Background: Uveal melanoma (UM) is the most common primary intraocular malignancy in adults. The median overall survival time for patients who develop metastasis is approximately one year. In this study, we aim to leverage deep learning (DL) techniques to analyze digital cytopathology images and directly predict the 48 month survival status on a patient level.

Methods: Fine-needle aspiration biopsy (FNAB) of the tumor was performed in each patient diagnosed with UM. The cell aspirate was smeared on a glass slide and stained with H&E. Each slide then underwent whole-slide scanning. Within each whole-slide image, regions of interest (ROIs) with UM cells were automatically extracted. Each ROI was converted into super pixels, and the super pixels were automatically detected, segmented and annotated as "tumor cell" or "background" using DL. Cell-level features were extracted from the segmented tumor cells. The cell-level features were aggregated into slide-level features which were learned by a fully connected layer in an artificial neural network, and the patient survival status was predicted directly from the slide-level features. The data were partitioned at the patient level (78% training and 22% testing). Our DL model was trained to perform the binary prediction of yes-versus-no survival by Month 48. The ground truth for patient survival was established via a retrospective chart review.

Results: A total of 74 patients were included in this study (43% female; mean age at the time of diagnosis: 61.8 ± 11.6 years), and 207,260 unique ROIs were generated for model training and testing. By Month 48 after diagnosis, 18 patients (24%) died from UM metastasis. Our hold-out test set contained 16 patients, where 6 patients had passed away and 10 patients were alive at Month 48. When using a sensitivity threshold of 80% in predicting UM-specific death by Month 48, our model achieved an overall accuracy of 75%. Within the subgroup of patients who died by Month 48, our model achieved a prediction accuracy of 83%. Of note, one patient in our test set was a clinical surprise, namely death by Month 48 despite having a GEP class 1A tumor, which typically portends a good prognosis. Our model correctly predicted this clinical surprise as well.

Conclusions: Our DL model was able to predict the Month 48 survival status directly from digital cytopathology images obtained from FNABs of UM tumors with reasonably robust performance. This approach, if validated prospectively, could serve as an alternative survival prediction tool for patients with UM to whom GEP is not available.

Download full-text PDF

Source
http://dx.doi.org/10.3390/cancers17020230DOI Listing

Publication Analysis

Top Keywords

survival status
16
month survival
12
digital cytopathology
12
cytopathology images
12
month
9
patients
9
survival
8
uveal melanoma
8
deep learning
8
predict month
8

Similar Publications

Introduction: This study investigated the role of fibroblast growth factor 23 (FGF23)/Klotho in the mortality of patients hospitalized with coronavirus disease 2019 (COVID-19), excluding those with chronic kidney disease (CKD).

Methodology: A prospective cross-sectional study was conducted from April 2021 to May 2022. Patients who tested positive for COVID-19 via polymerase chain reaction and were hospitalized, were classified into two groups (survivors and non-survivors) at the end of their hospital follow-up.

View Article and Find Full Text PDF

The association between Chlamydia pneumoniae infection and prognosis in lung cancer patients: a prospective study.

BMC Infect Dis

January 2025

Department of Epidemiology and Health Statistics, School of Public Health, Fujian Medical University, Fuzhou, China.

Background: The prognostic value of Chlamydia pneumoniae (Cpn) infection in postoperative lung cancer patients remains unclear. This study aimed to evaluate the association between Cpn infection and survival in lung cancer patients.

Methods: This study included 309 newly diagnosed primary lung cancer patients from three hospitals in Fuzhou, China.

View Article and Find Full Text PDF

Background: Evidence is lacking on whether chronic pain is related to the risk of cancer mortality. This study seeks to unveil the association between chronic pain and all-cause, cancer, as well as non-cancer death in cancer patients based on the National Health and Nutrition Examination Survey (NHANES) database.

Methods: Cancer survivors aged at least 20 (n = 1369) from 3 NHANES (1999-2004) cycles were encompassed.

View Article and Find Full Text PDF

Joint association of objective and subjective aging with premature mortality.

NPJ Aging

January 2025

Department of Epidemiology, Celia Scott Weatherhead School of Public Health and Tropical Medicine, Tulane University, New Orleans, LA, USA.

Objective and subjective aging indicators reflect diverse biological and psychosocial processes, yet their combined association with premature mortality remains underexplored. This study aimed to investigate the association between a multidomain framework of aging indicators and premature mortality, addressing gaps in understanding cumulative effects. We included 369,741 UK Biobank participants initially free of cardiovascular disease (CVD) and cancer, followed until December 31, 2022.

View Article and Find Full Text PDF

[Clinical characteristics and prognosis of ovarian juvenile granulosa cell tumors].

Zhonghua Fu Chan Ke Za Zhi

January 2025

Department of Gynecology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing100021, China.

To analyze the clinical characteristics, treatments, and prognosis of patients with ovarian juvenile granulosa cell tumor (JGCT). Clinical and pathological data, and follow-up information of 34 patients diagnosed with JGCT from 2000 to 2021 were collected from the surveillance, epidemiology, and end results (SEER) database. A retrospective analysis was conducted to summarize the patients' clinical and pathological characteristics, treatments, and prognosis.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!