cancer detection from histopathology images.
CONCLUSION
This review has presented a thorough account of the current state-of-the-art techniques for detecting breast cancer using histopathology images. The integration of machine learning and deep learning algorithms has demonstrated promising results in accurately identifying breast cancer from histopathology images. The insights gathered from this review can act as a valuable reference for researchers in this field who are developing diagnostic strategies using histopathology images. Overall, the objective of this review is to spark interest among scholars in this complex field and acquaint them with cutting-edge technologies in breast cancer detection using histopathology images.
Topics: Humans; Breast Neoplasms; Deep Learning; Female; Image Processing, Computer-Assisted; Algorithms; Image Interpretation, Computer-Assisted
PubMed: 38517775
DOI: 10.3233/CBM-230251 -
JCO Clinical Cancer Informatics Jun 2024Prostate cancer (PCa) represents a highly heterogeneous disease that requires tools to assess oncologic risk and guide patient management and treatment planning. Current...
PURPOSE
Prostate cancer (PCa) represents a highly heterogeneous disease that requires tools to assess oncologic risk and guide patient management and treatment planning. Current models are based on various clinical and pathologic parameters including Gleason grading, which suffers from a high interobserver variability. In this study, we determine whether objective machine learning (ML)-driven histopathology image analysis would aid us in better risk stratification of PCa.
MATERIALS AND METHODS
We propose a deep learning, histopathology image-based risk stratification model that combines clinicopathologic data along with hematoxylin and eosin- and Ki-67-stained histopathology images. We train and test our model, using a five-fold cross-validation strategy, on a data set from 502 treatment-naïve PCa patients who underwent radical prostatectomy (RP) between 2000 and 2012.
RESULTS
We used the concordance index as a measure to evaluate the performance of various risk stratification models. Our risk stratification model on the basis of convolutional neural networks demonstrated superior performance compared with Gleason grading and the Cancer of the Prostate Risk Assessment Post-Surgical risk stratification models. Using our model, 3.9% of the low-risk patients were correctly reclassified to be high-risk and 21.3% of the high-risk patients were correctly reclassified as low-risk.
CONCLUSION
These findings highlight the importance of ML as an objective tool for histopathology image assessment and patient risk stratification. With further validation on large cohorts, the digital pathology risk classification we propose may be helpful in guiding administration of adjuvant therapy including radiotherapy after RP.
Topics: Humans; Prostatic Neoplasms; Male; Deep Learning; Neoplasm Grading; Risk Assessment; Prostatectomy; Aged; Middle Aged; Image Processing, Computer-Assisted
PubMed: 38900978
DOI: 10.1200/CCI.23.00184 -
Scientific Reports Aug 2023Technical advances in microsurgery have enabled complex oncological reconstructions by performing free tissue transfers, nerve and lymphatic reconstructions. However,... (Randomized Controlled Trial)
Randomized Controlled Trial
Technical advances in microsurgery have enabled complex oncological reconstructions by performing free tissue transfers, nerve and lymphatic reconstructions. However, the manual abilities required to perform microsurgery can be affected by human fatigue and physiological tremor resulting in tissue damage and compromised outcomes. Robotic assistance has the potential to overcome issues of manual microsurgery by improving clinical value and anastomoses' outcomes. The Symani Surgical System, a robotic platform designed for microsurgery, was used in this in-vivo preclinical study using a rat animal model. The tests included anastomoses on veins and arteries performed by microsurgeons manually and robotically, with the latter approach using Symani. The anastomoses were assessed for patency, histopathology, and execution time. Patency results confirmed that the robotic and manual techniques for venous and arterial anastomoses were equivalent after anastomosis, however, the time to perform the anastomosis was longer with the use of the robot (p < 0.0001). Histological analysis showed less total average host reaction score at the anastomotic site in robotic anastomosis for both veins and arteries. This study demonstrates the equivalence of vessel patency after microsurgical anastomoses with the robotic system and with manual technique. Furthermore, robotic anastomosis has proven to be slightly superior to manual anastomosis in terms of decreased tissue damage, as shown by histological analysis.
Topics: Animals; Humans; Rats; Anastomosis, Surgical; Arteries; Essential Tremor; Robotic Surgical Procedures; Veins
PubMed: 37635195
DOI: 10.1038/s41598-023-41143-z