Digital cytology: Current status and future prospects

Saini, Tarunpreet; Bansal, Baneet; Dey, Pranab

doi:10.1002/dc.25099

Cited by 6 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rapid cytological evaluation procedures such as ROSE or rapid remote online evaluation initially allow an assessment of the quantitative and qualitative suitability of obtained cellular samples for further required standard and immunochemical analyses, as well as for necessary molecular pathological investigations [24][25][26]. In the end, rapid cytological analyses are expected to reduce the number of repeated endoscopic examinations, along with the associated costs and biopsy-related risks.…”

Section: Discussionmentioning

confidence: 99%

Rapid Remote Online Evaluation in Endoscopic Diagnostics: An Analysis of Biopsy-Proven Respiratory Cytopathology

Elmas,

Önal,

Steurer

et al. 2023

Diagnostics

View full text Add to dashboard Cite

Background: This prospective study assesses the use of rapid remote online cytological evaluation for diagnosing endoscopical achieved biopsies. It focuses on its effectiveness in identifying benign and malignant conditions using digital image processing. Methods: The study was conducted between April 2021 and September 2022 and involved analyses of 314 Rapid Remote Online Cytological Evaluations in total (154 imprint cytologies, 143 fine needle aspirations and 17 brush cytologies) performed on 239 patients at the LungenClinic Grosshansdorf. During on-site evaluation via telecytology, the time requirement was recorded and the findings were compared with the cyto-/histological and final diagnoses. Results: By means of rapid remote online evaluation, findings of 86 cytological benign, 190 malignant and 38 unclear diagnoses were recorded (Ø assessment time, 100 s; range, 11–370 s). In 27 of the 37 specimens with unclear diagnoses, the final findings were malignant tumours and only 6 were benign changes. The diagnosis of another 4 of these 37 findings remained unclear. Excluding these 37 specimens, rapid remote online evaluation achieved a sensitivity of 90.5% with a specificity of 98.5% and a correct classification rate of 92.4% with regard to the final diagnosis of all cases. As expected, an increase in the sensitivity rate for the cytological detection of malignant tumours (76.1% vs. 92.5%) was found especially in fine-needle aspirations. Conclusions: Rapid remote online analysis allows the fast quantitative and qualitative evaluation of clinically obtained cytological specimens. With a correct classification rate of more than 93%, sampling deficiencies can be corrected promptly and diagnostic and therapeutic approaches can be derived.

show abstract

Section: Discussionmentioning

confidence: 99%

Rapid Remote Online Evaluation in Endoscopic Diagnostics: An Analysis of Biopsy-Proven Respiratory Cytopathology

Elmas,

Önal,

Steurer

et al. 2023

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Most often, however, pathologists can visually distinguish adenocarcinoma from squamous carcinoma on cytology smears, but not the origin of the tumor cells 13 , 23 , 25 . Therefore, precise cytological assessment may help in the appropriate management of patients with CUP and pleural or peritoneal metastasis, guide optimal therapeutic strategies, avoid unnecessary surgeries and further prolong overall survival 27 – 29 .…”

Section: Mainmentioning

confidence: 99%

Prediction of tumor origin in cancers of unknown primary origin with cytology-based deep learning

Tian,

Liu,

Wei

et al. 2024

Nat Med

View full text Add to dashboard Cite

Cancer of unknown primary (CUP) site poses diagnostic challenges due to its elusive nature. Many cases of CUP manifest as pleural and peritoneal serous effusions. Leveraging cytological images from 57,220 cases at four tertiary hospitals, we developed a deep-learning method for tumor origin differentiation using cytological histology (TORCH) that can identify malignancy and predict tumor origin in both hydrothorax and ascites. We examined its performance on three internal (n = 12,799) and two external (n = 14,538) testing sets. In both internal and external testing sets, TORCH achieved area under the receiver operating curve values ranging from 0.953 to 0.991 for cancer diagnosis and 0.953 to 0.979 for tumor origin localization. TORCH accurately predicted primary tumor origins, with a top-1 accuracy of 82.6% and top-3 accuracy of 98.9%. Compared with results derived from pathologists, TORCH showed better prediction efficacy (1.677 versus 1.265, P < 0.001), enhancing junior pathologists’ diagnostic scores significantly (1.326 versus 1.101, P < 0.001). Patients with CUP whose initial treatment protocol was concordant with TORCH-predicted origins had better overall survival than those who were administrated discordant treatment (27 versus 17 months, P = 0.006). Our study underscores the potential of TORCH as a valuable ancillary tool in clinical practice, although further validation in randomized trials is warranted.

show abstract

Correspondence on “Evaluating the use of virtual microscopy in cytology education”

Dhane

2023

Journal of the American Society of Cytopathology

View full text Add to dashboard Cite

Digital cytology: Current status and future prospects

Cited by 6 publications

References 40 publications

Rapid Remote Online Evaluation in Endoscopic Diagnostics: An Analysis of Biopsy-Proven Respiratory Cytopathology

Rapid Remote Online Evaluation in Endoscopic Diagnostics: An Analysis of Biopsy-Proven Respiratory Cytopathology

Prediction of tumor origin in cancers of unknown primary origin with cytology-based deep learning

Correspondence on “Evaluating the use of virtual microscopy in cytology education”

Contact Info

Product

Resources

About