Journal of Pathology and Translational Medicine

Original Article

Artificial intelligence algorithm for neoplastic cell percentage estimation and its application to copy number variation in urinary tract cancer: Jinahn Jeong, Deokhoon Kim, Yeon-Mi Ryu, Ja-Min Park, Sun Young Yoon, Bokyung Ahn, Gi Hwan Kim, Se Un Jeong, Hyun-Jung Sung, Yong Il Lee, Sang-Yeob Kim, Yong Mee Cho; J Pathol Transl Med. 2024;58(5):229-240. Published online August 9, 2024; DOI: https://doi.org/10.4132/jptm.2024.07.13

576 View
84 Download

Abstract PDF Supplementary Material: Background
Bladder cancer is characterized by frequent mutations, which provide potential therapeutic targets for most patients. The effectiveness of emerging personalized therapies depends on an accurate molecular diagnosis, for which the accurate estimation of the neoplastic cell percentage (NCP) is a crucial initial step. However, the established method for determining the NCP, manual counting by a pathologist, is time-consuming and not easily executable.
Methods
To address this, artificial intelligence (AI) models were developed to estimate the NCP using nine convolutional neural networks and the scanned images of 39 cases of urinary tract cancer. The performance of the AI models was compared to that of six pathologists for 119 cases in the validation cohort. The ground truth value was obtained through multiplexed immunofluorescence. The AI model was then applied to 41 cases in the application cohort that underwent next-generation sequencing testing, and its impact on the copy number variation (CNV) was analyzed.
Results
Each AI model demonstrated high reliability, with intraclass correlation coefficients (ICCs) ranging from 0.82 to 0.88. These values were comparable or better to those of pathologists, whose ICCs ranged from 0.78 to 0.91 in urothelial carcinoma cases, both with and without divergent differentiation/ subtypes. After applying AI-driven NCP, 190 CNV (24.2%) were reclassified with 66 (8.4%) and 78 (9.9%) moved to amplification and loss, respectively, from neutral/minor CNV. The neutral/minor CNV proportion decreased by 6%.
Conclusions
These results suggest that AI models could assist human pathologists in repetitive and cumbersome NCP calculations.

Case Study

Primary hepatic mixed germ cell tumor in an adult: Hyun-Jung Sung, Jihun Kim, Kyu-rae Kim, Shinkyo Yoon, Jae Hoon Lee, Hyo Jeong Kang; J Pathol Transl Med. 2021;55(5):355-359. Published online August 3, 2021; DOI: https://doi.org/10.4132/jptm.2021.06.16

3,110 View
97 Download
1 Web of Science
1 Crossref

Primary hepatic mixed germ cell tumor (GCT) is very rare, and less than 10 cases have been reported. We report a case of mixed GCT composed of a choriocarcinoma and yolk sac tumor, which occurred in the liver of a 40-year-old woman. A large mass was detected by computed tomography solely in the liver. Serum β-human chorionic gonadotropin (hCG) was highly elevated, otherwise, other serum tumor markers were slightly elevated or within normal limits. For hepatic choriocarcinoma, neoadjuvant chemotherapy was administered, followed by right lobectomy. Histologic features of the resected tumor revealed characteristic choriocarcinoma features with diffuse positivity for hCG in the syncytiotrophoblasts and diffuse positivity for α-fetoprotein and Sal-like protein 4 in the yolk sac tumor components. Primary malignant GCT in the liver is associated with a poor prognosis and requires specific treatment. Therefore, GCT should be considered during a differential diagnosis of a rapidly growing mass in the liver.

Citations

Citations to this article as recorded by

Testicular Seminoma in Prostate: Case Report and Review of Literature
Peter Lesko, Jana Obertova, Karol Kajo, Katarina Rejlekova, Zuzana Orszaghova, Viera Lehotska, Martina Ondrusova, Michal Chovanec, Dalibor Ondrus, Michal Mego
Clinical Genitourinary Cancer.2024; 22(2): 210. CrossRef

First
Prev
Page of 1
Next
Last

Search